Foresight—a generative pretrained transformer for modelling of patient timelines using electronic health records: a retrospective modelling study

时间轴 计算机科学 变压器 健康信息学 情报检索 病历 人工智能 自然语言处理 数据科学 医学 公共卫生 工程类 护理部 考古 放射科 电压 电气工程 历史
作者
Željko Kraljević,Daniel Bean,Anthony Shek,Rebecca Bendayan,Harry Hemingway,Joshua Au Yeung,Alexander Deng,Alfred Balston,Jack Ross,Esther Idowu,James Teo,Richard Dobson
出处
期刊:The Lancet Digital Health [Elsevier]
卷期号:6 (4): e281-e290 被引量:14
标识
DOI:10.1016/s2589-7500(24)00025-6
摘要

BackgroundAn electronic health record (EHR) holds detailed longitudinal information about a patient's health status and general clinical history, a large portion of which is stored as unstructured, free text. Existing approaches to model a patient's trajectory focus mostly on structured data and a subset of single-domain outcomes. This study aims to evaluate the effectiveness of Foresight, a generative transformer in temporal modelling of patient data, integrating both free text and structured formats, to predict a diverse array of future medical outcomes, such as disorders, substances (eg, to do with medicines, allergies, or poisonings), procedures, and findings (eg, relating to observations, judgements, or assessments).MethodsForesight is a novel transformer-based pipeline that uses named entity recognition and linking tools to convert EHR document text into structured, coded concepts, followed by providing probabilistic forecasts for future medical events, such as disorders, substances, procedures, and findings. The Foresight pipeline has four main components: (1) CogStack (data retrieval and preprocessing); (2) the Medical Concept Annotation Toolkit (structuring of the free-text information from EHRs); (3) Foresight Core (deep-learning model for biomedical concept modelling); and (4) the Foresight web application. We processed the entire free-text portion from three different hospital datasets (King's College Hospital [KCH], South London and Maudsley [SLaM], and the US Medical Information Mart for Intensive Care III [MIMIC-III]), resulting in information from 811 336 patients and covering both physical and mental health institutions. We measured the performance of models using custom metrics derived from precision and recall.FindingsForesight achieved a precision@10 (ie, of 10 forecasted candidates, at least one is correct) of 0·68 (SD 0·0027) for the KCH dataset, 0·76 (0·0032) for the SLaM dataset, and 0·88 (0·0018) for the MIMIC-III dataset, for forecasting the next new disorder in a patient timeline. Foresight also achieved a precision@10 value of 0·80 (0·0013) for the KCH dataset, 0·81 (0·0026) for the SLaM dataset, and 0·91 (0·0011) for the MIMIC-III dataset, for forecasting the next new biomedical concept. In addition, Foresight was validated on 34 synthetic patient timelines by five clinicians and achieved a relevancy of 33 (97% [95% CI 91–100]) of 34 for the top forecasted candidate disorder. As a generative model, Foresight can forecast follow-on biomedical concepts for as many steps as required.InterpretationForesight is a general-purpose model for biomedical concept modelling that can be used for real-world risk forecasting, virtual trials, and clinical research to study the progression of disorders, to simulate interventions and counterfactuals, and for educational purposes.FundingNational Health Service Artificial Intelligence Laboratory, National Institute for Health and Care Research Biomedical Research Centre, and Health Data Research UK.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
小蘑菇应助我先睡了采纳,获得10
2秒前
子春完成签到 ,获得积分10
4秒前
大个应助丹丹采纳,获得10
4秒前
劲秉应助科研狗-加班族采纳,获得10
4秒前
毛通完成签到,获得积分10
5秒前
Cristina2024完成签到,获得积分10
5秒前
zeroy完成签到,获得积分10
6秒前
微笑驳发布了新的文献求助10
7秒前
荀代灵完成签到,获得积分10
8秒前
8秒前
占那个发布了新的文献求助10
9秒前
9秒前
刘大大123发布了新的文献求助10
13秒前
辣辣完成签到,获得积分10
14秒前
14秒前
CodeCraft应助体贴的兔子采纳,获得10
14秒前
lishan发布了新的文献求助20
17秒前
17秒前
迷路安白完成签到 ,获得积分10
18秒前
尊敬的半梅完成签到 ,获得积分10
18秒前
19秒前
领导范儿应助hanzhang采纳,获得10
20秒前
科研通AI2S应助fifteen采纳,获得10
24秒前
丹丹发布了新的文献求助10
25秒前
25秒前
丘比特应助结实星星采纳,获得10
28秒前
29秒前
打打应助lishan采纳,获得10
30秒前
郭二发布了新的文献求助10
30秒前
星辰大海应助11采纳,获得10
31秒前
32秒前
33秒前
33秒前
shandy完成签到,获得积分20
33秒前
wendy完成签到,获得积分10
34秒前
852应助刘大大123采纳,获得10
34秒前
35秒前
35秒前
36秒前
shandy发布了新的文献求助10
37秒前
高分求助中
Spray / Wall-interaction Modelling by Dimensionless Data Analysis 2000
ALA生合成不全マウスでの糖代謝異常の分子機構解析 520
安全防范技术与工程 500
Mathematics and Finite Element Discretizations of Incompressible Navier—Stokes Flows 500
A real-time energy management strategy based on fuzzy control and ECMS for PHEVs 400
2024 Medicinal Chemistry Reviews 400
Why I Chose China [by Morris R. Wills] in "Look", February 8 and 22, 1966; 400
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3191424
求助须知:如何正确求助?哪些是违规求助? 2840741
关于积分的说明 8029841
捐赠科研通 2504130
什么是DOI,文献DOI怎么找? 1337399
科研通“疑难数据库(出版商)”最低求助积分说明 638073
邀请新用户注册赠送积分活动 606605