How sri-nadella-c/cuffless-bp-monitoring works
This repository is a cuffless blood-pressure research pipeline: an engineer supplies MATLAB patient records and runs main.py to produce pooled beat-level features, model evaluations, personalization and robustness results, example predictions, and figures. The graph separates record ingestion, feature construction, analysis stages, and presentation. Calls and file reads/writes are shown where the excerpts support them; analysis stages share src/modeling.py, and the README documents the broader reported capabilities.
Main entry points: main.py Pipeline runner · figures.py Plot generation · pipeline.py Pooled dataset · results Analysis tables
Components 14
Signal ingestion
- MAT records
data - Record discovery
src/pipeline.py - Record reader
src/pipeline.py - Beat features
src/pipeline.py - Pooled dataset
src/pipeline.py
BP analysis
- Baseline models
src/modeling.py - Personalization
src/modeling.py - Robustness checks
src/modeling.py - Patient examples
src/modeling.py
Results and figures
- Analysis tables
results - Plot generation
src/figures.py - Figures
figures
Other components
- Researcher
- Pipeline runner
main.py
Connections 26
- Researcher → Pipeline runner: runs
README.md - MAT records → Record discovery: scans
src/pipeline.py - Record discovery → Record reader: opens files
src/pipeline.py - Record discovery → Pipeline runner: builds dataset
main.py - Record reader → Beat features: yields records
src/pipeline.py - Beat features → Pooled dataset: extracts beats
src/pipeline.py - Pipeline runner → Baseline models: evaluates
main.py - Pipeline runner → Personalization: calibrates
main.py - Pipeline runner → Robustness checks: checks stability
main.py - Pipeline runner → Patient examples: generates examples
main.py - Pooled dataset → Baseline models: provides data
main.py - Pooled dataset → Personalization: provides data
main.py - Pooled dataset → Robustness checks: provides data
main.py - Pooled dataset → Patient examples: provides data
main.py - Pipeline runner → Analysis tables: writes tables
main.py - Baseline models → Analysis tables: returns metrics
- Personalization → Analysis tables: returns metrics
- Robustness checks → Analysis tables: returns checks
- Patient examples → Analysis tables: returns predictions
- Pipeline runner → Plot generation: dispatches plots
main.py - Pooled dataset → Plot generation: provides plot data
main.py - Baseline models → Plot generation: provides metrics
main.py - Personalization → Plot generation: provides metrics
main.py - Patient examples → Plot generation: provides predictions
main.py - Plot generation → MAT records: reads sample record
src/figures.py - Plot generation → Figures: saves plots
src/figures.py