Gensini Score Prediction
Gensini score prediction using Artificial Neural Networks
Introduction:
- Role of Metabolic Obesity and Body Mass Index in patients of various age group with coronary artery diseases.
- Metabolic Obesity (Insulin resistance syndrome).
- Indian subcontinent is highly predisposed to this condition.
- Prevalence of Insulin resistance syndrome among Indians (≥30%).
- Among females is higher than males (50%).
Problem definition:
Train a model capable of predicting the GENSINI score which determines the severity of CAD in the following groups:
- Metabolically Healthy Normal Weight (MHNW)
- Metabolically Obese Normal Weight (MONW)
- Metabolically Healthy Obese (MHO)
- Metabolically Abnormal Obese (MAO)
Gensini Scoring:
- It is a scoring system for determining the severity of coronary heart disease.
- It provides an accurate stratification of patients according to the functional significance of their disease.
- It provides an opportunity to match patients with similar degrees of coronary artery disease who are receiving different forms of treatment.
Objective:
- To find the group showing a good association to severity of Coronary artery disease that is which category is more prone to CAD, metabolically obese or phenotypically obese.
- To find the prognostic markers for CAD among factors like HBA1C, FI, HOMA IR, TC, TG, HDL, LDL and hsCRP and which group shows more association.
- Several algorithms were compared for predicting the GENSINI scores from the given features. Algorithms used are:
- Ridge Regression
- LASSO Regression
- Neural Networks
- Ridge Regression
Scope/Importance of Project:
- There are no study done in India in relation to importance of Metabolic Obesity and BMI status with severity of Coronary artery disease.
- Helpful to find how the Insulin resistance, hsCRP and Lp(a) is associated with the severity of Coronary artery disease.
- Effect of Lifestyle modification on Body Mass Index and Waist Circumference in post angioplasty patients.
More on this project can be found here