Brian D Earp, Sebastian Porsdam Mann, Jemima Allen, Sabine Salloch, Vynn Suren, Karin Jongsma, Matthias Braun, Dominic Wilkinson, Walter Sinnott-Armstrong, Annette Rid, David Wendler, Julian Savulescu
{"title":"医疗保健中替代判断的个性化患者偏好预测器:技术上可行,伦理上可取。","authors":"Brian D Earp, Sebastian Porsdam Mann, Jemima Allen, Sabine Salloch, Vynn Suren, Karin Jongsma, Matthias Braun, Dominic Wilkinson, Walter Sinnott-Armstrong, Annette Rid, David Wendler, Julian Savulescu","doi":"10.1080/15265161.2023.2296402","DOIUrl":null,"url":null,"abstract":"<p><p>When making substituted judgments for incapacitated patients, surrogates often struggle to guess what the patient would want if they had capacity. Surrogates may also agonize over having the (sole) responsibility of making such a determination. To address such concerns, a Patient Preference Predictor (PPP) has been proposed that would use an algorithm to infer the treatment preferences of individual patients from population-level data about the known preferences of people with similar demographic characteristics. However, critics have suggested that even if such a PPP were more accurate, on average, than human surrogates in identifying patient preferences, the proposed algorithm would nevertheless fail to respect the patient's (former) autonomy since it draws on the 'wrong' kind of data: namely, data that are not specific to the individual patient and which therefore may not reflect their actual values, or their reasons for having the preferences they do. Taking such criticisms on board, we here propose a new approach: the <i>Personalized</i> Patient Preference Predictor (P4). The P4 is based on recent advances in machine learning, which allow technologies including large language models to be more cheaply and efficiently 'fine-tuned' on person-specific data. The P4, unlike the PPP, would be able to infer an individual patient's preferences from material (e.g., prior treatment decisions) that is in fact specific to them. Thus, we argue, in addition to being potentially more accurate at the individual level than the previously proposed PPP, the predictions of a P4 would also more directly reflect each patient's own reasons and values. In this article, we review recent discoveries in artificial intelligence research that suggest a P4 is technically feasible, and argue that, if it is developed and appropriately deployed, it should assuage some of the main autonomy-based concerns of critics of the original PPP. We then consider various objections to our proposal and offer some tentative replies.</p>","PeriodicalId":50962,"journal":{"name":"American Journal of Bioethics","volume":null,"pages":null},"PeriodicalIF":17.0000,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11248995/pdf/","citationCount":"0","resultStr":"{\"title\":\"A Personalized Patient Preference Predictor for Substituted Judgments in Healthcare: Technically Feasible and Ethically Desirable.\",\"authors\":\"Brian D Earp, Sebastian Porsdam Mann, Jemima Allen, Sabine Salloch, Vynn Suren, Karin Jongsma, Matthias Braun, Dominic Wilkinson, Walter Sinnott-Armstrong, Annette Rid, David Wendler, Julian Savulescu\",\"doi\":\"10.1080/15265161.2023.2296402\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>When making substituted judgments for incapacitated patients, surrogates often struggle to guess what the patient would want if they had capacity. Surrogates may also agonize over having the (sole) responsibility of making such a determination. To address such concerns, a Patient Preference Predictor (PPP) has been proposed that would use an algorithm to infer the treatment preferences of individual patients from population-level data about the known preferences of people with similar demographic characteristics. However, critics have suggested that even if such a PPP were more accurate, on average, than human surrogates in identifying patient preferences, the proposed algorithm would nevertheless fail to respect the patient's (former) autonomy since it draws on the 'wrong' kind of data: namely, data that are not specific to the individual patient and which therefore may not reflect their actual values, or their reasons for having the preferences they do. Taking such criticisms on board, we here propose a new approach: the <i>Personalized</i> Patient Preference Predictor (P4). The P4 is based on recent advances in machine learning, which allow technologies including large language models to be more cheaply and efficiently 'fine-tuned' on person-specific data. The P4, unlike the PPP, would be able to infer an individual patient's preferences from material (e.g., prior treatment decisions) that is in fact specific to them. Thus, we argue, in addition to being potentially more accurate at the individual level than the previously proposed PPP, the predictions of a P4 would also more directly reflect each patient's own reasons and values. In this article, we review recent discoveries in artificial intelligence research that suggest a P4 is technically feasible, and argue that, if it is developed and appropriately deployed, it should assuage some of the main autonomy-based concerns of critics of the original PPP. We then consider various objections to our proposal and offer some tentative replies.</p>\",\"PeriodicalId\":50962,\"journal\":{\"name\":\"American Journal of Bioethics\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":17.0000,\"publicationDate\":\"2024-07-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11248995/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"American Journal of Bioethics\",\"FirstCategoryId\":\"98\",\"ListUrlMain\":\"https://doi.org/10.1080/15265161.2023.2296402\",\"RegionNum\":1,\"RegionCategory\":\"哲学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/1/16 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q1\",\"JCRName\":\"ETHICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"American Journal of Bioethics","FirstCategoryId":"98","ListUrlMain":"https://doi.org/10.1080/15265161.2023.2296402","RegionNum":1,"RegionCategory":"哲学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/1/16 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"ETHICS","Score":null,"Total":0}
A Personalized Patient Preference Predictor for Substituted Judgments in Healthcare: Technically Feasible and Ethically Desirable.
When making substituted judgments for incapacitated patients, surrogates often struggle to guess what the patient would want if they had capacity. Surrogates may also agonize over having the (sole) responsibility of making such a determination. To address such concerns, a Patient Preference Predictor (PPP) has been proposed that would use an algorithm to infer the treatment preferences of individual patients from population-level data about the known preferences of people with similar demographic characteristics. However, critics have suggested that even if such a PPP were more accurate, on average, than human surrogates in identifying patient preferences, the proposed algorithm would nevertheless fail to respect the patient's (former) autonomy since it draws on the 'wrong' kind of data: namely, data that are not specific to the individual patient and which therefore may not reflect their actual values, or their reasons for having the preferences they do. Taking such criticisms on board, we here propose a new approach: the Personalized Patient Preference Predictor (P4). The P4 is based on recent advances in machine learning, which allow technologies including large language models to be more cheaply and efficiently 'fine-tuned' on person-specific data. The P4, unlike the PPP, would be able to infer an individual patient's preferences from material (e.g., prior treatment decisions) that is in fact specific to them. Thus, we argue, in addition to being potentially more accurate at the individual level than the previously proposed PPP, the predictions of a P4 would also more directly reflect each patient's own reasons and values. In this article, we review recent discoveries in artificial intelligence research that suggest a P4 is technically feasible, and argue that, if it is developed and appropriately deployed, it should assuage some of the main autonomy-based concerns of critics of the original PPP. We then consider various objections to our proposal and offer some tentative replies.
期刊介绍:
The American Journal of Bioethics (AJOB) is a renowned global publication focused on bioethics. It tackles pressing ethical challenges in the realm of health sciences.
With a commitment to the original vision of bioethics, AJOB explores the social consequences of advancements in biomedicine. It sparks meaningful discussions that have proved invaluable to a wide range of professionals, including judges, senators, journalists, scholars, and educators.
AJOB covers various areas of interest, such as the ethical implications of clinical research, ensuring access to healthcare services, and the responsible handling of medical records and data.
The journal welcomes contributions in the form of target articles presenting original research, open peer commentaries facilitating a dialogue, book reviews, and responses to open peer commentaries.
By presenting insightful and authoritative content, AJOB continues to shape the field of bioethics and engage diverse stakeholders in crucial conversations about the intersection of medicine, ethics, and society.