Supervised Matrix Factorization for Estimating Individualized Treatment Rule: Incorporating Medical Notes in Decision Making
Statistical Analysis and Data Mining: An ASA Data Science Journal · 2026-12 · 19 (6)
DOI: 10.1002/sam.70120 ↗At a glance
Journal article in Statistical Analysis and Data Mining: An ASA Data Science Journal, published online on 2026-11-10. Written by Crystal Zang and 2 co-authors. 49 references. The full text is freely available (open access, CC BY 4.0). Funded by: National Institutes of Health, Medical Center, University of Pittsburgh.
Abstract (original language)
Precision medicine aims to tailor treatments to the unique characteristics of individual patients. In this paper, we develop a classification‐based approach to estimate an individualized treatment rule (ITR) by leveraging both structured quantitative data and high‐dimensional unstructured text documents. To tackle the challenge of incorporating text data, we propose an outcome‐driven supervised nonnegative matrix factorization (NMF) method that extracts relevant topics for ITR estimation in a one‐step procedure. Our proposed method factorizes vectorized documents into a document‐topic matrix and a topic‐word matrix, guided by the outcome. For estimation, we construct a weighted and penalized objective function, solved by a projected gradient approach, to jointly estimate the document representation and the ITR. Our formulation enables the interpretability of the effect of the learned topics on the ITR. We demonstrate the performance of our method through simulation studies and a real‐world example from the MIMIC‐IV intensive care unit dataset. Applied to MIMIC‐IV radiology notes, supervised NMF identifies predictive but less prevalent topics, improves interpretability by refining broad topics, and achieves a 4.2% reduction in classification error and 4.1% lower RMSE than two‐stage learning using NMF.
Funding
- National Institutes of Health
- Medical Center, University of Pittsburgh
Cite
APA
Zang, C., Deek, R. A., & Tang, L. (2026). Supervised Matrix Factorization for Estimating Individualized Treatment Rule: Incorporating Medical Notes in Decision Making. Statistical Analysis and Data Mining: An ASA Data Science Journal, 19(6). https://doi.org/10.1002/sam.70120
Vancouver
Zang C, Deek RA, Tang L. Supervised Matrix Factorization for Estimating Individualized Treatment Rule: Incorporating Medical Notes in Decision Making. Statistical Analysis and Data Mining: An ASA Data Science Journal. 2026;19(6). doi:10.1002/sam.70120
BibTeX
@article{Zang2026,
author = {Zang, Crystal and Deek, Rebecca A. and Tang, Lu},
title = {Supervised Matrix Factorization for Estimating Individualized Treatment Rule: Incorporating Medical Notes in Decision Making},
journal = {Statistical Analysis and Data Mining: An ASA Data Science Journal},
year = {2026},
volume = {19},
number = {6},
doi = {10.1002/sam.70120}
}
EUVIMED