Deep learning analysis of the myocardium in coronary CT angiography for identification of patients with functionally significant coronary artery stenosis

In patients with coronary artery stenoses of intermediate severity, the functional significance needs to be determined. Fractional flow reserve (FFR) measurement, performed during invasive coronary angiography (ICA), is most often used in clinical practice. To reduce the number of ICA procedures, we present a method for automatic identification of patients with functionally significant coronary artery stenoses, employing deep learning analysis of the left ventricle (LV) myocardium in rest coronary CT angiography (CCTA). The study includes consecutively acquired CCTA scans of 166 patients who underwent invasive FFR measurements. To identify patients with a functionally significant coronary artery stenosis, analysis is performed in several stages. First, the LV myocardium is segmented using a multiscale convolutional neural network (CNN). To characterize the segmented LV myocardium, it is subsequently encoded using unsupervised convolutional autoencoder (CAE). As ischemic changes are expected to appear locally, the LV myocardium is divided into a number of spatially connected clusters, and statistics of the encodings are computed as features. Thereafter, patients are classified according to the presence of functionally significant stenosis using an SVM classifier based on the extracted features. Quantitative evaluation of LV myocardium segmentation in 20 images resulted in an average Dice coefficient of 0.91 and an average mean absolute distance between the segmented and reference LV boundaries of 0.7 mm. Twenty CCTA images were used to train the LV myocardium encoder. Classification of patients was evaluated in the remaining 126 CCTA scans in 50 10-fold cross-validation experiments and resulted in an area under the receiver operating characteristic curve of 0.74 ± 0.02. At sensitivity levels 0.60, 0.70 and 0.80, the corresponding specificity was 0.77, 0.71 and 0.59, respectively. The results demonstrate that automatic analysis of the LV myocardium in a single CCTA scan acquired at rest, without assessment of the anatomy of the coronary arteries, can be used to identify patients with functionally significant coronary artery stenosis. This might reduce the number of patients undergoing unnecessary invasive FFR measurements.

A convolutional autoencoder approach for mining features in cellular electron cryo-tomograms and weakly supervised coarse segmentation

Cellular electron cryo-tomography enables the 3D visualization of cellular organization in the near-native state and at submolecular resolution. However, the contents of cellular tomograms are often complex, making it difficult to automatically isolate different in situ cellular components. In this paper, we propose a convolutional autoencoder-based unsupervised approach to provide a coarse grouping of 3D small subvolumes extracted from tomograms. We demonstrate that the autoencoder can be used for efficient and coarse characterization of features of macromolecular complexes and surfaces, such as membranes. In addition, the autoencoder can be used to detect non-cellular features related to sample preparation and data collection, such as carbon edges from the grid and tomogram boundaries. The autoencoder is also able to detect patterns that may indicate spatial interactions between cellular components. Furthermore, we demonstrate that our autoencoder can be used for weakly supervised semantic segmentation of cellular components, requiring a very small amount of manual annotation.

Unsupervised learning framework for temperature compensated damage identification and localization in ultrasonic guided wave SHM with transfer learning

Damage localization algorithms for ultrasonic guided wave-based structural health monitoring (GW-SHM) typically utilize manually-defined features and supervised machine learning on data collected under various conditions. This scheme has limitations that affect prediction accuracy in practical settings when the model encounters data with a distribution different from that used for training, especially due to variation in environmental factors (e.g., temperature) and types of damages. While deep learning based models that overcome these limitations have been reported in literature, they typically comprise of millions of trainable parameters. As an alternative, we propose an unsupervised approach for temperature-compensated damage identification and localization in GW-SHM systems based on transferring learning from a convolutional auto encoder (TL-CAE). Remarkably, without using signals corresponding to the damages during training (unsupervised), our method demonstrates more accurate damage detection and localization as well as robustness to temperature variations than supervised approaches reported on the publicly available Open Guided Waves (OGW) dataset. Additionally, we have demonstrated reduction in number of trainable parameters using transfer learning (TL) to leverage similarities between time-series among various sensor paths. It is also worth noting that the proposed framework uses raw time-domain signals, without any pre-processing or knowledge of material properties. It should therefore be scalable and adaptable for other materials, structures, damages, and temperature ranges, should more data become available in the future. We present an extensive parametric study to demonstrate feasibility of the proposed method.

