Multilayer Convolutional Neural Network Research Articles

AACFlow: an end-to-end model based on attention augmented convolutional neural network and flow-attention mechanism for identification of anticancer peptides.

Anticancer peptides (ACPs) have natural cationic properties and can act on the anionic cell membrane of cancer cells to kill cancer cells. Therefore, ACPs have become a potential anticancer drug with good research value and prospect. In this article, we propose AACFlow, an end-to-end model for identification of ACPs based on deep learning. End-to-end models have more room to automatically adjust according to the data, making the overall fit better and reducing error propagation. The combination of attention augmented convolutional neural network (AAConv) and multi-layer convolutional neural network (CNN) forms a deep representation learning module, which is used to obtain global and local information on the sequence. Based on the concept of flow network, multi-head flow-attention mechanism is introduced to mine the deep features of the sequence to improve the efficiency of the model. On the independent test dataset, the ACC, Sn, Sp, and AUC values of AACFlow are 83.9%, 83.0%, 84.8%, and 0.892, respectively, which are 4.9%, 1.5%, 8.0%, and 0.016 higher than those of the baseline model. The MCC value is 67.85%. In addition, we visualize the features extracted by each module to enhance the interpretability of the model. Various experiments show that our model is more competitive in predicting ACPs.

Vision-Sensor Enabled Multilayer CNN Scheme and Impact Analysis of Learning Rate Parameter for Speed Bump Detection in Autonomous Vehicle System

Vision-Sensor Enabled Multilayer CNN Scheme and Impact Analysis of Learning Rate Parameter for Speed Bump Detection in Autonomous Vehicle System

Innovative Label Embedding for Food Safety Comment Classification: Fusion of Self-Semantic and Self-Knowledge Features

Food safety comment classification represents a specialized task within the realm of text classification. The objective is to efficiently identify a large volume of food safety comments, aiding relevant authorities in timely food analysis and safety alerts. Traditional methods typically employ one-hot encoding for label processing. However, in real-world situations, classified labels often convey valuable semantic information and guidance. This paper introduces an innovative approach to enhance the classification performance of food safety comments by embedding label information. Initially, we extracted generic sentiment pivot words from various classification labels as label description information. Subsequently, we employ a joint embedding approach to integrate this label description information into the text. This process will pool the expressions of the pivot word into the corresponding sentiment labels in the known domains after averaging to get the embedded expression. This aims to acquire highly detailed self-semantic feature vectors and self-knowledge feature vectors that are integrated with labeled descriptive information. Then, feed the semantic representation of comments and the word-embedded representation of labeled description information into a time-step-based multilayer Bi-LSTM and a step-based multilayer CNN, respectively. Ultimately, we concatenate these two feature vectors to facilitate matching, thereby fusing the self-semantic and self-knowledge features of labeled description information to train a classification model for food safety comments. Experimental results on the food safety comment dataset showcase a noteworthy improvement of 1.74% and 1.27% in Macro_Precision and Macro_F1 metrics, respectively, compared to BERT, BERT-RNN, and BERT-CNN. Through extensive ablation experiments and additional studies, our method effectively embeds labeling information, demonstrating a clear advantage over traditional methods in the task of classifying food safety comments. Doi: 10.28991/HIJ-2024-05-01-013 Full Text: PDF

CircRNA identification and feature interpretability analysis

BackgroundCircular RNAs (circRNAs) can regulate microRNA activity and are related to various diseases, such as cancer. Functional research on circRNAs is the focus of scientific research. Accurate identification of circRNAs is important for gaining insight into their functions. Although several circRNA prediction models have been developed, their prediction accuracy is still unsatisfactory. Therefore, providing a more accurate computational framework to predict circRNAs and analyse their looping characteristics is crucial for systematic annotation.ResultsWe developed a novel framework, CircDC, for classifying circRNAs from other lncRNAs. CircDC uses four different feature encoding schemes and adopts a multilayer convolutional neural network and bidirectional long short-term memory network to learn high-order feature representation and make circRNA predictions. The results demonstrate that the proposed CircDC model is more accurate than existing models. In addition, an interpretable analysis of the features affecting the model is performed, and the computational framework is applied to the extended application of circRNA identification.ConclusionsCircDC is suitable for the prediction of circRNA. The identification of circRNA helps to understand and delve into the related biological processes and functions. Feature importance analysis increases model interpretability and uncovers significant biological properties. The relevant code and data in this article can be accessed for free at https://github.com/nmt315320/CircDC.git.

