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:Td6c,The potential association of artificial intelligence (AI)-powered informational tools with consumer health needs outcomes is not well understood. Such tools could potentially be associated with the volume and distribution of patients seeking care. To investigate the association of an AI-powered dermatology application with changes in consumer understanding of retrospective skin condition cases. This survey study used a between-participants randomized survey with 3 arms: control (using existing tools, such as web search), AI (with access to predictions from a prototype AI application), and a Wizard of Oz method (with the same interface as in the AI group but using dermatologist panel ground truth differentials instead of AI predictions) run on a commercial panel platform. Participants interpreted retrospective deidentified skin condition cases containing images and structured medical history. US-based participants who self-reported having sought information for a skin concern within the past year were included. The survey was conducted March 17 to May 16, 2023, and data were analyzed from June 2023 through November 2024. Participants in AI and Wizard of Oz arms were presented 3 to 7 conditions per case patient as a horizontal carousel of condition cards. Cards included textbook images of each condition and brief descriptions and could be expanded to show more textbook images and details about each condition's background and treatment. Conditions in the Wizard of Oz arm had identical visual presentation, but predicted conditions were the dermatologist-provided ground truth. Participants in each arm self-reported whether they could name the condition depicted, and if so, they could list 1 or more conditions they thought were shown. Participants also reported the next step they thought appropriate for each case patient, as well as their self-reported confidence in their assessment and satisfaction with the information search experience. Condition name and next step accuracy were assessed against a reference diagnosis from dermatologists, and next steps were derived from the conditions. Among 2345 participants (509 aged 30-39 years [21.71%]; 1650 female [70.36%]), 11 725 participant case patient reads were obtained across 3 study arms. Compared with the control group (41.21%; 95% CI, 39.66%-42.76%), participants were more willing to name a condition in AI (62.26%; 95% CI, 60.75%-63.76%) and Wizard of Oz (61.76%; 95% CI, 60.21%-63.28%) arms (both P < .001; permutation test with false discovery rate correction), with increased accuracy for AI (22.79%; 95% CI, 21.48%-24.09%; P < .001) and Wizard of Oz (36.20%; 95% CI, 34.70%-37.73%; P = .002) vs control (7.86%; 95% CI, 7.03%-8.71%). Next-step accuracy increased for the Wizard of Oz (62.95%; 95% CI, 61.42%-64.44%; P < .001) compared with the control group (60.10%; 95% CI, 58.55%-61.65%). In this study, AI applications were associated with increased accuracy and confidence of consumer understanding of skin concerns, with the degree of improvement in accuracy varying by the accuracy of presented conditions; benefits further improved when predictions were as accurate as possible. Imperfect guessing accuracy when predictions presented matched dermatologist differentials highlighted the need for further design improvements (such as the condition information presented) to help consumers better understand skin conditions.31:T13e9, Importance The potential association of artificial intelligence (AI)–powered informational tools with consumer health needs outcomes is not well understood. Such tools could potentially be associated with the volume and distribution of patients seeking care. Objective To investigate the association of an AI-powered dermatology application with changes in consumer understanding of retrospective skin condition cases. Design, Setting, and Participants This survey study used a between-participants