All Projects Clinical ML · Health Informatics · Live Demo

AZ T1D CGM Analytics Platform

A Python/Streamlit platform for analyzing continuous glucose-monitoring (CGM) data from 25 Type 1 Diabetes patients. Engineered a validated data-loading pipeline with ADA-aligned clinical features, DVC data versioning, and a 49-test suite. The interactive dashboard exposes four tabs: glucose visualization, clinical metrics, risk analysis (ADA goal tracking + ML model results), and counterfactual parameter adjustment. Built as an ASU team project. Primary contributions: data pipeline, clinical feature engineering, test suite, and all ML/AI modules.

Public ASU Team Project (Lead: ML/AI) Launch Live Demo GitHub ↗
Problem

Type 1 Diabetes patients and clinicians need early warning of dangerous blood-sugar drops (hypoglycemia), explainable risk predictions they can trust, and data systems that plug into existing electronic health records.

Approach

Built a validated data pipeline for continuous glucose monitor (CGM) data, engineered ADA-aligned clinical features, trained a hypoglycemia risk model, added SHAP explainability and a retrieval-augmented (RAG) clinical chatbot over ADA guidelines, and exposed a FHIR R4 export layer for EHR interoperability.

Tools
Python Streamlit Scikit-Learn SHAP MLflow DVC Pandas Plotly FHIR R4 SAS Tableau
Result

Achieved 0.985 AUC on held-out patients, backed by a 49-test validated data pipeline where real patient data is never committed to version control.

Why It Matters

Demonstrates explainable clinical ML (SHAP), healthcare data interoperability (FHIR R4), and production-grade data validation — the combination clinical ML and health-tech teams look for when hiring for patient-facing risk models.

0.985
AUC (Hypo Risk)
49
Validated Tests
25
Patients
4
Dashboard Tabs
FHIR
R4 Interop

Interactive Dashboard

View Streamlit version ↗
Patient:

How to use this dashboard

  • Select a patient from the dropdown above to load their CGM data across all tabs.
  • Glucose Visualization shows 14 days of continuous glucose readings with color-coded zones (green = target range, red = hypoglycemia, yellow = hyperglycemia).
  • Clinical Metrics displays ADA-aligned summary statistics for the selected patient.
  • Risk Analysis shows the hypoglycemia risk model performance (ROC curve), which clinical features drive predictions (SHAP importance), and how the patient tracks against ADA goals.
  • Counterfactual lets you adjust insulin sensitivity, carb ratio, and TIR target with sliders to model "what if" glucose scenarios in real time.

ROC Curve (AUC = 0.985)

Feature Importance (SHAP)

ADA Goal Attainment

Adjust parameters to model "what if" glycemic scenarios. Charts update in real time.

Note: dashboard uses synthetic CGM data. Real patient data is DVC-tracked and never committed to version control.

Project Highlights

  • Hypoglycemia risk model: AUC 0.985 on held-out subjects using clinical CGM features
  • SHAP beeswarm and importance plots for full model explainability across patient cohort
  • RAG clinical chatbot over ADA guidelines, providing retrieval-augmented generation with context-aware answers
  • FHIR R4 interoperability layer for EHR-compatible data export
  • ADA-aligned clinical feature engineering: TIR, GMI, CV%, hypoglycemia/hyperglycemia episodes
  • Counterfactual parameter adjustment tab for "what if" glycemic scenario modeling
  • 49-test validated data pipeline with DVC versioning; real patient data never committed
  • MLflow experiment tracking across model variants; SAS analytics companion; Tableau dashboard
  • ASU team project. Primary contributor: data pipeline, feature engineering, test suite, all ML/AI modules

Dashboard Tabs

1:Glucose Visualization
Interactive CGM time-series with insulin and carbohydrate overlays; multi-patient comparison.
2:Clinical Metrics
ADA-aligned features: Time in Range (TIR), GMI, CV%, hypo/hyperglycemia episode counts.
3:Risk Analysis
ADA goal attainment tracking, ML model results (AUC 0.985), SHAP explainability plots.
4:Counterfactual
"What if" glycemic parameter adjustment for scenario modeling and intervention planning.

Tech Stack

Python Streamlit Scikit-Learn SHAP MLflow DVC Pandas Plotly FHIR R4 SAS Tableau

Domain Tags

Health Informatics Clinical ML FHIR Explainable AI

Data Privacy

Real patient CGM data managed via DVC:never committed to version control. Demo uses synthetic data.

Infographics

Platform overview: ingestion through interactive dashboard

Platform overview: ingestion through interactive dashboard

Clinical feature engineering pipeline for CGM data

Clinical feature engineering pipeline for CGM data

ML pipeline and SHAP explainability system

ML pipeline and SHAP explainability system

Screenshots

Glucose visualization tab: interactive CGM time-series with insulin and carb overlays

Glucose visualization tab: interactive CGM time-series with insulin and carb overlays

Glucose visualization tab: multi-patient comparison view

Glucose visualization tab: multi-patient comparison view

Risk analysis tab: ADA goal attainment and ML results (AUC 0.985)

Risk analysis tab: ADA goal attainment and ML results (AUC 0.985)

Clinical metrics tab: TIR, GMI, CV% and episode counts

Clinical metrics tab: TIR, GMI, CV% and episode counts

Counterfactual adjustment tab

Counterfactual adjustment tab

SHAP beeswarm: feature contributions to hypoglycemia risk

SHAP beeswarm: feature contributions to hypoglycemia risk

ROC curve (AUC 0.985 on held-out subjects)

ROC curve (AUC 0.985 on held-out subjects)

Feature importance ranking

Feature importance ranking