Detection of protein, starch, oil, and moisture content of corn kernels using one-dimensional convolutional autoencoder and near-infrared spectroscopy

Background

Analysis of the nutritional values and chemical composition of grain products plays an essential role in determining the quality of the products. Near-infrared spectroscopy has attracted the attention of researchers in recent years due to its advantages in the analysis process. However, preprocessing and regression models in near-infrared spectroscopy are usually determined by trial and error. Combining newly popular deep learning algorithms with near-infrared spectroscopy has brought a new perspective to this area.

Methods

This article presents a new method that combines a one-dimensional convolutional autoencoder with near-infrared spectroscopy to analyze the protein, moisture, oil, and starch content of corn kernels. First, a one-dimensional convolutional autoencoder model was created for three different spectra in the corn dataset. Thirty-two latent variables were obtained for each spectrum, which is a low-dimensional spectrum representation. Multiple linear regression models were built for each target using the latent variables of obtained autoencoder models.

Results

R², RMSE, and RMSPE were used to show the performance of the proposed model. The created one-dimensional convolutional autoencoder model achieved a high reconstruction rate with a mean RMSPE value of 1.90% and 2.27% for calibration and prediction sets, respectively. This way, a spectrum with 700 features was converted to only 32 features. The created MLR models which use these features as input were compared to partial least squares regression and principal component regression combined with various preprocessing methods. Experimental results indicate that the proposed method has superior performance, especially in MP5 and MP6 datasets.

Machine learning enhanced evaluation of semiconductor quantum dots

A key challenge in quantum photonics today is the efficient and on-demand generation of high-quality single photons and entangled photon pairs. In this regard, one of the most promising types of emitters are semiconductor quantum dots, fluorescent nanostructures also described as artificial atoms. The main technological challenge in upscaling to an industrial level is the typically random spatial and spectral distribution in their growth. Furthermore, depending on the intended application, different requirements are imposed on a quantum dot, which are reflected in its spectral properties. Given that an in-depth suitability analysis is lengthy and costly, it is common practice to pre-select promising candidate quantum dots using their emission spectrum. Currently, this is done by hand. Therefore, to automate and expedite this process, in this paper, we propose a data-driven machine-learning-based method of evaluating the applicability of a semiconductor quantum dot as single photon source. For this, first, a minimally redundant, but maximally relevant feature representation for quantum dot emission spectra is derived by combining conventional spectral analysis with an autoencoding convolutional neural network. The obtained feature vector is subsequently used as input to a neural network regression model, which is specifically designed to not only return a rating score, gauging the technical suitability of a quantum dot, but also a measure of confidence for its evaluation. For training and testing, a large dataset of self-assembled InAs/GaAs semiconductor quantum dot emission spectra is used, partially labelled by a team of experts in the field. Overall, highly convincing results are achieved, as quantum dots are reliably evaluated correctly. Note, that the presented methodology can account for different spectral requirements and is applicable regardless of the underlying photonic structure, fabrication method and material composition. We therefore consider it the first step towards a fully integrated evaluation framework for quantum dots, proving the use of machine learning beneficial in the advancement of future quantum technologies.

Enhanced reptile search optimization with convolutional autoencoder for soil nutrient classification model

Background

Soil nutrients play an important role in soil fertility and other environmental factors. Soil testing is an effective tool for evaluating soil nutrient levels and calculating the appropriate quantitative of soil nutrients based on fertility and crop requirements. Because traditional soil nutrient testing models are impractical for real-time applications, efficient soil nutrient and potential hydrogen (pH) prediction models are required to improve overall crop productivity. Soil testing is an effective method to evaluate the presence of nutrient status of soil and assists in determining appropriate nutrient quantity.

Methods

Various machine learning (ML) models proposed, predict the soil nutrients, soil type, and soil moisture. To assess the significant soil nutrient content, this study develops an enhanced reptile search optimization with convolutional autoencoder (ERSOCAE-SNC) model for classifying and predicting the fertility indices. The model majorly focuses on the soil test reports. For classification, CAE model is applied which accurately determines the nutrient levels such as phosphorus (P), available potassium (K), organic carbon (OC), boron (B) and soil pH level. Since the trial-and-error method for hyperparameter tuning of CAE model is a tedious and erroneous process, the ERSO algorithm has been utilized which in turn enhances the classification performance. Besides, the ERSO algorithm is derived by incorporating the chaotic concepts into the RSO algorithm.

