# Deep auscultation: Predicting respiratory anomalies and diseases via recurrent neural networks

Source: [Deep auscultation: Predicting respiratory anomalies and diseases via recurrent neural networks](<https://www.sota2.com/research/paper/68fa66141e209131cea0e231>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:42:29.976Z

Authors: Diego Perna, Andrea Tagarelli

Published: 2019-07-11T17:16:42.000Z

## Abstract

Respiratory diseases are among the most common causes of severe illness and death worldwide. Prevention and early diagnosis are essential to limit or even reverse the trend that characterizes the diffusion of such diseases. In this regard, the development of advanced computational tools for the analysis of respiratory auscultation sounds can become a game changer for detecting disease-related anomalies, or diseases themselves. In this work, we propose a novel learning framework for respiratory auscultation sound data. Our approach combines state-of-the-art feature extraction techniques and advanced deep-neural-network architectures. Remarkably, to the best of our knowledge, we are the first to model a recurrent-neural-network based learning framework to support the clinician in detecting respiratory diseases, at either level of abnormal sounds or pathology classes. Results obtained on the ICBHI benchmark dataset show that our approach outperforms competing methods on both anomaly-driven and pathology-driven prediction tasks, thus advancing the state-of-the-art in respiratory disease analysis.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Pathological Classification on ICBHI 2017 (train val)](<https://www.sota2.com/research/sota/pathological-classification-on-icbhi-2017-train-val.md>): Pathological Classification; ICBHI 2017 (train-val); Accuracy: 99.

- [Ternary Chronic Classification on ICBHI 2017 (train-val)](<https://www.sota2.com/research/sota/ternary-chronic-classification-on-icbhi-2017-train-val.md>): Ternary Chronic Classification; ICBHI 2017 (train-val); Specificity: 99.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1907.05708>)

[PDF](<https://arxiv.org/pdf/1907.05708.pdf>)