Intelligent diagnosis of cardiac valve calcification in ESRD patients with peritoneal dialysis based on improved Takagi-Sugeno-Kang fuzzy system

Abstract

Without a B-ultrasound result, if a doctor diagnoses a suspected patient using only the basic clinical features, such as age, gender, serum calcium, and urea clearance index (KT/V), the diagnostic accuracy will be very low (even less than 50%). To solve this problem, a machine learning technology is proposed to intelligently diagnose cardiac valve calcification in end-stage renal disease (ESRD) patients with peritoneal dialysis. Compared with classical classification technologies, the proposed method aims to develop a model that has both medical interpretability and high recognition performance. In terms of interpretability, the Takagi-Sugeno-Kang fuzzy system is considered a basic model due to its built-in interpretable ability. In addition, because the distribution of the positive class (cardiac valve calcification is positive) and negative class (cardiac valve calcification is negative) in the peritoneal dialysis patient dataset is unbalanced, a novel unbalanced TSK (Takagi-Sugeno-Kang) fuzzy system (B-TSK-FS) is developed using a novel unbalanced fuzzy learning mechanism. The corresponding results reveal that the B-TSK-FS method obtains promising results (the max testing accuracy is over 98%) compared with classical machine learning methods for intelligently diagnosing cardiac valve calcification in ESRD patients with peritoneal dialysis.