Refining Cancer Prediction with Deoxyribonucleic acid Sequencing and Combined Machine Learning Approaches

In the realm of cancer research, artificial intelligence (AI) algorithms have emerged as robust tools for analyzing Deoxyribonucleic acid sequences, a critical aspect for early detection and risk assessment. Despite notable advancements in this domain, there exists a persistent demand for a predictive model that demonstrates high accuracy in estimating cancer risk. This study endeavors to address this exigency by employing an array of classification algorithms, including Logistic Regression, Gradient Boosting, Gaussian Naive Bayes, and a combined approach (blending model) that amalgamates Logistic Regression and Gaussian Naive Bayes. These AI-powered algorithms are fine-tuned with hyperparameters through Grid search techniques to predict cancer occurrences within a cohort of 390 individuals with characterized Deoxyribonucleic acid sequences. The combined approach exhibits superior predictive performance in discerning five specific types of cancer: Breast Cancer gene 1, Kidney Renal Clear Cell Carcinoma, Colorectal Adenocarcinoma, Lung Adenocarcinoma, and Prostate Adenocarcinoma, achieving accuracy rates ranging from 96–100%. Notably, it significantly surpasses individual algorithms in predicting Lung Adenocarcinoma (LUAD) and Prostate Adenocarcinoma (PRAD), with the combined approach (incorporating Logistic Regression and Gaussian Naive Bayes) attaining an accuracy of 98%. The magnitude of this enhancement is manifest in the Micro-average and Macro-average Receiver Operating Characteristic (ROC) curves, which ascend to 99%. These findings underscore the potential of the combined approach as a valuable asset in cancer research, presenting promising prospects for enhanced accuracy and efficacy in cancer prediction endeavors.