Improving access to essential medicines via decision-aware machine learning | Nature
Subjects
- Computer science
- Developing world
Abstract
A critical challenge in healthcare systems in low- and middle-income countries is the efficient and equitable allocation of scarce resources, particularly essential medicines1. This problem is complicated by limited high-quality data, which restricts the applicability of traditional data-driven techniques2,3,4,5. Here we propose a novel decision-aware machine learning framework for the allocation of essential medicines, which additionally leverages multi-task learning to ensure sample efficiency and catalytic priors to ensure equitable allocation. In collaboration with the national government of Sierra Leone, we performed a staggered, nationwide deployment of our system as a decision support tool. Our econometric evaluation finds an estimated 19% increase in consumption of allocated products in treated districts, demonstrating its efficacy at improving access to essential medicines. Our tool was subsequently scaled nationwide, covering an estimated two million women and children under 5 years of age. Our work demonstrates how machine learning methods can improve efficiency at very low cost in resource-constrained global health settings.
Access through your institution
Buy or subscribe
This is a preview of subscription content, access via your institution
Access options
Access through your institution
Access Nature and 54 other Nature Portfolio journals
Get Nature+, our best-value online-access subscription
$32.99 / 30 days
cancel any time
Learn more
Subscribe to this journal
Receive 51 print issues and online access
$199.00 per year
only $3.90 per issue
Learn more
Buy this article
- Purchase on SpringerLink
- Instant access to the full article PDF.
USD 39.95
Prices may be subject to local taxes which are calculated during checkout
Fig. 1: System overview.The alternative text for this image may have been generated using AI.
Fig. 2: Map of treatment distribution in the second quarter of 2023.The alternative text for this image may have been generated using AI.
Fig. 3: Average normalized consumption time trends.The alternative text for this image may have been generated using AI.
Data availability
To support further research, anonymized evaluation data and documentation are available at https://doi.org/10.5061/dryad.h9w0vt4tw (ref. 66); data used for machine learning experiment are available from https://github.com/Angel-Chung/AllocMedSL-DAwareML. WorldPop Global Project Population Data, the global friction surface dataset (Oxford/MAP/friction_surface_2019) and satellite imagery are publicly accessible through Google Earth https://earthengine.google.com.
Code availability
All code used in this paper was written in Python 3.9 and R (v4.2.1). The code for reproducing our econometric evaluation results is available at https://github.com/Angel-Chung/AllocMedSL_Eval and the code for reproducing our pre-deployment simulation experiments is available at https://github.com/Angel-Chung/AllocMedSL-DAwareML.
References
- Yadav, P. Health product supply chains in developing countries: diagnosis of the root causes of underperformance and an agenda for reform. Health Syst. Reform 1, 142–154 (2015).
Article
PubMed
Google Scholar
- UNICEF. The State of the World’s Children 2015: Executive Summary (UN, 2015).
- Gallien, J., Leung, N.-H. Z. & Yadav, P. Inventory policies for pharmaceutical distribution in Zambia: improving availability and access equity. Prod. Oper. Manag. 30, 4501–4521 (2021).
Article
Google Scholar
- Merkuryeva, G., Valberga, A. & Smirnov, A. Demand forecasting in pharmaceutical supply chains: a case study. Procedia Comput. Sci. 149, 3–10 (2019).
Article
Google Scholar
- Yenet, A., Nibret, G. & Tegegne, B. A. Challenges to the availability and affordability of essential medicines in African countries: a scoping review. Clin. Outcomes Res. 15, 443–458 (2023).
Article
Google Scholar
- De Fauw, J. et al. Clinically applicable deep learning for diagnosis and referral in retinal disease. Nat. Med. 24, 1342–1350 (2018).
Article
PubMed
Google Scholar
- Esteva, A. et al. A guide to deep learning in healthcare. Nat. Med. 25, 24–29 (2019).
Article
CAS
PubMed
Google Scholar
- Ngiam, K. Y. & Khor, W. Big data and machine learning algorithms for health-care delivery. Lancet Oncol. 20, e262–e273 (2019).
Article
PubMed
Google Scholar
- Bastani, H. et al. Efficient and targeted COVID-19 border testing via reinforcement learning. Nature 599, 108–113 (2021).
Article
ADS
CAS
PubMed
Google Scholar
- Yang, X. et al. A large language model for electronic health records. npj Digit. Med. 5, 194 (2022).
Article
PubMed
PubMed Central
Google Scholar
- Zuma, S. M. & Modiba, L. M. Challenges associated with provision of essential medicines in the Republic of South Africa and other selected African countries. World J. Pharm. Res. 8, 1532–1547 (2019).
Google Scholar
- World Health Organization. Service availabili