Published Paper Details:

Predicting genomic disorder is a significant and crucial problem in biomedical research. Multivariate diseases with high global death rates, such as cancer, dementia, diabetes, cystic fibrosis, Leigh syndrome, etc., are brought on by genome defects. Historically, theoretical and explanatory Methods for predicting genetic disorders were introduced. As technology advanced, genetic data were expanded to nearly encompass the entire genome and proteins. Subsequently, machine learning and deep learning techniques were employed to forecast disorders related to the genome. Deep learning and machine learning techniques were introduced in parallel. Numerous studies on the prediction of genomic disorders have been carried out in the past utilizing supervised, unsupervised, and semi-supervised learning techniques; the majority of these studies used genetic sequence data to predict binary problems. These techniques' prediction findings were unclear because to due to their reduced accuracy rate and binary class prediction methods that use genome sequence data but do not use the medical history of patients with genome disorders. Consequently, an advanced genomic disorder prediction model (AGDPM) was developed in this study using a huge quantity of data by utilizing XGBoost and SVM, an efficient Machine Learning architecture. When compared to the pre-trained XGBoost model, AGDPM produces the greatest results, with training and testing accuracy rates respectively. Therefore, the advanced genome disease prediction model demonstrates the capacity to process a substantial quantity of data and forecast genomic disorders effectively. genetic disease data from patients using a multi-class prediction technique. According to a number of statistical performance metrics, AGDPM has demonstrated its ability to predict single gene inheritance disorders, mitochondrial gene inheritance disorders, and multifactorial gene inheritance disorders. Therefore, biomedical research will be enhanced with the aid of AGDPM in order to forecast genetic illnesses and control excessive death rates.