RA-QA: A Benchmarking System for Respiratory Audio Question Answering Under Real-World Heterogeneity

TL;DR

The paper introduces RA-QA, a comprehensive benchmark for respiratory audio question answering that evaluates AI performance under real-world heterogeneity across modalities, devices, and question types.

Contribution

It presents a new standardized dataset, data generation pipeline, and evaluation protocol for respiratory audio question answering, addressing the lack of real-world heterogeneity in existing studies.

Findings

Current models struggle with heterogeneity in data.

Benchmark establishes baseline performance for respiratory audio QA.

RA-QA dataset includes 9 million diverse QA pairs.

Abstract

As conversational multimodal AI tools are increasingly adopted to process patient data for health assessment, robust benchmarks are needed to measure progress and expose failure modes under realistic conditions. Despite the importance of respiratory audio for mobile health screening, respiratory audio question answering remains underexplored, with existing studies evaluated narrowly and lacking real-world heterogeneity across modalities, devices, and question types. We hence introduce the Respiratory-Audio Question-Answering (RA-QA) benchmark, including a standardized data generation pipeline, a comprehensive multimodal QA collection, and a unified evaluation protocol. RA-QA harmonizes public RA datasets into a collection of 9 million format-diverse QA pairs covering diagnostic and contextual attributes. We benchmark classical ML baselines alongside multimodal audio-language models, establishing reproducible reference points and showing how current approaches fail under heterogeneity.