Spectrally Segmented-Enhanced Neural Network for Precise Land Cover Object Classification in Hyperspectral Imagery

The paradigm shift brought by deep learning in land cover object classification in hyperspectral images (HSIs) is undeniable, particularly in addressing the intricate 3D cube structure inherent in HSI data. Leveraging convolutional neural networks (CNNs), despite their architectural constraints, offers a promising solution for precise spectral data classification. However, challenges persist in object classification in hyperspectral imagery or hyperspectral image classification, including the curse of dimensionality, data redundancy, overfitting, and computational costs. To tackle these hurdles, we introduce the spectrally segmented-enhanced neural network (SENN), a novel model integrating segmentation-based, multi-layer CNNs, SVM classification, and spectrally segmented dimensionality reduction. SENN adeptly integrates spectral–spatial data and is particularly crucial for agricultural land classification. By strategically fusing CNNs and support vector machines (SVMs), SENN enhances class differentiation while mitigating overfitting through dropout and early stopping techniques. Our contributions extend to effective dimensionality reduction, precise CNN-based classification, and enhanced performance via CNN-SVM fusion. SENN harnesses spectral information to surmount challenges in “hyperspectral image classification in hyperspectral imagery”, marking a significant advancement in accuracy and efficiency within this domain.

Monkeypox detection and classification using multi-layer convolutional neural network from skin images

The latest pandemic of monkeypox is a significant cause for worry for the public's health due to the rapidity with which it has spread to more than 40 nations outside of Africa. When monkeypox is so like both measles and chickenpox, making an accurate clinical diagnosis of the disease may be difficult. The monitoring and early identification of suspected cases of monkeypox may benefit from computer-assisted detection of lesions. This is particularly true in environments where confirmatory Polymerase Chain Reaction (PCR) assays are not easily accessible. It has been shown that it is possible to do automated skin lesion identification via deep learning (DL) approaches given sufficient training instances. However, it is expected that these procedures will be followed. However, there are currently no datasets of this sort available for monkeypox. Focusing on forecasting monkeypox disease from skin pictures, this study focuses on developing a transfer learning-based multi-layer convolutional neural network (MLCNN) algorithm. Through pre-processing, we can ensure that all the images are of the same quality and that any distracting sounds have been eliminated. The simulation results showed that the proposed MLCNN outperformed the conventional model, proving the validity of the proposed approach. The MLCNN resulted in an accuracy is 99.1, precision is 99.1%, recall is 99.1%, and F1-score is 99.1%.

Intelligent Assistance Method for Preschool Education Dance Curriculum Based on Deep Learning

Abstract Preschool education is vital for shaping the foundation of young children’s development across cognitive, social, emotional, and physical dimensions. Dance courses are often included in preschool curricula to foster creativity, expression, physical coordination, and emotional regulation. Understanding and interpreting emotions conveyed through dance movements can be instrumental in enhancing children’s emotional intelligence and overall well-being. This paper investigates an innovative approach to intelligent assistance in preschool dance courses by utilizing deep learning methods for emotion recognition within dance movements. The proposed model integrates deep and shallow features to improve the precision of emotion detection, offering a promising means to facilitate personalized and interactive learning experiences. First, emotions in dance are extracted through a multi-layer convolutional neural network, and high-level features are fused with low-level features. Then, the fused features of different depths are used as the basis for emotion recognition. The convolutional neural network’s fully connected layer outputs the emotional probabilities of dance movements, allowing for the identification of emotional categories in dance movements. Finally, experiments are conducted using the fusion of features from different convolutional layers, validating the effectiveness of the proposed method in emotion recognition.

Phishing Website Detection Using Improved Multilayered Convolutional Neural Networks

Phishing Website Detection Using Improved Multilayered Convolutional Neural Networks

Information Enhancement With Multilayer Convolutional Neural Network for Accurate Lung Imaging

Information Enhancement With Multilayer Convolutional Neural Network for Accurate Lung Imaging

Improved Generative Adversarial Network Stock Price Prediction Method

In response to the challenges posed by the nonlinearity, instability, and complexity of the stock market in the insurance industry, we propose an enhanced generative adversarial neural network-based stock prediction model termed CAL-WGAN-GP. The model's generator incorporates components such as the CNN-BiLSTM model and a self-attention mechanism, employed to generate precise predictions for stock closing prices. The discriminator, comprising a multi-layer convolutional neural network, is tasked with distinguishing between the stock closing prices generated by the generator and actual stock closing prices. To assess the model's generalization capability, stock data from China Ping an, China Life, XinHua Insurance, and Pacific Insurance is selected. During the dataset construction, relevant features, including technical indicators, are incorporated to facilitate the model in better learning hidden data information. Experimental results demonstrate that CAL-WGAN-GP urpasses baseline models across four evaluation metrics: Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R-squared (R2), achieving the highest degree of data fitting

