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
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
| File | Size |
|---|---|
| HLS-CMDS.zip | 35.9 MB |
pip install ucimlrepo
from ucimlrepo import fetch_ucirepo # fetch dataset hls_cmds_heart_and_lung_sounds_dataset_recorded_from_a_clinical_manikin_using_digital_stethoscope = fetch_ucirepo(id=1202) # data (as pandas dataframes) X = hls_cmds_heart_and_lung_sounds_dataset_recorded_from_a_clinical_manikin_using_digital_stethoscope.data.features y = hls_cmds_heart_and_lung_sounds_dataset_recorded_from_a_clinical_manikin_using_digital_stethoscope.data.targets # metadata print(hls_cmds_heart_and_lung_sounds_dataset_recorded_from_a_clinical_manikin_using_digital_stethoscope.metadata) # variable information print(hls_cmds_heart_and_lung_sounds_dataset_recorded_from_a_clinical_manikin_using_digital_stethoscope.variables)
Torabi, Y., Shirani, S., & Reilly, J. (2025). HLS-CMDS: Heart and Lung Sounds Dataset Recorded from a Clinical Manikin using Digital Stethoscope [Dataset]. UCI Machine Learning Repository. https://doi.org/10.1109/IEEEDATA.2025.3566012.
Keywords
Creators
Yasaman Torabi
McMaster University
Shahram Shirani
McMaster University
James P. Reilly
McMaster University
Notes
License
This dataset is licensed under a Creative Commons Attribution 4.0 International (CC BY 4.0) license.
This allows for the sharing and adaptation of the datasets for any purpose, provided that the appropriate credit is given.