A Generalisable Heartbeat Classifier Leveraging Self-Supervised Learning for ECG Analysis During Magnetic Resonance Imaging.

Electrocardiogram (ECG) is acquired during Magnetic Resonance Imaging (MRI) to monitor patients and synchronize image acquisition with the heart motion. ECG signals are highly distorted during MRI due to the complex electromagnetic environment. Automated ECG analysis is therefore complicated in this context and there is no reference technique in MRI to classify pathological heartbeats. Imaging arrhythmic patients is hence difficult in MRI. Deep Learning based heartbeat classifier have been suggested but require large databases whereas existing annotated sets of ECG in MRI are very small. We proposed a Siamese network to leverage a large database of unannotated ECGs outside MRI. This was used to develop an efficient representation of ECG signals, further used to develop a heartbeat classifier. We extensively tested several data augmentations and self-supervised learning (SSL) techniques and assessed the generalization of the obtained classifier to ECG signals acquired in MRI. These augmentations included random noises and a model simulating MRI specific artefacts. SSL pretraining improved the generalizability of heartbeat classifiers in MRI (F1=0.75) compared to Deep Learning not relying on SSL (F1=0.46) and another classical machine learning approach (F1=0.40). These promising results seem to indicate that the use of SSL techniques can learn efficient ECG signal representation, and are useful for the development of Deep Learning models even when only scarce annotated medical data are available.

AcquisitionFocus: Joint Optimization of Acquisition Orientation and Cardiac Volume Reconstruction Using Deep Learning.

In cardiac cine imaging, acquiring high-quality data is challenging and time-consuming due to the artifacts generated by the heart's continuous movement. Volumetric, fully isotropic data acquisition with high temporal resolution is, to date, intractable due to MR physics constraints. To assess whole-heart movement under minimal acquisition time, we propose a deep learning model that reconstructs the volumetric shape of multiple cardiac chambers from a limited number of input slices while simultaneously optimizing the slice acquisition orientation for this task. We mimic the current clinical protocols for cardiac imaging and compare the shape reconstruction quality of standard clinical views and optimized views. In our experiments, we show that the jointly trained model achieves accurate high-resolution multi-chamber shape reconstruction with errors of <13 mm HD95 and Dice scores of >80%, indicating its effectiveness in both simulated cardiac cine MRI and clinical cardiac MRI with a wide range of pathological shape variations.

Application of PET imaging delta radiomics for predicting progression-free survival in rare high-grade glioma.

This study assesses the feasibility of using a sample-efficient model to investigate radiomics changes over time for predicting progression-free survival in rare diseases. Eighteen high-grade glioma patients underwent two L-3,4-dihydroxy-6-[18F]-fluoro-phenylalanine positron emission tomography (PET) dynamic scans: the first during treatment and the second at temozolomide chemotherapy discontinuation. Radiomics features from static/dynamic parametric images, alongside conventional features, were extracted. After excluding highly correlated features, 16 different models were trained by combining various feature selection methods and time-to-event survival algorithms. Performance was assessed using cross-validation. To evaluate model robustness, an additional dataset including 35 patients with a single PET scan at therapy discontinuation was used. Model performance was compared with a strategy extracting informative features from the set of 35 patients and applying them to the 18 patients with 2 PET scans. Delta-absolute radiomics achieved the highest performance when the pipeline was directly applied to the 18-patient subset (support vector machine (SVM) and recursive feature elimination (RFE): C-index = 0.783 [0.744-0.818]). This result remained consistent when transferring informative features from 35 patients (SVM + RFE: C-index = 0.751 [0.716-0.784], p = 0.06). In addition, it significantly outperformed delta-absolute conventional (C-index = 0.584 [0.548-0.620], p < 0.001) and single-time-point radiomics features (C-index = 0.546 [0.512-0.580], p < 0.001), highlighting the considerable potential of delta radiomics in rare cancer cohorts.

A Human-Centered AI Framework for Efficient Labelling of ECGs From Drug Safety Trials.

