Browsing by Author "Rad, Ali Bahrami"
Now showing 1 - 5 of 5
- Results Per Page
- Sort Options
- Automatic Cardiac Rhythm Classification With Concurrent Manual Chest Compressions
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä(2019) Isasi, Iraia; Irusta, Unai; Rad, Ali Bahrami; Aramendi, Elisabete; Zabihi, Morteza; Eftestol, Trygve; Kramer-Johansen, Jo; Wik, LarsElectrocardiogram (EKG) based classification of out-of-hospital cardiac arrest (OHCA) rhythms is important to guide treatment and to retrospectively elucidate the effects of therapy on patient response. OHCA rhythms are grouped into five categories: ventricular fibrillation (VF) and tachycardia (VT), asystole (AS), pulseless electrical activity (PEA), and pulse-generating rhythms (PR). Clinically these rhythms are grouped into broader categories like shockable (VF/VT), non-shockable (AS/PEA/PR), or organized (ORG, PEA/PR). OHCA rhythm classification is further complicated because EKGs are corrupted by cardiopulmonary resuscitation (CPR) artifacts. The objective of this study was to demonstrate a framework for automatic multiclass OHCA rhythm classification in the presence of CPR artifacts. In total, 2133 EKG segments from 272 OHCA patients were used: 580 AS, 94 PR, 953 PEA, 479 VF, and 27 VT. CPR artifacts were adaptively filtered, 93 features were computed from the stationary wavelet transform analysis, and random forests were used for classification. A repeated stratified nested cross-validation procedure was used for feature selection, parameter tuning, and model assessment. Data were partitioned patient-wise. The classifiers were evaluated using per class sensitivity, and the unweighted mean of sensitivities (UMS) as a global performance metric. Four levels of clinical detail were studied: shock/no-shock, shock/AS/ORG, VF/VT/AS/ORG, and VF/VT/AS/PEA/PR. The median UMS (interdecile range) for the 2, 3, 4, and 5-class classifiers were: 95.4% (95.1-95.6), 87.6% (87.3-88.1), 80.6% (79.3-81.8), and 71.9% (69.5-74.6), respectively. For shock/no-shock decisions sensitivities were 93.5% (93.0-93.9) and 97.2% (97.0-97.4), meeting clinical standards for artifact-free EKG. The UMS for five classes with CPR artifacts was 5.8-points below that of the best algorithms without CPR artifacts, but improved the UMS of latter by over 19-points for EKG with CPR artifacts. A robust and accurate approach for multiclass OHCA rhythm classification during CPR has been demonstrated, improving the accuracy of the current state-of-the-art methods. - Automatic Sleep Arousal Detection Using State Distance Analysis in Phase Space
A4 Artikkeli konferenssijulkaisussa(2018-09-01) Zabihi, Morteza; Rad, Ali Bahrami; Sarkka, Simo; Kiranyaz, Serkan; Katsaggelos, Aggelos K.; Gabbouj, MoncefDefective sleep arousal can contribute to significant sleep-related injuries and affect the quality of life. Investigating the arousal process is a challenging task as most of such events may be associated with subtle electrophysiological indications. Thus, developing an accurate model is an essential step toward the diagnosis and assessment of arousals. Here we introduce a novel approach for automatic arousal detection inspired by the states' recurrences in nonlinear dynamics. We first show how the states distance matrices of a complex system can be reconstructed to decrease the effect of false neighbors. Then, we use a convolutional neural network for probing the correlated structures inside the distance matrices with the arousal occurrences. Contrary to earlier studies in the literature, the proposed approach focuses on the dynamic behavior of polysomnography recordings rather than frequency analysis. The proposed approach is evaluated on the training dataset in a 3-fold cross-validation scheme and achieved an average of 19.20% and 78.57% for the area under the precision-recall (AUPRC) and area under the ROC curves, respectively. The overall AUPRC on the unseen test dataset is 19%. - ECG Rhythm Analysis during Manual Chest Compressions Using an Artefact Removal Filter and Random Forest Classifiers
