2f:I[703058,["/_next/static/immutable/chunks/3bhq_5eh1d760.js","/_next/static/immutable/chunks/1855-ogyi8eh4.js","/_next/static/immutable/chunks/2pfsjpn6k6zlg.js","/_next/static/immutable/chunks/26c7v3_3uwnwu.js","/_next/static/immutable/chunks/25a3ozcrvi1ff.js","/_next/static/immutable/chunks/2r4wx50nvjh_4.js","/_next/static/immutable/chunks/23fsw06hsi5b1.js","/_next/static/immutable/chunks/06_yt270h41rg.js","/_next/static/immutable/chunks/3ezsiz-7shkna.js","/_next/static/immutable/chunks/20x2y96ldu5wx.js","/_next/static/immutable/chunks/2lxntcm3pd1_h.js","/_next/static/immutable/chunks/00dgco8irq3jw.js","/_next/static/immutable/chunks/00nwe-kq0rboc.js","/_next/static/immutable/chunks/2051ffx3xzio9.js"],"PaperListPageClient"] 30:T8b9,Failure of conventional imaging to detect pancreatic ductal adenocarcinoma (PDA) at its visually occult pre-diagnostic stage is a primary barrier to improving its otherwise poor rate of survival. To develop and validate the Radiomics-based Early Detection MODel (REDMOD), an AI framework to identify subvisual radiomic signatures of pre-diagnostic PDA on standard-of-care CT. REDMOD was trained on a multi-institutional cohort (n=969; 156 pre-diagnostic, 813 control) and tested on an independent set (n=493; 63 pre-diagnostic, 430 control), simulating a low prevalence (~1:6) early detection paradigm. The fully automated framework couples AI-driven segmentation with a heterogeneous ensemble architecture trained on a 40-feature radiomic signature derived from Synthetic Minority Over-sampling Technique (SMOTE)-balanced data. A tunable Youden Index-optimised classification threshold enables performance calibration without retraining. Validation included direct comparison with radiologists, longitudinal test-retest analysis and external specificity validation across two independent cohorts (n=539 and n=80). On an independent test set (n=493), REDMOD identified occult PDA (AUC 0.82; 73.0% sensitivity) at a median 475-day lead time. This represented nearly twofold higher sensitivity than radiologists (38.9%; p<0.001), which grew to nearly threefold (68.0% vs 23.0%) at >24 months lead time. REDMOD showed strong longitudinal stability (90-92% concordance) and generalisable specificity across multi-institutional (81.3%; n=539) and public (87.5%; n=80) datasets. Mechanistic analyses confirmed predictive power derived principally from multi-scale wavelet-filtered textural features (90% of selected signature), which outperformed unfiltered features (AUC 0.82 vs 0.74; p=0.007) in capturing subvisual architectural disruptions. REDMOD is an automated, mechanistically grounded, longitudinally stable, externally validated AI that surpasses radiologists for PDA detection at its visually occult pre-diagnostic stage. These attributes position it for prospective validation in high-risk cohorts, a necessary step towards shifting the paradigm from late-stage symptomatic diagnosis to proactive pre-clinical interception.31:Tba3, Background Failure of conventional imaging to detect pancreatic ductal adenocarcinoma (PDA) at its visually occult pre-diagnostic stage is a primary barrier to improving its otherwise poor rate of survival. Objective To develop and validate the Radiomics-based Early Detection MODel (REDMOD), an AI framework to identify subvisual radiomic signatures of pre-diagnostic PDA on standard-of-care CT. Designs REDMOD was trained on a multi-institutional cohort (n=969; 156 pre-diagnostic, 813 control) and tested on an independent set (n=493; 63 pre-diagnostic, 430 control), simulating a low prevalence (~1:6) early detection paradigm. The fully automated framework couples AI-driven segmentation with a heterogeneous ensemble architecture trained on a 40-feature radiomic signature derived from Synthetic Minority Over-sampling Technique (SMOTE)-balanced data. A tunable Youden Index-optimised classification threshold enables performance calibration without retraining. Validation included direct comparison with radiologists, longitudinal test–retest analysis and external specificity validation across two independent cohorts (n=539 and n=80). Results On an independent test set (n=493), REDMOD identified occult PDA (AUC 0.82; 73.0% sensitivity) at a median 475-day lead time. This represented nearly twofold higher sensitivity than radiologists (38.9%; p<0.001), which grew to nearly threefold (68.0% vs 23.0%) at >24 months lead time. REDMOD showed strong longitudinal stability (90–92% concordance) and generalisable specificity across multi-institutional (81.3%; n=539) and public (87.5%; n=80) datasets. Mechanistic analyses confirmed predictive power derived principally from multi-scale wavelet-filtered textural features (90% of selected signature), which outperformed unfiltered features (AUC 0.82 vs 0.74; p=0.007) in capturing subvisual architectural disruptions. Conclusions REDMOD is an automated, mechanistically grounded, longitudinally stable, externally validated AI that surpasses radiologists for PDA detection at its visually occult pre-diagnostic stage. These attributes position it for prospective validation in high-risk cohorts, a necessary step towards shifting the paradigm from late-stage symptomatic diagnosis to proactive pre-clinical interception. 25:[[["$","script","0",{"type":"application/ld+json","dangerouslySetInnerHTML":{"__html":"{\"@context\":\"https://schema.org\",\"@type\":\"CollectionPage\",\"name\":\"Computed Tomography: modality Research & Clinical Takeaways\",\"description\":\"Explore peer-reviewed papers on Computed Tomography (modality). Clinician-written summaries and actionable practice insights. Updated daily.\",\"url\":\"https://www.reachrx.ai/hub/tag/modality/Computed%20Tomography\",\"breadcrumb\":{\"@type\":\"BreadcrumbList\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https://www.reachrx.ai\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Research Hub\",\"item\":\"https://www.reachrx.ai/hub\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"Modalities\",\"item\":\"https://www.reachrx.ai/hub/tag/modality\"},{\"@type\":\"ListItem\",\"position\":4,\"name\":\"Computed Tomography\",\"item\":\"https://www.reachrx.ai/hub/tag/modality/Computed%20Tomography\"}]}}"}}]],["$","$L2f",null,{"title":"Computed Tomography: Research & Clinical Takeaways","description":"Review evidence by treatment modality: Computed Tomography — concise summaries and practical next steps.","papers":[{"doi":"10.1001/jamaoto.2026.2316","pmid":"42623057","title":"Intentional Imaging for Primary Hyperparathyroidism","journal_title":"JAMA Otolaryngology–Head & Neck Surgery","journal_issn":"2168-6181","published_at":"2026-08-20T00:00:00.000Z","url":"https://doi.org/10.1001/jamaoto.2026.2316","source_score":7,"is_retracted":false,"is_open_access":false,"raw_metadata":{"pubmed":true,"crossref":true,"unpaywall":true},"created_at":"2026-08-26T06:19:53.575Z","updated_at":"2026-08-26T06:19:53.575Z","tags":[{"paper_doi":"10.1001/jamaoto.2026.2316","tag_type":"age_group","value":"adult","value_numeric":null},{"paper_doi":"10.1001/jamaoto.2026.2316","tag_type":"category","value":"Surgery","value_numeric":null},{"paper_doi":"10.1001/jamaoto.2026.2316","tag_type":"condition","value":"Primary Hyperparathyroidism","value_numeric":null},{"paper_doi":"10.1001/jamaoto.2026.2316","tag_type":"generic","value":"choline C-11","value_numeric":null},{"paper_doi":"10.1001/jamaoto.2026.2316","tag_type":"generic","value":"technetium Tc 99m sestamibi","value_numeric":null},{"paper_doi":"10.1001/jamaoto.2026.2316","tag_type":"impact_flag","value":"practice_changing","value_numeric":null},{"paper_doi":"10.1001/jamaoto.2026.2316","tag_type":"level_of_evidence","value":"5","value_numeric":null},{"paper_doi":"10.1001/jamaoto.2026.2316","tag_type":"modality","value":"Computed Tomography","value_numeric":null},{"paper_doi":"10.1001/jamaoto.2026.2316","tag_type":"modality","value":"Nuclear Medicine Imaging","value_numeric":null},{"paper_doi":"10.1001/jamaoto.2026.2316","tag_type":"modality","value":"Positron Emission Tomography","value_numeric":null},{"paper_doi":"10.1001/jamaoto.2026.2316","tag_type":"modality","value":"Ultrasonography","value_numeric":null},{"paper_doi":"10.1001/jamaoto.2026.2316","tag_type":"study_design","value":"Narrative Review","value_numeric":null},{"paper_doi":"10.1001/jamaoto.2026.2316","tag_type":"warning","value":"No original patient data are presented; radiation dose ranges are drawn from referenced sources, not a pooled analysis. Sensitivity/specificity values for each modality are discussed qualitatively but not formally compared. The 'practice_changing' flag reflects the authors' explicit recommendation to limit imaging to confirmed diagnoses and select modalities intentionally — this represents expert opinion, not a trial result.","value_numeric":null}],"summaries":{"what_studied":"A review of preoperative parathyroid imaging modalities for primary hyperparathyroidism (pHPT), comparing radiation exposure (in mSv) across ultrasonography, Tc-99m sestamibi SPECT ± CT, 4D-CT, and choline-based PET ± CT in patients planning parathyroidectomy or revision surgery.","key_result":"Radiation doses vary widely by modality: ultrasound (0 mSv), Tc-99m sestamibi SPECT ± CT (8.6–12.1 mSv), 4D-CT (9.3–20.2 mSv), and choline-based PET ± CT (6.7–11.8 mSv). Authors recommend imaging only after confirmed diagnosis and advocate for intentional, individualized modality selection.","limitations":"This is a narrative review without a systematic meta-analysis or original patient data; radiation exposure ranges are reported but sensitivity/specificity data are referenced rather than pooled. No direct cost-effectiveness analysis is provided.","practice_takeaway":"Confirm the diagnosis of pHPT before ordering any imaging, and start with ultrasound (zero radiation) as the first-line localization study. Reserve higher-dose modalities like 4D-CT or choline PET for revision/complex cases, weighing local expertise and cost alongside radiation burden."