Prediction of Risk Factors from Gastric Cancer Genetic Data Using Machine Learning

Le résumé fourni par la source

Conventional statistical methods are challenging to predict cancer risk factors due to complex, non-linear, interactions among genetic factors. They often fail to handle high-dimensional data and dynamic risk factors effectively. This paper aims to utilize machine learning techniques to identify key genetic features from genomic data that contribute to the development of gastric cancer. The dataset comprises 192,781 instances with 64 annotated genetic variant features from gastric cancer patients, subjected to thorough preprocessing and quality checks prior to analysis. Feature selection was employed to identify critical features, which are used to develop five ensemble classifiers: Bagging, Random Forest, Extra Trees, AdaBoost, and Gradient Boosting. The Extra Trees classifier achieved an accuracy of 97.57%, precision of 95.62%, recall of 90%, F1-score of 92.73%, and Matthews Correlation Coefficient (MCC) of 0.91 on the imbalanced dataset, with an Area Under the Curve (AUC) of 98% for the positive class. Random undersampling of the dataset yielded promising results, reinforcing the selected features' effectiveness with consensus classification, achieving an accuracy of 96.06%, precision of 95.74%, recall of 96.33%, F1-score of 96.04%, MCC of 0.92, and Receiver Operating Characteristic (ROC) of 96.06%. Feature selection applied to both balanced and imbalanced datasets markedly improved model performance metrics, enhancing interpretability and precision for the minority class. The extracted features substantially reduced computational complexity in next-generation sequencing analysis. Moreover, these features provide critical insights into identifying novel therapeutic targets by predicting interactions with disease-associated proteins, thereby facilitating molecular dynamics investigations. This methodology significantly advances the development of personalized medicine applications. The findings underscore the effectiveness of feature selection in optimizing genomic data analysis for precision healthcare.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.