Comparative Performance of Machine Learning Algorithms for Early Genetic Disorder and Subclass Classification

TL;DR

The study tackles early classification of genetic disorders across broad classes and subtypes using machine learning on indicators measurable at birth or infancy. It evaluates six supervised algorithms (SVM, Random Forest, CatBoost, Gradient Boosting, LightGBM, with Logistic Regression and KNN excluded after poor preliminary performance) on a Kaggle-derived dataset of 22,083 samples with 42 features and two labels. CatBoost achieves the highest accuracy for disorder classes (77%), while SVM leads for disorder subclasses (80%), with strong AUC values across many categories. The results demonstrate the feasibility of using readily available clinical data for early, multi-class genetic disorder screening, though future work on larger, more balanced datasets and clinical integration is needed for robust, real-world deployment.

Abstract

A great deal of effort has been devoted to discovering a particular genetic disorder, but its classification across a broad spectrum of disorder classes and types remains elusive. Early diagnosis of genetic disorders enables timely interventions and improves outcomes. This study implements machine learning models using basic clinical indicators measurable at birth or infancy to enable diagnosis in preliminary life stages. Supervised learning algorithms were implemented on a dataset of 22083 instances with 42 features like family history, newborn metrics, and basic lab tests. Extensive hyperparameter tuning, feature engineering, and selection were undertaken. Two multi-class classifiers were developed: one for predicting disorder classes (mitochondrial, multifactorial, and single-gene) and one for subtypes (9 disorders). Performance was evaluated using accuracy, precision, recall, and the F1-score. The CatBoost classifier achieved the highest accuracy of 77% for predicting genetic disorder classes. For subtypes, SVM attained a maximum accuracy of 80%. The study demonstrates the feasibility of using basic clinical data in machine learning models for early categorization and diagnosis across various genetic disorders. Applying ML with basic clinical indicators can enable timely interventions once validated on larger datasets. It is necessary to conduct further studies to improve model performance on this dataset.

Figures (6)

• Figure 1: Proposed Workflow
• Figure 2: (a) Accuracy and (b) Precision for Genetic Disorder Classifier.
• Figure 3: (a) Recall and (b) F1-score for Genetic Disorder Classifier.
• Figure 4: (a) Overall Accuracy and (b) Accuracy for Disorder Subclass Classifier.
• Figure 5: ROC curves (a) SVM (b) Catboost classifiers for Genetic Disorder