}},{"doi":"10.1001/jamapediatrics.2026.3401","pmid":"42573989","title":"Rapid MRI, Not Repeat CT, for Pediatric Head Trauma—A Call to Action","journal_title":"JAMA Pediatrics","journal_issn":"2168-6203","published_at":"2026-08-10T00:00:00.000Z","url":"https://doi.org/10.1001/jamapediatrics.2026.3401","source_score":18,"is_retracted":false,"is_open_access":false,"raw_metadata":{"pubmed":true,"crossref":true,"unpaywall":true},"created_at":"2026-08-17T13:33:05.078Z","updated_at":"2026-08-17T13:33:05.078Z","tags":[{"paper_doi":"10.1001/jamapediatrics.2026.3401","tag_type":"age_group","value":"pediatric","value_numeric":null},{"paper_doi":"10.1001/jamapediatrics.2026.3401","tag_type":"category","value":"Pediatrics","value_numeric":null},{"paper_doi":"10.1001/jamapediatrics.2026.3401","tag_type":"condition","value":"Traumatic Brain Injury","value_numeric":null},{"paper_doi":"10.1001/jamapediatrics.2026.3401","tag_type":"impact_flag","value":"practice_changing","value_numeric":null},{"paper_doi":"10.1001/jamapediatrics.2026.3401","tag_type":"level_of_evidence","value":"7","value_numeric":null},{"paper_doi":"10.1001/jamapediatrics.2026.3401","tag_type":"modality","value":"Computed Tomography","value_numeric":null},{"paper_doi":"10.1001/jamapediatrics.2026.3401","tag_type":"modality","value":"Magnetic Resonance Imaging","value_numeric":null},{"paper_doi":"10.1001/jamapediatrics.2026.3401","tag_type":"study_design","value":"Expert Opinion / Viewpoint","value_numeric":null},{"paper_doi":"10.1001/jamapediatrics.2026.3401","tag_type":"warning","value":"Abstract is brief; full text may contain additional framework details, supporting evidence, or referenced studies not captured here.","value_numeric":null},{"paper_doi":"10.1001/jamapediatrics.2026.3401","tag_type":"warning","value":"The 'practice_changing' impact flag reflects the authors' explicit call to change clinical practice, but the recommendation is not yet supported by prospective clinical trial evidence.","value_numeric":null},{"paper_doi":"10.1001/jamapediatrics.2026.3401","tag_type":"warning","value":"This is a viewpoint/opinion piece, not an original research study — no patient data, sample size, or comparative outcomes are reported.","value_numeric":null}],"summaries":{"what_studied":"A viewpoint proposing a surveillance imaging framework for pediatric traumatic brain injury (TBI), recommending rapid MRI in place of repeat CT after an index CT establishes the diagnosis.","key_result":"The authors call for using rapid MRI—rather than repeat CT—for ongoing surveillance of pediatric TBI, aiming to reduce ionizing radiation exposure in children without sacrificing diagnostic quality.","limitations":"This is an expert opinion/viewpoint with no original clinical data, patient cohort, or comparative outcomes reported; recommendations are not validated by a prospective trial.","practice_takeaway":"When a child's head trauma is first diagnosed by CT, consider switching to rapid MRI for any follow-up imaging to avoid repeat radiation exposure. Institutions should develop protocols to make rapid MRI accessible in the acute pediatric TBI setting."}},{"doi":"10.1136/emermed-2025-215859","pmid":"42431724","title":"Clinician characteristics associated with CT use in children with minor blunt head trauma at very low risk for clinically important traumatic brain injuries","journal_title":"Emergency Medicine Journal","journal_issn":"1472-0205","published_at":"2026-07-10T00:00:00.000Z","url":"https://doi.org/10.1136/emermed-2025-215859","source_score":1,"is_retracted":false,"is_open_access":true,"raw_metadata":{"pubmed":true,"crossref":true,"unpaywall":true},"created_at":"2026-07-19T13:40:00.281Z","updated_at":"2026-07-19T13:40:00.281Z","tags":[{"paper_doi":"10.1136/emermed-2025-215859","tag_type":"age_group","value":"pediatric","value_numeric":null},{"paper_doi":"10.1136/emermed-2025-215859","tag_type":"category","value":"Emergency Medicine","value_numeric":null},{"paper_doi":"10.1136/emermed-2025-215859","tag_type":"condition","value":"Minor Blunt Head Trauma","value_numeric":null},{"paper_doi":"10.1136/emermed-2025-215859","tag_type":"condition","value":"Traumatic Brain Injury","value_numeric":null},{"paper_doi":"10.1136/emermed-2025-215859","tag_type":"impact_flag","value":"practice_changing","value_numeric":null},{"paper_doi":"10.1136/emermed-2025-215859","tag_type":"level_of_evidence","value":"2","value_numeric":null},{"paper_doi":"10.1136/emermed-2025-215859","tag_type":"modality","value":"Computed Tomography","value_numeric":null},{"paper_doi":"10.1136/emermed-2025-215859","tag_type":"sample_size","value":"n=8957","value_numeric":8957},{"paper_doi":"10.1136/emermed-2025-215859","tag_type":"sex","value":"mixed","value_numeric":null},{"paper_doi":"10.1136/emermed-2025-215859","tag_type":"study_design","value":"Prospective Multicentre Cohort Study","value_numeric":null},{"paper_doi":"10.1136/emermed-2025-215859","tag_type":"warning","value":"88% clinician survey completion rate is high but ~12% non-response could introduce some bias in clinician-level estimates.","value_numeric":null},{"paper_doi":"10.1136/emermed-2025-215859","tag_type":"warning","value":"Sample size (n=8,957) reflects only the very low-risk PECARN-negative subgroup, not the full study cohort of all minor head trauma patients; total enrolled children are not explicitly reported in this abstract.","value_numeric":null},{"paper_doi":"10.1136/emermed-2025-215859","tag_type":"warning","value":"The 'avoidance of uncertain outcomes' measure is a self-reported psychometric construct whose specific validated instrument is not described in the abstract — clinical interpretation should be cautious.","value_numeric":null}],"summaries":{"what_studied":"This prospective multicentre study examined which clinician-level characteristics were associated with CT ordering in children classified as very low risk for clinically important traumatic brain injury (ciTBI) by the PECARN TBI clinical prediction rules (CPRs), enrolling 8,957 such children across 481 ED clinicians.","key_result":"7.3% (654/8,957) of very low-risk children received a CT scan. In multivariable analysis, CT ordering was independently associated with more years of clinical experience (aOR 1.02 per year, 95% CI 1.00–1.03), caring for <50% children in one's practice (aOR 1.55, 95% CI 1.13–2.12), and higher avoidance of uncertain outcomes (aOR 1.31, 95% CI 1.02–1.69).","limitations":"Survey self-report introduces social desirability bias; the study cannot establish causality between clinician traits and CT ordering; generalizability may be limited to centres participating in PECARN-affiliated research networks.","practice_takeaway":"Clinicians with less paediatric caseload, more years of experience, and lower risk tolerance are more likely to CT scan very low-risk children — consider targeted education and involving paediatric-focused providers in imaging decisions to reduce unnecessary radiation exposure."}},{"doi":"10.1001/jamadermatol.2026.2163","pmid":"42418212","title":"Consensus Guidelines for Staging and Surveillance Imaging in Cutaneous Squamous Cell Carcinoma","journal_title":"JAMA Dermatology","journal_issn":"2168-6068","published_at":"2026-07-08T00:00:00.000Z","url":"https://doi.org/10.1001/jamadermatol.2026.2163","source_score":10,"is_retracted":false,"is_open_access":false,"raw_metadata":{"pubmed":true,"crossref":true,"unpaywall":true},"created_at":"2026-07-12T13:19:34.247Z","updated_at":"2026-07-12T13:19:34.247Z","tags":[{"paper_doi":"10.1001/jamadermatol.2026.2163","tag_type":"age_group","value":"adult","value_numeric":null},{"paper_doi":"10.1001/jamadermatol.2026.2163","tag_type":"category","value":"Dermatology","value_numeric":null},{"paper_doi":"10.1001/jamadermatol.2026.2163","tag_type":"condition","value":"Cutaneous Squamous Cell Carcinoma","value_numeric":null},{"paper_doi":"10.1001/jamadermatol.2026.2163","tag_type":"impact_flag","value":"practice_changing","value_numeric":null},{"paper_doi":"10.1001/jamadermatol.2026.2163","tag_type":"level_of_evidence","value":"5","value_numeric":null},{"paper_doi":"10.1001/jamadermatol.2026.2163","tag_type":"modality","value":"Computed Tomography","value_numeric":null},{"paper_doi":"10.1001/jamadermatol.2026.2163","tag_type":"sample_size","value":"n=45","value_numeric":45},{"paper_doi":"10.1001/jamadermatol.2026.2163","tag_type":"sex","value":"mixed","value_numeric":null},{"paper_doi":"10.1001/jamadermatol.2026.2163","tag_type":"study_design","value":"Delphi Consensus Study","value_numeric":null},{"paper_doi":"10.1001/jamadermatol.2026.2163","tag_type":"warning","value":"Delphi panels reflect expert opinion (Level 5 evidence); these recommendations should not be treated as equivalent to guideline recommendations backed by clinical trial data.","value_numeric":null},{"paper_doi":"10.1001/jamadermatol.2026.2163","tag_type":"warning","value":"The 15% metastasis risk threshold used to trigger imaging is a consensus-derived benchmark, not validated in prospective studies — apply with clinical judgment.","value_numeric":null},{"paper_doi":"10.1001/jamadermatol.2026.2163","tag_type":"warning","value":"The panel was predominantly White and academic — applicability to diverse or community practice settings may be limited.","value_numeric":null}],"summaries":{"what_studied":"A multidisciplinary Delphi consensus panel (n=45) evaluated when and how to use staging and surveillance imaging for localized cutaneous squamous cell carcinoma (CSCC), across 3 iterative survey rounds (January–June 2025).","key_result":"Consensus (≥80% agreement) was reached to recommend imaging for CSCCs with ≥15% metastasis risk — including tumors ≥4 cm, bone invasion, invasion beyond subcutaneous fat, or large-caliber nerve invasion. CT was the preferred modality for both nodal staging (84%) and surveillance (78%). Consensus supported imaging surveillance for at least 2 years; near-consensus (70–79%) supported at least 3 years.","limitations":"Expert opinion-based Delphi design without prospective clinical validation; panel was predominantly White (67%) and academic, which may limit generalizability; thresholds (e.g., 15% metastasis risk) are consensus-derived, not empirically tested.","practice_takeaway":"For CSCC with high-risk features — diameter ≥4 cm, bone or deep soft tissue invasion, large-caliber perineural invasion, or poorly differentiated histology combined with ≥2 cm size or lymphovascular invasion — obtain CT imaging for nodal staging and plan surveillance imaging for at least 2–3 years. Use this framework to standardize practice while awaiting prospective guideline data."