Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

Isaac25-lgtm/heartsense-group6

Domain:

healthcare

Record type:

model
Creator:
Isa
Host:
Heart disease risk prediction tool built with Random Forest, Logistic Regression, and XGBoost. Features dual-mode clinical screening (full and routine-care) with SHAP explainability. CSC8204 AI/ML project, Uganda Christian University. # HeartSense Heart Disease Risk Prediction for Early Clinical Decision Support Using Machine Learning. ## About HeartSense is a machine learning-based screening support tool that predicts heart disease risk from routine clinical indicators. It was built as a proof-of-concept prototype for primary healthcare settings in Uganda and East Africa, where access to specialist cardiac diagnostics is limited. The system features a dual-mode prediction tool: a full model using all 11 clinical features (including exercise stress test results), and a routine-care model using only the 7 features available during a standard patient visit at Health Centre III/IV facilities. **Live Demo:** heartsense-group6-cpjbyehstjdbxgv52aenhb.streamlit.app ## Team **Group 6** | Uganda Christian University | Faculty of Engineering Design & Technology | Student | Registration No. | Programme | |---------|-----------------|-----------| | Nixon Kamugisha | B00321 | MSc Data Science and Analytics | | Musoke Emmanuel | B31367 | MSc Data Science and Analytics | | Mwesigwa Simon Peter Godwin | B31335 | MSc Data Science and Analytics | | Omoding Isaac | B31331 | MSc Data Science and Analytics | **Course:** CSC8204 - Artificial Intelligence and Machine Learning | Easter 2026 ## Dataset The Combined Heart Disease Dataset by fedesoriano, published under CC BY 4.0. It merges clinical records from five cardiology institutions (Cleveland, Hungarian, Swiss, Long Beach VA, Statlog) into 918 unique patient records with 11 clinical features and 1 binary target variable. | Feature | Type | Description | |---------|------|-------------| | Age | Numeric | Patient age in years | | Sex | Categorical | M (Male) / F (Female) | | ChestPainType | Categorical | ASY, ATA, NAP, or TA | | RestingBP | Numeric | Resting blood pressure (mmHg) | | Cholesterol | Numeric | Serum cholesterol (mg/dl) | | FastingBS | Binary | 1 if fasting blood sugar > 120 mg/dl | | RestingECG | Categorical | Normal / ST / LVH | | MaxHR | …

Visit

github.com

Tasks

text classification

Similar

Isaac25-lgtm/mars-malaria-surveillanceIsaac25-lgtm/uganda-malaria-early-warning

Isaac25-lgtm/mars-malaria-surveillance

National malaria antimalarial-resistance surveillance for Uganda. HMIS-grounded governed analytics,

Isaac25-lgtm/uganda-malaria-early-warning

District-level malaria surge forecasting and early warning for Uganda's 146 districts, using DHIS2 H