HLS-CMDS: Heart and Lung Sounds Dataset Recorded from a Clinical Manikin using Digital Stethoscope

Donated on 8/12/2025

This dataset contains 535 recordings of heart and lung sounds captured using a digital stethoscope from a clinical manikin, including both individual and mixed recordings of heart and lung sounds; 50 heart sounds, 50 lung sounds, and 145 mixed sounds. For each mixed sound, the corresponding source heart sound (145 recordings) and source lung sound (145 recordings) were also recorded. It includes recordings from different anatomical chest locations, with normal and abnormal sounds. Each recording has been filtered to highlight specific sound types, making it valuable for artificial intelligence (AI) research and applications.

Dataset Characteristics

Tabular

Subject Area

Health and Medicine

Associated Tasks

Classification, Regression, Clustering, Other

Feature Type

Real

# Instances

535

# Features

-

Dataset Information

Has Missing Values?

No

Introductory Paper

Descriptor: Heart and Lung Sounds Dataset Recorded From a Clinical Manikin Using Digital Stethoscope (HLS-CMDS)

By Yasaman Torabi, Shahram Shirani, James P. Reilly. 2025

Published in IEEE Data Descriptions

Variable Information

Each .wav file contains a 15-second audio recording sampled at 22,050 Hz, capturing either heart, lung, or mixed cardiopulmonary sounds. The metadata CSV files include the following categorical variables: Gender: F = female, M = male. Location: Auscultation landmark for lung sounds — RUA, RMA, RLA, LUA, LMA, LLA; for heart sounds — Apex (A), RUSB, LUSB, LLSB, RC, LC. Sound type: Heart sounds — NH, LDM, MSM, LSM, AF, S4, ESM, S3, T, AVB; lung sounds — NL, W, FC, R, PR, CC. Sound ID: Name of the .wav file containing the recorded sound.

Dataset Files

FileSize
HLS-CMDS.zip35.9 MB
Download (35.9 MB)
1 citations
1165 views

Creators

Yasaman Torabi

McMaster University

Shahram Shirani

McMaster University

James P. Reilly

McMaster University

Notes

License

By using the UCI Machine Learning Repository, you acknowledge and accept the cookies and privacy practices used by the UCI Machine Learning Repository.

Read Policy