Deep cox mixtures for survival regression

C Nagpal, S Yadlowsky… - Machine Learning …, 2021 - proceedings.mlr.press
Survival analysis is a challenging variation of regression modeling because of the presence
of censoring, where the outcome measurement is only partially known, due to, for example …

Causal rule ensemble: Interpretable discovery and inference of heterogeneous treatment effects

FJ Bargagli-Stoffi, R Cadei, K Lee… - ar** with censored time-to-events
C Nagpal, M Goswami, K Dufendach… - Proceedings of the 28th …, 2022 - dl.acm.org
Estimation of treatment efficacy of real-world clinical interventions involves working with
continuous time-to-event outcomes such as time-to-death, re-hospitalization, or a composite …

Fair and robust estimation of heterogeneous treatment effects for policy learning

K Kim, JR Zubizarreta - International Conference on …, 2023 - proceedings.mlr.press
We propose a simple and general framework for nonparametric estimation of
heterogeneous treatment effects under fairness constraints. Under standard regularity …

Computer-aided diagnosis through medical image retrieval in radiology

W Silva, T Gonçalves, K Härmä, E Schröder… - Scientific reports, 2022 - nature.com
Currently, radiologists face an excessive workload, which leads to high levels of fatigue, and
consequently, to undesired diagnosis mistakes. Decision support systems can be used to …

Auton-survival: an open-source package for regression, counterfactual estimation, evaluation and phenoty** with censored time-to-event data

C Nagpal, W Potosnak… - Machine Learning for …, 2022 - proceedings.mlr.press
Applications of machine learning in healthcare often require working with time-to-event
prediction tasks including prognostication of an adverse event, re-hospitalization, and …

Probing Digital Footprints and Reaching for Inherent Preferences: A Cause-Disentanglement Approach to Personalized Recommendations

C Wang, Y Shi, X Guo, G Chen - Information Systems …, 2024 - pubsonline.informs.org
The abundance of multiple types of consumer digital footprints recorded on e-commerce
platforms has fueled the design of personalized recommender systems for decision support …

Interpretable subgroup discovery in treatment effect estimation with application to opioid prescribing guidelines

C Nagpal, D Wei, B Vinzamuri, M Shekhar… - Proceedings of the …, 2020 - dl.acm.org
The dearth of prescribing guidelines for physicians is one key driver of the current opioid
epidemic in the United States. In this work, we analyze medical and pharmaceutical claims …

On the Intersection of Explainable and Reliable AI for physical fatigue prediction

S Narteni, V Orani, E Cambiaso, M Rucco… - IEEE …, 2022 - ieeexplore.ieee.org
In the era of Industry 4.0, the use of Artificial Intelligence (AI) is widespread in occupational
settings. Since dealing with human safety, explainability and trustworthiness of AI are even …

CURLS: Causal Rule Learning for Subgroups with Significant Treatment Effect

J Zhou, L Yang, X Liu, X Gu, L Sun… - Proceedings of the 30th …, 2024 - dl.acm.org
In causal inference, estimating heterogeneous treatment effects (HTE) is critical for
identifying how different subgroups respond to interventions, with broad applications in …