Results

Finally, the influence of the ERSOCAE-SNC model is examined using a series of simulations. The ERSOCAE-SNC model reported best results over other approaches and produces an accuracy of 98.99% for soil nutrients and 99.12% for soil pH. The model developed for the ML decision systems will help the Tamil Nadu government to manage the problems in soil nutrient deficiency and improve the soil health and environmental quality. Also reduces the input expenditures of fertilizers and saves time of soil experts.

Development of weighted residual RNN model with hybrid heuristic algorithm for movement recognition framework in ambient assisted living

In healthcare applications, automatic and intelligent movement recognition systems in Ambient Assisted Living (AAL) are designed for elderly and disabled persons. The AAL provides assistance as well as secure feelings to disabled persons and elderly individuals. In AAL, the movement recognition process has been emerging in recent days. The automatic and safe living of the disabled person is ensured by performing movement recognition in AAL. Movement recognition in the AAL is developed for disabled and elderly people and is also performed to provide healthcare assistance to the elderly and disabled person. The weighted deep learning model and a hybrid heuristic algorithm are proposed to achieve this goal. The required input data is initially gathered from the standard data sources. Subsequently, the essential deep features are extracted from the input data using a Convolutional Autoencoder. Finally, the resultant features are subjected to the movement recognition model, termed as Weighted Residual Recurrent Neural Network. For achieving a better training and testing process, the weights in the RRNN model are optimally selected by using the hybrid algorithm named Hybrid Rat Swarm with Coati Optimization Algorithm, which is developed with the integration of the Rat Warm Optimization and Coati Optimization. The movement recognition results are used for providing medical assistance to elderly and disabled persons. Lastly, the efficacy of the suggested strategy is validated with different measures. From the experiments, the proposed system attains standard results in terms of improved system performance and accuracy that can aid in significantly recognizing human movements.

Anomaly detection in genomic catalogues using unsupervised multi-view autoencoders

Background

Accurate identification of Transcriptional Regulator binding locations is essential for analysis of genomic regions, including Cis Regulatory Elements. The customary NGS approaches, predominantly ChIP-Seq, can be obscured by data anomalies and biases which are difficult to detect without supervision.

Results

Here, we develop a method to leverage the usual combinations between many experimental series to mark such atypical peaks. We use deep learning to perform a lossy compression of the genomic regions’ representations with multiview convolutions. Using artificial data, we show that our method correctly identifies groups of correlating series and evaluates CRE according to group completeness. It is then applied to the ReMap database’s large volume of curated ChIP-seq data. We show that peaks lacking known biological correlators are singled out and less confirmed in real data. We propose normalization approaches useful in interpreting black-box models.

Conclusion

Our approach detects peaks that are less corroborated than average. It can be extended to other similar problems, and can be interpreted to identify correlation groups. It is implemented in an open-source tool called atyPeak.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-021-04359-2.

Latent space representation of electronic health records for clustering dialysis-associated kidney failure subtypes

OBJECTIVE

Kidney failure manifests in various forms, from sudden occurrences such as Acute Kidney Injury (AKI) to progressive like Chronic Kidney Disease (CKD). Given its intricate nature, marked by overlapping comorbidities and clinical similarities-including treatment modalities like dialysis-we sought to design and validate an end-to-end framework for clustering kidney failure subtypes.

MATERIALS AND METHODS

Our emphasis was on dialysis, utilizing a comprehensive dataset from the UK Biobank (UKB). We transformed raw Electronic Health Record (EHR) data into standardized matrices that incorporate patient demographics, clinical visit data, and the innovative feature of visit time-gaps. This matrix structure was achieved using a unique data cutting method. Latent space transformation was facilitated using a convolution autoencoder (ConvAE) model, which was then subjected to clustering using Principal Component Analysis (PCA) and K-means algorithms.

RESULTS

Our transformation model effectively reduced data dimensionality, thereby accelerating computational processes. The derived latent space demonstrated remarkable clustering capacities. Through cluster analysis, two distinct groups were identified: CKD-majority (cluster 1) and a mixed group of non-CKD and some CKD subtypes (cluster 0). Cluster 1 exhibited notably low survival probability, suggesting it predominantly represented severe CKD. In contrast, cluster 0, with substantially higher survival probability, likely to include milder CKD forms and severe AKI. Our end-to-end framework effectively differentiates kidney failure subtypes using the UKB dataset, offering potential for nuanced therapeutic interventions.

