physiokit 0.7.0

PhysioKit, process raw ambulatory bio-signals.

A Python toolkit to process raw ambulatory bio-signals.

🚧 PhysioKit is under active development

---

Documentation: https://ambiqai.github.io/physiokit

Source Code: https://github.com/AmbiqAI/physiokit

---

Key Features:

• Handles a variety of physiological signals including ECG, PPG, RSP, and IMU.
• Geared towards real-time, noisy wearable sensor data.
• Provide advanced signal processing and feature extraction methods.
• Create synthetic signals for testing and benchmarking.

Requirements

• Python 3.11+

Installation

Installing PhysioKit can be done using Poetry or pip.

pip install physiokit

poetry add physiokit

Example

In this example, we will generate a synthetic ECG signal, clean it, and compute heart rate and HRV metrics.

import physiokit as pk

fs = 1000 # Hz
tgt_hr = 64 # BPM


# Generate synthetic ECG signal
ecg = pk.ecg.synthesize(
    duration=10,
    sample_rate=fs,
    heart_rate=tgt_hr,
    leads=1
)

# Clean ECG signal
ecg_clean = pk.ecg.clean(ecg, sample_rate=fs)

# Compute heart rate
hr_bpm, _ = pk.ecg.compute_heart_rate(ecg_clean, sample_rate=fs)

# Extract R-peaks and RR-intervals
peaks = pk.ecg.find_peaks(ecg_clean, sample_rate=fs)
rri = pk.ecg.compute_rr_intervals(peaks)
mask = pk.ecg.filter_rr_intervals(rri, sample_rate=fs)

# Re-compute heart rate
hr_bpm = 60 / (np.nanmean(rri[mask == 0]) / fs)

# Compute HRV metrics
hrv_td = pk.hrv.compute_hrv_time(rri[mask == 0], sample_rate=fs)

bands = [(0.04, 0.15), (0.15, 0.4), (0.4, 0.5)]
hrv_fd = pk.hrv.compute_hrv_frequency(
    peaks[mask == 0],
    rri[mask == 0],
    bands=bands,
    sample_rate=fs
)

License

This project is licensed under the terms of BSD 3-Clause.