Drug safety trials require substantial ECG labelling like, in thorough QT studies, measurements of the QT interval, whose prolongation is a biomarker of proarrhythmic risk. The traditional method of manually measuring the QT interval is time-consuming and error-prone. Studies have demonstrated the potential of deep learning (DL)-based methods to automate this task but expert validation of these computerized measurements remains of paramount importance, particularly for abnormal ECG recordings. In this paper, we propose a highly automated framework that combines such a DL-based QT estimator with human expertise. The framework consists of 3 key components: (1) automated QT measurement with uncertainty quantification (2) expert review of a few DL-based measurements, mostly those with high model uncertainty and (3) recalibration of the unreviewed measurements based on the expert-validated data. We assess its effectiveness on 3 drug safety trials and show that it can significantly reduce effort required for ECG labelling-in our experiments only 10% of the data were reviewed per trial-while maintaining high levels of QT accuracy. Our study thus demonstrates the possibility of productive human-machine collaboration in ECG analysis without any compromise on the reliability of subsequent clinical interpretations.

Body Surface Gastrointestinal Potential Mapping: A Simulation Framework to Evaluate Source Separation Algorithms.

Gastrointestinal (GI) potential mapping could be useful for evaluating GI motility disorders. Such disorders are found in inflammatory bowel diseases, such as Crohn's disease, or GI functional disorders. GI potential mapping data originate from a mixture of several GI electrophysiological sources (termed ExG) and other noise sources, including the electrocardiogram (ECG) and respiration. Denoising and/or source separation techniques are required, however, with real measurements, no ground truth is available. In this paper we propose a framework for the simulation of body surface GI potential mapping data. The framework is an electrostatic model, based on fecgsyn toolbox, using dipoles as electrical sources for the heart, stomach, small bowel and colon, and an array of surface electrodes. It is shown to generate realistic ExG waveforms, which are then used to compare several ECG and respiration cancellation techniques, based on, fast independent component analysis (FastICA) and pseudo-periodic component analysis (PiCA). The best performance was obtained with PiCA with a median root mean squared error of 0.005.

A Generative Adversarial Network to Synthesize 3D Magnetohydrodynamic Distortions for Electrocardiogram Analyses Applied to Cardiac Magnetic Resonance Imaging.

Recently, deep learning (DL) models have been increasingly adopted for automatic analyses of medical data, including electrocardiograms (ECGs). Large, available ECG datasets, generally of high quality, often lack specific distortions, which could be helpful for enhancing DL-based algorithms. Synthetic ECG datasets could overcome this limitation. A generative adversarial network (GAN) was used to synthesize realistic 3D magnetohydrodynamic (MHD) distortion templates, as observed during magnetic resonance imaging (MRI), and then added to available ECG recordings to produce an augmented dataset. Similarity metrics, as well as the accuracy of a DL-based R-peak detector trained with and without data augmentation, were used to evaluate the effectiveness of the synthesized data. Three-dimensional MHD distortions produced by the proposed GAN were similar to the measured ones used as input. The precision of a DL-based R-peak detector, tested on actual unseen data, was significantly enhanced by data augmentation; its recall was higher when trained with augmented data. Using synthesized MHD-distorted ECGs significantly improves the accuracy of a DL-based R-peak detector, with a good generalization capacity. This provides a simple and effective alternative to collecting new patient data. DL-based algorithms for ECG analyses can suffer from bias or gaps in training datasets. Using a GAN to synthesize new data, as well as metrics to evaluate its performance, can overcome the scarcity issue of data availability.

Initial Evaluation of Focal Bone Lesions: How Do We Do It?

Focal bone lesions are frequent, and management greatly depends on the characteristics of their images. After briefly discussing the required work-up, we analyze the most relevant imaging signs for assessing potential aggressiveness. We also describe the imaging aspects of the various types of lesion matrices and their clinical implications.

Deep learning HASTE sequence compared with T2-weighted BLADE sequence for liver MRI at 3 Tesla: a qualitative and quantitative prospective study.