randomized survey with 3 arms: control (using existing tools, such as web search), AI (with access to predictions from a prototype AI application), and a Wizard of Oz method (with the same interface as in the AI group but using dermatologist panel ground truth differentials instead of AI predictions) run on a commercial panel platform. Participants interpreted retrospective deidentified skin condition cases containing images and structured medical history. US-based participants who self-reported having sought information for a skin concern within the past year were included. The survey was conducted March 17 to May 16, 2023, and data were analyzed from June 2023 through November 2024. Interventions Participants in AI and Wizard of Oz arms were presented 3 to 7 conditions per case patient as a horizontal carousel of condition cards. Cards included textbook images of each condition and brief descriptions and could be expanded to show more textbook images and details about each condition’s background and treatment. Conditions in the Wizard of Oz arm had identical visual presentation, but predicted conditions were the dermatologist-provided ground truth. Main Outcomes and Measures Participants in each arm self-reported whether they could name the condition depicted, and if so, they could list 1 or more conditions they thought were shown. Participants also reported the next step they thought appropriate for each case patient, as well as their self-reported confidence in their assessment and satisfaction with the information search experience. Condition name and next step accuracy were assessed against a reference diagnosis from dermatologists, and next steps were derived from the conditions. Results Among 2345 participants (509 aged 30-39 years [21.71%]; 1650 female [70.36%]), 11 725 participant case patient reads were obtained across 3 study arms. Compared with the control group (41.21%; 95% CI, 39.66%-42.76%), participants were more willing to name a condition in AI (62.26%; 95% CI, 60.75%-63.76%) and Wizard of Oz (61.76%; 95% CI, 60.21%-63.28%) arms (both P &lt; .001; permutation test with false discovery rate correction), with increased accuracy for AI (22.79%; 95% CI, 21.48%-24.09%; P &lt; .001) and Wizard of Oz (36.20%; 95% CI, 34.70%-37.73%; P = .002) vs control (7.86%; 95% CI, 7.03%-8.71%). Next-step accuracy increased for the Wizard of Oz (62.95%; 95% CI, 61.42%-64.44%; P &lt; .001) compared with the control group (60.10%; 95% CI, 58.55%-61.65%). Conclusions and Relevance In this study, AI applications were associated with increased accuracy and confidence of consumer understanding of skin concerns, with the degree of improvement in accuracy varying by the accuracy of presented conditions; benefits further improved when predictions were as accurate as possible. Imperfect guessing accuracy when predictions presented matched dermatologist differentials highlighted the need for further design improvements (such as the condition information presented) to help consumers better understand skin conditions. 25:[[["$","script","0",{"type":"application/ld+json","dangerouslySetInnerHTML":{"__html":"{\"@context\":\"https://schema.org\",\"@type\":\"CollectionPage\",\"name\":\"Randomized Survey Study: study design Research & Clinical Takeaways\",\"description\":\"Explore peer-reviewed papers on Randomized Survey Study (study design). Clinician-written summaries and actionable practice insights. Updated daily.