Supervised Matrix Factorization for Estimating Individualized Treatment Rule: Incorporating Medical Notes in Decision Making

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.