π― Helping clinicians and researchers unlock insights from biomedical data using AI, XAI & Generative Models
π Linkedin | π― Website | π Google Scholar | π GitHub Projects
- Prodromal_Parkinson_XAI β Predictive modeling and SHAP explainability for Parkinson prodrome detection from IMU data
- EMG_HSP_XAI β Deep learning + SHAP on EMG signals to identify muscle drivers in spastic gait (HSP disorder)
- FallRiskPredictor β Explainable Streamlit webapp to estimate fall risk in neurological patients
- Fall risk prediction with XAI for Parkinsonβs patients
- Prodromal signature discovery using SHAPSetPlot on wearable data
- Muscle importance analysis for rare disorders via BiLSTM + CNN on EMG
- Synthetic data generation (ctGAN) for class balancing in clinical datasets
- Patient clustering using unsupervised learning + radar profiling in rehabilitation units
- π° Machine Learning Approach to Support the Detection of Parkinson's Disease via IMU Gait AnalysisI
Published in Sensors (2022) β 100 citations - π° Optimizing Rare Disease Gait Classification through Data Balancing and Generative AI
Published in Sensors (2024) β 18+ citations
Explore all publications on Google Scholar
Python PyTorch scikit-learn SHAP Streamlit ctGAN
Docker PostgreSQL FastAPI XGBoost LightGBM
Pandas NumPy Matplotlib Plotly SHAPSetPlot
I support:
- Clinicians who want to bring AI to their data without writing code
- Research centers looking for interpretable and publishable ML pipelines
- Biotech / digital health companies in need of end-to-end ML solutions
π© Email β dantetrb@gmail.com