Výsledky vyhledávání

Report

Interpretable (not just posthoc-explainable) heterogeneous survivor bias-corrected treatment effects for assignment of postdischarge interventions to prevent readmissions

Autor: Xia, Hongjing, Chang, Joshua C., Nowak, Sarah, Mahajan, Sonya, Mahajan, Rohit, Chang, Ted L., Chow, Carson C.

Publikováno v: PMLR 219:884-905, 2023

We used survival analysis to quantify the impact of postdischarge evaluation and management (E/M) services in preventing hospital readmission or death. Our approach avoids a specific pitfall of applying machine learning to this problem, which is an i

Externí odkaz: http://arxiv.org/abs/2304.09981

Zobrazit plný text záznamu

Report

Interpretable (not just posthoc-explainable) medical claims modeling for discharge placement to prevent avoidable all-cause readmissions or death

Autor: Chang, Joshua C., Chang, Ted L., Chow, Carson C., Mahajan, Rohit, Mahajan, Sonya, Maisog, Joe, Vattikuti, Shashaank, Xia, Hongjing

We developed an inherently interpretable multilevel Bayesian framework for representing variation in regression coefficients that mimics the piecewise linearity of ReLU-activated deep neural networks. We used the framework to formulate a survival mod

Externí odkaz: http://arxiv.org/abs/2208.12814

Zobrazit plný text záznamu

Akademický článek

Interpretable (not just posthoc-explainable) medical claims modeling for discharge placement to reduce preventable all-cause readmissions or death.

Autor: Chang, Ted L.^1,2 (AUTHOR), Xia, Hongjing^1,2 (AUTHOR), Mahajan, Sonya^1,2 (AUTHOR), Mahajan, Rohit^1,2 (AUTHOR), Maisog, Joe³ (AUTHOR), Vattikuti, Shashaank⁴ (AUTHOR), Chow, Carson C.^2,5 (AUTHOR), Chang, Joshua C.^1,2,6 (AUTHOR) josh.chang@nih.gov

Publikováno v: PLoS ONE. 5/9/2024, Vol. 19 Issue 5, p1-20. 20p.

Zobrazit plný text záznamu

Plný text ve formátu HTML

Report

Sparse encoding for more-interpretable feature-selecting representations in probabilistic matrix factorization

Autor: Chang, Joshua C., Fletcher, Patrick, Han, Jungmin, Chang, Ted L., Vattikuti, Shashaank, Desmet, Bart, Zirikly, Ayah, Chow, Carson C.

Dimensionality reduction methods for count data are critical to a wide range of applications in medical informatics and other fields where model interpretability is paramount. For such data, hierarchical Poisson matrix factorization (HPF) and other s

Externí odkaz: http://arxiv.org/abs/2012.04171

Zobrazit plný text záznamu