Prediction and Analysis of Heart Failure Decompensation Events Based on Telemonitored Data and Artificial Intelligence Methods

Abstract

Cardiovascular diseases are the leading cause of death globally, taking an estimated 17.9 million lives each year. Heart failure (HF) occurs when the heart is not able to pump enough blood to satisfy metabolic needs. People diagnosed with chronic HF may suffer from cardiac decompensation events (CDEs), which cause patients’ worsening. Being able to intervene before decompensation occurs is the major challenge addressed in this study. The aim of this study is to exploit available patient data to develop an artificial intelligence (AI) model capable of predicting the risk of CDEs timely and accurately. Materials and Methods: The vital variables of patients (n = 488) diagnosed with chronic heart failure were monitored between 2014 and 2022. Several supervised classification models were trained with these monitoring data to predict CDEs, using clinicians’ annotations as the gold standard. Feature extraction methods were applied to identify significant variables. Results: The XGBoost classifier achieved an AUC of 0.72 in the cross-validation process and 0.69 in the testing set. The most predictive physiological variables for CAE decompensations are weight gain, oxygen saturation in the final days, and heart rate. Additionally, the answers to questionnaires on wellbeing, orthopnoea, and ankles are strongly significant predictors.

DigiHEALTH: Suite of Digital Solutions for Long-Term Healthy and Active Aging

“…Patients with HF suffer decompensation, a clinical condition in which a structural or functional alteration of the heart results in a lack of capacity to transport (or eject) blood within the required physiological pressure levels. This leads to functional limitations requiring immediate therapeutic intervention [ 51 ].…”

Heart Diseases of Uncertain Etiology: A New Definition of Heart Failure for Epidemiological Studies

“…The etiology of HDUE, although probably multiple, is still vague and elusive, and the need of a systematic search seems of great importance. Future investigations need to be stimulated, as we believe it essential to segregate HDUE from CHD when relationships are investigated among risk factors [ 51 ] and outcomes either individually or when multiple definitions (such as in the case of CVD) are adopted for both mortality and incidence [ 52 ]. In fact, mixing up HDUE and IHD/CHD cases might impact, by dilution, results and conclusions and impinge upon the relevance that older and new risk factors might have and/or on their capacity to predict outcomes.…”

Development of Machine Learning-Based Web System for Estimating Pleural Effusion Using Multi-Frequency Bioelectrical Impedance Analyses

“…Compared to traditional risk estimation methods, the strength of machine learning is its ability to detect complex nonlinear relationships and iteratively improve its models with more data, resulting in more accurate estimates and fewer false alarms [14,50]. Examples of predictive models enhanced by machine learning include those that predict arrhythmia, cardiac arrest, and thromboembolism [51].…”

“…On the other hand, a recent report suggested that a remote monitoring system that collects physical findings can be used to predict clinical worsening and the need for early therapeutic intervention [12]. In addition, studies have sought to apply machine learning to the prediction of cardiovascular disease [13,14]. We hypothesized that by constructing a prediction system using machine learning that incorporates impedance measurements, physical findings, blood test results, and weight changes, we might be able to predict the state of pleural effusion observed in patients with heart failure and its process with higher accuracy.…”