Interpretable deep learning for automatic diagnosis of 12-lead electrocardiogram.
Ontology highlight
ABSTRACT:
SUBMITTER: Zhang D
PROVIDER: S-EPMC8082080 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:The role of automatic electrocardiogram (ECG) analysis in clinical practice is limited by the accuracy of existing models. Deep Neural Networks (DNNs) are models composed of stacked transformations that learn tasks by examples. This technology has recently achieved striking success in a variety of task and there are great expectations on how it might improve clinical practice. Here we present a DNN model trained in a dataset with more than 2 million labeled exams analyzed by the Telehealth Network of Minas Gerais and collected under the scope of the CODE (Clinical Outcomes in Digital Electrocardiology) study. The DNN outperform cardiology resident medical doctors in recognizing 6 types of abnormalities in 12-lead ECG recordings, with F1 scores above 80% and specificity over 99%. These results indicate ECG analysis based on DNNs, previously studied in a single-lead setup, generalizes well to 12-lead exams, taking the technology closer to the standard clinical practice.
| S-EPMC7145824 | biostudies-literature
Project description:Atrial fibrillation (AF) is the most prevalent arrhythmia and is associated with increased morbidity and mortality. Its early detection is challenging because of the low detection yield of conventional methods. We aimed to develop a deep learning-based algorithm to identify AF during normal sinus rhythm (NSR) using 12-lead electrocardiogram (ECG) findings. We developed a new deep neural network to detect subtle differences in paroxysmal AF (PAF) during NSR using digital data from standard 12-lead ECGs. Raw digital data of 2,412 12-lead ECGs were analyzed. The artificial intelligence (AI) model showed that the optimal interval to detect subtle changes in PAF was within 0.24 s before the QRS complex in the 12-lead ECG. We allocated the enrolled ECGs to the training, internal validation, and testing datasets in a 7:1:2 ratio. Regarding AF identification, the AI-based algorithm showed the following values in the internal and external validation datasets: area under the receiver operating characteristic curve, 0.79 and 0.75; recall, 82% and 77%; specificity, 78% and 72%; F1 score, 75% and 74%; and overall accuracy, 72.8% and 71.2%, respectively. The deep learning-based algorithm using 12-lead ECG demonstrated high accuracy for detecting AF during NSR.
| S-EPMC8211689 | biostudies-literature
Project description:AimsThis study aims to assess whether information derived from the raw 12-lead electrocardiogram (ECG) combined with clinical information is predictive of atrial fibrillation (AF) development.Methods and resultsWe use a subset of the Telehealth Network of Minas Gerais (TNMG) database consisting of patients that had repeated 12-lead ECG measurements between 2010 and 2017 that is 1 130 404 recordings from 415 389 unique patients. Median and interquartile of age for the recordings were 58 (46-69) and 38% of the patients were males. Recordings were assigned to train-validation and test sets in an 80:20% split which was stratified by class, age and gender. A random forest classifier was trained to predict, for a given recording, the risk of AF development within 5 years. We use features obtained from different modalities, namely demographics, clinical information, engineered features, and features from deep representation learning. The best model performance on the test set was obtained for the model combining features from all modalities with an area under the receiver operating characteristic curve (AUROC) = 0.909 against the best single modality model which had an AUROC = 0.839.ConclusionOur study has important clinical implications for AF management. It is the first study integrating feature engineering, deep learning, and Electronic medical record system (EMR) metadata to create a risk prediction tool for the management of patients at risk of AF. The best model that includes features from all modalities demonstrates that human knowledge in electrophysiology combined with deep learning outperforms any single modality approach. The high performance obtained suggest that structural changes in the 12-lead ECG are associated with existing or impending AF.
| S-EPMC9707938 | biostudies-literature
Project description:BackgroundPredicting the origin of premature ventricular contraction (PVC) from the preoperative electrocardiogram (ECG) is important for catheter ablation therapies. We propose an explainable method that localizes PVC origin based on the semantic segmentation result of a 12-lead ECG using a deep neural network, considering suitable diagnosis support for clinical application.MethodsThe deep learning-based semantic segmentation model was trained using 265 12-lead ECG recordings from 84 patients with frequent PVCs. The model classified each ECG sampling time into four categories: background (BG), sinus rhythm (SR), PVC originating from the left ventricular outflow tract (PVC-L), and PVC originating from the right ventricular outflow tract (PVC-R). Based on the ECG segmentation results, a rule-based algorithm classified ECG recordings into three categories: PVC-L, PVC-R, as well as Neutral, which is a group for the recordings requiring the physician's careful assessment before separating them into PVC-L and PVC-R. The proposed method was evaluated with a public dataset which was used in previous research.ResultsThe evaluation of the proposed method achieved neutral rate, accuracy, sensitivity, specificity, F1-score, and area under the curve of 0.098, 0.932, 0.963, 0.882, 0.945, and 0.852 on a private dataset, and 0.284, 0.916, 0.912, 0.930, 0.943, and 0.848 on a public dataset, respectively. These quantitative results indicated that the proposed method outperformed almost all previous studies, although a significant number of recordings resulted in requiring the physician's assessment.ConclusionsThe feasibility of explainable localization of premature ventricular contraction was demonstrated using deep learning-based semantic segmentation of 12-lead ECG.Clinical trial registration: M26-148-8.
