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

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.

References in corpus (8)

• Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Making
• "It's the only thing I can trust": Envisioning Large Language Model Use by Autistic Workers for Communication Assistance
• Understanding Public Perceptions of AI Conversational Agents: A Cross-Cultural Analysis
• A Scoping Study of Evaluation Practices for Responsible AI Tools: Steps Towards Effectiveness Evaluations
• Sketching AI Concepts with Capabilities and Examples: AI Innovation in the Intensive Care Unit
• The Digital Transformation in Health: How AI Can Improve the Performance of Health Systems
• Physical and Augmented Reality based Playful Activities for Refresher Training of ASHA Workers in India
• Replay, Revise, and Refresh: Smartphone-based Refresher Training for Community Healthcare Workers in India

Cited by in corpus (2)

• Streaming, Fast and Slow: Cognitive Load-Aware Streaming for Efficient LLM Serving
• Mapping and Comparing Climate Equity Policy Practices Using RAG LLM-Based Semantic Analysis and Recommendation Systems