Automatic diagnosis of newly emerged heart failure from serial electrocardiography by repeated structuring & learning procedure. (January 2023)

• Record Type: Journal Article
• Authors: Sbrollini, Agnese; Barocci, Maddalena; Mancinelli, Martina; Paris, Michele; Raffaelli, Simone; Marcantoni, Ilaria; Morettini, Micaela; Swenne, Cees A.; Burattini, Laura
• Is Part Of: Biomedical signal processing and control. Volume 79(2023)Part 2
• Publication Date: 2023-01
• Subjects: Deep Learning -- Machine Learning -- Artificial Neural Network -- Repeated Structuring and Learning Procedure -- Heart Failure -- Serial Electrocardiography; Acc accuracy -- ANN artificial neural networks -- AUC area under the curve -- CI 95% confidence intervals -- ECG electrocardiogram -- HF Heart failure -- HFDB heart-failure database -- LCT learning computational time -- MNC maximal number of confirmations -- MNI maximal number of initializa-tions -- MNL maximal number of hidden layers -- NTOT total number of neurons -- OP operating point -- P level of statistical significance -- ROC receiver operating characteristic -- RS&LP repeated structuring & learning procedure -- Se sensitivity -- Sp specificity -- TCT testing computational time -- VCG vectorcardiogram; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2022.104185
• Languages: English
• ISSNs: 1746-8094

Abstract

Graphical abstract: Highlights: Heart failure (HF) diagnosis is typically performed by serial electrocardiography. Serial electrocardiographic analysis may be supported by machine learning approaches. Repeated Structuring & Learning Procedure (RS&LP) is a machine learning approach. RS&LP reliably diagnose HF from serial electrocardiography. Abstract: Heart failure (HF) diagnosis, typically visually performed by serial electrocardiography, may be supported by machine-learning approaches. Repeated structuring & learning procedure (RS&LP) is a constructive algorithm able to automatically create artificial neural networks (ANN); it relies on three parameters, namely maximal number of hidden layers (MNL), initializations (MNI) and confirmations (MNC), arbitrarily set by the user. The aim of this study is to evaluate RS&LP robustness to varying values of parameters and to identify an optimized combination of parameter values for HF diagnosis. To this aim, the Leiden University Medical Center HF database was used. The database is constituted by 129 serial ECG pairs acquired in patients who experienced myocardial infarction; 48 patients developed HF at follow-up (cases), while 81 remained clinically stable (controls). Overall, 15 ANNs were created by considering 13 serial ECG features as inputs (extracted from each serial ECG pair), 2 classes as outputs (cases/controls), and varying values of MNL (1, 2, 3, 4 and 10), MNI (50, 250, 500, 1000 and 1500) and MNC (2, 5, 10, 20 and 50). The area under the curve (AUC) of the receiver operating characteristic did not significantly vary with varying parameter values ( P ≥ 0.09). The optimized combination of parameter values, identified as the one showing the highest AUC, was obtained for MNL = 3, MNI = 500 and MNC = 50 (AUC = 86 %; ANN structure: 3 hidden layers of 14, 14 and 13 neurons, respectively). Thus, RS&LP is robust, and the optimized ANN represents a potentially useful clinical tool for a reliable automatic HF diagnosis.