1
|
Delliaux S, Sow AK, Echcherki A, Benyamine A, Gomes de Pinho Q, Brégeon F, Granel B. Heart rate variability helps classify phenotype in systemic sclerosis. Sci Rep 2024; 14:11151. [PMID: 38750078 PMCID: PMC11096350 DOI: 10.1038/s41598-024-60553-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/21/2023] [Accepted: 04/24/2024] [Indexed: 05/18/2024] Open
Abstract
We aimed to develop a systemic sclerosis (SSc) subtypes classifier tool to be used at the patient's bedside. We compared the heart rate variability (HRV) at rest (5-min) and in response to orthostatism (5-min) of patients (n = 58) having diffuse (n = 16, dcSSc) and limited (n = 38, lcSSc) cutaneous forms. The HRV was evaluated from the beat-to-beat RR intervals in time-, frequency-, and nonlinear-domains. The dcSSc group differed from the lcSSc group mainly by a higher heart rate (HR) and a lower HRV, in decubitus and orthostatism conditions. Stand-up maneuver lowered HR standard deviation (sd_HR), the major axis length of the fitted ellipse of Poincaré plot of RR intervals (SD2), and the correlation dimension (CorDim) in the dcSSc group while increased these HRV indexes in the lcSSc group (p = 0.004, p = 0.002, and p = 0.004, respectively). We identified the 5 most informative and discriminant HRV variables. We then compared 341 classifying models (1 to 5 variables combinations × 11 classifier algorithms) according to mean squared error, logloss, sensitivity, specificity, precision, accuracy, area under curve of the ROC-curves and F1-score. F1-score ranged from 0.823 for the best 1-variable model to a maximum of 0.947 for the 4-variables best model. Most specific and precise models included sd_HR, SD2, and CorDim. In conclusion, we provided high performance classifying models able to distinguish diffuse from limited cutaneous SSc subtypes easy to perform at the bedside from ECG recording. Models were based on 1 to 5 HRV indexes used as nonlinear markers of autonomic integrated influences on cardiac activity.
Collapse
Affiliation(s)
- Stéphane Delliaux
- INSERM, INRAE, C2VN, Aix Marseille Univ, Marseille, France.
- Explorations Fonctionnelles Respiratoires, AP-HM, Hôpital Nord, Marseille, France.
- CNRS, CPT, Aix Marseille Univ, Marseille, France.
- Laënnec Institute - Digital Sciences for Health, Aix Marseille Univ, Marseille, France.
| | - Abdou Khadir Sow
- Explorations Fonctionnelles Respiratoires, AP-HM, Hôpital Nord, Marseille, France
- Laboratoire de Physiologie, Cheikh Anta Diop University, Dakar, Senegal
| | - Anass Echcherki
- Laënnec Institute - Digital Sciences for Health, Aix Marseille Univ, Marseille, France
| | - Audrey Benyamine
- INSERM, INRAE, C2VN, Aix Marseille Univ, Marseille, France
- Service de Médecine Interne, AP-HM, Hôpital Nord, Marseille, France
| | - Quentin Gomes de Pinho
- INSERM, INRAE, C2VN, Aix Marseille Univ, Marseille, France
- Service de Médecine Interne, AP-HM, Hôpital Nord, Marseille, France
| | - Fabienne Brégeon
- Explorations Fonctionnelles Respiratoires, AP-HM, Hôpital Nord, Marseille, France
- AP-HM, Microbes Evolution Phylogeny and Infections (MEPHI), IHU-Méditerranée Infection, Aix Marseille Univ, Marseille, France
| | - Brigitte Granel
- INSERM, INRAE, C2VN, Aix Marseille Univ, Marseille, France
- Service de Médecine Interne, AP-HM, Hôpital Nord, Marseille, France
| |
Collapse
|
2
|
Automatic Atrial Fibrillation Arrhythmia Detection Using Univariate and Multivariate Data. ALGORITHMS 2022. [DOI: 10.3390/a15070231] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/10/2022]
Abstract
Atrial fibrillation (AF) is still a major cause of disease morbidity and mortality, making its early diagnosis desirable and urging researchers to develop efficient methods devoted to automatic AF detection. Till now, the analysis of Holter-ECG recordings remains the gold-standard technique to screen AF. This is usually achieved by studying either RR interval time series analysis, P-wave detection or combinations of both morphological characteristics. After extraction and selection of meaningful features, each of the AF detection methods might be conducted through univariate and multivariate data analysis. Many of these automatic techniques have been proposed over the last years. This work presents an overview of research studies of AF detection based on RR interval time series. The aim of this paper is to provide the scientific community and newcomers to the field of AF screening with a resource that presents introductory concepts, clinical features, and a literature review that describes the techniques that are mostly followed when RR interval time series are used for accurate detection of AF.