A4 Artikkeli konferenssijulkaisussa(2018-09-01) Isasi, Iraia; Rad, Ali Bahrami; Irusta, Unai; Zabihi, Morteza; Aramendi, Elisabete; Eftestol, Trygve; Kramer-Johansen, Jo; Wik, LarsInterruptions in cardiopulmonary resuscitation (CPR) decrease the chances of survival. However, CPR must be interrupted for a reliable rhythm analysis because chest compressions (CCs) induce artifacts in the ECG. This paper introduces a double-stage shock advice algorithm (SAA) for a reliable rhythm analysis during manual CCs. The method used two configurations of the recursive least-squares (RLS) filter to remove CC artifacts from the ECG. For each filtered ECG segment over 200 shock/no-shock decision features were computed and fed into a random forest (RF) classifier to select the most discriminative 25 features. The proposed SAA is an ensemble of two RF classifiers which were trained using the 25 features derived from different filter configurations. Then, the average value of class posterior probabilities was used to make a final shock/no-shock decision. The dataset was comprised of 506 shockable and 1697 non-shockable rhythms which were labelled by expert rhythm resuscitation reviewers in artifact-free intervals. Shock/no-shock diagnoses obtained through the proposed double-stage SAA were compared with the rhythm annotations to obtain the Sensitivity (Se), Specificity (Sp) and balanced accuracy (BAC) of the method. The results were 93.5%, 96.5% and 95.0%, respectively. - Kalman-based Spectro-Temporal ECG Analysis using Deep Convolutional Networks for Atrial Fibrillation Detection
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä(2020-07-01) Zhao, Zheng; Särkkä, Simo; Rad, Ali BahramiIn this article, we propose a novel ECG classification framework for atrial fibrillation (AF) detection using spectro-temporal representation (i.e., time varying spectrum) and deep convolutional networks. In the first step we use a Bayesian spectro-temporal representation based on the estimation of time-varying coefficients of Fourier series using Kalman filter and smoother. Next, we derive an alternative model based on a stochastic oscillator differential equation to accelerate the estimation of the spectro-temporal representation in lengthy signals. Finally, after comparative evaluations of different convolutional architectures, we propose an efficient deep convolutional neural network to classify the 2D spectro-temporal ECG data. The ECG spectro-temporal data are classified into four different classes: AF, non-AF normal rhythm (Normal), non-AF abnormal rhythm (Other), and noisy segments (Noisy). The performance of the proposed methods is evaluated and scored with the PhysioNet/Computing in Cardiology (CinC) 2017 dataset. The experimental results show that the proposed method achieves the overall F1 score of 80.2%, which is in line with the state-of-the-art algorithms. - Machine Learning Methods for Neonatal Mortality and Morbidity Classification
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä(2020-07-02) Jaskari, Joel; Myllarinen, Janne; Leskinen, Markus; Rad, Ali Bahrami; Hollmén, Jaakko; Andersson, Sture; Sarkka, SimoPreterm birth is the leading cause of mortality in children under the age of five. In particular, low birth weight and low gestational age are associated with an increased risk of mortality. Preterm birth also increases the risks of several complications, which can increase the risk of death, or cause long-term morbidities with both individual and societal impacts. In this work, we use machine learning for prediction of neonatal mortality as well as neonatal morbidities of bronchopulmonary dysplasia, necrotizing enterocolitis, and retinopathy of prematurity, among very low birth weight infants. Our predictors include time series data and clinical variables collected at the neonatal intensive care unit of Children's Hospital, Helsinki University Hospital. We examine 9 different classifiers and present our main results in AUROC, similar to our previous studies, and in F1-score, which we propose for classifier selection in this study. We also investigate how the predictive performance of the classifiers evolves as the length of time series is increased, and examine the relative importance of different features using the random forest classifier, which we found to generally perform the best in all tasks. Our systematic study also involves different data preprocessing methods which can be used to improve classifier sensitivities. Our best classifier AUROC is 0.922 in the prediction of mortality, 0.899 in the prediction of bronchopulmonary dysplasia, 0.806 in the prediction of necrotizing enterocolitis, and 0.846 in the prediction of retinopathy of prematurity. Our best classifier F1-score is 0.493 in the prediction of mortality, 0.704 in the prediction of bronchopulmonary dysplasia, 0.215 in the prediction of necrotizing enterocolitis, and 0.368 in the prediction of retinopathy of prematurity.