}},{"doi":"10.1111/1742-6723.70305","pmid":"42366324","title":"Implementation of Electronic Clinical Decision Support for Radiology Referrals: The Role of Governance, Clinician Engagement and Education","journal_title":"Emergency Medicine Australasia","journal_issn":"1742-6731","published_at":"2026-06-28T00:00:00.000Z","url":"https://doi.org/10.1111/1742-6723.70305","source_score":1,"is_retracted":false,"is_open_access":true,"raw_metadata":{"pubmed":true,"crossref":true,"unpaywall":true},"created_at":"2026-07-02T13:33:26.229Z","updated_at":"2026-07-02T13:33:26.229Z","tags":[{"paper_doi":"10.1111/1742-6723.70305","tag_type":"age_group","value":"mixed","value_numeric":null},{"paper_doi":"10.1111/1742-6723.70305","tag_type":"brand","value":"Cerner Millennium","value_numeric":null},{"paper_doi":"10.1111/1742-6723.70305","tag_type":"brand","value":"MedCurrent OrderWise","value_numeric":null},{"paper_doi":"10.1111/1742-6723.70305","tag_type":"category","value":"Emergency Medicine","value_numeric":null},{"paper_doi":"10.1111/1742-6723.70305","tag_type":"condition","value":"Imaging Overutilisation","value_numeric":null},{"paper_doi":"10.1111/1742-6723.70305","tag_type":"condition","value":"Pulmonary Embolism","value_numeric":null},{"paper_doi":"10.1111/1742-6723.70305","tag_type":"impact_flag","value":"practice_changing","value_numeric":null},{"paper_doi":"10.1111/1742-6723.70305","tag_type":"level_of_evidence","value":"4","value_numeric":null},{"paper_doi":"10.1111/1742-6723.70305","tag_type":"modality","value":"Clinical Decision Support System","value_numeric":null},{"paper_doi":"10.1111/1742-6723.70305","tag_type":"modality","value":"Computed Tomography","value_numeric":null},{"paper_doi":"10.1111/1742-6723.70305","tag_type":"sex","value":"mixed","value_numeric":null},{"paper_doi":"10.1111/1742-6723.70305","tag_type":"study_design","value":"Descriptive Implementation Study","value_numeric":null},{"paper_doi":"10.1111/1742-6723.70305","tag_type":"warning","value":"No inferential statistics were performed; observed utilisation changes cannot be causally attributed to eCDS or the engagement programme alone.","value_numeric":null},{"paper_doi":"10.1111/1742-6723.70305","tag_type":"warning","value":"Sample size (number of patients or ED presentations) is not reported as a discrete figure — only utilisation rates per 100 ED presentations are provided, so a sample_size tag was omitted.","value_numeric":null},{"paper_doi":"10.1111/1742-6723.70305","tag_type":"warning","value":"The impact_flag 'practice_changing' reflects the finding that pre-go-live engagement alone drove a measurable utilisation shift, which has direct workflow implications — but evidence level is observational.","value_numeric":null},{"paper_doi":"10.1111/1742-6723.70305","tag_type":"warning","value":"The study covers multiple time periods (2017–2025); the 'engagement phase' and 'deployment phase' findings reflect institutional trends, not controlled comparisons.","value_numeric":null}],"summaries":{"what_studied":"This descriptive implementation study examined an organisational strategy for deploying an electronic Clinical Decision Support (eCDS) system (MedCurrent OrderWise integrated into Cerner Millennium EMR) for imaging referrals at a quaternary ED in Melbourne, Australia, evaluating CT utilisation trends across pre-engagement, engagement, and deployment phases from 2017 to mid-2025.","key_result":"CT utilisation rose from 32 to 44 per 100 ED presentations pre-eCDS. During the pre-go-live clinician engagement and education phase, CT ordering fell by 9.1% (44 → 40 per 100 ED presentations). After eCDS deployment, utilisation stabilised without further decline. For CTPA specifically, eCDS recommended alternative investigations in 28.8% of cases and CTPA positivity improved from 11.6% to 12.9%.","limitations":"- Single-centre, descriptive design with no inferential statistics — causal attribution to eCDS is not possible.\n- CT per ED presentation is an indirect surrogate; imaging appropriateness and decision quality were not formally assessed.\n- Concurrent education initiatives and organisational changes may independently explain observed utilisation shifts.","practice_takeaway":"Clinician engagement and education before eCDS go-live may drive early reductions in CT ordering — consider launching these activities well ahead of system deployment. Passive eCDS rollout alone is unlikely to achieve lasting change; governance structures and sustained education are key."}},{"doi":"10.1186/s12873-026-01658-w","pmid":"42343206","title":"Development of a novel clinical decision support tool for determining the need for whole-body computed tomography in pediatric trauma patients: the WHOLE score","journal_title":"BMC Emergency Medicine","journal_issn":"1471-227X","published_at":"2026-06-24T00:00:00.000Z","url":"https://doi.org/10.1186/s12873-026-01658-w","source_score":1,"is_retracted":false,"is_open_access":true,"raw_metadata":{"pubmed":true,"crossref":true,"unpaywall":true},"created_at":"2026-07-02T13:33:26.712Z","updated_at":"2026-07-02T13:33:26.712Z","tags":[{"paper_doi":"10.1186/s12873-026-01658-w","tag_type":"age_group","value":"pediatric","value_numeric":null},{"paper_doi":"10.1186/s12873-026-01658-w","tag_type":"category","value":"Emergency Medicine","value_numeric":null},{"paper_doi":"10.1186/s12873-026-01658-w","tag_type":"condition","value":"Pediatric Trauma","value_numeric":null},{"paper_doi":"10.1186/s12873-026-01658-w","tag_type":"impact_flag","value":"limited_evidence","value_numeric":null},{"paper_doi":"10.1186/s12873-026-01658-w","tag_type":"level_of_evidence","value":"4","value_numeric":null},{"paper_doi":"10.1186/s12873-026-01658-w","tag_type":"modality","value":"Computed Tomography","value_numeric":null},{"paper_doi":"10.1186/s12873-026-01658-w","tag_type":"sample_size","value":"n=407","value_numeric":407},{"paper_doi":"10.1186/s12873-026-01658-w","tag_type":"sex","value":"mixed","value_numeric":null},{"paper_doi":"10.1186/s12873-026-01658-w","tag_type":"study_design","value":"Retrospective Observational Study","value_numeric":null},{"paper_doi":"10.1186/s12873-026-01658-w","tag_type":"warning","value":"No external or prospective validation cohort exists; the score's performance in other centers or populations is unknown.","value_numeric":null},{"paper_doi":"10.1186/s12873-026-01658-w","tag_type":"warning","value":"The age threshold of ≥133 months (~11 years) as a predictor is an unusual cut-point derived from ROC analysis and may not be clinically intuitive.","value_numeric":null},{"paper_doi":"10.1186/s12873-026-01658-w","tag_type":"warning","value":"The primary outcome (multi-region injury on WBCT) is a surrogate marker and does not directly capture clinical necessity of WBCT, limiting direct translation to practice.","value_numeric":null},{"paper_doi":"10.1186/s12873-026-01658-w","tag_type":"warning","value":"Trial registration was done retrospectively (February 2026 for a study conducted in 2021–2022), which is a methodological concern.","value_numeric":null}],"summaries":{"what_studied":"This single-center retrospective study developed the WHOLE score — a clinical decision support tool to identify pediatric trauma patients (under 18 years) at low risk for multi-region injuries on WBCT, using data from 407 patients at a tertiary pediatric trauma center (June 2021–June 2022).","key_result":"The WHOLE score (range 0–8) achieved an AUC of 0.84 (95% CI 0.80–0.88). At a cut-off of ≥2 points, sensitivity was 96.7% (CI 92.5–98.9) and NPV was 94.8% for detecting injuries in ≥2 anatomical regions (present in 37.6%, n=153/407). Independent predictors included age ≥133 months, tachycardia, hypoxia, head/thoracic/pelvic/lower extremity exam findings, and AST ≥50 U/L.","limitations":"- Single-center derivation study with no external validation cohort — findings may not generalize.\n- Primary outcome (multi-region injury on WBCT) does not directly measure clinical need for WBCT.\n- Study protocol was registered retrospectively, raising potential for selection or reporting bias.","practice_takeaway":"A WHOLE score of 0–1 may safely support withholding WBCT in low-risk pediatric trauma patients, potentially reducing radiation exposure; however, do not use this score in routine practice until prospective external validation is completed."