{"title":"在开始治疗时识别抑郁症及其决定因素：ChatGPT与初级保健医生。","authors":"Inbar Levkovich, Zohar Elyoseph","doi":"10.1136/fmch-2023-002391","DOIUrl":null,"url":null,"abstract":"<p><strong>Objective: </strong>To compare evaluations of depressive episodes and suggested treatment protocols generated by Chat Generative Pretrained Transformer (ChatGPT)-3 and ChatGPT-4 with the recommendations of primary care physicians.</p><p><strong>Methods: </strong>Vignettes were input to the ChatGPT interface. These vignettes focused primarily on hypothetical patients with symptoms of depression during initial consultations. The creators of these vignettes meticulously designed eight distinct versions in which they systematically varied patient attributes (sex, socioeconomic status (blue collar worker or white collar worker) and depression severity (mild or severe)). Each variant was subsequently introduced into ChatGPT-3.5 and ChatGPT-4. Each vignette was repeated 10 times to ensure consistency and reliability of the ChatGPT responses.</p><p><strong>Results: </strong>For mild depression, ChatGPT-3.5 and ChatGPT-4 recommended psychotherapy in 95.0% and 97.5% of cases, respectively. Primary care physicians, however, recommended psychotherapy in only 4.3% of cases. For severe cases, ChatGPT favoured an approach that combined psychotherapy, while primary care physicians recommended a combined approach. The pharmacological recommendations of ChatGPT-3.5 and ChatGPT-4 showed a preference for exclusive use of antidepressants (74% and 68%, respectively), in contrast with primary care physicians, who typically recommended a mix of antidepressants and anxiolytics/hypnotics (67.4%). Unlike primary care physicians, ChatGPT showed no gender or socioeconomic biases in its recommendations.</p><p><strong>Conclusion: </strong>ChatGPT-3.5 and ChatGPT-4 aligned well with accepted guidelines for managing mild and severe depression, without showing the gender or socioeconomic biases observed among primary care physicians. Despite the suggested potential benefit of using atificial intelligence (AI) chatbots like ChatGPT to enhance clinical decision making, further research is needed to refine AI recommendations for severe cases and to consider potential risks and ethical issues.</p>","PeriodicalId":44590,"journal":{"name":"Family Medicine and Community Health","volume":"11 4","pages":""},"PeriodicalIF":2.6000,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/6f/f6/fmch-2023-002391.PMC10582915.pdf","citationCount":"0","resultStr":"{\"title\":\"Identifying depression and its determinants upon initiating treatment: ChatGPT versus primary care physicians.\",\"authors\":\"Inbar Levkovich, Zohar Elyoseph\",\"doi\":\"10.1136/fmch-2023-002391\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Objective: </strong>To compare evaluations of depressive episodes and suggested treatment protocols generated by Chat Generative Pretrained Transformer (ChatGPT)-3 and ChatGPT-4 with the recommendations of primary care physicians.</p><p><strong>Methods: </strong>Vignettes were input to the ChatGPT interface. These vignettes focused primarily on hypothetical patients with symptoms of depression during initial consultations. The creators of these vignettes meticulously designed eight distinct versions in which they systematically varied patient attributes (sex, socioeconomic status (blue collar worker or white collar worker) and depression severity (mild or severe)). Each variant was subsequently introduced into ChatGPT-3.5 and ChatGPT-4. Each vignette was repeated 10 times to ensure consistency and reliability of the ChatGPT responses.</p><p><strong>Results: </strong>For mild depression, ChatGPT-3.5 and ChatGPT-4 recommended psychotherapy in 95.0% and 97.5% of cases, respectively. Primary care physicians, however, recommended psychotherapy in only 4.3% of cases. For severe cases, ChatGPT favoured an approach that combined psychotherapy, while primary care physicians recommended a combined approach. The pharmacological recommendations of ChatGPT-3.5 and ChatGPT-4 showed a preference for exclusive use of antidepressants (74% and 68%, respectively), in contrast with primary care physicians, who typically recommended a mix of antidepressants and anxiolytics/hypnotics (67.4%). Unlike primary care physicians, ChatGPT showed no gender or socioeconomic biases in its recommendations.