Scholarlink

<p>We present <i>MIMIC-III-Ext-PPG</i>, 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.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

MIMIC-III-Ext-PPG, a PPG-based Benchmark Dataset for Cardiovascular and Respiratory Signal Analysis

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月28日

查看全文
  • Mohammad Moulaeifard,
  • Marie Kutscher,
  • Philip J. Aston,
  • Peter H. Charlton,
  • Nils Strodthoff

摘要

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.