}},{"doi":"10.1016/j.ajem.2026.06.003","pmid":null,"title":"Cranial CT yield and predictors in children aged 0–36 months with head trauma","journal_title":"The American Journal of Emergency Medicine","journal_issn":"0735-6757","published_at":"2026-06-03T00:00:00.000Z","url":"https://doi.org/10.1016/j.ajem.2026.06.003","source_score":1,"is_retracted":false,"is_open_access":false,"raw_metadata":{"pubmed":false,"crossref":true,"unpaywall":true},"created_at":"2026-06-10T14:24:06.761Z","updated_at":"2026-06-10T14:24:06.761Z","tags":[{"paper_doi":"10.1016/j.ajem.2026.06.003","tag_type":"age_group","value":"child","value_numeric":null},{"paper_doi":"10.1016/j.ajem.2026.06.003","tag_type":"age_group","value":"infant","value_numeric":null},{"paper_doi":"10.1016/j.ajem.2026.06.003","tag_type":"category","value":"Emergency Medicine","value_numeric":null},{"paper_doi":"10.1016/j.ajem.2026.06.003","tag_type":"condition","value":"Head Trauma","value_numeric":null},{"paper_doi":"10.1016/j.ajem.2026.06.003","tag_type":"condition","value":"Traumatic Brain Injury","value_numeric":null},{"paper_doi":"10.1016/j.ajem.2026.06.003","tag_type":"impact_flag","value":"limited_evidence","value_numeric":null},{"paper_doi":"10.1016/j.ajem.2026.06.003","tag_type":"modality","value":"Computed Tomography","value_numeric":null},{"paper_doi":"10.1016/j.ajem.2026.06.003","tag_type":"study_design","value":"Observational Study","value_numeric":null},{"paper_doi":"10.1016/j.ajem.2026.06.003","tag_type":"warning","value":"Only paper metadata (title, DOI, journal, publication date) was provided — no abstract, methods, results, or full text were available. Key result, sample size, and most tags could not be extracted. Summaries are based solely on the title and inferred study scope.","value_numeric":null},{"paper_doi":"10.1016/j.ajem.2026.06.003","tag_type":"warning","value":"Publication date is June 3, 2026, which is within days of today's date — full text may not yet be broadly accessible.","value_numeric":null},{"paper_doi":"10.1016/j.ajem.2026.06.003","tag_type":"warning","value":"Study design is inferred from context (likely retrospective or prospective observational); this could not be confirmed from the available text.","value_numeric":null}],"summaries":{"what_studied":"This study evaluated the diagnostic yield of cranial CT and identified clinical predictors of positive CT findings in children aged 0–36 months presenting to the emergency department with head trauma.","limitations":"The paper metadata provided does not include full-text results, limiting extraction of specific outcomes, sample size, or quantitative predictors.","practice_takeaway":"Identifying reliable clinical predictors for cranial CT in young children with head trauma can help reduce unnecessary radiation exposure; clinicians should await validated decision rules before broadly applying findings."}},{"doi":"10.1002/acr.80083","pmid":"42112848","title":"Rheumatoid Arthritis and Coronary Artery Calcium Progression: A Case Cohort Analysis From\n ELSA\n ‐Brasil","journal_title":"Arthritis Care & Research","journal_issn":"2151-464X","published_at":"2026-05-26T00:00:00.000Z","url":"https://doi.org/10.1002/acr.80083","source_score":3,"is_retracted":false,"is_open_access":true,"raw_metadata":{"pubmed":true,"crossref":true,"unpaywall":true},"created_at":"2026-06-22T13:23:58.049Z","updated_at":"2026-06-22T13:23:58.049Z","tags":[{"paper_doi":"10.1002/acr.80083","tag_type":"age_group","value":"adult","value_numeric":null},{"paper_doi":"10.1002/acr.80083","tag_type":"category","value":"Rheumatology","value_numeric":null},{"paper_doi":"10.1002/acr.80083","tag_type":"condition","value":"Coronary Artery Calcification","value_numeric":null},{"paper_doi":"10.1002/acr.80083","tag_type":"condition","value":"Rheumatoid Arthritis","value_numeric":null},{"paper_doi":"10.1002/acr.80083","tag_type":"condition","value":"Subclinical Atherosclerosis","value_numeric":null},{"paper_doi":"10.1002/acr.80083","tag_type":"impact_flag","value":"practice_changing","value_numeric":null},{"paper_doi":"10.1002/acr.80083","tag_type":"level_of_evidence","value":"3","value_numeric":null},{"paper_doi":"10.1002/acr.80083","tag_type":"modality","value":"Computed Tomography","value_numeric":null},{"paper_doi":"10.1002/acr.80083","tag_type":"sample_size","value":"n=585","value_numeric":585},{"paper_doi":"10.1002/acr.80083","tag_type":"sex","value":"mixed","value_numeric":null},{"paper_doi":"10.1002/acr.80083","tag_type":"study_design","value":"Case-Cohort Study","value_numeric":null},{"paper_doi":"10.1002/acr.80083","tag_type":"warning","value":"Impact flag 'practice_changing' applied cautiously: the finding is novel and biologically plausible, but the small RA follow-up sample (n=58) warrants replication before firm guideline changes.","value_numeric":null},{"paper_doi":"10.1002/acr.80083","tag_type":"warning","value":"No information on RA treatment (DMARDs, biologics, corticosteroids) was reported in the abstract, which is a key potential confounder for both inflammation and cardiovascular risk.","value_numeric":null},{"paper_doi":"10.1002/acr.80083","tag_type":"warning","value":"The incidence odds ratio has an extremely wide 95% CI (0.05–3.08), suggesting the study was underpowered for that specific outcome — interpret with caution.","value_numeric":null}],"summaries":{"what_studied":"A case-cohort study within ELSA-Brasil examined whether RA is associated with CAC prevalence, incidence, and progression over 4 years in 585 adults (86 with RA, 499 controls) without prior cardiovascular disease, using CT-based Agatston scoring.","key_result":"RA was not linked to CAC prevalence (OR 1.34; 95% CI 0.69–2.55) or incidence (OR 0.83; 95% CI 0.05–3.08), but was strongly associated with CAC progression (OR 3.11–4.29 across models; bootstrap 95% CI 1.52–14.65).","limitations":"- Small RA sample (86 at baseline, 58 at follow-up) limits precision, especially for incidence estimates with very wide CIs.\n- Case-cohort design within a single Brazilian cohort may limit generalizability.\n- Residual confounding from RA disease activity, treatment (e.g., DMARDs, steroids), and cardiovascular risk factors cannot be excluded.","practice_takeaway":"Even when baseline coronary calcium is absent or low, patients with RA may experience faster CAC progression — a marker of subclinical atherosclerosis. Clinicians should consider longitudinal cardiovascular monitoring in RA patients, regardless of initial CAC score."}},{"doi":"10.1097/tp.0000000000005748","pmid":"42132499","title":"Automated Computed Tomography–based Liver Steatosis Risk Stratification of Deceased Organ Donors Using Real-world Data","journal_title":"Transplantation","journal_issn":"0041-1337","published_at":"2026-05-13T00:00:00.000Z","url":"https://doi.org/10.1097/tp.0000000000005748","source_score":30,"is_retracted":false,"is_open_access":false,"raw_metadata":{"pubmed":true,"crossref":true,"unpaywall":true},"created_at":"2026-06-01T13:39:36.319Z","updated_at":"2026-06-01T13:39:36.319Z","tags":[{"paper_doi":"10.1097/tp.0000000000005748","tag_type":"age_group","value":"adult","value_numeric":null},{"paper_doi":"10.1097/tp.0000000000005748","tag_type":"category","value":"Surgery","value_numeric":null},{"paper_doi":"10.1097/tp.0000000000005748","tag_type":"condition","value":"Hepatic Steatosis","value_numeric":null},{"paper_doi":"10.1097/tp.0000000000005748","tag_type":"condition","value":"Liver Transplantation","value_numeric":null},{"paper_doi":"10.1097/tp.0000000000005748","tag_type":"impact_flag","value":"practice_changing","value_numeric":null},{"paper_doi":"10.1097/tp.0000000000005748","tag_type":"level_of_evidence","value":"3","value_numeric":null},{"paper_doi":"10.1097/tp.0000000000005748","tag_type":"modality","value":"Computed Tomography","value_numeric":null},{"paper_doi":"10.1097/tp.0000000000005748","tag_type":"modality","value":"Machine Learning","value_numeric":null},{"paper_doi":"10.1097/tp.0000000000005748","tag_type":"modality","value":"Radiomics","value_numeric":null},{"paper_doi":"10.1097/tp.0000000000005748","tag_type":"sample_size","value":"n=147","value_numeric":147},{"paper_doi":"10.1097/tp.0000000000005748","tag_type":"sex","value":"mixed","value_numeric":null},{"paper_doi":"10.1097/tp.0000000000005748","tag_type":"study_design","value":"Retrospective Cohort Study","value_numeric":null},{"paper_doi":"10.1097/tp.0000000000005748","tag_type":"warning","value":"Donor age and sex distributions are not reported in the available text; the 'mixed' sex tag is assumed based on typical organ donor populations.","value_numeric":null},{"paper_doi":"10.1097/tp.0000000000005748","tag_type":"warning","value":"The full text of the paper was not accessible — only the abstract and results sections were available for extraction; the publisher permissions page was returned instead of the manuscript body.","value_numeric":null},{"paper_doi":"10.1097/tp.0000000000005748","tag_type":"warning","value":"The 'practice_changing' impact flag is applied cautiously — the study is single-center and small, but the performance data suggest meaningful clinical utility if validated externally.","value_numeric":null}],"summaries":{"what_studied":"This study evaluated automated CT-based methods for predicting macrovesicular steatosis ≥30% in deceased organ donors, comparing 7 approaches—from clinical-only models to radiomics and a 3D convolutional neural network—using 147 CT scans with paired liver biopsies from a single organ procurement organization (2019–2024).","key_result":"The 2-step model (liver-spleen difference + radiomics with XGBoost) achieved the best performance (AUROC 0.87, IQR 0.81–0.92), significantly outperforming the clinical-only model (AUROC 0.65, IQR 0.57–0.72; P=0.028). Even simple univariable models performed well: liver attenuation AUROC 0.81, liver-to-spleen ratio 0.84, liver-spleen difference 0.83.","limitations":"Single-center organ procurement organization limits generalizability; small sample (n=147) with only 25.9% positive cases; 11.6% contrast-enhanced scans only, which may reduce CT attenuation accuracy for steatosis assessment.","practice_takeaway":"Automated CT radiomic analysis can reliably flag donor livers at risk for significant macrovesicular steatosis (≥30%), potentially accelerating the donor evaluation process. Even simpler metrics like liver-to-spleen attenuation ratio perform well and may support rapid triage without complex modeling."