Timesias: A machine learning pipeline for predicting outcomes from time-series clinical records

Hanrui Zhang; Daiyao Yi; Yuanfang Guan

doi:10.1016/j.xpro.2021.100639

Timesias: A machine learning pipeline for predicting outcomes from time-series clinical records

STAR Protoc. 2021 Jul 2;2(3):100639. doi: 10.1016/j.xpro.2021.100639. eCollection 2021 Sep 17.

Authors

Hanrui Zhang¹, Daiyao Yi¹, Yuanfang Guan^{1

2}

Affiliations

¹ Department of Computational Medicine and Bioinformatics, Michigan Medicine, University of Michigan, Ann Arbor, MI, USA.
² Department of Internal Medicine, Michigan Medicine, University of Michigan, Ann Arbor, MI, USA.

Abstract

The prediction of outcomes is a critical part of the clinical surveillance for hospitalized patients. Here, we present Timesias, a machine learning pipeline which predicts outcomes from real-time sequential clinical data. The strategy implemented in Timesias is the first-place solution in the crowd-sourcing DII (discover, innovate, impact) National Data Science Challenge involving more than 100,000 patients, achieving 0.85 as evaluated by AUROC (area under receiver operator characteristic curve) in predicting the early onset of sepsis status. Timesias is freely available via PyPI and GitHub. For complete details on the use and execution of this protocol, please refer to Guan et al. (2021).

Keywords: Bioinformatics; Clinical Protocol; Health Sciences.

Publication types

Research Support, N.I.H., Extramural
Research Support, U.S. Gov't, Non-P.H.S.

MeSH terms

Algorithms
Humans
Machine Learning*
Medical Records*
Outcome Assessment, Health Care*
Prognosis
Time Factors