Real Time Quality Detection and Automatic Recognition of Concrete Structures: Image Processing Algorithm Based on Deep Learning

The safety and durability of concrete structure is an important issue in engineering quality management. In this paper, an image processing algorithm based on deep learning is proposed to realize real-time quality inspection and automatic defect identification of concrete structures. This algorithm uses the Convolutional Neural Network (CNN) to automatically extract the features of concrete surface quality images, and then identify the existence of defects, thus improving the detection efficiency and accuracy. In this paper, for this method, data samples with different specific structures are collected and manually labeled to the data set; then, a multi-layer CNN model with convolution layer, pool layer and full connection layer is designed to train the model, and then image enhancement technology is used to reduce information noise, and data enhancement technology is used to improve the problem-solving ability of the model. In addition, the strategy of Dropout is used to close some nodes to reduce parameters and prevent over-fitting, and the learning rate is adjusted to optimize the classification effect. In addition, this study constructs an all-weather real-time detection framework, including data acquisition, preprocessing, feature extraction, classification and identification and decision-making alarm system, to ensure the rapid positioning of the detection system. To sum up, the results of this study show that the deep learning image processing algorithm has good contrast performance in the field of real-time quality inspection of concrete structures. CNN model has better performance than GAN (Generative Adversarial Network) and LSTM (Long Short-Term Memory) models in detection time, defect identification resolution and detection accuracy. The maximum detection time is 366ms and the shortest is 213 ms. The successful development of this algorithm provides a new method for automatic detection of concrete structure quality, which has important application value in engineering practice. This research has a broad development prospect.

A neural tensor decomposition model for high-order sparse data recovery

Tensor decomposition has attracted wide attention in the low-rank tensor completion (LRTC) problem because of its marvelous recovering ability to missing entries. However, previous LRTC methods are generally based on linear and shallow models, which are prone to overfitting when the data is sparse, resulting in significantly degraded performance. Meanwhile, the models are highly sensitive and suffer from the difficult rank selection problem. To address these issues, we propose an effective and novel tensor-ring (TR) decomposition method based on the convolutional computation (ConvTR), which can be regarded as a natural extension of deep learning models for the LRTC problem. Specifically, ConvTR employs a multi-layer convolutional neural network (CNN) to model the complex interactions between TR factors. Each element in the index vector of the observation tensor can be embedded as a corresponding tensor slice in the factor tensor decomposed by the TR model. These individual slice matrices are then concatenated to get a wider matrix used for extracting the nonlinear features by feeding them into a 2D convolutional layer. A fully-connected layer is utilized to aggregate the final convoluted features to a scalar value, which is the desired missing entry indexed by the original index vector exactly. Extensive experiments on various common datasets verified the effectiveness of the proposed method and demonstrated its superior to the traditional TR-based completion methods and other state-of-the-art network-based methods.

An improved human activity recognition technique based on convolutional neural network

A convolutional neural network (CNN) is an important and widely utilized part of the artificial neural network (ANN) for computer vision, mostly used in the pattern recognition system. The most important applications of CNN are medical image analysis, image classification, object recognition from videos, recommender systems, financial time series analysis, natural language processing, and human–computer interfaces. However, after the technological advancement in the power of computing ability and the emergence of huge quantities of labeled data provided through enhanced algorithms, nowadays, CNN is widely used in almost every area of study. One of the main uses of wearable technology and CNN within medical surveillance is human activity recognition (HAR), which must require constant tracking of everyday activities. This paper provides a comprehensive study of the application of CNNs in the classification of HAR tasks. We describe their enhancement, from their antecedents up to the current state-of-the-art systems of deep learning (DL). We have provided a comprehensive working principle of CNN for HAR tasks, and a CNN-based model is presented to perform the classification of human activities. The proposed technique interprets data from sensor sequences of inputs by using a multi-layered CNN that gathers temporal and spatial data related to human activities. The publicly available WISDM dataset for HAR has been used to perform this study. This proposed study uses the two-dimensional CNN approach to make a model for the classification of different human activities. A recent version of Python software has been used to perform the study. The rate of accuracy for HAR through the proposed model in this experiment is 97.20%, which is better than the previously estimated state-of-the-art technique. The findings of the study imply that using DL methods for activity recognition might greatly increase accuracy and increase the range of applications where HAR can be used successfully. We have also described the future research trends in the field of HAR in this article.

