Predicting Treatment Adherence of Tuberculosis Patients at Scale

Mihir Kulkarni, Satvik Golechha, Rishi Raj, Jithin K. Sreedharan, Ankit Bhardwaj, Santanu Rathod, Bhavin Vadera, Jayakrishna Kurada, Sanjay Mattoo, Rajendra Joshi, Kirankumar Rade, Alpan Raval
Proceedings of the 2nd Machine Learning for Health symposium, PMLR 193:35-61, 2022.

Abstract

Tuberculosis (TB), an infectious bacterial disease, is a significant cause of death, especially in low-income countries, with an estimated ten million new cases reported globally in 2020. While TB is treatable, non-adherence to the medication regimen is a significant cause of morbidity and mortality. Thus, proactively identifying patients at risk of dropping off their medication regimen enables corrective measures to mitigate adverse outcomes. Using a proxy measure of extreme non-adherence and a dataset of nearly $700,000$ patients from four states in India, we formulate and solve the machine learning (ML) problem of early prediction of non-adherence based on a custom rank-based metric. We train ML models and evaluate against baselines, achieving a $\sim 100%$ lift over rule-based baselines and $\sim 214%$ over a random classifier, taking into account country-wide large-scale future deployment. We deal with various issues in the process, including data quality, high-cardinality categorical data, low target prevalence, distribution shift, variation across cohorts, algorithmic fairness, and the need for robustness and explainability. Our findings indicate that risk stratification of non-adherent patients is a viable, deployable-at-scale ML solution. As the official AI partner of India’s Central TB Division, we are working on multiple city and state-level pilots with the goal of pan-India deployment.

Cite this Paper

BibTeX
@InProceedings{pmlr-v193-kulkarni22a, title = {Predicting Treatment Adherence of Tuberculosis Patients at Scale}, author = {Kulkarni, Mihir and Golechha, Satvik and Raj, Rishi and Sreedharan, Jithin K. and Bhardwaj, Ankit and Rathod, Santanu and Vadera, Bhavin and Kurada, Jayakrishna and Mattoo, Sanjay and Joshi, Rajendra and Rade, Kirankumar and Raval, Alpan}, booktitle = {Proceedings of the 2nd Machine Learning for Health symposium}, pages = {35--61}, year = {2022}, editor = {Parziale, Antonio and Agrawal, Monica and Joshi, Shalmali and Chen, Irene Y. and Tang, Shengpu and Oala, Luis and Subbaswamy, Adarsh}, volume = {193}, series = {Proceedings of Machine Learning Research}, month = {28 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v193/kulkarni22a/kulkarni22a.pdf}, url = {https://proceedings.mlr.press/v193/kulkarni22a.html}, abstract = {Tuberculosis (TB), an infectious bacterial disease, is a significant cause of death, especially in low-income countries, with an estimated ten million new cases reported globally in 2020. While TB is treatable, non-adherence to the medication regimen is a significant cause of morbidity and mortality. Thus, proactively identifying patients at risk of dropping off their medication regimen enables corrective measures to mitigate adverse outcomes. Using a proxy measure of extreme non-adherence and a dataset of nearly $700,000$ patients from four states in India, we formulate and solve the machine learning (ML) problem of early prediction of non-adherence based on a custom rank-based metric. We train ML models and evaluate against baselines, achieving a $\sim 100%$ lift over rule-based baselines and $\sim 214%$ over a random classifier, taking into account country-wide large-scale future deployment. We deal with various issues in the process, including data quality, high-cardinality categorical data, low target prevalence, distribution shift, variation across cohorts, algorithmic fairness, and the need for robustness and explainability. Our findings indicate that risk stratification of non-adherent patients is a viable, deployable-at-scale ML solution. As the official AI partner of India’s Central TB Division, we are working on multiple city and state-level pilots with the goal of pan-India deployment.} }
Endnote
%0 Conference Paper %T Predicting Treatment Adherence of Tuberculosis Patients at Scale %A Mihir Kulkarni %A Satvik Golechha %A Rishi Raj %A Jithin K. Sreedharan %A Ankit Bhardwaj %A Santanu Rathod %A Bhavin Vadera %A Jayakrishna Kurada %A Sanjay Mattoo %A Rajendra Joshi %A Kirankumar Rade %A Alpan Raval %B Proceedings of the 2nd Machine Learning for Health symposium %C Proceedings of Machine Learning Research %D 2022 %E Antonio Parziale %E Monica Agrawal %E Shalmali Joshi %E Irene Y. Chen %E Shengpu Tang %E Luis Oala %E Adarsh Subbaswamy %F pmlr-v193-kulkarni22a %I PMLR %P 35--61 %U https://proceedings.mlr.press/v193/kulkarni22a.html %V 193 %X Tuberculosis (TB), an infectious bacterial disease, is a significant cause of death, especially in low-income countries, with an estimated ten million new cases reported globally in 2020. While TB is treatable, non-adherence to the medication regimen is a significant cause of morbidity and mortality. Thus, proactively identifying patients at risk of dropping off their medication regimen enables corrective measures to mitigate adverse outcomes. Using a proxy measure of extreme non-adherence and a dataset of nearly $700,000$ patients from four states in India, we formulate and solve the machine learning (ML) problem of early prediction of non-adherence based on a custom rank-based metric. We train ML models and evaluate against baselines, achieving a $\sim 100%$ lift over rule-based baselines and $\sim 214%$ over a random classifier, taking into account country-wide large-scale future deployment. We deal with various issues in the process, including data quality, high-cardinality categorical data, low target prevalence, distribution shift, variation across cohorts, algorithmic fairness, and the need for robustness and explainability. Our findings indicate that risk stratification of non-adherent patients is a viable, deployable-at-scale ML solution. As the official AI partner of India’s Central TB Division, we are working on multiple city and state-level pilots with the goal of pan-India deployment.
APA
Kulkarni, M., Golechha, S., Raj, R., Sreedharan, J.K., Bhardwaj, A., Rathod, S., Vadera, B., Kurada, J., Mattoo, S., Joshi, R., Rade, K. & Raval, A.. (2022). Predicting Treatment Adherence of Tuberculosis Patients at Scale. Proceedings of the 2nd Machine Learning for Health symposium, in Proceedings of Machine Learning Research 193:35-61 Available from https://proceedings.mlr.press/v193/kulkarni22a.html.

Related Material