}},{"doi":"10.1111/acem.70299","pmid":"42108559","title":"Clinical Features,\n CT\n Imaging Decisions and Yield by Age in Adults With Abdominal Pain in the Emergency Department","journal_title":"Academic Emergency Medicine","journal_issn":"1069-6563","published_at":"2026-05-10T00:00:00.000Z","url":"https://doi.org/10.1111/acem.70299","source_score":1,"is_retracted":false,"is_open_access":true,"raw_metadata":{"pubmed":true,"crossref":true,"unpaywall":true},"created_at":"2026-05-18T13:25:34.600Z","updated_at":"2026-05-18T13:25:34.600Z","tags":[{"paper_doi":"10.1111/acem.70299","tag_type":"age_group","value":"mixed","value_numeric":null},{"paper_doi":"10.1111/acem.70299","tag_type":"category","value":"Emergency Medicine","value_numeric":null},{"paper_doi":"10.1111/acem.70299","tag_type":"condition","value":"Abdominal Pain","value_numeric":null},{"paper_doi":"10.1111/acem.70299","tag_type":"impact_flag","value":"confirms_prior","value_numeric":null},{"paper_doi":"10.1111/acem.70299","tag_type":"level_of_evidence","value":"3","value_numeric":null},{"paper_doi":"10.1111/acem.70299","tag_type":"modality","value":"Computed Tomography","value_numeric":null},{"paper_doi":"10.1111/acem.70299","tag_type":"sample_size","value":"n=1169","value_numeric":1169},{"paper_doi":"10.1111/acem.70299","tag_type":"sex","value":"mixed","value_numeric":null},{"paper_doi":"10.1111/acem.70299","tag_type":"study_design","value":"Retrospective Cohort Study","value_numeric":null},{"paper_doi":"10.1111/acem.70299","tag_type":"warning","value":"Clinician 'index of suspicion' was self-reported on a 1–10 scale; subjective reporting bias cannot be excluded.","value_numeric":null},{"paper_doi":"10.1111/acem.70299","tag_type":"warning","value":"CT modality (non-contrast vs. contrast vs. angiography) was not differentiated, limiting interpretation of yield by scan type.","value_numeric":null},{"paper_doi":"10.1111/acem.70299","tag_type":"warning","value":"Data are from a single 10-month period (2016–2017) at one urban community hospital — practice patterns and patient demographics may not reflect current national trends or other settings.","value_numeric":null},{"paper_doi":"10.1111/acem.70299","tag_type":"warning","value":"Lactic acid and hepatobiliary/pancreatic labs were not available in the dataset, which may affect completeness of adverse outcome capture.","value_numeric":null},{"paper_doi":"10.1111/acem.70299","tag_type":"warning","value":"The 'older adult' cutoff was set at ≥60 years for statistical power reasons, which is younger than the commonly used ≥65 threshold; findings may underestimate age-related differences.","value_numeric":null}],"summaries":{"what_studied":"This retrospective analysis of a prospective cohort (March 2016–January 2017) examined 1,169 adult ED visits for non-traumatic abdominal pain at a single community teaching hospital in southwest Baltimore, comparing CT utilization, CT diagnostic yield, admission, surgery, and physical exam operating characteristics across three age groups: 18–39, 40–59, and ≥60 years.","key_result":"CT ordering rose with age (41.7% → 66.2% → 70.7%; p<0.001), as did CT yield (18.4% → 31.2% → 37.7%; p<0.001), admissions (12.1% → 28.0% → 37.6%), and surgeries (4.6% → 9.0% → 10.6%). Despite similar clinician-reported pretest suspicion across age groups, abdominal tenderness was less sensitive for adverse outcomes in older adults (sensitivity 0.58 in ≥60 vs. 0.73 in younger groups), while rebound tenderness remained highly specific across all ages (specificity 0.96–0.98).","limitations":"- Single urban community hospital in southwest Baltimore limits generalizability.\n- Small number of patients ≥60 (n=229) reduced power for subgroup analyses within older adults.\n- No follow-up data beyond index visit (no 30-day mortality, ED revisits, or missed diagnoses among CT-negative patients).","practice_takeaway":"In older adults with ED abdominal pain, physical exam findings like tenderness are less reliable — clinicians should maintain a lower threshold for CT even when the exam seems reassuring. The persistently higher CT yield in older adults suggests that current imaging rates may still be insufficient to capture all actionable pathology in this group."}},{"doi":"10.1136/gutjnl-2025-337266","pmid":"42049489","title":"Next-generation AI for visually occult pancreatic cancer detection in a low-prevalence setting with longitudinal stability and multi-institutional generalisability","journal_title":"Gut","journal_issn":"0017-5749","published_at":"2026-04-29T00:00:00.000Z","url":"https://doi.org/10.1136/gutjnl-2025-337266","source_score":659,"is_retracted":false,"is_open_access":false,"raw_metadata":{"ooir":{"day":"2026-05-06","doi":"10.1136/gutjnl-2025-337266","days":"14","issn":"0017-5749","rank":"1","field":"Clinical Medicine","score":"659","category":"Gastroenterology & Hepatology","categories":["Gastroenterology & Hepatology"],"_categories":["Gastroenterology & Hepatology"]},"pubmed":{"doi":"10.1136/gutjnl-2025-337266","title":"Next-generation AI for visually occult pancreatic cancer detection in a low-prevalence setting with longitudinal stability and multi-institutional generalisability.","journal":"Gut","methods":"","results":"On an independent test set (n=493), REDMOD identified occult PDA (AUC 0.82; 73.0% sensitivity) at a median 475-day lead time. This represented nearly twofold higher sensitivity than radiologists (38.9%; p<0.001), which grew to nearly threefold (68.0% vs 23.0%) at >24 months lead time. REDMOD showed strong longitudinal stability (90-92% concordance) and generalisable specificity across multi-institutional (81.3%; n=539) and public (87.5%; n=80) datasets. Mechanistic analyses confirmed predictive power derived principally from multi-scale wavelet-filtered textural features (90% of selected signature), which outperformed unfiltered features (AUC 0.82 vs 0.74; p=0.007) in capturing subvisual architectural disruptions.","abstract":"$30","keywords":["AI (Artificial Intelligence)","IMAGING","PANCREAS","PANCREATIC CANCER","PANCREATIC TUMOURS"],"pubmed_id":"42049489","conclusions":"","publication_date":"2026-04-29T00:00:00"},"crossref":{"DOI":"10.1136/gutjnl-2025-337266","URL":"https://doi.org/10.1136/gutjnl-2025-337266","ISSN":["0017-5749","1468-3288"],"link":[{"URL":"https://syndication.highwire.org/content/doi/10.1136/gutjnl-2025-337266","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"page":"gutjnl-2025-337266","type":"journal-article","issue":null,"score":1,"title":["Next-generation AI for visually occult pancreatic cancer detection in a low-prevalence setting with longitudinal stability and multi-institutional generalisability"],"author":[{"given":"Sovanlal","family":"Mukherjee","sequence":"first","affiliation":[{"name":"Department of Radiology, Mayo Clinic, Rochester, Minnesota, USA"}]},{"given":"Ajith","family":"Antony","sequence":"additional","affiliation":[{"name":"Department of Radiology, Mayo Clinic, Rochester, Minnesota, USA"},{"name":"Radiology, University of Texas MD Anderson Cancer Center, Houston, Texas, USA"}]},{"given":"Nandakumar G","family":"Patnam","sequence":"additional","affiliation":[{"name":"Department of Radiology, Mayo Clinic, Rochester, Minnesota, USA"},{"name":"Radiology, University of Washington, Seattle, Washington, USA"}]},{"given":"Kamaxi H","family":"Trivedi","sequence":"additional","affiliation":[{"name":"Department of Radiology, Mayo Clinic, Rochester, Minnesota, USA"},{"name":"Radiology, University of Washington, Seattle, Washington, USA"}]},{"given":"Aashna","family":"Karbhari","sequence":"additional","affiliation":[{"name":"Department of Radiology, Mayo Clinic, Rochester, Minnesota, USA"},{"name":"Radiology, University of Washington, Seattle, Washington, USA"}]},{"given":"Khurram Khaliq","family":"Bhinder","sequence":"additional","affiliation":[{"name":"Department of Radiology, Mayo Clinic, Rochester, Minnesota, USA"}]},{"given":"Armin","family":"Zarrintan","sequence":"additional","affiliation":[{"name":"Department of Radiology, Mayo Clinic, Rochester, Minnesota, USA"}]},{"given":"Joel G","family":"Fletcher","sequence":"additional","affiliation":[{"name":"Department of Radiology, Mayo Clinic, Rochester, Minnesota, USA"}]},{"given":"Mark","family":"Truty","sequence":"additional","affiliation":[{"name":"Surgery, Mayo Clinic, Rochester, Minnesota, USA"}]},{"given":"Matthew P","family":"Johnson","sequence":"additional","affiliation":[{"name":"Quantitative Health Sciences, Mayo Clinic, Rochester, Minnesota, USA"}]},{"given":"Suresh T","family":"Chari","sequence":"additional","affiliation":[{"name":"Gastroenterology, Hepatology and Nutrition, University of Texas MD Anderson Cancer Center, Houston, Texas, USA"}]},{"given":"Ajit Harishkumar","family":"Goenka","sequence":"additional","affiliation":[{"name":"Department of Radiology, Mayo Clinic, Rochester, Minnesota, USA"}]}],"funder":[{"name":"Champions for Hope Pancreatic Cancer Research Program of the Funk Zitiello Foundation"},{"name":"Hoveida Family Foundation"},{"name":"Mayo Clinic Comprehensive Cancer Center"},{"id":[{"id":"10.13039/100000002","id-type":"DOI","asserted-by":"publisher"}],"DOI":"10.13039/100000002","name":"National Institutes of Health","award":["R01CA256969"],"award-info":[{"award-number":["R01CA256969"]}],"doi-asserted-by":"publisher"},{"id":[{"id":"10.13039/100000002","id-type":"DOI","asserted-by":"publisher"}],"DOI":"10.13039/100000002","name":"National Institutes of Health","award":["R01CA272628"],"award-info":[{"award-number":["R01CA272628"]}],"doi-asserted-by":"publisher"},{"name":"Centene Charitable Foundation"}],"issued":{"date-parts":[[2026,4,28]]},"member":"239","prefix":"10.1136","source":"Crossref","volume":null,"created":{"date-time":"2026-04-29T00:00:11Z","timestamp":1777420811000,"date-parts":[[2026,4,29]]},"indexed":{"date-time":"2026-05-12T22:04:56Z","timestamp":1778623496231,"date-parts":[[2026,5,12]]},"license":[{"URL":"https://creativecommons.org/licenses/by-nc/4.0/","start":{"date-time":"2026-04-28T00:00:00Z","timestamp":1777334400000,"date-parts":[[2026,4,28]]},"delay-in-days":0,"content-version":"unspecified"}],"subject":[],"abstract":"$31","accepted":{"date-parts":[[2026,3,5]]},"language":"en","relation":{},"resource":{"primary":{"URL":"https://gut.bmj.com/lookup/doi/10.1136/gutjnl-2025-337266"}},"subtitle":[],"deposited":{"date-time":"2026-04-29T00:00:15Z","timestamp":1777420815000,"date-parts":[[2026,4,29]]},"issn-type":[{"type":"print","value":"0017-5749"},{"type":"electronic","value":"1468-3288"}],"published":{"date-parts":[[2026,4,28]]},"publisher":"BMJ","reference":[{"DOI":"10.3322/caac.21871","key":"2026042817000558000_gutjnl-2025-337266v1.1","year":null,"issue":null,"author":null,"volume":null,"first-page":null,"unstructured":null,"article-title":null,"journal-title":null,"doi-asserted-by":"publisher"},{"DOI":"10.1097/MPA.0000000000001762","key":"2026042817000558000_gutjnl-2025-337266v1.2","year":null,"issue":null,"author":null,"volume":null,"first-page":null,"unstructured":null,"article-title":null,"journal-title":null,"doi-asserted-by":"publisher"},{"DOI":"10.1097/MPA.0000000000000368","key":"2026042817000558000_gutjnl-2025-337266v1.3","year":null,"issue":null,"author":null,"volume":null,"first-page":null,"unstructured":null,"article-title":null,"journal-title":null,"doi-asserted-by":"publisher"},{"DOI":null,"key":"2026042817000558000_gutjnl-2025-337266v1.4","year":"2025","issue":null,"author":"Antony","volume":"2025","first-page":"1","unstructured":null,"article-title":"Artificial Intelligence-Augmented Imaging for Early Pancreatic Cancer Detection","journal-title":"Visc Med","doi-asserted-by":null},{"DOI":"10.1016/j.gastro.2005.05.007","key":"2026042817000558000_gutjnl-2025-337266v1.5","year":null,"issue":null,"author":null,"volume":null,"first-page":null,"unstructured":null,"article-title":null,"journal-title":null,"doi-asserted-by":"publisher"},{"DOI":"10.1053/j.gastro.2018.05.023","key":"2026042817000558000_gutjnl-2025-337266v1.6","year":null,"issue":null,"author":null,"volume":null,"first-page":null,"unstructured":null,"article-title":null,"journal-title":null,"doi-asserted-by":"publisher"},{"DOI":null,"key":"2026042817000558000_gutjnl-2025-337266v1.7","year":null,"issue":null,"author":null,"volume":null,"first-page":null,"unstructured":"National Institute for Health and Care Excellence (NICE) . Suspected cancer: recognition and referral. NICE Guideline NG12. 