ASHABot: An LLM-Powered Chatbot to Support the Informational Needs of Community Health Workers

TL;DR

ASHABot is an LLM-powered WhatsApp chatbot designed to support community health workers in India by providing reliable, private, and authoritative health information, enhancing their ability to deliver last-mile healthcare services.

Contribution

This paper introduces ASHABot, a novel LLM-based chatbot integrated with human oversight, tailored for community health workers' informational needs in low-resource settings.

Findings

CHWs used ASHABot for sensitive questions, increasing trust.

Supervisors contributed answers, expanding knowledge but raising workload concerns.

ASHABot served as a trusted, authoritative resource for CHWs.

Abstract

Community health workers (CHWs) provide last-mile healthcare services but face challenges due to limited medical knowledge and training. This paper describes the design, deployment, and evaluation of ASHABot, an LLM-powered, experts-in-the-loop, WhatsApp-based chatbot to address the information needs of CHWs in India. Through interviews with CHWs and their supervisors and log analysis, we examine factors affecting their engagement with ASHABot, and ASHABot's role in addressing CHWs' informational needs. We found that ASHABot provided a private channel for CHWs to ask rudimentary and sensitive questions they hesitated to ask supervisors. CHWs trusted the information they received on ASHABot and treated it as an authoritative resource. CHWs' supervisors expanded their knowledge by contributing answers to questions ASHABot failed to answer, but were concerned about demands on their workload and increased accountability. We emphasize positioning LLMs as supplemental fallible resources within the community healthcare ecosystem, instead of as replacements for supervisor support.