OBJECTIVES: To qualitatively and quantitatively compare a single breath-hold fast half-Fourier single-shot turbo spin echo sequence with deep learning reconstruction (DL HASTE) with T2-weighted BLADE sequence for liver MRI at 3 T. METHODS: From December 2020 to January 2021, patients with liver MRI were prospectively included. For qualitative analysis, sequence quality, presence of artifacts, conspicuity, and presumed nature of the smallest lesion were assessed using the chi-squared and McNemar tests. For quantitative analysis, number of liver lesions, size of the smallest lesion, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) in both sequences were assessed using the paired Wilcoxon signed-rank test. Intraclass correlation coefficients (ICCs) and kappa coefficients were used to assess agreement between the two readers. RESULTS: One hundred and twelve patients were evaluated. Overall image quality (p = .006), artifacts (p < .001), and conspicuity of the smallest lesion (p = .001) were significantly better for the DL HASTE sequence than for the T2-weighted BLADE sequence. Significantly more liver lesions were detected with the DL HASTE sequence (356 lesions) than with the T2-weighted BLADE sequence (320 lesions; p < .001). CNR was significantly higher for the DL HASTE sequence (p < .001). SNR was higher for the T2-weighted BLADE sequence (p < .001). Interreader agreement was moderate to excellent depending on the sequence. Of the 41 supernumerary lesions visible only on the DL HASTE sequence, 38 (93%) were true-positives. CONCLUSION: The DL HASTE sequence can be used to improve image quality and contrast and reduces artifacts, allowing the detection of more liver lesions than with the T2-weighted BLADE sequence. CLINICAL RELEVANCE STATEMENT: The DL HASTE sequence is superior to the T2-weighted BLADE sequence for the detection of focal liver lesions and can be used in daily practice as a standard sequence. KEY POINTS: • The half-Fourier acquisition single-shot turbo spin echo sequence with deep learning reconstruction (DL HASTE sequence) has better overall image quality, reduced artifacts (particularly motion artifacts), and improved contrast, allowing the detection of more liver lesions than with the T2-weighted BLADE sequence. • The acquisition time of the DL HASTE sequence is at least eight times faster (21 s) than that of the T2-weighted BLADE sequence (3-5 min). • The DL HASTE sequence could replace the conventional T2-weighted BLADE sequence to meet the growing indication for hepatic MRI in clinical practice, given its diagnostic and time-saving performance.

Generalizable and robust deep learning algorithm for atrial fibrillation diagnosis across geography, ages and sexes.

To drive health innovation that meets the needs of all and democratize healthcare, there is a need to assess the generalization performance of deep learning (DL) algorithms across various distribution shifts to ensure that these algorithms are robust. This retrospective study is, to the best of our knowledge, an original attempt to develop and assess the generalization performance of a DL model for AF events detection from long term beat-to-beat intervals across geography, ages and sexes. The new recurrent DL model, denoted ArNet2, is developed on a large retrospective dataset of 2,147 patients totaling 51,386 h obtained from continuous electrocardiogram (ECG). The model's generalization is evaluated on manually annotated test sets from four centers (USA, Israel, Japan and China) totaling 402 patients. The model is further validated on a retrospective dataset of 1,825 consecutives Holter recordings from Israel. The model outperforms benchmark state-of-the-art models and generalized well across geography, ages and sexes. For the task of event detection ArNet2 performance was higher for female than male, higher for young adults (less than 61 years old) than other age groups and across geography. Finally, ArNet2 shows better performance for the test sets from the USA and China. The main finding explaining these variations is an impairment in performance in groups with a higher prevalence of atrial flutter (AFL). Our findings on the relative performance of ArNet2 across groups may have clinical implications on the choice of the preferred AF examination method to use relative to the group of interest.

A Deep Learning Architecture Using 3D Vectorcardiogram to Detect R-Peaks in ECG with Enhanced Precision.

Providing reliable detection of QRS complexes is key in automated analyses of electrocardiograms (ECG). Accurate and timely R-peak detections provide a basis for ECG-based diagnoses and to synchronize radiologic, electrophysiologic, or other medical devices. Compared with classical algorithms, deep learning (DL) architectures have demonstrated superior accuracy and high generalization capacity. Furthermore, they can be embedded on edge devices for real-time inference. 3D vectorcardiograms (VCG) provide a unifying framework for detecting R-peaks regardless of the acquisition strategy or number of ECG leads. In this article, a DL architecture was demonstrated to provide enhanced precision when trained and applied on 3D VCG, with no pre-processing nor post-processing steps. Experiments were conducted on four different public databases. Using the proposed approach, high F1-scores of 99.80% and 99.64% were achieved in leave-one-out cross-validation and cross-database validation protocols, respectively. False detections, measured by a precision of 99.88% or more, were significantly reduced compared with recent state-of-the-art methods tested on the same databases, without penalty in the number of missed peaks, measured by a recall of 99.39% or more. This approach can provide new applications for devices where precision, or positive predictive value, is essential, for instance cardiac magnetic resonance imaging.

AI-Assisted QT Measurements for Highly Automated Drug Safety Studies.