2025. Available: https://www.nice.org.uk/guidance/ng12/chapter/Recommendations-organised-by-site-of-cancer [Accessed 26 Sep 2025].","article-title":null,"journal-title":null,"doi-asserted-by":null},{"DOI":"10.1007/s00261-024-04775-x","key":"2026042817000558000_gutjnl-2025-337266v1.8","year":"2025","issue":null,"author":"Antony","volume":"50","first-page":"3214","unstructured":null,"article-title":"AI-driven insights in pancreatic cancer imaging: from pre-diagnostic detection to prognostication","journal-title":"Abdom Radiol (NY)","doi-asserted-by":"crossref"},{"DOI":"10.1053/j.gastro.2022.06.066","key":"2026042817000558000_gutjnl-2025-337266v1.9","year":"2022","issue":null,"author":"Mukherjee","volume":"163","first-page":"1435","unstructured":null,"article-title":"Radiomics-based Machine-learning Models Can Detect Pancreatic Cancer on Prediagnostic Computed Tomography Scans at a Substantial Lead Time Before Clinical Diagnosis","journal-title":"Gastroenterology","doi-asserted-by":"crossref"},{"DOI":"10.1007/s00261-023-04127-1","key":"2026042817000558000_gutjnl-2025-337266v1.10","year":"2024","issue":null,"author":"Mukherjee","volume":"49","first-page":"964","unstructured":null,"article-title":"Assessing the robustness of a machine-learning model for early detection of pancreatic adenocarcinoma (PDA): evaluating resilience to variations in image acquisition and radiomics workflow using image perturbation methods","journal-title":"Abdom Radiol (NY)","doi-asserted-by":"crossref"},{"DOI":"10.3233/CBM-210273","key":"2026042817000558000_gutjnl-2025-337266v1.11","year":"2022","issue":null,"author":"Qureshi","volume":"33","first-page":"211","unstructured":null,"article-title":"Predicting pancreatic ductal adenocarcinoma using artificial intelligence analysis of pre-diagnostic computed tomography images","journal-title":"Cancer Biomark","doi-asserted-by":"crossref"},{"DOI":"10.3389/fonc.2022.1007990","key":"2026042817000558000_gutjnl-2025-337266v1.12","year":"2022","issue":null,"author":"Javed","volume":"12","first-page":null,"unstructured":null,"article-title":"Risk prediction of pancreatic cancer using AI analysis of pancreatic subregions in computed tomography images","journal-title":"Front Oncol","doi-asserted-by":"crossref"},{"DOI":"10.14309/ctg.0000000000000548","key":"2026042817000558000_gutjnl-2025-337266v1.13","year":"2023","issue":null,"author":"Chen","volume":"14","first-page":null,"unstructured":null,"article-title":"Quantitative Radiomic Features From Computed Tomography Can Predict Pancreatic Cancer up to 36 Months Before Diagnosis","journal-title":"Clin Transl Gastroenterol","doi-asserted-by":"crossref"},{"DOI":"10.1097/RCT.0000000000001374","key":"2026042817000558000_gutjnl-2025-337266v1.14","year":"2022","issue":null,"author":"Khasawneh","volume":"46","first-page":"841","unstructured":null,"article-title":"Volumetric Pancreas Segmentation on Computed Tomography: Accuracy and Efficiency of a Convolutional Neural Network Versus Manual Segmentation in 3D Slicer in the Context of Interreader Variability of Expert Radiologists","journal-title":"J Comput Assist Tomogr","doi-asserted-by":"crossref"},{"DOI":"10.1002/mp.14782","key":"2026042817000558000_gutjnl-2025-337266v1.15","year":"2021","issue":null,"author":"Panda","volume":"48","first-page":"2468","unstructured":null,"article-title":"Two-stage deep learning model for fully automated pancreas segmentation on computed tomography: Comparison with intra-reader and inter-reader reliability at full and reduced radiation dose on an external dataset","journal-title":"Med Phys","doi-asserted-by":"crossref"},{"DOI":"10.1053/j.gastro.2023.08.034","key":"2026042817000558000_gutjnl-2025-337266v1.16","year":null,"issue":null,"author":null,"volume":null,"first-page":null,"unstructured":null,"article-title":null,"journal-title":null,"doi-asserted-by":"publisher"},{"DOI":"10.2214/AJR.24.31151","key":"2026042817000558000_gutjnl-2025-337266v1.17","year":"2024","issue":null,"author":"Huang","volume":"223","first-page":null,"unstructured":null,"article-title":"Imaging for Early Detection of Pancreatic Ductal Adenocarcinoma: Updates and Challenges in the Implementation of Screening and Surveillance Programs","journal-title":"AJR Am J Roentgenol","doi-asserted-by":"crossref"},{"DOI":"10.1038/s41598-025-01802-9","key":"2026042817000558000_gutjnl-2025-337266v1.18","year":"2025","issue":null,"author":"Mukherjee","volume":"15","first-page":null,"unstructured":null,"article-title":"Pancreas segmentation using AI developed on the largest CT dataset with multi-institutional validation and implications for early cancer detection","journal-title":"Sci Rep","doi-asserted-by":"crossref"},{"DOI":"10.3389/fneur.2024.1305543","key":"2026042817000558000_gutjnl-2025-337266v1.19","year":"2024","issue":null,"author":"Ni","volume":"15","first-page":null,"unstructured":null,"article-title":"Synthetic minority over-sampling technique-enhanced machine learning models for predicting recurrence of postoperative chronic subdural hematoma","journal-title":"Front Neurol","doi-asserted-by":"crossref"},{"DOI":"10.1038/s41592-020-01008-z","key":"2026042817000558000_gutjnl-2025-337266v1.20","year":null,"issue":null,"author":null,"volume":null,"first-page":null,"unstructured":null,"article-title":null,"journal-title":null,"doi-asserted-by":"publisher"},{"DOI":"10.1109/TPAMI.2005.159","key":"2026042817000558000_gutjnl-2025-337266v1.21","year":null,"issue":null,"author":null,"volume":null,"first-page":null,"unstructured":null,"article-title":null,"journal-title":null,"doi-asserted-by":"publisher"},{"DOI":"10.1016/j.pan.2021.03.016","key":"2026042817000558000_gutjnl-2025-337266v1.22","year":"2021","issue":null,"author":"Suman","volume":"21","first-page":"1001","unstructured":null,"article-title":"Quality gaps in public pancreas imaging datasets: Implications & challenges for AI applications","journal-title":"Pancreatology","doi-asserted-by":"crossref"},{"DOI":"10.1158/1055-9965.EPI-23-1594","key":"2026042817000558000_gutjnl-2025-337266v1.23","year":"2024","issue":null,"author":"Zheng","volume":"33","first-page":"1150","unstructured":null,"article-title":"Designing Rigorous and Efficient Clinical Utility Studies for Early Detection Biomarkers","journal-title":"Cancer Epidemiol Biomarkers Prev","doi-asserted-by":"crossref"},{"DOI":"10.1053/j.gastro.2021.10.014","key":"2026042817000558000_gutjnl-2025-337266v1.24","year":null,"issue":null,"author":null,"volume":null,"first-page":null,"unstructured":null,"article-title":null,"journal-title":null,"doi-asserted-by":"publisher"},{"DOI":"10.1053/j.gastro.2021.11.021","key":"2026042817000558000_gutjnl-2025-337266v1.25","year":"2022","issue":null,"author":"Chhoda","volume":"162","first-page":"786","unstructured":null,"article-title":"Late-Stage Pancreatic Cancer Detected During High-Risk Individual Surveillance: A Systematic Review and Meta-Analysis","journal-title":"Gastroenterology","doi-asserted-by":"crossref"},{"DOI":"10.1136/gutjnl-2014-308653","key":"2026042817000558000_gutjnl-2025-337266v1.26","year":null,"issue":null,"author":null,"volume":null,"first-page":null,"unstructured":null,"article-title":null,"journal-title":null,"doi-asserted-by":"publisher"},{"DOI":"10.1097/00000658-199603000-00007","key":"2026042817000558000_gutjnl-2025-337266v1.27","year":null,"issue":null,"author":null,"volume":null,"first-page":null,"unstructured":null,"article-title":null,"journal-title":null,"doi-asserted-by":"publisher"},{"DOI":"10.1053/j.gastro.2019.01.259","key":"2026042817000558000_gutjnl-2025-337266v1.28","year":null,"issue":null,"author":null,"volume":null,"first-page":null,"unstructured":null,"article-title":null,"journal-title":null,"doi-asserted-by":"publisher"},{"DOI":null,"key":"2026042817000558000_gutjnl-2025-337266v1.29","year":null,"issue":null,"author":null,"volume":null,"first-page":null,"unstructured":"PYMNTS . Mayo Clinic Uses AI to Detect Pancreatic Cancer Earlier. 