Detection of Genetic Disorders Using Ensemble Machine Learning Techniques: An Exploratory Study on the Identification of Genetic Abnormalities Through Advanced Computational Methods

Genetic disorders arise from alterations in DNA sequences, presenting complex structures and diverse symptomatology that necessitate the use of sophisticated algorithmic methodologies for early identification. This paper focuses on improving the precision of a model designed for accurate detection of genetic disorders and evaluating the efficacy of eight machine learning methodologies in analyzing genomic data. Through rigorous assessment of these algorithms during both training and testing phases, their suitability is determined and compared against existing prediction models. Notably, the Extra Tree algorithm achieves outstanding accuracy, scoring 95.72% during training and 95% during testing. Furthermore, by leveraging ensemble techniques, the Extra Tree and Random Forest algorithms achieve a remarkable 96% accuracy. The study underscores the significance of methodically selecting a proficient machine learning algorithm and meticulously fine-tuning its parameters before analyzing genomic data. Based on its exceptional precision and accuracy, the Extra Tree algorithm emerges as the most suitable method for genetic data analysis. Researchers working with genomic data are encouraged to carefully choose an appropriate methodology and thoroughly evaluate its parameters to ensure dependable and accurate results.