A Novel and Effective Method for Congestive Heart Failure Detection and Quantification Using Dynamic Heart Rate Variability Measurement

• Published in: PloS one Vol. 11; no. 11; p. e0165304
• Main Authors: Chen, Wenhui, Zheng, Lianrong, Li, Kunyang, Wang, Qian, Liu, Guanzheng, Jiang, Qing
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 11.11.2016; Public Library of Science (PLoS)
• Subjects: Accuracy; Analysis; Anesthesia; Artificial intelligence; Biology and Life Sciences; Biomedical engineering; Cardiac patients; Case-Control Studies; Classification; Computer and Information Sciences; Congestive heart failure; Critical care; Cybernetics; Databases, Factual; Decision Trees; Disease detection; Drug therapy; Engineering and Technology; Engineering schools; Entropy; Failure detection; Heart failure; Heart Failure - diagnosis; Heart Failure - physiopathology; Heart Rate; Humans; Mathematical models; Measurement; Medical equipment; Medical research; Medical technology; Medicine and Health Sciences; Methods; Model accuracy; Models, Statistical; Multistage; Nervous system; Neural networks; Patients; Physical Sciences; Prognosis; Research and Analysis Methods; Risk analysis; Risk Assessment; Science; Severity of Illness Index; Support Vector Machine; Transplantation; Variability; New York; United States > US; China
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0165304

Risk assessment of congestive heart failure (CHF) is essential for detection, especially helping patients make informed decisions about medications, devices, transplantation, and end-of-life care. The majority of studies have focused on disease detection between CHF patients and normal subjects using short-/long-term heart rate variability (HRV) measures but not much on quantification. We downloaded 116 nominal 24-hour RR interval records from the MIT/BIH database, including 72 normal people and 44 CHF patients. These records were analyzed under a 4-level risk assessment model: no risk (normal people, N), mild risk (patients with New York Heart Association (NYHA) class I-II, P1), moderate risk (patients with NYHA III, P2), and severe risk (patients with NYHA III-IV, P3). A novel multistage classification approach is proposed for risk assessment and rating CHF using the non-equilibrium decision-tree-based support vector machine classifier. We propose dynamic indices of HRV to capture the dynamics of 5-minute short term HRV measurements for quantifying autonomic activity changes of CHF. We extracted 54 classical measures and 126 dynamic indices and selected from these using backward elimination to detect and quantify CHF patients. Experimental results show that the multistage risk assessment model can realize CHF detection and quantification analysis with total accuracy of 96.61%. The multistage model provides a powerful predictor between predicted and actual ratings, and it could serve as a clinically meaningful outcome providing an early assessment and a prognostic marker for CHF patients.