# Learning to Prescribe Interventions for Tuberculosis Patients Using Digital Adherence Data

arXiv: https://arxiv.org/abs/1902.01506 · HTML: https://mlsanity.com/paper/1902.01506/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Feb 2019.

## Built on by (most cited first, 21 of 21)

- [Field Study in Deploying Restless Multi-Armed Bandits: Assisting Non-Profits in Improving Maternal and Child Health](https://mlsanity.com/paper/2109.08075/) (2021)
- [Change Matters: Medication Change Prediction with Recurrent Residual Networks](https://mlsanity.com/paper/2105.01876/) (2021)
- [Learn to Intervene: An Adaptive Learning Policy for Restless Bandits in Application to Preventive Healthcare](https://mlsanity.com/paper/2105.07965/) (2021)
- [Q-Learning Lagrange Policies for Multi-Action Restless Bandits](https://mlsanity.com/paper/2106.12024/) (2021)
- [How Good Is NLP? A Sober Look at NLP Tasks through the Lens of Social Impact](https://mlsanity.com/paper/2106.02359/) (2021)
- [IBM Quantum Computers: Evolution, Performance, and Future Directions](https://mlsanity.com/paper/2410.00916/) (2024)
- [Selective Intervention Planning using Restless Multi-Armed Bandits to Improve Maternal and Child Health Outcomes](https://mlsanity.com/paper/2103.09052/) (2021)
- [Efficient Algorithms for Finite Horizon and Streaming Restless Multi-Armed Bandit Problems](https://mlsanity.com/paper/2103.04730/) (2021)
- [Context in Public Health for Underserved Communities: A Bayesian Approach to Online Restless Bandits](https://mlsanity.com/paper/2402.04933/) (2024)
- [Evaluating the Effectiveness of Index-Based Treatment Allocation](https://mlsanity.com/paper/2402.11771/) (2024)
- [Improved Policy Evaluation for Randomized Trials of Algorithmic Resource Allocation](https://mlsanity.com/paper/2302.02570/) (2023)
- [Learning MDPs from Features: Predict-Then-Optimize for Sequential Decision Problems by Reinforcement Learning](https://mlsanity.com/paper/2106.03279/) (2021)
- [Analyzing and Predicting Low-Listenership Trends in a Large-Scale Mobile Health Program: A Preliminary Investigation](https://mlsanity.com/paper/2311.07139/) (2023)
- [Improving Health Information Access in the World's Largest Maternal Mobile Health Program via Bandit Algorithms](https://mlsanity.com/paper/2407.12131/) (2024)
- [Predicting Treatment Adherence of Tuberculosis Patients at Scale](https://mlsanity.com/paper/2211.02943/) (2022)
- [Decision-Focused Evaluation: Analyzing Performance of Deployed Restless Multi-Arm Bandits](https://mlsanity.com/paper/2301.07835/) (2023)
- [Reproducible workflow for online AI in digital health](https://mlsanity.com/paper/2509.13499/) (2025)
- [Who will Leave a Pediatric Weight Management Program and When? -- A machine learning approach for predicting attrition patterns](https://mlsanity.com/paper/2202.01765/) (2022)
- [A predict-and-optimize approach to profit-driven churn prevention](https://mlsanity.com/paper/2310.07047/) (2023)
- [Efficient Public Health Intervention Planning Using Decomposition-Based Decision-Focused Learning](https://mlsanity.com/paper/2403.05683/) (2024)
- [Decisions and Deployment: The Five-Year SAHELI Project (2020-2025) on Restless Multi-Armed Bandits for Improving Maternal and Child Health](https://mlsanity.com/paper/2604.07384/) (2026)

## Abstract (arXiv)

Digital Adherence Technologies (DATs) are an increasingly popular method for verifying patient adherence to many medications. We analyze data from one city served by 99DOTS, a phone-call-based DAT deployed for Tuberculosis (TB) treatment in India where nearly 3 million people are afflicted with the disease each year. The data contains nearly 17,000 patients and 2.1M dose records. We lay the groundwork for learning from this real-world data, including a method for avoiding the effects of unobserved interventions in training data used for machine learning. We then construct a deep learning model, demonstrate its interpretability, and show how it can be adapted and trained in different clinical scenarios to better target and improve patient care. In the real-time risk prediction setting our model could be used to proactively intervene with 21% more patients and before 76% more missed doses than current heuristic baselines. For outcome prediction, our model performs 40% better than baseline methods, allowing cities to target more resources to clinics with a heavier burden of patients at risk of failure. Finally, we present a case study demonstrating how our model can be trained in an end-to-end decision focused learning setting to achieve 15% better solution quality in an example decision problem faced by health workers.