\",\"url\":\"https://www.reachrx.ai/hub/tag/study_design/Randomized%20Survey%20Study\",\"breadcrumb\":{\"@type\":\"BreadcrumbList\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https://www.reachrx.ai\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Research Hub\",\"item\":\"https://www.reachrx.ai/hub\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"Study Designs\",\"item\":\"https://www.reachrx.ai/hub/tag/study_design\"},{\"@type\":\"ListItem\",\"position\":4,\"name\":\"Randomized Survey Study\",\"item\":\"https://www.reachrx.ai/hub/tag/study_design/Randomized%20Survey%20Study\"}]}}"}}]],["$","$L2f",null,{"title":"Randomized Survey Study: Research & Clinical Takeaways","description":"Browse Randomized Survey Study research papers with clear, practical takeaways for your clinical practice.","papers":[{"doi":"10.1001/jamadermatol.2026.0597","pmid":"41984449","title":"Consumer Understanding of Skin Concerns With an AI-Powered Informational Tool","journal_title":"JAMA Dermatology","journal_issn":"2168-6068","published_at":"2026-04-15T00:00:00.000Z","url":"https://doi.org/10.1001/jamadermatol.2026.0597","source_score":45,"is_retracted":false,"is_open_access":true,"raw_metadata":{"ooir":{"day":"2026-04-19","doi":"10.1001/jamadermatol.2026.0597","days":"30","issn":"2168-6068","rank":"5","field":"Clinical Medicine","score":"45","category":"Dermatology","categories":["Dermatology"],"_categories":["Dermatology"]},"pubmed":{"doi":"10.1001/jamadermatol.2026.0597","title":"Consumer Understanding of Skin Concerns With an AI-Powered Informational Tool.","journal":"JAMA dermatology","methods":"","results":"Among 2345 participants (509 aged 30-39 years [21.71%]; 1650 female [70.36%]), 11 725 participant case patient reads were obtained across 3 study arms. Compared with the control group (41.21%; 95% CI, 39.66%-42.76%), participants were more willing to name a condition in AI (62.26%; 95% CI, 60.75%-63.76%) and Wizard of Oz (61.76%; 95% CI, 60.21%-63.28%) arms (both P < .001; permutation test with false discovery rate correction), with increased accuracy for AI (22.79%; 95% CI, 21.48%-24.09%; P < .001) and Wizard of Oz (36.20%; 95% CI, 34.70%-37.73%; P = .002) vs control (7.86%; 95% CI, 7.03%-8.71%). Next-step accuracy increased for the Wizard of Oz (62.95%; 95% CI, 61.42%-64.44%; P < .001) compared with the control group (60.10%; 95% CI, 58.55%-61.65%).","abstract":"$30","keywords":[],"pubmed_id":"41984449","conclusions":"","publication_date":"2026-04-15T00:00:00"},"crossref":{"DOI":"10.1001/jamadermatol.2026.0597","URL":"https://doi.org/10.1001/jamadermatol.2026.0597","ISSN":["2168-6068"],"link":[{"URL":"https://jamanetwork.com/journals/jamadermatology/articlepdf/2847784/jamadermatology_sayres_2026_oi_260011_1776180070.7728.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"page":null,"type":"journal-article","issue":null,"score":1,"title":["Consumer Understanding of Skin Concerns With an AI-Powered Informational Tool"],"author":[{"given":"Rory","family":"Sayres","sequence":"first","affiliation":[{"name":"Google Research, Google, Mountain View, California"}]},{"given":"Ayush","family":"Jain","sequence":"additional","affiliation":[{"name":"Google Research, Google, Mountain View, California"}]},{"given":"Maya","family":"Venkatraman","sequence":"additional","affiliation":[{"name":"Google Research, Google, Mountain View, California"}]},{"given":"Preeti","family":"Singh","sequence":"additional","affiliation":[{"name":"Google Research, Google, Mountain View, California"}]},{"given":"Yuan","family":"Liu","sequence":"additional","affiliation":[{"name":"Google Research, Google, Mountain View, California"}]},{"given":"Samantha","family":"Winter","sequence":"additional","affiliation":[{"name":"Google Research, Google, Mountain View, California"}]},{"given":"Mike","family":"Schaekermann","sequence":"additional","affiliation":[{"name":"Google Research, Google, Mountain View, California"}]},{"given":"Aaron","family":"Loh","sequence":"additional","affiliation":[{"name":"Google Research, Google, Mountain View, California"}]},{"given":"Sonali","family":"Verma","sequence":"additional","affiliation":[{"name":"Google Research, Google, Mountain View, California"}]},{"given":"Yossi","family":"Matias","sequence":"additional","affiliation":[{"name":"Google Research, Google, Mountain View, California"}]},{"given":"Greg S.","family":"Corrado","sequence":"additional","affiliation":[{"name":"Google Research, Google, Mountain