AI GENETIC RISK PREDICTION FOR HEREDITARY DISEASE SCREENING

Genetic disorders depend on multiple genetic factors passed down through inheritance, family history and other patient related factors.This makes identifying patterns from this wide range of attributes a complex classification problem.In this study, we explored using machine learning approaches in order to classify genetic disorders into general categories and specific diseases.We used a publically available dataset from the HackerEarth ML challenge called Of Genomes and Genetics.Our process included data cleaning, missing value handling, feature encoding, and then comparing the performance between six different classifiers: Logistic Regression, Decision Tree, Random Forest, XGBoost, CatBoost and Voting Classifier.From our validation phase, we found that the CatBoost model had an accuracy of 40.25%, weighted precision of 39.67%, weighted recall of 40.25% and weighted F1 Score of 38.78% when classifying the specific disease.This shows a comparison between the models and highlights how difficult it is to distinguish between different specific diseases.We also explored using Explainable Artificial Intelligence (XAI) to understand which features influence our model.We created a web application containing our prediction pipeline to display our classification results and their feature explanations.This work shows how machine learning and explainability can be applied to predicting the risk of hereditary diseases.However, we would need to test our system with labelled data and validate with clinicians before it could be considered for medical use.

Publication Details

Journal
International Research Journal of Modernization in Engineering Technology and Science
Published
2026-11-14
DOI
https://doi.org/10.56726/irjmets104009
Primary Topic
Artificial Intelligence in Healthcare
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

AI GENETIC RISK PREDICTION FOR HEREDITARY DISEASE SCREENING

International Research Journal of Modernization in Engineering Technology and Science
Artificial Intelligence in Healthcare
article

AI GENETIC RISK PREDICTION FOR HEREDITARY DISEASE SCREENING

article en

Abstract

Genetic disorders depend on multiple genetic factors passed down through inheritance, family history and other patient related factors.This makes identifying patterns from this wide range of attributes a complex classification problem.In this study, we explored using machine learning approaches in order to classify genetic disorders into general categories and specific diseases.We used a publically available dataset from the HackerEarth ML challenge called Of Genomes and Genetics.Our process included data cleaning, missing value handling, feature encoding, and then comparing the performance between six different classifiers: Logistic Regression, Decision Tree, Random Forest, XGBoost, CatBoost and Voting Classifier.From our validation phase, we found that the CatBoost model had an accuracy of 40.25%, weighted precision of 39.67%, weighted recall of 40.25% and weighted F1 Score of 38.78% when classifying the specific disease.This shows a comparison between the models and highlights how difficult it is to distinguish between different specific diseases.We also explored using Explainable Artificial Intelligence (XAI) to understand which features influence our model.We created a web application containing our prediction pipeline to display our classification results and their feature explanations.This work shows how machine learning and explainability can be applied to predicting the risk of hereditary diseases.However, we would need to test our system with labelled data and validate with clinicians before it could be considered for medical use.

International Research Journal of Modernization in Engineering Technology and Science
Artificial Intelligence in Healthcare
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon