ZPE-Bio V0.0: DETERMINISTIC 8-PRIMITIVE BIOSIGNAL CODEC: ECG | EEG | EMG | PPG | SpO2 | Respiration | Wearable Transport | Rust Core

The new PhysioNet platform.

Sleep stage classification from raw EEG/EOG using a spatial-temporal CNN (Chambon 2018 variant). Trained on PhysioNet SleepEDF-78 with MNE-Python preprocessing, ICA artifact removal, and PyTorch. Achieves ~0.72 Cohen's Kappa on subject-wise held-out test set.

When does suppressing low-confidence clinical alerts actually reduce alarm fatigue? Empirical two-regime analysis on PhysioNet 2019 sepsis data — ceiling effects, floor effects, and when neither applies.

An automated biomedical signal processing pipeline using Discrete Wavelet Transforms (DWT) to denoise ECG data and detect cardiac arrhythmias.

Website for the MIMIC Critical Care Database (currently version MIMIC-III)

Production-ready ML pipeline for sleep apnea detection from ECG signals (AUROC: 0.755). Features HRV/QRS extraction, signal quality gating, and patient-level AHI estimation on 70 PhysioNet patients.

A Fog Computing-based real-time sleep quality monitoring system using LSTM deep learning on wearable sensor data (PPG + Accelerometer). Trained on the MMASH dataset (PhysioNet) from 22 real subjects, achieving 92.8% accuracy. Features a Streamlit live dashboard and Arduino hardware integration.

Multi-domain scientific dataset fetcher — neuroscience, biology, pharmacology, medical. Part of SciTeX.

Which ICU variables warn of sepsis earliest? A temporal analysis of 40,336 patients that reveals what the model ignores and why.

Beat-level Congestive Heart Failure detection from QRS complex using ML — Research code for published paper.

Native Python WFDB package

End-to-end ML system for early sepsis detection on 20,317 real ICU stays. XGBoost AUROC 0.9514 · FastAPI · Streamlit · Drift monitoring

Implicit equilibrium dynamics, energy-based anomaly scoring, ECG experiments, temporal evaluation, and honest negative zero-shot results.

Python pipeline for the CHB-MIT Scalp EEG database featuring ictal/pre-ictal segment extraction and covariance-based feature engineering

A toolkit for evaluating and monitoring AI models in clinical settings

Repository for a signal analysis project in Python for my Signal Analysis course on the 5th semester of studying Mathematics at Gdańsk University of Technology

Preictal seizure analysis on the Siena Scalp EEG dataset

Clasificación de estadios de sueño usando EEG, EOG y EMG del dataset Sleep-EDF Expanded // Sleep stage classification using EEG, EOG, and EMG from the Sleep-EDF Expanded dataset

Heart rate and ECG signal analysis using MIT BIH Arrhythmia data. Includes waveform visualization, R-peak detection, and basic cardiac rhythm classification. Built using Python, WFDB, and Google Colab