</p><p><strong>Conclusion: </strong>ChatGPT-3.5 and ChatGPT-4 aligned well with accepted guidelines for managing mild and severe depression, without showing the gender or socioeconomic biases observed among primary care physicians. Despite the suggested potential benefit of using atificial intelligence (AI) chatbots like ChatGPT to enhance clinical decision making, further research is needed to refine AI recommendations for severe cases and to consider potential risks and ethical issues.</p>\",\"PeriodicalId\":44590,\"journal\":{\"name\":\"Family Medicine and Community Health\",\"volume\":\"11 4\",\"pages\":\"\"},\"PeriodicalIF\":2.6000,\"publicationDate\":\"2023-09-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/6f/f6/fmch-2023-002391.PMC10582915.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Family Medicine and Community Health\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1136/fmch-2023-002391\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"PRIMARY HEALTH CARE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Family Medicine and Community Health","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1136/fmch-2023-002391","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PRIMARY HEALTH CARE","Score":null,"Total":0}
Identifying depression and its determinants upon initiating treatment: ChatGPT versus primary care physicians.
Objective: To compare evaluations of depressive episodes and suggested treatment protocols generated by Chat Generative Pretrained Transformer (ChatGPT)-3 and ChatGPT-4 with the recommendations of primary care physicians.
Methods: Vignettes were input to the ChatGPT interface. These vignettes focused primarily on hypothetical patients with symptoms of depression during initial consultations. The creators of these vignettes meticulously designed eight distinct versions in which they systematically varied patient attributes (sex, socioeconomic status (blue collar worker or white collar worker) and depression severity (mild or severe)). Each variant was subsequently introduced into ChatGPT-3.5 and ChatGPT-4. Each vignette was repeated 10 times to ensure consistency and reliability of the ChatGPT responses.
Results: For mild depression, ChatGPT-3.5 and ChatGPT-4 recommended psychotherapy in 95.0% and 97.5% of cases, respectively. Primary care physicians, however, recommended psychotherapy in only 4.3% of cases. For severe cases, ChatGPT favoured an approach that combined psychotherapy, while primary care physicians recommended a combined approach. The pharmacological recommendations of ChatGPT-3.5 and ChatGPT-4 showed a preference for exclusive use of antidepressants (74% and 68%, respectively), in contrast with primary care physicians, who typically recommended a mix of antidepressants and anxiolytics/hypnotics (67.4%). Unlike primary care physicians, ChatGPT showed no gender or socioeconomic biases in its recommendations.
Conclusion: ChatGPT-3.5 and ChatGPT-4 aligned well with accepted guidelines for managing mild and severe depression, without showing the gender or socioeconomic biases observed among primary care physicians. Despite the suggested potential benefit of using atificial intelligence (AI) chatbots like ChatGPT to enhance clinical decision making, further research is needed to refine AI recommendations for severe cases and to consider potential risks and ethical issues.
期刊介绍：
Family Medicine and Community Health (FMCH) is a peer-reviewed, open-access journal focusing on the topics of family medicine, general practice and community health. FMCH strives to be a leading international journal that promotes ‘Health Care for All’ through disseminating novel knowledge and best practices in primary care, family medicine, and community health. FMCH publishes original research, review, methodology, commentary, reflection, and case-study from the lens of population health. FMCH’s Asian Focus section features reports of family medicine development in the Asia-pacific region. FMCH aims to be an exemplary forum for the timely communication of medical knowledge and skills with the goal of promoting improved health care through the practice of family and community-based medicine globally. FMCH aims to serve a diverse audience including researchers, educators, policymakers and leaders of family medicine and community health. We also aim to provide content relevant for researchers working on population health, epidemiology, public policy, disease control and management, preventative medicine and disease burden. FMCH does not impose any article processing charges (APC) or submission charges.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
