Diagnostic prediction models for primary care, based on artificial intelligence and electronic health records: a systematic review (Preprint)

Author:

Hunik LiesbethORCID,Chaabouni AsmaORCID,van Laarhoven TwanORCID,olde Hartman Tim CORCID,Leijenaar Ralph THORCID,Cals Jochen WLORCID,Uijen Annemarie AORCID,Schers Henk JORCID

Abstract

BACKGROUND

Artificial intelligence (AI) based diagnostic prediction models could aid primary care (PC) in decision making for faster and more accurate diagnoses. AI has the potential to transform electronic health records (EHR) data into valuable diagnostic prediction models. Different prediction models based on EHR have been developed. However, there are currently no systematic reviews that evaluate AI-based diagnostic prediction models for PC using EHR data.

OBJECTIVE

To provide an overview of diagnostic prediction models based on AI and EHR in primary care and to evaluate the content of each model, including risk of bias and applicability.

METHODS

This systematic review was performed according to the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. MEDLINE, EMBASE, Web of Science and Cochrane were searched. We included observational and intervention studies using AI and primary care EHRs and developing or testing a diagnostic prediction model for health conditions. Two independent reviewers used a standardised data extraction form. Risk of bias and applicability were assessed using PROBAST (Prediction model Risk Of Bias ASsessment Tool).

RESULTS

From 10,657 retrieved records, a total of 15 papers were selected. Most EHR papers focused on one chronic healthcare condition (n=11). From the 15 papers, 13 described a study that developed a diagnostic prediction model and 2 described a study that externally validated and tested the model in a primary care setting. Studies used a variety of AI techniques. The predictors used to develop the model were all registered in the EHR. We found no papers with a low risk of bias, high risk of bias was found in 9 papers. Biases covered an unjustified small sample size (n=5), not excluding predictors from the outcome definition (n=2) and the inappropriate evaluation of the performance measures (n=2). Unclear risk of bias was found in 6 papers, as no information was provided on the handling of missing data (n=10) and no results were reported from the multivariate analysis (n=9). Applicability was unclear in 10 papers, mainly due to lack of clarity in reporting the time interval between outcomes and predictors.

CONCLUSIONS

Most AI-based diagnostic prediction models based on EHR data in primary care focused on one chronic condition. Only two papers tested the model in a primary care setting. The lack of sufficiently described methods led to a high risk of bias. Our findings highlight that the currently available diagnostic prediction models are not yet ready for clinical implementation in primary care.

Publisher

JMIR Publications Inc.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3