How appropriate are ChatGPT-5’s answers to acne questions?

{"Online":[0],"conversational":[1],"tools":[2],"have":[3],"become":[4],"increasingly":[5],"common":[6],"sources":[7],"of":[8,38,48,207],"health":[9],"information,":[10,118],"with":[11,90],"many":[12],"patients":[13],"seeking":[14],"acne":[15,35,66],"advice":[16],"through":[17],"such":[18],"platforms.":[19],"Although":[20],"they":[21],"may":[22,211],"enhance":[23],"awareness":[24],"and":[25,71,76,96,113,116,119,121,151,176,179,184,200,220,226],"encourage":[26],"early":[27],"consultation,":[28],"their":[29],"medical":[30],"reliability":[31],"remains":[32],"uncertain.":[33],"Because":[34],"is":[36,51],"one":[37],"the":[39,46,128,230],"most":[40,192],"frequently":[41,64],"searched":[42],"dermatologic":[43],"conditions,":[44],"verifying":[45],"accuracy":[47],"automated":[49],"responses":[50,62],"crucial":[52],"to":[53,59,63,72],"prevent":[54],"misinformation.":[55],"This":[56],"study":[57],"aimed":[58],"evaluate":[60],"ChatGPT-5":[61,131,210],"asked":[65,101],"questions":[67,103],"in":[68,133],"dermatology":[69],"practice":[70],"determine":[73],"category-specific":[74],"strengths":[75],"limitations":[77],"based":[78],"on":[79,86],"blinded":[80],"expert":[81],"assessment.":[82],"The":[83,191],"analysis":[84],"focused":[85],"identifying":[87],"error":[88],"patterns":[89],"potential":[91],"implications":[92],"for":[93,153,172,181,195,216,232],"patient":[94,102],"education":[95],"clinical":[97],"safety.":[98],"Twenty-five":[99],"commonly":[100],"were":[104,155,167,197],"classified":[105],"into":[106,127],"4":[107],"categories:":[108],"skin":[109,173],"care":[110,174],"routine,":[111],"nutrition":[112,177],"lifestyle,":[114],"diagnosis":[115,185],"general":[117],"treatment":[120,182,221],"medications.":[122],"Each":[123],"question":[124],"was":[125,170,189],"entered":[126],"publicly":[129],"available":[130],"interface":[132],"3":[134],"independent":[135],"sessions,":[136],"yielding":[137],"75":[138,163],"unique":[139],"responses.":[140],"Three":[141],"dermatologists":[142],"independently":[143],"rated":[144],"each":[145],"response":[146],"as":[147],"\\"appropriate\\"":[148],"or":[149],"\\"inappropriate,\\"":[150],"reasons":[152,194],"rejection":[154],"categorized":[156],"using":[157],"a":[158],"predefined":[159],"9-item":[160],"list.":[161],"Of":[162],"responses,":[164],"49":[165],"(65.3%)":[166],"appropriate.":[168],"Appropriateness":[169],"highest":[171],"(83.3%)":[175],"(77.8%)":[178],"lowest":[180],"(50.0%)":[183],"(33.3%).":[186],"Inter-rater":[187],"agreement":[188],"low.":[190],"frequent":[193],"inappropriateness":[196],"misleading":[198],"information":[199,215],"overly":[201],"technical":[202],"language,":[203],"followed":[204],"by":[205],"lack":[206],"risk":[208],"disclosure.":[209],"provide":[212],"helpful":[213],"introductory":[214],"patients;":[217],"however,":[218],"diagnostic":[219],"guidance":[222],"often":[223],"lacked":[224],"clarity":[225],"safety":[227],"detail,":[228],"underscoring":[229],"need":[231],"dermatologist":[233],"oversight.":[234]}

Authors

Institutions

Publication Details

Journal
Medicine
Published
2026-09-18
DOI
https://doi.org/10.1097/md.0000000000050664
Primary Topic
Artificial Intelligence in Healthcare and Education
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
article

How appropriate are ChatGPT-5’s answers to acne questions?

Nazlı Caf, Defne Özkoca, Zekayі Kutlubay, Tuğba Kevser Uzunçakmak
Medicine
Artificial Intelligence in Healthcare and Education
article

How appropriate are ChatGPT-5’s answers to acne questions?

Nazlı Caf, Defne Özkoca, Zekayі Kutlubay, Tuğba Kevser Uzunçakmak
article en

Abstract

Online conversational tools have become increasingly common sources of health information, with many patients seeking acne advice through such platforms. Although they may enhance awareness and encourage early consultation, their medical reliability remains uncertain. Because acne is one of the most frequently searched dermatologic conditions, verifying the accuracy of automated responses is crucial to prevent misinformation. This study aimed to evaluate ChatGPT-5 responses to frequently asked acne questions in dermatology practice and to determine category-specific strengths and limitations based on blinded expert assessment. The analysis focused on identifying error patterns with potential implications for patient education and clinical safety. Twenty-five commonly asked patient questions were classified into 4 categories: skin care routine, nutrition and lifestyle, diagnosis and general information, and treatment and medications. Each question was entered into the publicly available ChatGPT-5 interface in 3 independent sessions, yielding 75 unique responses. Three dermatologists independently rated each response as "appropriate" or "inappropriate," and reasons for rejection were categorized using a predefined 9-item list. Of 75 responses, 49 (65.3%) were appropriate. Appropriateness was highest for skin care (83.3%) and nutrition (77.8%) and lowest for treatment (50.0%) and diagnosis (33.3%). Inter-rater agreement was low. The most frequent reasons for inappropriateness were misleading information and overly technical language, followed by lack of risk disclosure. ChatGPT-5 may provide helpful introductory information for patients; however, diagnostic and treatment guidance often lacked clarity and safety detail, underscoring the need for dermatologist oversight.

MedicineVol. 105(38)
Istanbul University-Cerrahpaşa (TR), Sağlık Bilimleri Üniversitesi (TR), Istanbul University (TR), University of Health Sciences Antigua (AG)
Quality Education
Openalex Percentile: Top 15%
Artificial Intelligence in Healthcare and Education
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.