Rate-corrected QT interval (QTc) prolongation has been suggested as a biomarker for the risk of drug-induced torsades de pointes, and is therefore monitored during clinical trials for the assessment of drug safety. Manual QT measurements by expert ECG analysts are expensive, laborious and prone to errors. Wavelet-based delineators and other automatic methods do not generalize well to different T wave morphologies and may require laborious tuning. Our study investigates the robustness of convolutional neural networks (CNNs) for QT measurement. We trained 3 CNN-based deep learning models on a private ECG database with human expert-annotated QT intervals. Among these models, we propose a U-Net model, which is widely used for segmentation tasks, to build a novel clinically useful QT estimator that includes QT delineation for better interpretability. We tested the 3 models on four external databases, amongst which a clinical trial investigating four drugs. Our results show that the deep learning models are in stronger agreement with the experts than the state-of-the-art wavelet-based algorithm. Indeed, the deep learning models yielded up to 71% of accurate QT measurements (absolute difference between manual and automatic QT below 15 ms) whereas the wavelet-based algorithm only allowed 52% of QT accuracy. For the 2 studies of drugs with small to no QT prolonging effect, a mean absolute difference of 6 ms (std = 5 ms) was obtained between the manual and deep learning methods. For the other 2 drugs with more significant effect on the volunteers, a mean difference of up to 17 ms (std = 17 ms) was obtained. The proposed models are therefore promising for automated QT measurements during clinical trials. They can analyze various ECG morphologies from a diversity of individuals although some QT-prolonged ECGs can be challenging. The U-Net model is particularly interesting for our application as it facilitates expert review of automatic QT intervals, which is still required by regulatory bodies, by providing QRS onset and T offset positions that are consistent with the estimated QT intervals.

Implementing the Point Spread Function Deconvolution for Better Molecular Characterization of Newly Diagnosed Gliomas: A Dynamic 18F-FDOPA PET Radiomics Study.

Purpose: This study aims to investigate the effects of applying the point spread function deconvolution (PSFd) to the radiomics analysis of dynamic L-3,4-dihydroxy-6-[18F]-fluoro-phenyl-alanine (18F-FDOPA) positron emission tomography (PET) images, to non-invasively identify isocitrate dehydrogenase (IDH) mutated and/or 1p/19q codeleted gliomas. Methods: Fifty-seven newly diagnosed glioma patients underwent dynamic 18F-FDOPA imaging on the same digital PET system. All images were reconstructed with and without PSFd. An L1-penalized (Lasso) logistic regression model, with 5-fold cross-validation and 20 repetitions, was trained with radiomics features extracted from the static tumor-to-background-ratio (TBR) and dynamic time-to-peak (TTP) parametric images, as well as a combination of both. Feature importance was assessed using Shapley additive explanation values. Results: The PSFd significantly modified 95% of TBR, but only 79% of TTP radiomics features. Applying the PSFd significantly improved the ability to identify IDH-mutated and/or 1p/19q codeleted gliomas, compared to PET images not processed with PSFd, with respective areas under the curve of 0.83 versus 0.79 and 0.75 versus 0.68 for a combination of static and dynamic radiomics features (p < 0.001). Without the PSFd, four and eight radiomics features contributed to 50% of the model for detecting IDH-mutated and/or 1p/19q codeleted gliomas, respectively. Application of the PSFd reduced this to three and seven contributive radiomics features. Conclusion: Application of the PSFd to dynamic 18F-FDOPA PET imaging significantly improves the detection of molecular parameters in newly diagnosed gliomas, most notably by modifying TBR radiomics features.

A comparative study of the performance of methods for f-wave extraction.

Objective.This study proposes a novel technique for atrial fibrillatory waves (f-waves) extraction and investigates the performance of the proposed method comparing with different f-wave extraction methods.Approach.We propose a novel technique combining a periodic component analysis (PiCA) and echo state network (ESN) for f-waves extraction, denoted PiCA-ESN. PiCA-ESN benefits from the advantages of using both source separation and nonlinear adaptive filtering. PiCA-ESN is evaluated by comparing with other state-of-the-art approaches, which include template subtraction technique based on principal component analysis, spatiotemporal cancellation, nonlinear adaptive filtering using an echo state neural network, and a source separation technique based on PiCA. Quality assessment is performed on a recently published reference database including a large number of simulated ECG signals in atrial fibrillation (AF). The performance of the f-wave extraction methods is evaluated in terms of signal quality metrics (SNR, ΔSNR) and robustness of f-wave features.Main results.The proposed method offers the best signal quality performance, with a ΔSNR of approximately 22 dB across all 8 sets of the reference database, as well as the most robust extraction of f-wave features, with 75% of all estimates of dominant atrial frequency well below 1 Hz.

