HLS-CMDS: Heart and Lung Sounds Dataset Recorded from a Clinical Manikin using Digital Stethoscope
Bibliographic record
Abstract
** Accepted in IEEE Data Descriptions Journal ** 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; It includes 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 in automated cardiopulmonary disease detection, sound classification, and deep learning algorithms related to audio signal processing. If you use this dataset in your research, please cite the following paper: Y. Torabi, S. Shirani and J. P. Reilly, "Descriptor: Heart and Lung Sounds Dataset Recorded from a Clinical Manikin using Digital Stethoscope (HLS-CMDS)," in IEEE Data Descriptions, https://doi.org/10.1109/IEEEDATA.2025.3566012 . Data Type: Audio files (.wav), Comma Separated Values (.CSV) Each category is accompanied by a corresponding CSV file that provides metadata for the respective audio files. The CSV files (HS.csv, LS.csv, and Mix.csv) contain metadata about the corresponding audio files, including the file name, gender, heart and lung sound type, and the anatomical location where we recorded the sound. Sound Types: Normal Heart, Late Diastolic Murmur, Mid Systolic Murmur, Late Systolic Murmur, Atrial Fibrillation, Fourth Heart Sound, Early Systolic Murmur, Third Heart Sound, Tachycardia, Atrioventricular Block, Normal Lung, Wheezing, Fine Crackles, Rhonchi, Pleural Rub, and Coarse Crackles. Auscultation Landmarks: Right Upper Sternal Border, Left Upper Sternal Border, Lower Left Sternal Border, Right Costal Margin, Left Costal Margin, Apex, Right Upper Anterior, Left Upper Anterior, Right Mid Anterior, Left Mid Anterior, Right Lower Anterior, and Left Lower Anterior. Applications: AI-based cardiopulmonary disease detection, unsupervised sound separation techniques, and deep learning for audio signal processing.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.002 |
| Meta-epidemiology (broad) | 0.002 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.006 | 0.016 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; both teacher heads agree on what is shown here.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".