AI-Powered Biosignal Analytics & Remote Patient Monitoring – Hands-on Bootcamp

To equip participants with practical skills to process biosignals from medical wearables, build AI-driven analytics pipelines, and develop prototype remote patient monitoring (RPM) dashboards for real-time health insights and decision support.

• Introduce participants to the fundamentals of medical wearables and biosignal acquisition.
• Provide hands-on experience in cleaning, preprocessing, and analyzing ECG, PPG, IMU, and SpO₂ data.
• Teach practical methods for feature extraction, including heart rate, HRV, and activity metrics.
• Enable participants to build basic machine learning models for health signal classification and prediction.
• Guide learners in developing functional Remote Patient Monitoring (RPM) dashboards with real-time data streams.
• Equip participants with skills to create end-to-end digital health workflows—from sensors to analytics to monitoring.
• Foster understanding of ethics, data privacy, and responsible AI practices in healthcare applications.

📅 Day 1 – Basics & Health Signal Lab (App – Part 1)

• Intro to medical wearables (ECG, PPG, IMU, SpO₂) & use-cases
• Set up Vibe Code IDE, clone template, run starter app
• Import & clean wearable datasets (file upload, timestamps, basic stats)
• Explore signals (time-series plots, signal explorer)
• Improve signal quality (basic filters, raw vs filtered views)

👉 Outcome: Health Signal Lab v1 – upload, clean, visualize, and filter biosignals.

📅 Day 2 – Features, ML & Health Signal Lab (App – Part 2)

• Heart rate & HRV (peak detection, HR/HRV metrics)
• IMU feature extraction & activity summaries
• Build a simple ML pipeline (features, labels, LogReg/RandomForest)
• Auto “Train Model” + accuracy & confusion matrix in-app
• Generate summary report & mini-project using full pipeline

👉 Outcome: Health Signal Lab v2 – full analytics + basic ML + reporting.

📅 Day 3 – Remote Monitoring & Mini RPM Dashboard

• Intro to Remote Patient Monitoring (RPM) architecture & examples
• Set up Mini RPM Dashboard template in Vibe Code IDE
• Simulate multi-patient HR/SpO₂ streams & data ingestion
• Build live clinician dashboard (patient cards, time-series, auto-refresh)
• Add simple alert rules + discuss ethics, privacy & consent
• Participant demos of both apps

👉 Outcome: Working Mini RPM Dashboard + end-to-end workflow from wearable data → analytics → remote monitoring.

• Healthcare professionals & clinicians interested in medical wearables, digital health, and remote patient monitoring (RPM).
• Biomedical, biotechnology, and healthcare researchers working with physiological signals or digital health data.
• Data scientists, AI/ML engineers, and analysts who want to apply machine learning to ECG, PPG, IMU, SpO₂ and other biosignals.
• Developers and engineers interested in building health data analytics tools, dashboards, and RPM applications.
• Students (UG/PG/PhD) in engineering, life sciences, medicine, or computer science who wish to enter the digital health and health-tech domain.

Prerequisites (recommended, not mandatory):

• Basic familiarity with programming concepts (Python preferred).
• Interest in healthcare, biosignals, or AI/ML applications in medicine.

• Work with real-world biosignal data from medical wearables (ECG, PPG, IMU, SpO₂).
• Clean, visualize, and pre-process time-series health data for analysis.
• Extract key features such as heart rate, HRV, and activity metrics from wearable signals.
• Build and evaluate basic machine learning pipelines for health analytics inside an app workflow.
• Develop a mini Remote Patient Monitoring (RPM) dashboard for multi-patient visualization.
• Implement simple alert rules and discuss ethical, privacy, and consent aspects in digital health.
• Create end-to-end prototypes connecting wearable data → analytics → remote monitoring interfaces.