Skip to main content

Variational Disentanglement for Rare Event Modeling.

Publication ,  Journal Article
Xiu, Z; Tao, C; Gao, M; Davis, C; Goldstein, BA; Henao, R
Published in: Proc AAAI Conf Artif Intell
May 18, 2021

Combining the increasing availability and abundance of healthcare data and the current advances in machine learning methods have created renewed opportunities to improve clinical decision support systems. However, in healthcare risk prediction applications, the proportion of cases with the condition (label) of interest is often very low relative to the available sample size. Though very prevalent in healthcare, such imbalanced classification settings are also common and challenging in many other scenarios. So motivated, we propose a variational disentanglement approach to semi-parametrically learn from rare events in heavily imbalanced classification problems. Specifically, we leverage the imposed extreme-distribution behavior on a latent space to extract information from low-prevalence events, and develop a robust prediction arm that joins the merits of the generalized additive model and isotonic neural nets. Results on synthetic studies and diverse real-world datasets, including mortality prediction on a COVID-19 cohort, demonstrate that the proposed approach outperforms existing alternatives.

Duke Scholars

Published In

Proc AAAI Conf Artif Intell

ISSN

2159-5399

Publication Date

May 18, 2021

Volume

35

Issue

12

Start / End Page

10469 / 10477

Location

United States
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Xiu, Z., Tao, C., Gao, M., Davis, C., Goldstein, B. A., & Henao, R. (2021). Variational Disentanglement for Rare Event Modeling. Proc AAAI Conf Artif Intell, 35(12), 10469–10477.
Xiu, Zidi, Chenyang Tao, Michael Gao, Connor Davis, Benjamin A. Goldstein, and Ricardo Henao. “Variational Disentanglement for Rare Event Modeling.Proc AAAI Conf Artif Intell 35, no. 12 (May 18, 2021): 10469–77.
Xiu Z, Tao C, Gao M, Davis C, Goldstein BA, Henao R. Variational Disentanglement for Rare Event Modeling. Proc AAAI Conf Artif Intell. 2021 May 18;35(12):10469–77.
Xiu, Zidi, et al. “Variational Disentanglement for Rare Event Modeling.Proc AAAI Conf Artif Intell, vol. 35, no. 12, May 2021, pp. 10469–77.
Xiu Z, Tao C, Gao M, Davis C, Goldstein BA, Henao R. Variational Disentanglement for Rare Event Modeling. Proc AAAI Conf Artif Intell. 2021 May 18;35(12):10469–10477.

Published In

Proc AAAI Conf Artif Intell

ISSN

2159-5399

Publication Date

May 18, 2021

Volume

35

Issue

12

Start / End Page

10469 / 10477

Location

United States