2022-12-31-wu22a.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
Despite machine learning models’ state-of-the-art performance in numerous clinical prediction and intervention tasks, their complex black-box processes pose a great barrier to their real-world deployment. Clinical experts must be able to understand the reasons behind a model’s recommendation before taking action, as it is crucial to assess for criteria other than accuracy, such as trust, safety, fairness, and robustness. In this work, we enable human inspection of clinical timeseries prediction models by learning concepts, or groupings of features into high-level clinical ideas such as illness severity or kidney function. We also propose an optimization method which then selects the most important features within each concept, learning a collection of sparse prediction models that are sufficiently expressive for examination. On a real-world task of predicting vasopressor onset in ICU units, our algorithm achieves predictive performance comparable to state-of-the-art deep learning models while learning concise groupings conducive for clinical inspection.	Proceedings of the 7th Machine Learning for Healthcare Conference	Learning Optimal Summaries of Clinical Time-series with Concept Bottleneck Models	182	2022	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	wu22a	0	Learning Optimal Summaries of Clinical Time-series with Concept Bottleneck Models	648	672	648-672	648	false	Wu, Carissa and Parbhoo, Sonali and Havasi, Marton and Doshi-Velez, Finale	given family Carissa Wu given family Sonali Parbhoo given family Marton Havasi given family Finale Doshi-Velez	2022-12-31		Proceedings of the 7th Machine Learning for Healthcare Conference	inproceedings	date-parts 2022 12 31	https://proceedings.mlr.press/v182/wu22a/wu22a.pdf