DeepAI AI Chat
Log In Sign Up

Learning Optimal Personalized Treatment Rules Using Robust Regression Informed K-NN

by   Ruidi Chen, et al.
Boston University

We develop a prediction-based prescriptive model for learning optimal personalized treatments for patients based on their Electronic Health Records (EHRs). Our approach consists of: (i) predicting future outcomes under each possible therapy using a robustified nonlinear model, and (ii) adopting a randomized prescriptive policy determined by the predicted outcomes. We show theoretical results that guarantee the out-of-sample predictive power of the model, and prove the optimality of the randomized strategy in terms of the expected true future outcome. We apply the proposed methodology to develop optimal therapies for patients with type 2 diabetes or hypertension using EHRs from a major safety-net hospital in New England, and show that our algorithm leads to the most significant reduction of the HbA1c, for diabetics, or systolic blood pressure, for patients with hypertension, compared to the alternatives. We demonstrate that our approach outperforms the standard of care under the robustified nonlinear predictive model.


page 1

page 2

page 3

page 4


Personalized Treatment for Coronary Artery Disease Patients: A Machine Learning Approach

Current clinical practice guidelines for managing Coronary Artery Diseas...

Empowering Patients Using Smart Mobile Health Platforms: Evidence From A Randomized Field Experiment

With today's technological advancements, mobile phones and wearable devi...

Inference for BART with Multinomial Outcomes

The multinomial probit Bayesian additive regression trees (MPBART) frame...

Predicting Inpatient Discharge Prioritization With Electronic Health Records

Identifying patients who will be discharged within 24 hours can improve ...

Causal Discovery on the Effect of Antipsychotic Drugs on Delirium Patients in the ICU using Large EHR Dataset

Delirium occurs in about 80 associated with a longer hospital stay, incr...