Overview
Cardiology workflows connect physiological signal ingestion, validated metrics, cohort comparison, and AI interpretation in a single study workspace. Each use case below maps a common research question to platform capabilities, data requirements, and a suggested analysis path.
Use case index
| Use case | Research question | Key capabilities |
|---|---|---|
| Holter HRV analysis | What are the HRV and signal quality characteristics of this recording? | ECG preprocessing, HRV metrics, waveform explorer, AI interpretation |
| ECG morphology phenotyping | What are the PR, QRS, QT/QTc, and ST characteristics of this recording? | ECG delineation, morphology metrics, landmark overlay, AI interpretation |
| Longitudinal wearable HRV | How does HRV change over a long recording, and how variable is it? | Sliding-window HRV, trends, windowed cohort comparison |
| Stress and activity | What do electrodermal and motion signals add, and is HRV motion-contaminated? | EDA tonic/phasic + SCRs, accelerometer activity, cross-modal motion quality |
| Pulse-wave and transit-time analysis | What do PPG pulse shape and ECG-to-PPG timing reveal about vascular state? | PPG pulse morphology, pulse arrival/transit time (PAT/PTT) |
| Wearable RR cohort | How do HRV metrics differ across a wearable or Holter-export cohort? | RR CSV ingestion, batch HRV, cohort comparison |
| Multimodal autonomic profiling | How do HRV, blood pressure, and respiration interact for this subject? | Cross-modal pipelines — baroreflex, RSA, mechanistic interpret |
| Cohort outcomes | Do physiological metrics differ by treatment group or associate with outcomes? | Group comparison, statistical tests, research risk stratification |
Who these use cases serve
| Audience | Typical goals |
|---|---|
| Cardiovascular researchers | ECG, HRV, telemetry, BP, PPG analysis with reproducible pipelines |
| Hospital research groups | Cohort analysis, signal quality filtering, treatment-response comparison |
| Wearable and digital health teams | Large-scale RR/PPG processing, artifact detection, feature extraction |
| Pharma and clinical trial teams | Physiological signal endpoints, digital biomarkers, longitudinal analysis |
Common data requirements
Most use cases start with a cardiology study containing:
- Datasets — ECG waveforms, RR interval CSVs, PPG, blood pressure, or respiration recordings
- Subjects (for cohort use cases) — participant metadata with treatment group, diagnosis, and optional outcomes
- Completed pipeline runs — preprocess and HRV runs linked to subjects for cohort comparison
Choosing a starting point
| If your primary data is… | Start with… |
|---|---|
| Single ECG or Holter recording | Holter HRV analysis |
| ECG intervals and waveform shape (QT, QRS, ST) | ECG morphology phenotyping |
| Long recordings where HRV changes over time | Longitudinal wearable HRV |
| EDA, accelerometer, and motion-aware ECG quality | Stress and activity |
| PPG pulse shape / cuffless-BP timing (paired ECG+PPG) | Pulse-wave and transit-time analysis |
| RR interval CSVs from wearables | Wearable RR cohort |
| ECG + BP + respiration for one subject | Multimodal autonomic profiling |
| Multi-subject study with group labels | Cohort outcomes |
What these use cases are not
These workflows support exploratory cardiovascular research. They are not clinical decision support or diagnostic tools. Arrhythmia outputs are burden metrics for research. Risk stratification is research-only. All AI interpretation outputs include disclaimers and cite computed metrics only.
Next steps
- Quick start — run your first ECG analysis
- Study workflow — how study pages fit together
- Pipelines reference — what each analysis step takes as input and produces as output