View, California"}]},{"given":"Avinatan","family":"Hassidim","sequence":"additional","affiliation":[{"name":"Google Research, Google, Mountain View, California"}]},{"given":"Dale R.","family":"Webster","sequence":"additional","affiliation":[{"name":"Google Research, Google, Mountain View, California"}]},{"given":"Peggy","family":"Bui","sequence":"additional","affiliation":[{"name":"Google Research, Google, Mountain View, California"}]},{"given":"Steven","family":"Lin","sequence":"additional","affiliation":[{"name":"Stanford Healthcare AI Applied Research Team Lab, Stanford, California"}]},{"given":"Justin","family":"Ko","sequence":"additional","affiliation":[{"name":"Stanford Healthcare AI Applied Research Team Lab, Stanford, California"},{"name":"Department of Dermatology, Stanford University School of Medicine, Palo Alto, California"}]},{"given":"Yun","family":"Liu","sequence":"additional","affiliation":[{"name":"Google Research, Google, Mountain View, California"}]}],"issued":{"date-parts":[[2026,4,15]]},"member":"10","prefix":"10.1001","source":"Crossref","volume":null,"created":{"date-time":"2026-04-15T15:30:25Z","timestamp":1776267025000,"date-parts":[[2026,4,15]]},"indexed":{"date-time":"2026-04-15T16:34:41Z","timestamp":1776270881462,"date-parts":[[2026,4,15]]},"subject":[],"abstract":"$31","language":"en","relation":{},"resource":{"primary":{"URL":"https://jamanetwork.com/journals/jamadermatology/fullarticle/2847784"}},"subtitle":[],"deposited":{"date-time":"2026-04-15T15:30:27Z","timestamp":1776267027000,"date-parts":[[2026,4,15]]},"issn-type":[{"type":"print","value":"2168-6068"}],"published":{"date-parts":[[2026,4,15]]},"publisher":"American Medical Association (AMA)","reference":[{"DOI":"10.1016/S0140-6736(18)32279-7","key":"doi260011r1","year":"2018","issue":"10159","author":"GBD 2017 Disease and Injury Incidence and Prevalence Collaborators","volume":"392","first-page":"1789","unstructured":null,"article-title":"Global, regional, and national incidence, prevalence, and years lived with disability for 354 diseases and injuries for 195 countries and territories, 1990-2017: a systematic analysis for the Global Burden of Disease Study 2017.","journal-title":"Lancet","doi-asserted-by":"publisher"},{"DOI":"10.1016/S0190-9622(97)70118-X","key":"doi260011r2","year":"1997","issue":"5 Pt 1","author":"Feldman","volume":"37","first-page":"784","unstructured":null,"article-title":"Increasing utilization of dermatologists by managed care: an analysis of the National Ambulatory Medical Care Survey, 1990-1994.","journal-title":"J Am Acad Dermatol","doi-asserted-by":"publisher"},{"DOI":"10.1001/jamadermatol.2020.5173","key":"doi260011r3","year":"2021","issue":"2","author":"Creadore","volume":"157","first-page":"181","unstructured":null,"article-title":"Insurance acceptance, appointment wait time, and dermatologist access across practice types in the US.","journal-title":"JAMA Dermatol","doi-asserted-by":"publisher"},{"DOI":"10.1038/nature21056","key":"doi260011r4","year":"2017","issue":"7639","author":"Esteva","volume":"542","first-page":"115","unstructured":null,"article-title":"Dermatologist-level classification of skin cancer with deep neural networks.","journal-title":"Nature","doi-asserted-by":"publisher"},{"DOI":"10.1371/journal.pone.0191493","key":"doi260011r5","year":"2018","issue":"1","author":"Han","volume":"13","first-page":null,"unstructured":null,"article-title":"Deep neural networks show an equivalent and often superior performance to dermatologists in onychomycosis diagnosis: automatic construction of onychomycosis datasets by region-based convolutional deep neural network.","journal-title":"PLoS One","doi-asserted-by":"publisher"},{"DOI":"10.1001/jamanetworkopen.2021.7249","key":"doi260011r6","year":"2021","issue":"4","author":"Jain","volume":"4","first-page":null,"unstructured":null,"article-title":"Development and assessment of an artificial intelligence-based tool for skin condition diagnosis by primary care physicians