Review on Classification of Amyotrophic Lateral Sclerosis Using Ensemble Classifiers

Amyotrophic lateral sclerosis is a neurodegenerative disorder that has a complex differential diagnosis that has not been elucidated due to the variety of clinical manifestations or specific biological markers. This review aims at studying the application of ensemble machine learning classifiers for enhancing the classification of ALS based on several models such as RandomForest, ExtraTrees, XGBoost, LightGBM, CatBoost, AdaBoost, Voting, and Stacking classifiers. Ensemble models offer enhanced performance in diagnosing ALS by utilizing diverse classification techniques with appropriate feature selection method. This study finds that while the Voting classifier produces comparatively inferior results, the ExtraTrees and CatBoost models perform better with adequate precision and recall and specificity. These studies on improvements in ensemble learning methods have the potential to greatly improve disease diagnosis and early identification, which will support individualized care plans for patient with ALS.