2025. Available: https://www.pymnts.com/artificial-intelligence-2/2025/mayo-clinic-uses-ai-to-detect-pancreatic-cancer-earlier/ [Accessed 17 Dec 2025].","article-title":null,"journal-title":null,"doi-asserted-by":null},{"DOI":"10.1056/NEJMoa1911793","key":"2026042817000558000_gutjnl-2025-337266v1.30","year":null,"issue":null,"author":null,"volume":null,"first-page":null,"unstructured":null,"article-title":null,"journal-title":null,"doi-asserted-by":"publisher"},{"DOI":"10.1056/NEJMoa1600249","key":"2026042817000558000_gutjnl-2025-337266v1.31","year":null,"issue":null,"author":null,"volume":null,"first-page":null,"unstructured":null,"article-title":null,"journal-title":null,"doi-asserted-by":"publisher"},{"DOI":"10.1136/thoraxjnl-2018-212152","key":"2026042817000558000_gutjnl-2025-337266v1.32","year":null,"issue":null,"author":null,"volume":null,"first-page":null,"unstructured":null,"article-title":null,"journal-title":null,"doi-asserted-by":"publisher"},{"DOI":null,"key":"2026042817000558000_gutjnl-2025-337266v1.33","year":"2023","issue":null,"author":"Akwo","volume":"5","first-page":null,"unstructured":null,"article-title":"Does the availability of prior mammograms improve radiologists’ observer performance? A scoping review","journal-title":"BJR Open","doi-asserted-by":null},{"DOI":null,"key":"2026042817000558000_gutjnl-2025-337266v1.34","year":"2018","issue":null,"author":"Torphy","volume":"2018","first-page":null,"unstructured":null,"article-title":"Stromal Content Is Correlated With Tissue Site, Contrast Retention, and Survival in Pancreatic Adenocarcinoma","journal-title":"JCO Precis Oncol","doi-asserted-by":null},{"DOI":"10.1158/2159-8290.CD-20-0841","key":"2026042817000558000_gutjnl-2025-337266v1.35","year":null,"issue":null,"author":null,"volume":null,"first-page":null,"unstructured":null,"article-title":null,"journal-title":null,"doi-asserted-by":"publisher"},{"DOI":"10.1053/j.gastro.2025.06.025","key":"2026042817000558000_gutjnl-2025-337266v1.36","year":"2026","issue":null,"author":"Chari","volume":"170","first-page":"106","unstructured":null,"article-title":"Risk of Pancreatic Cancer in Glycemically Defined New-Onset Diabetes: A Prospective Cohort Study","journal-title":"Gastroenterology","doi-asserted-by":"crossref"},{"DOI":null,"key":"2026042817000558000_gutjnl-2025-337266v1.37","year":null,"issue":null,"author":null,"volume":null,"first-page":null,"unstructured":"NIH RePORT . Anticancer ELNP nanovaccines for curative treatment of pancreatic cancer. 2025. Available: https://reporter.nih.gov/search/Oz5oAFm3kUqjvhzx1Kz7gQ/project-details/11040015#details [Accessed 26 Sep 2025].","article-title":null,"journal-title":null,"doi-asserted-by":null},{"DOI":"10.1001/jamanetworkopen.2024.8755","key":"2026042817000558000_gutjnl-2025-337266v1.38","year":"2024","issue":null,"author":"Daher","volume":"7","first-page":null,"unstructured":null,"article-title":"Hepatocellular Carcinoma Screening in a Contemporary Cohort of At-Risk Patients","journal-title":"JAMA Netw Open","doi-asserted-by":"crossref"},{"DOI":"10.1002/hep.32284","key":"2026042817000558000_gutjnl-2025-337266v1.39","year":"2022","issue":null,"author":"Rich","volume":"75","first-page":"740","unstructured":null,"article-title":"Overdiagnosis of hepatocellular carcinoma: Prevented by guidelines?","journal-title":"Hepatology","doi-asserted-by":"crossref"}],"short-title":[],"update-policy":"https://doi.org/10.1136/crossmarkpolicy","alternative-id":["10.1136/gutjnl-2025-337266"],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"original-title":[],"container-title":["Gut"],"reference-count":39,"published-online":{"date-time":null,"timestamp":null,"date-parts":[[2026,4,28]]},"references-count":39,"short-container-title":["Gut"],"is-referenced-by-count":1},"unpaywall":{"doi":"10.1136/gutjnl-2025-337266","is_oa":false,"title":"Next-generation AI for visually occult pancreatic cancer detection in a low-prevalence setting with longitudinal stability and multi-institutional generalisability","updated":"2026-05-02T09:05:40+00:00","published_date":"2026-04-28","best_oa_location":null}},"created_at":"2026-05-07T22:51:01.508Z","updated_at":"2026-05-14T15:13:26.918Z","tags":[{"paper_doi":"10.1136/gutjnl-2025-337266","tag_type":"age_group","value":"adult","value_numeric":null},{"paper_doi":"10.1136/gutjnl-2025-337266","tag_type":"category","value":"Gastroenterology & Hepatology","value_numeric":null},{"paper_doi":"10.1136/gutjnl-2025-337266","tag_type":"condition","value":"Pancreatic Ductal Adenocarcinoma","value_numeric":null},{"paper_doi":"10.1136/gutjnl-2025-337266","tag_type":"impact_flag","value":"practice_changing","value_numeric":null},{"paper_doi":"10.1136/gutjnl-2025-337266","tag_type":"level_of_evidence","value":"3","value_numeric":null},{"paper_doi":"10.1136/gutjnl-2025-337266","tag_type":"modality","value":"Computed Tomography","value_numeric":null},{"paper_doi":"10.1136/gutjnl-2025-337266","tag_type":"modality","value":"Radiomics / AI Imaging","value_numeric":null},{"paper_doi":"10.1136/gutjnl-2025-337266","tag_type":"sample_size","value":"n=2081 (training + test + external validation cohorts combined)","value_numeric":2081},{"paper_doi":"10.1136/gutjnl-2025-337266","tag_type":"sex","value":"mixed","value_numeric":null},{"paper_doi":"10.1136/gutjnl-2025-337266","tag_type":"study_design","value":"Retrospective Cohort Study with External Validation","value_numeric":null},{"paper_doi":"10.1136/gutjnl-2025-337266","tag_type":"warning","value":"The 'practice_changing' impact flag reflects the AI's strong performance metrics and head-to-head radiologist comparison, but the authors explicitly note prospective validation is still required before clinical use.","value_numeric":null},{"paper_doi":"10.1136/gutjnl-2025-337266","tag_type":"warning","value":"The study simulates a ~1:6 prevalence ratio, which is substantially higher than real-world population-level pancreatic cancer prevalence; positive predictive value in true screening settings would be considerably lower.","value_numeric":null},{"paper_doi":"10.1136/gutjnl-2025-337266","tag_type":"warning","value":"Total sample size of 2081 is an aggregate across training (n=969), test (n=493), and two external specificity cohorts (n=539 and n=80); these sets are non-overlapping but the combined figure may overstate a single study population size.","value_numeric":null}],"summaries":{"what_studied":"REDMOD, an AI radiomic framework, was developed and validated to detect visually occult pre-diagnostic pancreatic ductal adenocarcinoma (PDA) on standard-of-care CT, trained on a multi-institutional cohort (n=969) and tested on an independent set (n=493) simulating a low-prevalence (~1:6) early detection setting.","key_result":"REDMOD achieved AUC 0.82 with 73.0% sensitivity at a median 475-day lead time before diagnosis — nearly 2× higher than radiologists (38.9%; p<0.001), rising to ~3× at >24 months lead time (68.0% vs 23.0%); external specificity was 81.3% (n=539) and 87.5% (n=80), with 90–92% longitudinal concordance.","limitations":"- Low-prevalence simulation (~1:6 case-to-control ratio) may not reflect real-world screening populations where prevalence is far lower.\n- Retrospective design; prospective validation in high-risk cohorts has not yet been performed.\n- Specificity thresholds were tuned post-hoc via Youden Index, which may not generalize without recalibration in new populations.","practice_takeaway":"REDMOD detects pancreatic cancer on CT nearly a year and a half before clinical diagnosis and far outperforms radiologists at the occult stage — but prospective validation in high-risk surveillance cohorts is still needed before clinical deployment."}},{"doi":"10.1001/jamadermatol.2026.0803","pmid":"42018290","title":"Diagnostic Modalities and Nodal Staging in High-Risk Cutaneous Squamous Cell Carcinoma","journal_title":"JAMA Dermatology","journal_issn":"2168-6068","published_at":"2026-04-22T00:00:00.000Z","url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13103882/","source_score":19,"is_retracted":false,"is_open_access":true,"raw_metadata":{"pubmed":true,"crossref":true,"unpaywall":true},"created_at":"2026-05-07T17:34:03.684Z","updated_at":"2026-05-07T17:34:03.684Z","tags":[{"paper_doi":"10.1001/jamadermatol.2026.0803","tag_type":"age_group","value":"older_adult","value_numeric":null},{"paper_doi":"10.1001/jamadermatol.2026.0803","tag_type":"category","value":"Dermatology","value_numeric":null},{"paper_doi":"10.1001/jamadermatol.2026.0803","tag_type":"condition","value":"Cutaneous Squamous Cell Carcinoma","value_numeric":null},{"paper_doi":"10.1001/jamadermatol.2026.0803","tag_type":"impact_flag","value":"practice_changing","value_numeric":null},{"paper_doi":"10.1001/jamadermatol.2026.0803","tag_type":"level_of_evidence","value":"2","value_numeric":null},{"paper_doi":"10.1001/jamadermatol.2026.0803","tag_type":"modality","value":"Computed Tomography","value_numeric":null},{"paper_doi":"10.1001/jamadermatol.2026.0803","tag_type":"modality","value":"Physical Examination","value_numeric":null},{"paper_doi":"10.1001/jamadermatol.2026.0803","tag_type":"modality","value":"Ultrasonography","value_numeric":null},{"paper_doi":"10.1001/jamadermatol.2026.0803","tag_type":"sample_size","value":"n=155","value_numeric":155},{"paper_doi":"10.1001/jamadermatol.2026.0803","tag_type":"sex","value":"mixed","value_numeric":null},{"paper_doi":"10.1001/jamadermatol.2026.0803","tag_type":"study_design","value":"Prospective Paired Diagnostic Study","value_numeric":null},{"paper_doi":"10.1001/jamadermatol.2026.0803","tag_type":"warning","value":"Full text is under PMC embargo until April 22, 2027; summary is based solely on the abstract and results excerpt.","value_numeric":null},{"paper_doi":"10.1001/jamadermatol.2026.0803","tag_type":"warning","value":"Study design is labeled 'paired diagnostic study' — not an RCT; level of evidence assigned as 2 based on prospective design with reference standard comparison.","value_numeric":null},{"paper_doi":"10.1001/jamadermatol.2026.0803","tag_type":"warning","value":"The metastatic event rate is low (n=12), making subgroup sensitivity estimates (especially for immunosuppressed patients) statistically imprecise with very wide confidence intervals.","value_numeric":null}],"summaries":{"what_studied":"This prospective, multicenter, paired diagnostic study compared physical examination, ultrasonography, and contrast-enhanced CT for detecting nodal metastases at baseline staging in 155 patients with high-risk cSCC (stage T2b/T3 or T2a with additional high-risk features) across 13 tertiary centers in Spain (January 2022–April 2025), stratified by immune status.","key_result":"Ultrasonography had the highest overall sensitivity (63.6%) vs. CT (54.5%) vs. physical exam (8.3%); specificities were 95.6%, 95.0%, and 99.3%, respectively. In immunocompetent patients, both imaging modalities reached 100% sensitivity (AUROC 0.98 each), but sensitivity collapsed in immunosuppressed patients (ultrasound 20.0%, CT 16.7%; AUROCs ~0.55–0.57). Ultrasonography and CT showed near-perfect agreement (κ = 0.87).","limitations":"- Small number of metastatic events (n=12; 7.7%) limits statistical precision, especially in subgroup analyses.