Task-Oriented Predictive (Top)-BERT: Novel Approach for Predicting Diabetic Complications Using a Single-Center EHR Data

Author:

Islam Humayera,Bartlett Gillian,Pierce Robert,Rao Praveen,Waitman Lemuel R.,Song Xing

Abstract

AbstractIn this study, we assess the capacity of the BERT (Bidirectional Encoder Representations from Transformers) framework to predict a 12-month risk for major diabetic complications—retinopathy, nephropathy, neuropathy, and major adverse cardiovascular events (MACE) using a single-center EHR dataset. We introduce a task-oriented predictive (Top)-BERT architecture, which is a unique end-to-end training and evaluation framework utilizing sequential input structure, embedding layer, and encoder stacks inherent to BERT. This enhanced architecture trains and evaluates the model across multiple learning tasks simultaneously, enhancing the model’s ability to learn from a limited amount of data. Our findings demonstrate that this approach can outperform both traditional pretraining-finetuning BERT models and conventional machine learning methods, offering a promising tool for early identification of patients at risk of diabetes-related complications. We also investigate how different temporal embedding strategies affect the model’s predictive capabilities, with simpler designs yielding better performance. The use of Integrated Gradients (IG) augments the explainability of our predictive models, yielding feature attributions that substantiate the clinical significance of this study. Finally, this study also highlights the essential role of proactive symptom assessment and the management of comorbid conditions in preventing the advancement of complications in patients with diabetes.

Publisher

Cold Spring Harbor Laboratory

Reference56 articles.

1. Center for Disease Controls and Prevention National Diabetes Statistics Report 2020: Estimates of Diabetes and Its Burden in the United States. (2020).

2. Characterizing Multimorbidity from Type 2 Diabetes: Insights from Clustering Approaches;Endocrinol Metab Clin North Am,2021

3. Ndjaboue, R. et al. Predictive models of diabetes complications: protocol for a scoping. Syst Rev 9, (2020).

4. Predicting hospital readmission via cost-sensitive deep learning;IEEE/ACM transactions on computational biology and bioinformatic,2018

5. AI-Assisted Decision-making in Healthcare

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