2022-12-31-huo22a.md

abstract	booktitle	title	volume	year	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	genre	issued	pdf	extras
Medical events of interest, such as mortality, often happen at a low rate in electronic medical records, as most admitted patients survive. Training models with this imbalance rate (class density discrepancy) may lead to suboptimal prediction. Traditionally this problem is addressed through ad-hoc methods such as resampling or reweighting but performance in many cases is still limited. We propose a framework for training models for this imbalance issue: 1) we first decouple the feature extraction and classification process, adjusting training batches separately for each component to mitigate bias caused by class density discrepancy; 2) we train the network with both a density-aware loss and a learnable cost matrix for misclassifications. We demonstrate our model’s improved performance in real-world medical datasets (TOPCAT and MIMIC-III) to show improved AUC-ROC, AUC-PRC, Brier Skill Score compared with the baselines in the domain.	Proceedings of the 7th Machine Learning for Healthcare Conference	Density-Aware Personalized Training for Risk Prediction in Imbalanced Medical Data	182	2022	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	huo22a	0	Density-Aware Personalized Training for Risk Prediction in Imbalanced Medical Data	101	122	101-122	101	false	Huo, Zepeng and Qian, Xiaoning and Huang, Shuai and Wang, Zhangyang and Mortazavi, Bobak J.	given family Zepeng Huo given family Xiaoning Qian given family Shuai Huang given family Zhangyang Wang given family Bobak J. Mortazavi	2022-12-31		Proceedings of the 7th Machine Learning for Healthcare Conference	inproceedings	date-parts 2022 12 31	https://proceedings.mlr.press/v182/huo22a/huo22a.pdf