| S-EPMC11317653 | biostudies-literature
Project description:BackgroundLong-term monitoring of Electrocardiogram (ECG) recordings is crucial to diagnose arrhythmias. Clinicians can find it challenging to diagnose arrhythmias, and this is a particular issue in more remote and underdeveloped areas. The development of digital ECG and AI methods could assist clinicians who need to diagnose arrhythmias outside of the hospital setting.MethodsWe constructed a large-scale Chinese ECG benchmark dataset using data from 272,753 patients collected from January 2017 to December 2021. The dataset contains ECG recordings from all common arrhythmias present in the Chinese population. Several experienced cardiologists from Shanghai First People's Hospital labeled the dataset. We then developed a deep learning-based multi-label interpretable diagnostic model from the ECG recordings. We utilized Accuracy, F1 score and AUC-ROC to compare the performance of our model with that of the cardiologists, as well as with six comparison models, using testing and hidden data sets.ResultsThe results show that our approach achieves an F1 score of 83.51%, an average AUC ROC score of 0.977, and 93.74% mean accuracy for 6 common arrhythmias. Results from the hidden dataset demonstrate the performance of our approach exceeds that of cardiologists. Our approach also highlights the diagnostic process.ConclusionsOur diagnosis system has superior diagnostic performance over that of clinicians. It also has the potential to help clinicians rapidly identify abnormal regions on ECG recordings, thus improving efficiency and accuracy of clinical ECG diagnosis in China. This approach could therefore potentially improve the productivity of out-of-hospital ECG diagnosis and provides a promising prospect for telemedicine.
| S-EPMC10901870 | biostudies-literature
Project description:BACKGROUND The correct interpretation of the ECG is pivotal for the accurate diagnosis of many cardiac abnormalities, and conventional computerized interpretation has not been able to reach physician-level accuracy in detecting (acute) cardiac abnormalities. This study aims to develop and validate a deep neural network for comprehensive automated ECG triage in daily practice. METHODS AND RESULTS We developed a 37-layer convolutional residual deep neural network on a data set of free-text physician-annotated 12-lead ECGs. The deep neural network was trained on a data set with 336.835 recordings from 142.040 patients and validated on an independent validation data set (n=984), annotated by a panel of 5 cardiologists electrophysiologists. The 12-lead ECGs were acquired in all noncardiology departments of the University Medical Center Utrecht. The algorithm learned to classify these ECGs into the following 4 triage categories: normal, abnormal not acute, subacute, and acute. Discriminative performance is presented with overall and category-specific concordance statistics, polytomous discrimination indexes, sensitivities, specificities, and positive and negative predictive values. The patients in the validation data set had a mean age of 60.4 years and 54.3% were men. The deep neural network showed excellent overall discrimination with an overall concordance statistic of 0.93 (95% CI, 0.92-0.95) and a polytomous discriminatory index of 0.83 (95% CI, 0.79-0.87). CONCLUSIONS This study demonstrates that an end-to-end deep neural network can be accurately trained on unstructured free-text physician annotations and used to consistently triage 12-lead ECGs. When further fine-tuned with other clinical outcomes and externally validated in clinical practice, the demonstrated deep learning-based ECG interpretation can potentially improve time to treatment and decrease healthcare burden.
| S-EPMC7660886 | biostudies-literature
Project description:Parkinson's disease (PD) diagnosis based on magnetic resonance imaging (MRI) is still challenging clinically. Quantitative susceptibility maps (QSM) can potentially provide underlying pathophysiological information by detecting the iron distribution in deep gray matter (DGM) nuclei. We hypothesized that deep learning (DL) could be used to automatically segment all DGM nuclei and use relevant features for a better differentiation between PD and healthy controls (HC). In this study, we proposed a DL-based pipeline for automatic PD diagnosis based on QSM and T1-weighted (T1W) images. This consists of (1) a convolutional neural network model integrated with multiple attention mechanisms which simultaneously segments caudate nucleus, globus pallidus, putamen, red nucleus, and substantia nigra from QSM and T1W images, and (2) an SE-ResNeXt50 model with an anatomical attention mechanism, which uses QSM data and the segmented nuclei to distinguish PD from HC. The mean dice values for segmentation of the five DGM nuclei are all >0.83 in the internal testing cohort, suggesting that the model could segment brain nuclei accurately. The proposed PD diagnosis model achieved area under the the receiver operating characteristic curve (AUCs) of 0.901 and 0.845 on independent internal and external testing cohorts, respectively. Gradient-weighted class activation mapping (Grad-CAM) heatmaps were used to identify contributing nuclei for PD diagnosis on patient level. In conclusion, the proposed approach can potentially be used as an automatic, explainable pipeline for PD diagnosis in a clinical setting.