and nurse practitioners in teledermatology practices.","journal-title":"JAMA Netw Open","doi-asserted-by":"publisher"},{"DOI":"10.1001/jamanetworkopen.2021.3287","key":"doi260011r7","year":"2021","issue":"3","author":"Levine","volume":"4","first-page":"e213287","unstructured":null,"article-title":"Assessment of diagnosis and triage in validated case vignettes among nonphysicians before and after internet search.","journal-title":"JAMA Netw Open","doi-asserted-by":"publisher"},{"DOI":"10.1001/jamadermatol.2019.5014","key":"doi260011r9","year":"2020","issue":"5","author":"Nelson","volume":"156","first-page":"501","unstructured":null,"article-title":"Patient perspectives on the use of artificial intelligence for skin cancer screening: a qualitative study.","journal-title":"JAMA Dermatol","doi-asserted-by":"publisher"},{"DOI":"10.1016/j.mcpdig.2024.07.001","key":"doi260011r11","year":"2024","issue":"3","author":"Devon-Sand","volume":"2","first-page":"463","unstructured":null,"article-title":"A multiparty collaboration to engage diverse populations in community-centered artificial intelligence research.","journal-title":"Mayo Clin Proc Digit Health","doi-asserted-by":"publisher"},{"DOI":"10.1016/j.jid.2020.01.019","key":"doi260011r12","year":"2020","issue":"9","author":"Han","volume":"140","first-page":"1753","unstructured":null,"article-title":"Augmented intelligence dermatology: deep neural networks empower medical professionals in diagnosing skin cancer and predicting treatment options for 134 skin disorders.","journal-title":"J Invest Dermatol","doi-asserted-by":"publisher"},{"DOI":"10.1038/s42256-021-00331-0","key":"doi260011r13","year":"2021","issue":null,"author":"Babic","volume":"3","first-page":"283","unstructured":null,"article-title":"Direct-to-consumer medical machine learning and artificial intelligence applications.","journal-title":"Nat Mach Intell","doi-asserted-by":"publisher"},{"DOI":"10.1038/s41746-023-00831-w","key":"doi260011r14","year":"2023","issue":"1","author":"Smak Gregoor","volume":"6","first-page":"90","unstructured":null,"article-title":"An artificial intelligence based app for skin cancer detection evaluated in a population based setting.","journal-title":"NPJ Digit Med","doi-asserted-by":"publisher"},{"DOI":"10.3390/jcm11226826","key":"doi260011r15","year":"2022","issue":"22","author":"Li","volume":"11","first-page":"6826","unstructured":null,"article-title":"Artificial intelligence in dermatology image analysis: current developments and future trends.","journal-title":"J Clin Med","doi-asserted-by":"publisher"},{"DOI":"10.1016/j.mcpdig.2024.01.005","key":"doi260011r16","year":"2024","issue":"1","author":"Rikhye","volume":"2","first-page":"107","unstructured":null,"article-title":"Differences between patient and clinician-taken images: implications for virtual care of skin conditions.","journal-title":"Mayo Clin Proc Digit Health","doi-asserted-by":"publisher"},{"DOI":"10.1126/sciadv.abq6147","key":"doi260011r17","year":"2022","issue":"32","author":"Daneshjou","volume":"8","first-page":null,"unstructured":null,"article-title":"Disparities in dermatology AI performance on a diverse, curated clinical image set.","journal-title":"Sci Adv","doi-asserted-by":"publisher"},{"DOI":"10.1016/j.eclinm.2024.102479","key":"doi260011r18","year":"2024","issue":null,"author":"Schaekermann","volume":"70","first-page":null,"unstructured":null,"article-title":"Health equity assessment of machine learning performance (HEAL): a framework and dermatology AI model case study.","journal-title":"EClinicalMedicine","doi-asserted-by":"publisher"},{"DOI":"10.2196/36885","key":"doi260011r19","year":"2022","issue":"1","author":"Jain","volume":"8","first-page":null,"unstructured":null,"article-title":"Race- and Ethnicity-Stratified Analysis of an Artificial Intelligence–Based Tool for Skin Condition Diagnosis by Primary Care Physicians and Nurse