Using LLM for Real-Time Transcription and Summarization of Doctor-Patient Interactions into ePuskesmas in Indonesia: A Proof-of-Concept Study

TL;DR

This study demonstrates a proof-of-concept system using large language models to automate real-time transcription and summarization of doctor-patient interactions in Bahasa Indonesia, aiming to reduce documentation burden in Indonesian health centers.

Contribution

The paper introduces a novel framework combining Whisper and GPT-3.5 models for real-time medical transcription and summarization in Bahasa Indonesia, implemented as a browser extension for ePuskesmas.

Findings

System processes 300+ second consultations in under 30 seconds

Maintains clinical accuracy in transcription and summarization

Establishes foundation for AI-assisted clinical documentation

Abstract

One of the critical issues contributing to inefficiency in Puskesmas (Indonesian community health centers) is the time-consuming nature of documenting doctor-patient interactions. Doctors must conduct thorough consultations and manually transcribe detailed notes into ePuskesmas electronic health records (EHR), which creates substantial administrative burden to already overcapacitated physicians. This paper presents a proof-of-concept framework using large language models (LLMs) to automate real-time transcription and summarization of doctor-patient conversations in Bahasa Indonesia. Our system combines Whisper model for transcription with GPT-3.5 for medical summarization, implemented as a browser extension that automatically populates ePuskesmas forms. Through controlled roleplay experiments with medical validation, we demonstrate the technical feasibility of processing detailed 300+ seconds trimmed consultations in under 30 seconds while maintaining clinical accuracy. This work establishes the foundation for AI-assisted clinical documentation in resource-constrained healthcare environments. However, concerns have also been raised regarding privacy compliance and large-scale clinical evaluation addressing language and cultural biases for LLMs.