CONCLUSIONS

This innovative approach integrates diverse data sources, providing a holistic understanding of kidney failure, which is imperative for patient management and targeted therapeutic interventions.

A fault diagnosis method for rolling bearings in open-set domain adaptation with adversarial learning

The closed-set assumption often fails in practical industrial applications, especially considering diverse working conditions where the data distribution may differ significantly. In light of this, a domain adaptation method with adversarial learning is designed for open-set fault diagnosis. Firstly, convolutional autoencoder is developed to distill the fault features; Secondly, an unknown boundary by weighting the similarity between known and unknown classes is established, to ensure shared class alignment between domains while classifying known classes across domains and identifying unknown fault samples. Finally, the diagnostic performance is evaluated using three sets of rolling bearing datasets. The proposed method achieved average diagnostic F1-scores of 96.60%, 96.56%, and 96.62% on these datasets, respectively. The results demonstrate that the method effectively rejects unknown fault data in the target domain while aligning known classes, validating its fault diagnosis capability under the open-world assumption.

A multi-stage transfer learning strategy for diagnosing a class of rare laryngeal movement disorders

BACKGROUND

It remains hard to directly apply deep learning-based methods to assist diagnosing essential tremor of voice (ETV) and abductor and adductor spasmodic dysphonia (ABSD and ADSD). One of the main challenges is that, as a class of rare laryngeal movement disorders (LMDs), there are limited available databases to be investigated. Another worthy explored research question is which above sub-disorder benefits most from diagnosis based on sustained phonations. The question is from the fact that sustained phonations can help detect pathological voice from healthy voice.

METHOD

A transfer learning strategy is developed for LMD diagnosis with limited data, which consists of three fundamental parts. (1) An extra vocally healthy database from the International Dialects of English Archive (IDEA) is employed to pre-train a convolutional autoencoder. (2) The transferred proportion of the pre-trained encoder is explored. And its impact on LMD diagnosis is also evaluated, yielding a two-stage transfer model. (3) A third stage is designed following the initial two stages to embed information of pathological sustained phonation into the model. This stage verifies the different effects of applying sustained phonation on diagnosing the three sub-disorders, and helps boost the final diagnostic performance.

RESULTS

The analysis in this study is based on clinician-labeled LMD data obtained from the Vanderbilt University Medical Center (VUMC). We find that diagnosing ETV shows sensitivity to sustained phonation within the current database. Meanwhile, the results show that the proposed multi-stage transfer learning strategy can produce (1) accuracy of 65.3% on classifying normal and other three sub-disorders all at once, (2) accuracy of 85.3% in differentiating normal, ABSD, and ETV, and (3) accuracy of 77.7% for normal, ADSD and ETV. These findings demonstrate the effectiveness of the proposed approach.

Privacy-protecting behaviours of risk detection in people with dementia using videos

BACKGROUND

People living with dementia often exhibit behavioural and psychological symptoms of dementia that can put their and others' safety at risk. Existing video surveillance systems in long-term care facilities can be used to monitor such behaviours of risk to alert the staff to prevent potential injuries or death in some cases. However, these behaviours of risk events are heterogeneous and infrequent in comparison to normal events. Moreover, analysing raw videos can also raise privacy concerns.

PURPOSE

In this paper, we present two novel privacy-protecting video-based anomaly detection approaches to detect behaviours of risks in people with dementia.

METHODS

We either extracted body pose information as skeletons or used semantic segmentation masks to replace multiple humans in the scene with their semantic boundaries. Our work differs from most existing approaches for video anomaly detection that focus on appearance-based features, which can put the privacy of a person at risk and is also susceptible to pixel-based noise, including illumination and viewing direction. We used anonymized videos of normal activities to train customized spatio-temporal convolutional autoencoders and identify behaviours of risk as anomalies.

RESULTS

We showed our results on a real-world study conducted in a dementia care unit with patients with dementia, containing approximately 21 h of normal activities data for training and 9 h of data containing normal and behaviours of risk events for testing. We compared our approaches with the original RGB videos and obtained a similar area under the receiver operating characteristic curve performance of 0.807 for the skeleton-based approach and 0.823 for the segmentation mask-based approach.

