TY - JOUR
T1 - A Factored Generalized Additive Model for Clinical Decision Support in the Operating Room
AU - Cui, Zhicheng
AU - Fritz, Bradley A.
AU - King, Christopher R.
AU - Avidan, Michael S.
AU - Chen, Yixin
N1 - Publisher Copyright:
©2019 AMIA - All rights reserved.
PY - 2019
Y1 - 2019
N2 - Logistic regression (LR) is widely used in clinical prediction because it is simple to deploy and easy to interpret. Nevertheless, being a linear model, LR has limited expressive capability and often has unsatisfactory performance. Generalized additive models (GAMs) extend the linear model with transformations of input features, though feature interaction is not allowed for all GAM variants. In this paper, we propose a factored generalized additive model (F-GAM) to preserve the model interpretability for targeted features while allowing a rich model for interaction with features fixed within the individual. We evaluate F-GAM on prediction of two targets, postoperative acute kidney injury and acute respiratory failure, from a single-center database. We find superior model performance of F-GAM in terms of AUPRC and AUROC compared to several other GAM implementations, random forests, support vector machine, and a deep neural network. We find that the model interpretability is good with results with high face validity.
AB - Logistic regression (LR) is widely used in clinical prediction because it is simple to deploy and easy to interpret. Nevertheless, being a linear model, LR has limited expressive capability and often has unsatisfactory performance. Generalized additive models (GAMs) extend the linear model with transformations of input features, though feature interaction is not allowed for all GAM variants. In this paper, we propose a factored generalized additive model (F-GAM) to preserve the model interpretability for targeted features while allowing a rich model for interaction with features fixed within the individual. We evaluate F-GAM on prediction of two targets, postoperative acute kidney injury and acute respiratory failure, from a single-center database. We find superior model performance of F-GAM in terms of AUPRC and AUROC compared to several other GAM implementations, random forests, support vector machine, and a deep neural network. We find that the model interpretability is good with results with high face validity.
UR - http://www.scopus.com/inward/record.url?scp=85083755458&partnerID=8YFLogxK
M3 - Article
C2 - 32308827
AN - SCOPUS:85083755458
SN - 1559-4076
VL - 2019
SP - 343
EP - 352
JO - AMIA ... Annual Symposium proceedings. AMIA Symposium
JF - AMIA ... Annual Symposium proceedings. AMIA Symposium
ER -