Related Experiment Video
Updated: Apr 30, 2026
Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis
Published on: April 26, 2024
MIMIC-III-Ext-PPG, a PPG-based Benchmark Dataset for Cardiovascular and Respiratory Signal Analysis
Mohammad Moulaeifard1, Marie Kutscher1, Philip J Aston2,3
1AI4Health Department, Oldenburg University, Oldenburg, Germany.
Abstract:
We present MIMIC-III-Ext-PPG, a large-scale, quality-assessed photoplethysmography (PPG) dataset derived from the matched waveform subset of MIMIC-III. Our dataset provides 30-second PPG segments with annotations tailored for various cardiovascular and respiratory analyses. In particular, with 6.3 million segments from 6,189 subjects, it represents the largest publicly available resource for heart rhythm classification, with heart rhythm annotations derived from bedside charted observations. For subsets where arterial blood pressure (ABP), respiratory (RESP), and/or electrocardiography (ECG) signals are available, we also provide systolic/diastolic blood pressure, respiratory rate, and heart rate annotations, extracted using best practice from the underlying signals. We provide signal quality assessments for all signals. This ensures a high-quality, publicly available dataset of unprecedented size that can be used as a benchmarking resource for machine learning approaches for a broad range of prediction tasks, which remains easily extendable by leveraging additional clinical metadata from the MIMIC-III clinical database.
Insights
We introduce MIMIC-III-Ext-PPG, a large, quality-assessed photoplethysmography (PPG) dataset for cardiovascular and respiratory analysis. It is the largest public resource for heart rhythm classification, aiding machine learning research.
Area of Science:
- Biomedical Engineering
- Medical Informatics
Background:
- Photoplethysmography (PPG) is crucial for non-invasive cardiovascular monitoring.
- Existing PPG datasets often lack scale, quality assessment, or comprehensive annotations.
- The MIMIC-III database provides rich clinical data but requires specialized waveform processing.
Purpose of the Study:
- To introduce MIMIC-III-Ext-PPG, a large-scale, quality-assessed PPG dataset.
- To provide annotations for cardiovascular and respiratory analyses, including heart rhythm, blood pressure, and respiratory rate.
- To establish a benchmarking resource for machine learning in healthcare.
Main Methods:
- Derived PPG segments from the MIMIC-III matched waveform subset.
- Extracted annotations for heart rhythm, blood pressure, respiratory rate, and heart rate from available signals (ECG, RESP, ABP).
- Performed rigorous signal quality assessments for all provided signals.
Main Results:
- MIMIC-III-Ext-PPG contains 6.3 million 30-second PPG segments from 6,189 subjects.
- It is the largest publicly available resource for heart rhythm classification.
- Annotations for systolic/diastolic blood pressure, respiratory rate, and heart rate are provided where applicable.
Conclusions:
- MIMIC-III-Ext-PPG offers an unprecedented, high-quality resource for PPG research.
- The dataset facilitates the development and benchmarking of machine learning models for diverse clinical prediction tasks.
- The dataset is extendable with existing MIMIC-III clinical metadata.