CONCLUSIONS

This is one of the first studies to incorporate privacy for the detection of behaviours of risks in people with dementia. Our research opens up new avenues to reduce injuries in long-term care homes, improve the quality of life of residents, and design privacy-aware approaches for people living in the community.

CystNet: An AI driven model for PCOS detection using multilevel thresholding of ultrasound images

Polycystic Ovary Syndrome (PCOS) is a widespread endocrinological dysfunction impacting women of reproductive age, categorized by excess androgens and a variety of associated syndromes, consisting of acne, alopecia, and hirsutism. It involves the presence of multiple immature follicles in the ovaries, which can disrupt normal ovulation and lead to hormonal imbalances and associated health complications. Routine diagnostic methods rely on manual interpretation of ultrasound (US) images and clinical assessments, which are time-consuming and prone to errors. Therefore, implementing an automated system is essential for streamlining the diagnostic process and enhancing accuracy. By automatically analyzing follicle characteristics and other relevant features, this research aims to facilitate timely intervention and reduce the burden on healthcare professionals. The present study proposes an advanced automated system for detecting and classifying PCOS from ultrasound images. Leveraging Artificial Intelligence (AI) based techniques, the system examines affected and unaffected cases to enhance diagnostic accuracy. The pre-processing of input images incorporates techniques such as image resizing, normalization, augmentation, Watershed technique, multilevel thresholding, etc. approaches for precise image segmentation. Feature extraction is facilitated by the proposed CystNet technique, followed by PCOS classification utilizing both fully connected layers with 5-fold cross-validation and traditional machine learning classifiers. The performance of the model is rigorously evaluated using a comprehensive range of metrics, incorporating AUC score, accuracy, specificity, precision, F1-score, recall, and loss, along with a detailed confusion matrix analysis. The model demonstrated a commendable accuracy of [Formula: see text] when utilizing a fully connected classification layer, as determined by a thorough 5-fold cross-validation process. Additionally, it has achieved an accuracy of [Formula: see text] when employing an ensemble ML classifier. This proposed approach could be suggested for predicting PCOS or similar diseases using datasets that exhibit multimodal characteristics.

Predicting the influence of extreme temperatures on grain production in the Middle-Lower Yangtze Plains using a spatially-aware deep learning model

Grain crops are vulnerable to anthropogenic climate change and extreme temperature events. Despite this, previous studies have often neglected the impact of the spatio-temporal distribution of extreme temperature events on regional grain outputs. This research focuses on the Middle-Lower Yangtze Plains and aims to address this gap as well as to provide a renewed projection of climate-induced grain production variability for the rest of the century. The proposed model performs significantly superior to the benchmark multilinear grain production model. By 2100, grain production in the MLYP is projected to decrease by over 100 tons for the low-radiative-forcing/sustainable development scenario (SSP126) and the medium-radiative-forcing scenario (SSP245), and about 270 tons for the high-radiative-forcing/fossil-fueled development scenario (SSP585). Grain production may experience less decline than previously projected by studies using Representative Concentration Pathways. This difference is likely due to a decrease in coldwave frequency, which can offset the effects of more frequent heatwaves on grain production, combined with alterations in supply-side policies. Notably, the frequency of encoded heatwaves and coldwaves has a stronger impact on grain production compared to precipitation and labor indicators; higher levels of projected heatwaves frequency correspond with increased output variability over time. This study emphasizes the need for developing crop-specific mitigation/adaptation strategies against heat and cold stress amidst global warming.

Multi-objective Genetic Algorithm Based Deep Learning Model for Automated COVID-19 Detection Using Medical Image Data

Purpose

In early 2020, the world is amid a significant pandemic due to the novel coronavirus disease outbreak, commonly called the COVID-19. Coronavirus is a lung infection disease caused by the Severe Acute Respiratory Syndrome Coronavirus 2 virus (SARS-CoV-2). Because of its high transmission rate, it is crucial to detect cases as soon as possible to effectively control the spread of this pandemic and treat patients in the early stages. RT-PCR-based kits are the current standard kits used for COVID-19 diagnosis, but these tests take much time despite their high precision. A faster automated diagnostic tool is required for the effective screening of COVID-19.

