MedTalkAI: Assisted Anamnesis Creation With Automatic Speech Recognition

Conventional approaches to documenting patient medical histories are often time-consuming and require significant healthcare professional involvement. This paper introduces MedTalkAI, which integrates ASR models, including Whisper and Wav2Vec 2.0, to transcribe audio recordings of patient histories in Brazilian Portuguese efficiently. MedTalkAI validates, corrects, and evaluates transcriptions, facilitating the creation of a unique medical audio-text database. Additionally, MedTalkAI enhances ASR models for medical applications using language models. This approach aims to improve medical history transcription and analysis, contributing to the development of more reliable ASR models and automating the documentation process.