Practitioners.","journal-title":"Iproceedings","doi-asserted-by":"publisher"},{"DOI":"10.1038/s41591-020-0842-3","key":"doi260011r20","year":"2020","issue":"6","author":"Liu","volume":"26","first-page":"900","unstructured":null,"article-title":"A deep learning system for differential diagnosis of skin diseases.","journal-title":"Nat Med","doi-asserted-by":"publisher"},{"DOI":"10.1016/j.ebiom.2025.105766","key":"doi260011r21","year":"2025","issue":null,"author":"Rikhye","volume":"116","first-page":null,"unstructured":null,"article-title":"Closing the AI generalisation gap by adjusting for dermatology condition distribution differences across clinical settings.","journal-title":"EBioMedicine","doi-asserted-by":"publisher"},{"DOI":"10.1111/j.1525-1497.2006.00532.x","key":"doi260011r22","year":"2006","issue":"8","author":"Wallace","volume":"21","first-page":"874","unstructured":null,"article-title":"Brief report: screening items to identify patients with limited health literacy skills.","journal-title":"J Gen Intern Med","doi-asserted-by":"publisher"},{"DOI":"10.1038/s41591-024-03423-7","key":"doi260011r23","year":"2025","issue":"3","author":"Singhal","volume":"31","first-page":"943","unstructured":null,"article-title":"Toward expert-level medical question answering with large language models.","journal-title":"Nat Med","doi-asserted-by":"publisher"},{"DOI":"10.1016/S2589-7500(22)00017-6","key":"doi260011r24","year":"2022","issue":"4","author":"Ruamviboonsuk","volume":"4","first-page":"e235","unstructured":null,"article-title":"Real-time diabetic retinopathy screening by deep learning in a multisite national screening programme: a prospective interventional cohort study.","journal-title":"Lancet Digit Health","doi-asserted-by":"publisher"},{"DOI":null,"key":"doi260011r10","year":"2025","issue":null,"author":"Sayres","volume":null,"first-page":"1","unstructured":null,"article-title":null,"journal-title":null,"doi-asserted-by":null},{"DOI":null,"key":"doi260011r25","year":"2019","issue":null,"author":"Chen","volume":null,"first-page":null,"unstructured":null,"article-title":null,"journal-title":null,"doi-asserted-by":null},{"DOI":"10.1101/2024.10.25.24316155","key":"doi260011r8","year":null,"issue":null,"author":null,"volume":null,"first-page":null,"unstructured":"Krogue? JD, Sayres? R, Hartford? J, . Searching for dermatology information online using images vs text: a randomized study.? medRxiv. Preprint posted online October 27, 2024. doi:10.1101/2024.10.25.24316155","article-title":null,"journal-title":null,"doi-asserted-by":"crossref"},{"DOI":null,"key":"doi260011r26","year":null,"issue":null,"author":null,"volume":null,"first-page":null,"unstructured":"US Census Bureau. SO101: age and sex. 2024. Accessed December 17, 2025. https://data.census.gov/table/ACSST1Y2024.S0101","article-title":null,"journal-title":null,"doi-asserted-by":null},{"DOI":null,"key":"doi260011r27","year":null,"issue":null,"author":null,"volume":null,"first-page":null,"unstructured":"R Core Team. The R project for statistical computing. 2023. Accessed March 13, 2026. https://www.R-project.org/","article-title":null,"journal-title":null,"doi-asserted-by":null}],"short-title":[],"content-domain":{"domain":[],"crossmark-restriction":false},"original-title":[],"container-title":["JAMA Dermatology"],"reference-count":27,"published-online":{"date-time":null,"timestamp":null,"date-parts":[[2026,4,15]]},"references-count":27,"short-container-title":["JAMA Dermatol"],"is-referenced-by-count":0},"unpaywall":{"doi":"10.1001/jamadermatol.2026.0597","is_oa":true,"title":"Consumer Understanding of Skin Concerns With an AI-Powered Informational Tool","updated":"2026-04-19T08:44:30+00:00","published_date":"2026-04-15","best_oa_location":{"url":"https://doi.org/10.1001/jamadermatol.2026.0597","pmh_id":null,"url_for_pdf":null,"url_for_landing_page":"https://doi.org/10.1001/jamadermatol.2026.0597"}}},"created_at":"2026-05-07T17:34:03.161Z","updated_at":"2026-05-14T15:13:26.918Z","tags":[{"paper_doi":"10.1001/jamadermatol.2026.0597","tag_type":"age_group","value":"adult","value_numeric":null},{"paper_doi":"10.1001/jamadermatol.2026.0597","tag_type":"category","value":"Dermatology","value_numeric":null},{"paper_doi":"10.1001/jamadermatol.2026.0597","tag_type":"condition","value":"Skin