摘要
Early prediction of patient outcomes is important for targeting preventive care. This protocol describes a practical workflow for developing deep-learning risk models that can predict various clinical and operational outcomes from structured electronic health record (EHR) data. The protocol comprises five main stages: formal problem definition, data pre-processing, architecture selection, calibration and uncertainty, and generalizability evaluation. We have applied the workflow to four endpoints (acute kidney injury, mortality, length of stay and 30-day hospital readmission). The workflow can enable continuous (e.g., triggered every 6 h) and static (e.g., triggered at 24 h after admission) predictions. We also provide an open-source codebase that illustrates some key principles in EHR modeling. This protocol can be used by interdisciplinary teams with programming and clinical expertise to build deep-learning prediction models with alternate data sources and prediction tasks. We present a practical workflow describing how to use deep learning to develop continuous-risk models that can predict various adverse outcomes from structured electronic health records.
学科与关键词
- Use of Deep Learning for Continuous Prediction of Mortality for All Admissions in Intensive Care UnitsZeng, Guangjian; Zhuang, Jinhu; Huang, Haofan; Tian, Mu; Gao, Yi; Liu, Yong*; Yu, Xiaxia*TSINGHUA SCIENCE AND TECHNOLOGY, 2023, 28(4): 639-648.
- Deep learning architecture to predict daily hospital admissionsRicardo, Navares; José L., AznarteNEURAL COMPUTING & APPLICATIONS, 2020, 32(20): 16235-16244.被引 2
- Development and validation of a deep interpretable network for continuous acute kidney injury prediction in critically ill patientsYang, Meicheng; Liu, Songqiao; Hao, Tong; Ma, Caiyun; Chen, Hui; Li, Yuwen; Wu, Changde; Xie, Jianfeng; Qiu, Haibo; Li, Jianqing*; Yang, Yi*; Liu, Chengyu*Artificial Intelligence in Medicine, 2024, 149: 102785.被引 1
