Diagnosis of breast cancer using skin surface electropotentials

Abstract

Breast cancer is the most common cancer in women in Singapore. The current screening techniques have limitations in detecting early stage breast cancer, especially in younger women. Hence, there is a need to develop an efficient, cost-effective screening technique so that the number of affected women can be reduced.

The main objective of this project is hence to study the application of Skin Surface Electropotentials and evaluate the effectiveness of Biofield Diagnostic System (BDS) as another adjunctive tool to screen patients for early detection of breast cancer and improving patient selection for biopsy.

The clinical results and neural network analyses conducted in this study have proved BDS as an effective adjunct to physical examination or routine diagnostic testing such as Ultrasound (US) and Mammography (MMG) for the detection of breast cancer. This is because BDS has sensitivity, specificity, accuracy and area under receiver operating characteristic curve (AROC) in excess of 90% in clinical results, as well as results obtained using Generalized Regression Neural Network (GRNN) and Probabilistic Neural Network (PNN) using MATLAB . Most importantly, use of BDS is able to prevent 41 out of 44 women from taking biopsy with ambiguous lesions of Prior LOS 2/3.