| S-EPMC10365226 | biostudies-literature
Project description:Rice disease has serious negative effects on crop yield, and the correct diagnosis of rice diseases is the key to avoid these effects. However, the existing disease diagnosis methods for rice are neither accurate nor efficient, and special equipment is often required. In this study, an automatic diagnosis method was developed and implemented in a smartphone app. The method was developed using deep learning based on a large dataset that contained 33,026 images of six types of rice diseases: leaf blast, false smut, neck blast, sheath blight, bacterial stripe disease, and brown spot. The core of the method was the Ensemble Model in which submodels were integrated. Finally, the Ensemble Model was validated using a separate set of images. Results showed that the three best submodels were DenseNet-121, SE-ResNet-50, and ResNeSt-50, in terms of several attributes, such as, learning rate, precision, recall, and disease recognition accuracy. Therefore, these three submodels were selected and integrated in the Ensemble Model. The Ensemble Model minimized confusion among the different types of disease, reducing misdiagnosis of the disease. Using the Ensemble Model to diagnose six types of rice diseases, an overall accuracy of 91% was achieved, which is considered to be reasonably good, considering the appearance similarities in some types of rice disease. The smartphone app allowed the client to use the Ensemble Model on the web server through a network, which was convenient and efficient for the field diagnosis of rice leaf blast, false smut, neck blast, sheath blight, bacterial stripe disease, and brown spot.
| S-EPMC8416767 | biostudies-literature
Project description:AimsAtrial flutter (AFlut) is a common re-entrant atrial tachycardia driven by self-sustainable mechanisms that cause excitations to propagate along pathways different from sinus rhythm. Intra-cardiac electrophysiological mapping and catheter ablation are often performed without detailed prior knowledge of the mechanism perpetuating AFlut, likely prolonging the procedure time of these invasive interventions. We sought to discriminate the AFlut location [cavotricuspid isthmus-dependent (CTI), peri-mitral, and other left atrium (LA) AFlut classes] with a machine learning-based algorithm using only the non-invasive signals from the 12-lead electrocardiogram (ECG).Methods and resultsHybrid 12-lead ECG dataset of 1769 signals was used (1424 in silico ECGs, and 345 clinical ECGs from 115 patients-three different ECG segments over time were extracted from each patient corresponding to single AFlut cycles). Seventy-seven features were extracted. A decision tree classifier with a hold-out classification approach was trained, validated, and tested on the dataset randomly split after selecting the most informative features. The clinical test set comprised 38 patients (114 clinical ECGs). The classifier yielded 76.3% accuracy on the clinical test set with a sensitivity of 89.7%, 75.0%, and 64.1% and a positive predictive value of 71.4%, 75.0%, and 86.2% for CTI, peri-mitral, and other LA class, respectively. Considering majority vote of the three segments taken from each patient, the CTI class was correctly classified at 92%.ConclusionOur results show that a machine learning classifier relying only on non-invasive signals can potentially identify the location of AFlut mechanisms. This method could aid in planning and tailoring patient-specific AFlut treatments.
| S-EPMC9301972 | biostudies-literature
Project description:BackgroundIdentifying which individuals will develop tuberculosis (TB) remains an unresolved problem due to few animal models and computational approaches that effectively address its heterogeneity. To meet these shortcomings, we show that Diversity Outbred (DO) mice reflect human-like genetic diversity and develop human-like lung granulomas when infected with Mycobacterium tuberculosis (M.tb) .MethodsFollowing M.tb infection, a "supersusceptible" phenotype develops in approximately one-third of DO mice characterized by rapid morbidity and mortality within 8 weeks. These supersusceptible DO mice develop lung granulomas patterns akin to humans. This led us to utilize deep learning to identify supersusceptibility from hematoxylin & eosin (H&E) lung tissue sections utilizing only clinical outcomes (supersusceptible or not-supersusceptible) as labels.FindingsThe proposed machine learning model diagnosed supersusceptibility with high accuracy (91.50 ± 4.68%) compared to two expert pathologists using H&E stained lung sections (94.95% and 94.58%). Two non-experts used the imaging biomarker to diagnose supersusceptibility with high accuracy (88.25% and 87.95%) and agreement (96.00%). A board-certified veterinary pathologist (GB) examined the imaging biomarker and determined the model was making diagnostic decisions using a form of granuloma necrosis (karyorrhectic and pyknotic nuclear debris). This was corroborated by one other board-certified veterinary pathologist. Finally, the imaging biomarker was quantified, providing a novel means to convert visual patterns within granulomas to data suitable for statistical analyses.ImplicationsOverall, our results have translatable implication to improve our understanding of TB and also to the broader field of computational pathology in which clinical outcomes alone can drive automatic identification of interpretable imaging biomarkers, knowledge discovery, and validation of existing clinical biomarkers.FundingNational Institutes of Health and American Lung Association.
| S-EPMC7658666 | biostudies-literature