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

10 Jan 2021 Zheming Zuo Jie Li Noura Al Moubayed

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... (read more)

PDF Abstract

Datasets


  Add Datasets introduced or used in this paper
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Breast Cancer Detection Breast Cancer Coimbra Data Set CFS-TSK+ Mean Accuracy 79.17 # 1
Breast Tissue Identification Breast Tissue Data Set CFS-QDA Mean Accuracy 100.00 # 1
Cervical cancer biopsy identification Cervical Cancer (Risk Factors) Data Set CFS-TSK+ Mean Accuracy 97.09 # 1
Diabetic Retinopathy Detection Diabetic Retinopathy Debrecen Data Set CFS-BPNN Mean Accuracy 74.72 # 1

Methods used in the Paper


METHOD TYPE
PCA
Dimensionality Reduction