Attention-based contextual local and global features for urgent posts classification in MOOCs discussion forums

The Massive Open Online Courses (MOOCs) platform offers communication channels for students to share concerns about the educational process. Due to the large number of students compared to the instructors’, it is challenging to identify urgent forum posts that require attention and prompt response from the instructor. This paper presents an innovative automated classification model called the “Attention Based on Contextual Local and Global Features (AT-CX-LGF)” classifier to identify MOOCs’ urgent posts. It can aid instructors in managing many posts and prioritizing their responses, allowing them to respond more quickly to student questions and reduce dropout rates while increasing completion rates. The suggested model obtains word embedding to represent the context information using BERT (Bidirectional Encoder Representation from Transformer). It depends on several phases. First, it extracts local and semantic (or global) contextual features using multi-layer CNN and Bi-LSTM. Then, two attention layers parallelly identify the most significant local and global features. After that, the outputs of the attention layers are concatenated and normalized. Finally, fully connected, and sigmoid layers are used for the classification process. On three groups (A, B, C) gathered from the Stanford MOOC Posts dataset, the AT-CX-LGF classifier obtained urgent posts recall of 87%, 87.1%, and 90.6% with 5.5%, 2.4%, and 7.5% improvements over the most recent algorithms, respectively. Furthermore, the model outperformed the state-of-the-art method in the weighted F1-score with handling the concept drift of the dataset.

WaveNet vocoder for prediction of time series with extreme events

Extreme events are typically defined as rare or unpredictable events that deviate significantly from typical behavior. Despite this, objective criteria for extreme events have yet to be established. Rareness may be characterized by certain scales or spatial and temporal boundaries, while intensity is an indication of an event’s potential to cause a significant change. One of the most prominent occurrences of extreme events in both neuroscience and medicine is in the case of epileptic seizures [1]. In speech synthesis, vocoder networks like WaveNet [2] generate audio. The model is a multi-layer convolutional neural network that functions as a causal filter and doesn’t predict the future. Due to this quality, the vocoder may have potential in time series prediction. Audio time series can be regarded as a dynamic system characterized by unpredictable switching regimes. For instance, transitioning from one letter to another can result in significant deviations in amplitude, similar to extreme events. This network receives r previous input counts known as a receptive field, and uses them to predict the next sample. The network is tree-like in structure, with exponentially increasing distances between subsequent layers of inputs. This is a necessary feature since the receptive field r is usually quite large, on the order of one or two thousand. Without this exponential increase in distance, the number of layers would depend linearly on r. Recurrent neural networks pose a challenge in optimizing the loss function when predicting time series sequences, as they tend to predict samples very similar to the previous one, causing the network to converge towards the mode. However, in a convolutional network, the output to the model will be longer due to the large receptive field. In the case of sound analysis, for instance, multiple oscillations occur within a given timeframe and the network does not elevate any specific sample. The study used artificial data generated from two coupled Hidmarsh–Rose neurons with chemical synaptic couplings. The observed variable was determined by the biological significance of the system, specifically the total membrane potential. The results exhibited extreme events across various coupling parameter values. Based on prior research [3], a numerical standard was selected for the events. The WaveNet vocoder model exhibits a 91% accuracy rate and 82% recall rate when forecasting extreme events of the same width as the prediction. It is noteworthy that recall is crucial in the forecast of extreme events since it identifies instances where the model predicted falsely that an extreme event would not occur.

Study on dynamic prediction method for degradation state of electric drive system based on deep learning and uncertainty quantification

Accurate prediction of degradation state (DS) in electric drive system (EDS) under time-varying conditions is of great importance for its reliability assessment and health monitoring. To address the complex degradation trajectories and the difficulty of dynamically evaluating the degradation state of EDS under user conditions, this paper proposes a dynamic prediction method for the DS of multiple components in EDS based on deep learning and uncertainty quantification. The method utilizes actual operating data spanning 350,000 km and constructs operating condition characteristics by combining physical models of component failure. A deep clustering algorithm is proposed to achieve clustering of operating conditions with similar degradation rates. Based on the resulting six clusters, linear degradation models for different components are established. The 42-dimensional features characterizing the operating conditions are constructed from time domain, frequency domain and load counting perspectives. An integrated approach combining autoencoders, multi-layer convolutional neural networks, and weight optimization algorithms is utilized to achieve accurate recognition of operating conditions, resulting in an average recognition accuracy of 94.5%, outperforming traditional methods. Considering the uncertainty in degradation rate and the errors in operating condition recognition, dynamic prediction of DS under varying operating conditions is achieved. The effectiveness of the prediction results is verified through constructed performance metrics such as the coefficient of determination, root mean square error, and average reproducibility ratio. The proposed method provides a theoretical basis and technical support for the dynamic assessment of system reliability.