Conditions","value_numeric":null},{"paper_doi":"10.1001/jamadermatol.2026.0597","tag_type":"impact_flag","value":"limited_evidence","value_numeric":null},{"paper_doi":"10.1001/jamadermatol.2026.0597","tag_type":"level_of_evidence","value":"2","value_numeric":null},{"paper_doi":"10.1001/jamadermatol.2026.0597","tag_type":"modality","value":"Artificial Intelligence Decision Support","value_numeric":null},{"paper_doi":"10.1001/jamadermatol.2026.0597","tag_type":"sample_size","value":"n=2345","value_numeric":2345},{"paper_doi":"10.1001/jamadermatol.2026.0597","tag_type":"sex","value":"mixed","value_numeric":null},{"paper_doi":"10.1001/jamadermatol.2026.0597","tag_type":"study_design","value":"Randomized Survey Study","value_numeric":null},{"paper_doi":"10.1001/jamadermatol.2026.0597","tag_type":"warning","value":"The paper is dated April 2026, which is future relative to most training data; content has been processed as provided without independent verification.","value_numeric":null},{"paper_doi":"10.1001/jamadermatol.2026.0597","tag_type":"warning","value":"The study population skewed female (70%) and was limited to US adults who had recently sought skin concern information, which may limit generalizability to broader or more diverse populations.","value_numeric":null},{"paper_doi":"10.1001/jamadermatol.2026.0597","tag_type":"warning","value":"The 'Wizard of Oz' arm used dermatologist ground-truth differentials presented through the AI interface — it is not a true AI condition but a methodological benchmark; clinicians should interpret the two active arms separately.","value_numeric":null}],"summaries":{"what_studied":"A 3-arm randomized survey study (n=2,345 US adults who sought skin concern info in the past year) tested whether an AI-powered dermatology app vs. web search (control) vs. a 'Wizard of Oz' dermatologist-ground-truth interface improved consumer understanding of retrospective skin condition cases, measured March–May 2023.","key_result":"Condition-naming accuracy rose from **7.86%** (control) to **22.79%** with AI and **36.20%** with dermatologist-level predictions (both P<.001); willingness to name a condition also jumped from 41% (control) to ~62% in both active arms. Next-step accuracy improved only in the Wizard of Oz arm (62.95% vs. 60.10% control; P<.001), not significantly with AI alone.","limitations":"- Survey used retrospective, deidentified cases rather than real-time clinical encounters, limiting generalizability to actual care-seeking behavior.\n- The AI prototype's prediction accuracy was imperfect, and the gap between AI and Wizard of Oz arms shows AI errors directly cap consumer understanding gains.\n- Self-reported outcomes (confidence, satisfaction, next step) may not translate to real-world clinical decisions or outcomes.","practice_takeaway":"AI dermatology tools can meaningfully boost consumer health literacy about skin conditions, but accuracy gains are tightly tied to the underlying model's precision — clinicians should be aware that imperfect AI predictions still leave a large gap versus expert-level guidance. Design improvements (richer condition descriptions, clearer guidance on when to seek care) are needed before these tools reliably improve care-seeking behavior."}}],"initialOffset":1,"fetchConfig":{"kind":"tags","tags":[{"tag_type":"study_design","value":"Randomized Survey Study"}]},"breadcrumbItems":[{"name":"Home","href":"/"},{"name":"Research Hub","href":"/hub"},{"name":"Study Designs","href":"/hub/tag/study_design"},{"name":"Randomized Survey Study"}],"hrefConfig":{"basePath":"/hub/papers","webViewQueryParams":{"hub_ctx":"tag","hub_tag_type":"study_design","hub_tag_value":"Randomized Survey Study"}}}]]

Papers