A hardware and software system for MRI applications requiring external device data.

PURPOSE: Numerous MRI applications require data from external devices. Such devices are often independent of the MRI system, so synchronizing these data with the MRI data is often tedious and limited to offline use. In this work, a hardware and software system is proposed for acquiring data from external devices during MR imaging, for use online (in real-time) or offline. METHODS: The hardware includes a set of external devices - electrocardiography (ECG) devices, respiration sensors, microphone, electronics of the MR system etc. - using various channels for data transmission (analog, digital, optical fibers), all connected to a server through a universal serial bus (USB) hub. The software is based on a flexible client-server architecture, allowing real-time processing pipelines to be configured and executed. Communication protocols and data formats are proposed, in particular for transferring the external device data to an open-source reconstruction software (Gadgetron), for online image reconstruction using external physiological data. The system performance is evaluated in terms of accuracy of the recorded signals and delays involved in the real-time processing tasks. Its flexibility is shown with various applications. RESULTS: The real-time system had low delays and jitters (on the order of 1 ms). Example MRI applications using external devices included: prospectively gated cardiac cine imaging, multi-modal acquisition of the vocal tract (image, sound, and respiration) and online image reconstruction with nonrigid motion correction. CONCLUSION: The performance of the system and its versatile architecture make it suitable for a wide range of MRI applications requiring online or offline use of external device data.

Predict alone, decide together: cardiac abnormality detection based on single lead classifier voting.

Objective. A classifier based on weighted voting of multiple single-lead based models combining deep learning (DL) representation and hand-crafted features was developed to classify 26 cardiac abnormalities from different lead subsets of short-term electrocardiograms (ECG).Approach. A two-stage method was proposed for the multilead prediction. First a lead-agnostic hybrid classifier was trained to predict the pathologies from single-lead ECG signals. The classifier combined fully automated DL features extracted through a convolutional neural network with hand-crafted features through a fully connected layer. Second, a voting of the single-lead based predictions was performed. For the 12-lead subset, voting consisted in an optimised weighting of the output probabilities of all available single lead predictions. For other lead subsets, voting simply consisted in the average of the lead predictions.Main results. This approach achieved a challenge test score of 0.48, 0.47, 0.46, 0.46, 0.45 on the 12, 6, 4, 3, 2-lead subsets respectively on the 2021 Physionet/Computing in Cardiology challenge hidden test set. The use of an hybrid approach and more advanced voting layer improved some individual class classification but did not offer better generalization than our baseline fully DL approach.Significance. The proposed approach showed potential at correctly classifying main cardiac abnormalities and dealt well with reduced lead subsets.

18F-FDOPA PET for the Noninvasive Prediction of Glioma Molecular Parameters: A Radiomics Study.

The assessment of gliomas by 18F-FDOPA PET imaging as an adjunct to MRI showed high performance by combining static and dynamic features to noninvasively predict the isocitrate dehydrogenase (IDH) mutations and the 1p/19q codeletion, which the World Health Organization classified as significant parameters in 2016. The current study evaluated whether other 18F-FDOPA PET radiomics features further improve performance and the contributions of each of these features to performance. Methods: Our study included 72 retrospectively selected, newly diagnosed glioma patients with 18F-FDOPA PET dynamic acquisitions. A set of 114 features, including conventional static features and dynamic features, as well as other radiomics features, were extracted and machine-learning models trained to predict IDH mutations and the 1p/19q codeletion. Models were based on a machine-learning algorithm built from stable, relevant, and uncorrelated features selected by hierarchic clustering followed by a bootstrapped feature selection process. Models were assessed by comparing area under the curve using a nested cross-validation approach. Feature importance was assessed using Shapley additive explanations values. Results: The best models were able to predict IDH mutations (logistic regression with L2 regularization) and the 1p/19q codeletion (support vector machine with radial basis function kernel) with an area under the curve of 0.831 (95% CI, 0.790-0.873) and 0.724 (95% CI, 0.669-0.782), respectively. For the prediction of IDH mutations, dynamic features were the most important features in the model (time to peak, 35.5%). In contrast, other radiomics features were the most useful for predicting the 1p/19q codeletion (up to 14.5% of importance for the small-zone low-gray-level emphasis). Conclusion:18F-FDOPA PET is an effective tool for the noninvasive prediction of glioma molecular parameters using a full set of amino-acid PET radiomics features. The contribution of each feature set shows the importance of systematically integrating dynamic acquisition for prediction of the IDH mutations as well as developing the use of radiomics features in routine practice for prediction of the 1p/19q codeletion.

