The signature-based model for early detection of sepsis from electronic health records in the intensive care unit

Author: 

Morrill, J
Kormilitzin, A
Nevado-Holgado, A
Swaminathan, S
Howison, S
Lyons, T

Publication Date: 

24 February 2020

Journal: 

2019 Computing in Cardiology (CinC)

Last Updated: 

2020-08-10T12:59:41.65+01:00

Volume: 

46

DOI: 

10.23919/CinC49843.2019.9005805

abstract: 

Optimal feature selection leads to enhanced efficiency and accuracy when developing both supervised and unsupervised machine-learning models. In this work, a new signature-based regression model is proposed to automatically identify a patient's risk of sepsis based on physiological data streams and to make a positive or negative prediction of sepsis for every time interval since admission to the intensive care unit. The gradient boosting machine algorithm that uses the features at the current time-points and the signature features extracted from the time-series to model the longitudinal effects of sepsis yields the utility function score of 0.360 (officially ranked 1st, team name: ‘Can I get your Signature?’) on the full test set. The signature method shows a systematic and competitive approach to model sepsis by learning from health data streams.

Symplectic id: 

1063244

Submitted to ORA: 

Submitted

Publication Type: 

Conference Paper

ISBN-13: 

9781728159423