Deep learning estimation of northern hemisphere soil freeze-thaw dynamics using satellite multi-frequency microwave brightness temperature observations.

Satellite microwave sensors are well suited for monitoring landscape freeze-thaw (FT) transitions owing to the strong brightness temperature (TB) or backscatter response to changes in liquid water abundance between predominantly frozen and thawed conditions. The FT retrieval is also a sensitive climate indicator with strong biophysical importance. However, retrieval algorithms can have difficulty distinguishing the FT status of soils from that of overlying features such as snow and vegetation, while variable land conditions can also degrade performance. Here, we applied a deep learning model using a multilayer convolutional neural network driven by AMSR2 and SMAP TB records, and trained on surface (~0-5 cm depth) soil temperature FT observations. Soil FT states were classified for the local morning (6 a.m.) and evening (6 p.m.) conditions corresponding to SMAP descending and ascending orbital overpasses, mapped to a 9 km polar grid spanning a five-year (2016-2020) record and Northern Hemisphere domain. Continuous variable estimates of the probability of frozen or thawed conditions were derived using a model cost function optimized against FT observational training data. Model results derived using combined multi-frequency (1.4, 18.7, 36.5 GHz) TBs produced the highest soil FT accuracy over other models derived using only single sensor or single frequency TB inputs. Moreover, SMAP L-band (1.4 GHz) TBs provided enhanced soil FT information and performance gain over model results derived using only AMSR2 TB inputs. The resulting soil FT classification showed favorable and consistent performance against soil FT observations from ERA5 reanalysis (mean percent accuracy, MPA: 92.7%) and in situ weather stations (MPA: 91.0%). The soil FT accuracy was generally consistent between morning and afternoon predictions and across different land covers and seasons. The model also showed better FT accuracy than ERA5 against regional weather station measurements (91.0% vs. 86.1% MPA). However, model confidence was lower in complex terrain where FT spatial heterogeneity was likely beneath the effective model grain size. Our results provide a high level of precision in mapping soil FT dynamics to improve understanding of complex seasonal transitions and their influence on ecological processes and climate feedbacks, with the potential to inform Earth system model predictions.

Gesture Classification in Electromyography Signals for Real-Time Prosthetic Hand Control Using a Convolutional Neural Network-Enhanced Channel Attention Model.

Accurate and real-time gesture recognition is required for the autonomous operation of prosthetic hand devices. This study employs a convolutional neural network-enhanced channel attention (CNN-ECA) model to provide a unique approach for surface electromyography (sEMG) gesture recognition. The introduction of the ECA module improves the model's capacity to extract features and focus on critical information in the sEMG data, thus simultaneously equipping the sEMG-controlled prosthetic hand systems with the characteristics of accurate gesture detection and real-time control. Furthermore, we suggest a preprocessing strategy for extracting envelope signals that incorporates Butterworth low-pass filtering and the fast Hilbert transform (FHT), which can successfully reduce noise interference and capture essential physiological information. Finally, the majority voting window technique is adopted to enhance the prediction results, further improving the accuracy and stability of the model. Overall, our multi-layered convolutional neural network model, in conjunction with envelope signal extraction and attention mechanisms, offers a promising and innovative approach for real-time control systems in prosthetic hands, allowing for precise fine motor actions.