\n- Immunosuppressed subgroup findings have very wide confidence intervals (e.g., sensitivity 0.5%–71.6%), suggesting results should be interpreted cautiously.\n- Full text is under embargo; some methodological details (e.g., exact reference standard breakdown between histology vs. follow-up) could not be verified.","practice_takeaway":"For immunocompetent patients with high-risk cSCC, ultrasound or CT can be used interchangeably at baseline staging — both detect nodal metastases reliably and far outperform physical exam alone. Immunosuppressed patients need close clinical follow-up regardless of negative imaging, as both modalities perform poorly in this group."}},{"doi":"10.1016/j.annemergmed.2026.02.012","pmid":"41989358","title":"Emergency Department Observation and Computed Tomography Use in Children With Blunt Abdominal Trauma","journal_title":"Annals of Emergency Medicine","journal_issn":"0196-0644","published_at":"2026-04-16T00:00:00.000Z","url":"https://doi.org/10.1016/j.annemergmed.2026.02.012","source_score":13,"is_retracted":false,"is_open_access":false,"raw_metadata":{"pubmed":true,"crossref":true,"unpaywall":true},"created_at":"2026-05-14T13:22:45.020Z","updated_at":"2026-05-14T13:22:45.020Z","tags":[{"paper_doi":"10.1016/j.annemergmed.2026.02.012","tag_type":"age_group","value":"pediatric","value_numeric":null},{"paper_doi":"10.1016/j.annemergmed.2026.02.012","tag_type":"category","value":"Emergency Medicine","value_numeric":null},{"paper_doi":"10.1016/j.annemergmed.2026.02.012","tag_type":"condition","value":"Blunt Abdominal Trauma","value_numeric":null},{"paper_doi":"10.1016/j.annemergmed.2026.02.012","tag_type":"condition","value":"Intra-Abdominal Injury","value_numeric":null},{"paper_doi":"10.1016/j.annemergmed.2026.02.012","tag_type":"impact_flag","value":"practice_changing","value_numeric":null},{"paper_doi":"10.1016/j.annemergmed.2026.02.012","tag_type":"level_of_evidence","value":"2","value_numeric":null},{"paper_doi":"10.1016/j.annemergmed.2026.02.012","tag_type":"modality","value":"Computed Tomography","value_numeric":null},{"paper_doi":"10.1016/j.annemergmed.2026.02.012","tag_type":"sample_size","value":"n=7442","value_numeric":7442},{"paper_doi":"10.1016/j.annemergmed.2026.02.012","tag_type":"sex","value":"mixed","value_numeric":null},{"paper_doi":"10.1016/j.annemergmed.2026.02.012","tag_type":"study_design","value":"Prospective Cohort Study (Secondary Analysis)","value_numeric":null},{"paper_doi":"10.1016/j.annemergmed.2026.02.012","tag_type":"warning","value":"No drug or device intervention is involved; modality tag reflects the diagnostic imaging being studied rather than a treatment.","value_numeric":null},{"paper_doi":"10.1016/j.annemergmed.2026.02.012","tag_type":"warning","value":"The study design is labeled as a secondary analysis of a prospective cohort, which is slightly ambiguous for level-of-evidence grading; level 2 was assigned based on the prospective multicenter cohort source data.","value_numeric":null},{"paper_doi":"10.1016/j.annemergmed.2026.02.012","tag_type":"warning","value":"This is a secondary analysis of an observational cohort; observation was not randomly assigned, so confounding by indication (lower-risk patients selected for observation) likely explains some of the difference in CT use and injury rates between groups.","value_numeric":null}],"summaries":{"what_studied":"This secondary analysis of a prospective multicenter cohort study examined whether ED observation with deferred CT decision-making was associated with lower CT use in 7,442 children presenting with blunt abdominal trauma, adjusting for age, site, clinician suspicion, and PECARN prediction rule variables.","key_result":"Observed children had CT use of 20.5% vs. 37.1% in non-observed children (difference 16.7%, 95% CI 14.5%–18.8%). Intra-abdominal injury requiring acute intervention occurred in 0.4% of observed vs. 2.5% of non-observed patients. Of 1,610 patients discharged without CT after observation, 0% (95% CI 0%–0.3%) had an injury requiring intervention. Observation was most strongly associated with reduced CT use when clinician suspicion was 6%–10% (OR 0.15, 95% CI 0.10–0.23).","limitations":"Secondary analysis design limits causal inference. Observation was not randomly assigned, so selection bias is likely (lower-risk patients may have been preferentially observed). The upper bound of the 95% CI for missed injuries in discharged-without-CT patients was 0.3%, meaning rare missed injuries cannot be excluded.","practice_takeaway":"For children with blunt abdominal trauma and intermediate clinical suspicion (1%–50%), a period of ED observation before committing to CT is associated with substantially fewer scans and no increase in missed injuries requiring intervention. Clinicians can safely defer CT decisions while observing these patients."}},{"doi":"10.1016/j.jacc.2026.02.5095","pmid":"41949516","title":"Opportunistic Cardiovascular Risk Assessment Using Routine Head CT in the Emergency Department","journal_title":"JACC","journal_issn":"0735-1097","published_at":"2026-04-08T00:00:00.000Z","url":"https://doi.org/10.1016/j.jacc.2026.02.5095","source_score":17,"is_retracted":false,"is_open_access":true,"raw_metadata":{"pubmed":true,"crossref":true,"unpaywall":true},"created_at":"2026-06-05T13:26:39.891Z","updated_at":"2026-06-05T13:26:39.891Z","tags":[{"paper_doi":"10.1016/j.jacc.2026.02.5095","tag_type":"age_group","value":"adult","value_numeric":null},{"paper_doi":"10.1016/j.jacc.2026.02.5095","tag_type":"category","value":"Cardiac & Cardiovascular Systems","value_numeric":null},{"paper_doi":"10.1016/j.jacc.2026.02.5095","tag_type":"condition","value":"Cardiovascular Disease","value_numeric":null},{"paper_doi":"10.1016/j.jacc.2026.02.5095","tag_type":"condition","value":"Coronary Artery Calcification","value_numeric":null},{"paper_doi":"10.1016/j.jacc.2026.02.5095","tag_type":"condition","value":"Heart Failure","value_numeric":null},{"paper_doi":"10.1016/j.jacc.2026.02.5095","tag_type":"condition","value":"Myocardial Infarction","value_numeric":null},{"paper_doi":"10.1016/j.jacc.2026.02.5095","tag_type":"condition","value":"Stroke","value_numeric":null},{"paper_doi":"10.1016/j.jacc.2026.02.5095","tag_type":"impact_flag","value":"practice_changing","value_numeric":null},{"paper_doi":"10.1016/j.jacc.2026.02.5095","tag_type":"level_of_evidence","value":"3","value_numeric":null},{"paper_doi":"10.1016/j.jacc.2026.02.5095","tag_type":"modality","value":"Computed Tomography","value_numeric":null},{"paper_doi":"10.1016/j.jacc.2026.02.5095","tag_type":"modality","value":"Deep Learning / Artificial Intelligence","value_numeric":null},{"paper_doi":"10.1016/j.jacc.2026.02.5095","tag_type":"sample_size","value":"n=27990","value_numeric":27990},{"paper_doi":"10.1016/j.jacc.2026.02.5095","tag_type":"sex","value":"mixed","value_numeric":null},{"paper_doi":"10.1016/j.jacc.2026.02.5095","tag_type":"study_design","value":"Retrospective Cohort Study","value_numeric":null},{"paper_doi":"10.1016/j.jacc.2026.02.5095","tag_type":"warning","value":"Median follow-up duration is not explicitly stated in the abstract, which limits interpretation of incident CVD event rates over time.","value_numeric":null},{"paper_doi":"10.1016/j.jacc.2026.02.5095","tag_type":"warning","value":"The CAC sub-cohort (n=2,313) required concurrent coronary CT angiography, which may not reflect the broader ED population and could introduce selection bias.","value_numeric":null},{"paper_doi":"10.1016/j.jacc.2026.02.5095","tag_type":"warning","value":"The impact_flag 'practice_changing' is applied cautiously — the findings are promising but remain single-center and retrospective; prospective validation is needed before clinical integration.","value_numeric":null}],"summaries":{"what_studied":"This retrospective cohort study evaluated whether deep learning models applied to routine head CT (CTH) scans from an ED setting (Aug 2020–Aug 2024) could predict incident CVD (MI, stroke, heart failure) and estimate coronary artery calcium (CAC) scores, compared against the AHA PREVENT risk model, in adults without known CVD.","key_result":"The CTH deep learning model achieved a C-index of 0.82 (95% CI: 0.78–0.85) vs. 0.75 (95% CI: 0.70–0.79) for PREVENT alone (difference 0.07; 95% CI: 0.04–0.10). For CAC >100, CTH+PREVENT reached AUC 0.80 (95% CI: 0.73–0.85). 15.7% of patients were risk-reclassified; reclassified higher-risk patients were younger but had more vascular calcifications (30.2% vs. 24.8%) and brain infarcts (20.1% vs. 5.8%).","limitations":"- Single-center retrospective design (Stanford ED) limits generalizability to other settings and populations.\n- CVD events were extracted from EHR, which may miss events occurring outside the health system.\n- CAC cohort (n=2,313) was smaller and required a separate CT angiography, potentially introducing selection bias.","practice_takeaway":"Head CTs already ordered in the ED can be repurposed by AI to flag patients at elevated cardiovascular risk — especially younger patients with subclinical vascular disease who may be missed by standard risk scores. If validated prospectively, this approach could enable no-cost, no-added-radiation CVD screening in a high-volume ED population."}}],"initialOffset":14,"fetchConfig":{"kind":"tags","tags":[{"tag_type":"modality","value":"Computed Tomography"}]},"breadcrumbItems":[{"name":"Home","href":"/"},{"name":"Research Hub","href":"/hub"},{"name":"Modalities","href":"/hub/tag/modality"},{"name":"Computed Tomography"}],"hrefConfig":{"basePath":"/hub/papers","webViewQueryParams":{"hub_ctx":"tag","hub_tag_type":"modality","hub_tag_value":"Computed Tomography"}}}]]

Papers