Relevance of Dynamic 18F-DOPA PET Radiomics for Differentiation of High-Grade Glioma Progression from Treatment-Related Changes.

This study evaluates the relevance of 18F-DOPA PET static and dynamic radiomics for differentiation of high-grade glioma (HGG) progression from treatment-related changes (TRC) by comparing diagnostic performances to the current PET imaging standard of care. Eighty-five patients with histologically confirmed HGG and investigated by dynamic 18F-FDOPA PET in two institutions were retrospectively selected. ElasticNet logistic regression, Random Forest and XGBoost machine models were trained with different sets of features-radiomics extracted from static tumor-to-background-ratio (TBR) parametric images, radiomics extracted from time-to-peak (TTP) parametric images, as well as combination of both-in order to discriminate glioma progression from TRC at 6 months from the PET scan. Diagnostic performances of the models were compared to a logistic regression model with TBRmean ± clinical features used as reference. Training was performed on data from the first center, while external validation was performed on data from the second center. Best radiomics models showed only slightly better performances than the reference model (respective AUCs of 0.834 vs. 0.792, p < 0.001). Our current results show similar findings at the multicentric level using different machine learning models and report a marginal additional value for TBR static and TTP dynamic radiomics over the classical analysis based on TBR values.

Impact of Pretreatment Ischemic Location on Functional Outcome after Thrombectomy.

Pretreatment ischemic location may be an important determinant for functional outcome prediction in acute ischemic stroke. In total, 143 anterior circulation ischemic stroke patients in the THRACE study were included. Ischemic lesions were semi-automatically segmented on pretreatment diffusion-weighted imaging and registered on brain atlases. The percentage of ischemic tissue in each atlas-segmented region was calculated. Statistical models with logistic regression and support vector machine were built to analyze the predictors of functional outcome. The investigated parameters included: age, baseline National Institutes of Health Stroke Scale score, and lesional volume (three-parameter model), together with the ischemic percentage in each atlas-segmented region (four-parameter model). The support vector machine with radial basis functions outperformed logistic regression in prediction accuracy. The support vector machine three-parameter model demonstrated an area under the curve of 0.77, while the four-parameter model achieved a higher area under the curve (0.82). Regions with marked impacts on outcome prediction were the uncinate fasciculus, postcentral gyrus, putamen, middle occipital gyrus, supramarginal gyrus, and posterior corona radiata in the left hemisphere; and the uncinate fasciculus, paracentral lobule, temporal pole, hippocampus, inferior occipital gyrus, middle temporal gyrus, pallidum, and anterior limb of the internal capsule in the right hemisphere. In conclusion, pretreatment ischemic location provided significant prognostic information for functional outcome in ischemic stroke.

An Interpretable Hand-Crafted Feature-Based Model for Atrial Fibrillation Detection.

Atrial Fibrillation (AF) is the most common type of cardiac arrhythmia. Early diagnosis of AF helps to improve therapy and prognosis. Machine Learning (ML) has been successfully applied to improve the effectiveness of Computer-Aided Diagnosis (CADx) systems for AF detection. Presenting an explanation for the decision made by an ML model is considerable from the cardiologists' point of view, which decreases the complexity of the ML model and can provide tangible information in their diagnosis. In this paper, a range of explanation techniques is applied to hand-crafted features based ML models for heart rhythm classification. We validate the impact of the techniques by applying feature selection and classification to the 2017 CinC/PhysioNet challenge dataset. The results show the effectiveness and efficiency of SHapley Additive exPlanations (SHAP) technique along with Random Forest (RF) for the classification of the Electrocardiogram (ECG) signals for AF detection with a mean F-score of 0.746 compared to 0.706 for a technique based on the same features based on a cascaded SVM approach. The study also highlights how this interpretable hand-crafted feature-based model can provide cardiologists with a more compact set of features and tangible information in their diagnosis.