Tri-MTL: A Triple Multitask Learning Approach for Respiratory Disease Diagnosis

TL;DR

This paper introduces Tri-MTL, a triple multitask learning framework that integrates respiratory sounds, disease manifestations, and patient metadata to improve respiratory disease diagnosis and classification accuracy.

Contribution

It presents a novel MTL architecture that effectively combines medical history, test results, and lung sounds, demonstrating significant performance improvements.

Findings

Enhanced lung sound classification accuracy

Improved disease diagnostic performance

Metadata integration benefits in MTL models

Abstract

Auscultation remains a cornerstone of clinical practice, essential for both initial evaluation and continuous monitoring. Clinicians listen to the lung sounds and make a diagnosis by combining the patient's medical history and test results. Given this strong association, multitask learning (MTL) can offer a compelling framework to simultaneously model these relationships, integrating respiratory sound patterns with disease manifestations. While MTL has shown considerable promise in medical applications, a significant research gap remains in understanding the complex interplay between respiratory sounds, disease manifestations, and patient metadata attributes. This study investigates how integrating MTL with cutting-edge deep learning architectures can enhance both respiratory sound classification and disease diagnosis. Specifically, we extend recent findings regarding the beneficial impact of metadata on respiratory sound classification by evaluating its effectiveness within an MTL framework. Our comprehensive experiments reveal significant improvements in both lung sound classification and diagnostic performance when the stethoscope information is incorporated into the MTL architecture.