Dynamic Mode Decomposition-Based Features for Ovarian Cancer Gene Expression Classification Using Machine Learning

Abstract

Machine learning (ML) algorithms have been deployed in recent years as models for the analysis of complex data. The ubiquity of ML  algorithms stems from their ability to learn the patterns and structures inherent in data. Additionally, they are adaptable to a wide range  of data types, irrespective of size, which allows them to learn and predict the future pattern of data. In this work, dynamic mode  decomposition (DMD), an ML algorithm, is deployed to analyse the pattern of gene expression data from patients with and without  ovarian cancer. Ovarian cancer is one of the deadliest gynaecologic cancers worldwide. The obscure nature of the symptoms makes early  detection of ovarian cancer difficult. Early diagnosis increases the chances of survival for patients. Furthermore, the modes computed  from DMD are used as features and separately fed into three ML classifiers- support vector machine (SVM), decision tree (DecTr), and K- nearest neighbour (KNN) to classify the gene expression into either cancer or non-cancer categories. Multiple metrics- sensitivity,  accuracy, precision, and error rate are used to assess the performance of the models, to have a balanced illustration of a model’s  performance. The DecTr outperforms the other two classifiersSVM and KNN, across the metrics used in evaluating the performance of  the models.