Curvature-based Feature Selection with Application in Classifying Electronic Health Records

Disruptive technologies provides unparalleled opportunities to contribute to the identifications of many aspects in pervasive healthcare, from the adoption of the Internet of Things through to Machine Learning (ML) techniques. As a powerful tool, ML has been widely applied in patient-centric healthcare solutions. To further improve the quality of patient care, Electronic Health Records (EHRs) are widely applied in healthcare facilities nowadays. Due to the inherent heterogeneity, unbalanced, incompleteness, and high-dimensional nature of EHRs, it is a challenging task to employ machine learning algorithms to analyse such EHRs for prediction and diagnostics within the scope of precision medicine. Dimensionality reduction is an efficient data preprocessing technique for the analysis of high dimensional data that reduces the number of features while improving the performance of the data analysis, e.g. classification. In this paper, we propose an efficient curvature-based feature selection method for supporting more precise diagnosis. The proposed method is a filter-based feature selection method, which directly utilises the Menger Curvature for ranking all the attributes in the given data set. We evaluate the performance of our method against conventional PCA and recent ones including BPCM, GSAM, WCNN, BLS II, VIBES, 2L-MJFA, RFGA, and VAF. Our method achieves state-of-the-art performance on four benchmark healthcare data sets including CCRFDS, BCCDS, BTDS, and DRDDS with impressive 24.73% and 13.93% improvements respectively on BTDS and CCRFDS, 7.97% improvement on BCCDS, and 3.63% improvement on DRDDS. Our CFS source code is publicly available at https://github.com/zhemingzuo/CFS.