Methods

In this study, a new semi-supervised feature learning technique is proposed to screen COVID-19 patients using chest CT scans. The model proposed in this study uses a three-step architecture, consisting of a convolutional autoencoder based unsupervised feature extractor, a multi-objective genetic algorithm (MOGA) based feature selector, and a Bagging Ensemble of support vector machines based binary classifier. The proposed architecture has been designed to provide precise and robust diagnostics for binary classification (COVID vs.nonCOVID). A dataset of 1252 COVID-19 CT scan images, collected from 60 patients, has been used to train and evaluate the model.

Results

The best performing classifier within 127 ms per image achieved an accuracy of 98.79%, the precision of 98.47%, area under curve of 0.998, and an F1 score of 98.85% on 497 test images. The proposed model outperforms the current state of the art COVID-19 diagnostic techniques in terms of speed and accuracy.

Conclusion

The experimental results prove the superiority of the proposed methodology in comparison to existing methods.The study also comprehensively compares various feature selection techniques and highlights the importance of feature selection in medical image data problems.

CLELNet: A continual learning network for esophageal lesion analysis on endoscopic images

BACKGROUND AND OBJECTIVE

A deep learning-based intelligent diagnosis system can significantly reduce the burden of endoscopists in the daily analysis of esophageal lesions. Considering the need to add new tasks in the diagnosis system, a deep learning model that can train a series of tasks incrementally using endoscopic images is essential for identifying the types and regions of esophageal lesions.

METHOD

In this paper, we proposed a continual learning-based esophageal lesion network (CLELNet), in which a convolutional autoencoder was designed to extract representation features of endoscopic images among different esophageal lesions. The proposed CLELNet consists of shared layers and task-specific layers. Shared layers are used to extract common features among different lesions while task-specific layers can complete different tasks. The first two tasks trained by the CLELNet are the classification (task 1) and the segmentation (task 2). We collected a dataset of esophageal endoscopic images from Macau Kiang Wu Hospital for training and testing the CLELNet.

RESULTS

The experimental results showed that the classification accuracy of task 1 was 95.96%, and the Intersection Over Union and the Dice Similarity Coefficient of task 2 were 65.66% and 78.08%, respectively.

CONCLUSIONS

The proposed CLELNet can realize task-incremental learning without forgetting the previous tasks and thus become a useful computer-aided diagnosis system in esophageal lesions analysis.

Using ECG signals for hypotensive episode prediction in trauma patients

BACKGROUND AND OBJECTIVES

Bleeding is the leading cause of death among trauma patients both in military and civilian scenarios, and it is also the most common cause of preventable death. Identifying a casualty who suffers from an internal bleeding and may deteriorate rapidly and develop hemorrhagic shock and multiorgan failure is a profound challenge. Blood pressure and heart rate are the main vital signs used nowadays for the casualty clinical evaluation in the battlefield and in intensive care unit. However, these vitals tend to deteriorate at a relatively late stage, when the ability to prevent hazardous complications is limited. Identifying, treating, and rapidly evacuating such casualties might mitigate these complications. In this work, we try to improve a state-of-the-art method for early identification of Hypotensive Episode (HE), by adding electrocardiogram signals to several vital signs.

METHODS

In this research, we propose to extend the state-of-the-art HE early detection method, In-Window Segmentation (InWise), by adding new types of features extracted from ECG signals. The new predictive features can be extracted from ECG signals both manually and automatically by a convolutional auto-encoder. In addition to InWise, we are trying to predict HE using a Transformer model. The Transformer is using the encoder output as an embedding of the ECG signal. The proposed approach is evaluated on trauma patients data from the MIMIC III database.

RESULTS

We evaluated the InWise prediction algorithm using four different groups of features. The first feature group contains the 93 original features extracted from vital signs. The second group contains, in addition to the original features, 24 features extracted manually from ECG signal (117 features in total). The third group contains the original features and 20 ECG features extracted by the AE (113 features in total), and the last group is the union of all three previous groups containing 137 features. The results show that each model, which has used ECG data, is outperforming the original InWise model, in terms of AUC and sensitivity with p-value <0.001 (by 0.7% in AUC and up to 3.8% in sensitivity). The model which has used all three feature types (vital signs, manual ECG and AE ECG), outperforms the original model both in terms of accuracy and specificity with p-value <0.001 (by 0.3% and 0.4% respectively).

CONCLUSION

The results show an improvement in the prediction success rates as a result of using ECG-based features. The importance of ECG features was confirmed by the feature importance analysis.