Collapse
|
3
|
Mandyam K S, Dasgupta AK, Sridhar U, Dasgupta P, Chakrabarti A. Network approaches in anomaly detection for disease conditions. Biomed Signal Process Control 2021. [DOI: 10.1016/j.bspc.2021.102659] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
|
4
|
Michel P, Ngo N, Pons JF, Delliaux S, Giorgi R. A filter approach for feature selection in classification: application to automatic atrial fibrillation detection in electrocardiogram recordings. BMC Med Inform Decis Mak 2021; 21:130. [PMID: 33947379 PMCID: PMC8094578 DOI: 10.1186/s12911-021-01427-8] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/25/2021] [Accepted: 02/09/2021] [Indexed: 12/03/2022] Open
Abstract
Background In high-dimensional data analysis, the complexity of predictive models can be reduced by selecting the most relevant features, which is crucial to reduce data noise and increase model accuracy and interpretability. Thus, in the field of clinical decision making, only the most relevant features from a set of medical descriptors should be considered when determining whether a patient is healthy or not. This statistical approach known as feature selection can be performed through regression or classification, in a supervised or unsupervised manner. Several feature selection approaches using different mathematical concepts have been described in the literature. In the field of classification, a new approach has recently been proposed that uses the \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$\gamma$$\end{document}γ-metric, an index measuring separability between different classes in heart rhythm characterization. The present study proposes a filter approach for feature selection in classification using this \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$\gamma$$\end{document}γ-metric, and evaluates its application to automatic atrial fibrillation detection. Methods The stability and prediction performance of the \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$\gamma$$\end{document}γ-metric feature selection approach was evaluated using the support vector machine model on two heart rhythm datasets, one extracted from the PhysioNet database and the other from the database of Marseille University Hospital Center, France (Timone Hospital). Both datasets contained electrocardiogram recordings grouped into two classes: normal sinus rhythm and atrial fibrillation. The performance of this feature selection approach was compared to that of three other approaches, with the first two based on the Random Forest technique and the other on receiver operating characteristic curve analysis. Results The \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$\gamma$$\end{document}γ-metric approach showed satisfactory results, especially for models with a smaller number of features. For the training dataset, all prediction indicators were higher for our approach (accuracy greater than 99% for models with 5 to 17 features), as was stability (greater than 0.925 regardless of the number of features included in the model). For the validation dataset, the features selected with the \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$\gamma$$\end{document}γ-metric approach differed from those selected with the other approaches; sensitivity was higher for our approach, but other indicators were similar. Conclusion This filter approach for feature selection in classification opens up new methodological avenues for atrial fibrillation detection using short electrocardiogram recordings. Supplementary Information The online version contains supplementary material available at 10.1186/s12911-021-01427-8.
Collapse
Affiliation(s)
- Pierre Michel
- CNRS, EHESS, Centrale Marseille, AMSE, Aix-Marseille Univ, Marseille, France.
| | - Nicolas Ngo
- INSERM, IRD, SESSTIM, Sciences Economiques & Sociales de la Santé & Traitement de l'Information Médicale, Aix Marseille Univ, Marseille, France
| | | | - Stéphane Delliaux
- INSERM, INRAE, C2VN, Aix Marseille Univ, Marseille, France.,Hôpital Nord, Service des Explorations Fonctionnelles Respiratoires, Pôle cardiovasculaire, APHM, Marseille, France
| | - Roch Giorgi
- APHM, INSERM, IRD, Sciences Economiques & Sociales de la Sante & Traitement de l'Information Médicale (SESSTIM), Hop Timone, Biostatistique et Technologies de l'Information et de la Communication (BioSTIC), Aix Marseille Univ, Marseille, France
| |
Collapse
|
5
|
Construction et comparaison de méthodes de sélections de variables en classification supervisée utilisant comme fonction d’évaluation un nouvel indice de séparabilité : la gamma-metric. Rev Epidemiol Sante Publique 2020. [DOI: 10.1016/j.respe.2020.03.039] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/24/2022] Open
|
6
|
Gadhoumi K, Do D, Badilini F, Pelter MM, Hu X. Wavelet leader multifractal analysis of heart rate variability in atrial fibrillation. J Electrocardiol 2018; 51:S83-S87. [PMID: 30177367 DOI: 10.1016/j.jelectrocard.2018.08.030] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/16/2018] [Revised: 08/15/2018] [Accepted: 08/21/2018] [Indexed: 10/28/2022]
Abstract
BACKGROUND Accurate and timely detection of atrial fibrillation (AF) episodes is important in primarily and secondary prevention of ischemic stroke and heart-related problems. In this work, heart rate regularity of ECG inter-beat intervals was investigated in episodes of AF and other rhythms using a wavelet leader based multifractal analysis. Our aim was to improve the detectability of AF episodes. METHODS Inter-beat intervals from 25 ECG recordings available in the MIT-BIH atrial fibrillation database were analysed. Four types of annotated rhythms (atrial fibrillation, atrial flutter, AV junctional rhythm, and other rhythms) were available. A wavelet leader based multifractal analysis was applied to 5 min non-overlapping windows of each recording to estimate the multifractal spectrum in each window. The width of the multifractal spectrum was analysed for its discrimination power between rhythm episodes. RESULTS In 10 of 25 recordings, the width of multifractal spectrum was significantly lower in episodes of AF than in other rhythms indicating increased regularity during AF. High classification accuracy (95%) of AF episodes was achieved using a combination of features derived from the multifractal analysis and statistical central moment features. CONCLUSIONS An increase in the regularity of inter-beat intervals was observed during AF episodes by means of multifractal analysis. Multifractal features may be used to improve AF detection accuracy.
Collapse
Affiliation(s)
- Kais Gadhoumi
- Department of Physiological Nursing, University of California, San Francisco, CA, USA.
| | - Duc Do
- David Geffen School of Medicine, University of California, Los Angeles, CA, USA
| | - Fabio Badilini
- Center for Physiologic Research, University of California, San Francisco, CA, USA
| | - Michele M Pelter
- Department of Physiological Nursing, University of California, San Francisco, CA, USA
| | - Xiao Hu
- Department of Physiological Nursing, University of California, San Francisco, CA, USA; Institute for Computational Health Sciences, University of California, San Francisco, CA, USA; Department of Neurological Surgery, University of California, San Francisco, CA, USA; Department of Neurosurgery, University of California, Los Angeles, CA, USA
| |
Collapse
|