Estimation of New York Heart Association class in heart failure patients based on machine learning techniques

Abstract

Abstract-The aim of this work is to present an automated method for the early identification of New York Heart Association (NYHA) class change in patients with heart failure using classification techniques. The proposed method consists of three main steps: a) data processing, b) feature selection, and c) classification. The estimation of the severity of heart failure in terms of NYHA class is addressed as two, three and, for the first time, as four class classification problem. Eleven classifiers are employed and combined with resampling techniques. The proposed method is evaluated on a dataset of 378 patients, through a 10-fold-cross-validation approach. The highest detection accuracy is 97, 87 and 67% for the two, three and the four class classification problem, respectively. I. INTRODUCTIONHeart failure (HF) is described by the inability of the heart to fulfill the circulatory demands of the body due to progressively impairment of the ventricle to fill with or eject blood. HF leads to damage of the cardiovascular system and becomes one of the major causes of mortality and morbidity [1]. This in combination with the severe consequences, in terms of quality of life, recurrent hospitalizations and escalating healthcare costs that HF disease induces for the patients and the healthcare systems, intensify the need for effective and efficient management of HF that includes early detection of HF, recognition of HF subtype, estimation of HF severity and treatment.In clinical practice, several criteria (e.g. Framingham,

Tele-monitoring Technology as a Tool for Monitoring and Management of Patients with Congestive Heart Failure

“…NYHA classification focuses on the exercise capacity of the patient and the symptomatic status of the disease. Based on the NYHA classification system, the estimation of HF severity can be classified as a stage two, three, or four, allowing the experts to adjust the treatment of the patient and minimize the risk of adverse events (Tripoliti et al, 2017).…”

Evaluating the Effect of Monitoring through Telephone (Tele-Monitoring) on Self-Care Behaviors and Readmission of Patients with Heart Failure after Discharge

“…Study population included HF patients hospitalized at the cardiac intensive care units of the Grand Hospital of Dezful in 2016. The inclusion criteria were diagnosis of HF with the New York Heart Association (NYHA) functional classes II and III, 24 age 45 years or older, ability to communicate in Farsi language, and access to a landline or mobile phone. The exclusion criteria were patients diagnosed with congenital heart disease, hearing impairments, major disability and limitation for self-care, mental illness, Alzheimer's, hemiplegia, paraplegia, and/or organ failure.…”

HEARTEN: An integrated mHealth platform for holistic HF management

“…It is a valuable tool that includes advanced data-driven techniques incorporated with expert-knowledge techniques towards effectively assessing the HF patient condition and enhancing patient adherence. The KMS enables users with advanced expert-knowledge techniques to effectively assess and exploit real patient data [12], [13].…”