Combining hypothesis-driven ECG indices with machine learning improves ventricular arrhythmic risk prediction in a low-risk population

Abstract Background Life-threatening ventricular arrhythmias (LTVA) are a leading cause of mortality, but early identification of high-risk individuals remains a major challenge. An ECG index, TMV (T-wave morphology variations), predicts LTVA in 51,794 individuals without known cardiovascular disease from the UK Biobank (UKB) within a 10-year follow up (cohort 1), with an area under the ROC curve (AUC) of 0.558 and a hazard ratio (HR) of 1.57. Machine learning on the ECG has shown a high accuracy in detecting patients with cardiovascular disease, but its LTVA predictive value in a low-risk population and comparisons with hypothesis-driven risk markers, like TMV, is unknown. Purpose We tested the LTVA predictive value of a score combining a multi-layer convolutional neural network (CNN) model and TMV in individuals without known cardiovascular disease. Methods Using UKB we split the individuals from cohort 1 into training (90%) and internal test (10%) sets (Figure 1). In the training set, we applied 10-fold cross validation to train a multi-layer CNN with an attention layer, where the input was a 15-second ECG at rest (lead I), and the output was occurrence (or not) of LTVA within a 10-year follow-up. We used 10-second ECG data (lead I) from an independent cohort of 32,209 individuals without cardiovascular disease from UKB (cohort 2) as an external test set (median follow-up was 3.4 years), where we also calculated TMV. We next combined them into a score (weighted by their relative contribution to LTVA in a logistic regression). The AUC, and Cox regression HRs were calculated to estimate the performance of the CNN, TMV and the combined score. Results In cohort 1, 217 subjects had a LTVA during the follow-up period. In the internal test set, the AUC of the CNN was 0.707. In the external test set (60 LTVA events during the follow-up period), the CNN’s prediction and TMV led to AUCs of 0.610 and 0.604, respectively. Interestingly, the CNN’s prediction and TMV were not correlated (ρ = 0.005), and the combined score led to an AUC of 0.627. We set a threshold at the score value that maximised sensitivity and specificity, and survival analyses showed a HR of 3.007 (P < 0.0001) for individuals in the score+ (score > threshold) versus those in the score- (score < threshold) group, after adjusting for age and gender (Figure 2). The continuous score also predicted LTVA independently from age and gender. Conclusions A CNN-based model predicts LTVA in a low-risk population independently from TMV, a strong ECG risk predictor derived from knowledge on the underlying electrophysiology. When TMV and the CNN are combined into a score, the LTVA risk stratification improves, independently from age and gender. Our findings support the combination of hypothesis-based risk markers and CNN approaches to optimise LTVA prediction in a low-risk population.Study designSurvival curves

Abstract 17454: Development and Validation of an Artificial Intelligence 12-Lead Electrocardiogram-Based Mutation Detector for Congenital Long QT Syndrome

Introduction: Over 100 FDA-approved medications, electrolyte perturbations, and many disease states can prolong the QT interval in up to 10% of patients. In contrast, approximately 1 in 2,000 people have congenital long QT syndrome (LQTS) hallmarked by pathological QT prolongation secondary to LQTS-causative mutations. Hypothesis: an artificial intelligence (AI) deep neural network (DNN) analysis of the 12-lead ECG can distinguish patients with LQTS from those with acquired QT prolongation. Methods: The study cohort included 1599 patients with genetically confirmed LQTS and over 2.5 million controls from Mayo Clinic’s ECG data vault. Every patient/control with ≥ 1 ECG above age- and sex- specific 99 th percentile values for QTc [> 460 ms for all patients (male/female) < 13 years of age, or > 470 ms for men and > 480 ms for women above this age] was included. An AI-DNN involving a multi-layer convolutional neural network was developed. To simulate screening conditions, patients were matched at a ratio of 1:2,000 (incidence of LQTS) or 1:200 (balance of LQTS vs acquired QT prolongation in a tertiary referral center). Results: Among the 1,599 patients with LQTS, 808 (> 50%) had ≥ 1 ECG with QTc above the aforementioned QTc thresholds (2,987 ECGs) compared to 361,069/2.5M controls (14% of Mayo Clinic patients getting an ECG, 989,313 ECGs). Following age- and sex- matching and splitting, the model successfully distinguished LQTS from those with acquired QT prolongation at 1:2,000 matching with an AUC of 0.937 (accuracy 89%, sensitivity 81%, specificity 90%, PPV 0.05, NPV 0.99). Furthermore, when matching at a rate that genetically-mediated QT prolongation would be encountered in clinic (1:200), the model still successfully separated the two groups (AUC 0.912, accuracy 88%, sensitivity 78%, specificity 89%, PPV 0.1, NPV 0.99). Conclusion: For patients with a QTc exceeding its 99 th percentile values seen in health, this novel AI-DNN 12-lead ECG distinguishes abnormal QT prolongation stemming from LQTS versus acquired QT prolongation with high performance characteristics (AUC > 0.93). Even when scaled to referral center and LQTS incidence ratios, a negative AI-DNN signal rules out the presence of a LQTS disease-causative mutation with 99% negative predictive value.