Diagnosis Model Research Articles

An Effective Classification of Brain Tumor using Deep Learning Techniques

Abstract: Brain tumor classification is a critical task in medical imaging, aiding in timely diagnosis and treatment planning. In this paper, we propose a comprehensive approach utilizing deep learning models for the classification of brain tumors into four categories: glioma, meningioma, pituitary tumors, and no tumors. We employ state-of-the-art convolutional neural network (CNN) architectures including ResNet50, DenseNet201, EfficientNetB3, and InceptionV3 for the classification task. To enhance the performance of the model, we employ resizing and augmentation techniques such as flips and rotation, thereby increasing the diversity of the training dataset. This is particularly crucial due to the limitations posed by small-sized datasets in previous methodologies. Our findings underscore the efficacy of deep learning approaches in brain tumor classification, with EfficientNetB3 emerging as a promising model for accurate diagnosis. Furthermore, our utilization of resizing and augmentation techniques demonstrates their significance in mitigating the challenges associated with limited training data.

Enhancing EfficientNetv2 with global and efficient channel attention mechanisms for accurate MRI-Based brain tumor classification

AbstractThe early and accurate diagnosis of brain tumors is critical for effective treatment planning, with Magnetic Resonance Imaging (MRI) serving as a key tool in the non-invasive examination of such conditions. Despite the advancements in Computer-Aided Diagnosis (CADx) systems powered by deep learning, the challenge of accurately classifying brain tumors from MRI scans persists due to the high variability of tumor appearances and the subtlety of early-stage manifestations. This work introduces a novel adaptation of the EfficientNetv2 architecture, enhanced with Global Attention Mechanism (GAM) and Efficient Channel Attention (ECA), aimed at overcoming these hurdles. This enhancement not only amplifies the model’s ability to focus on salient features within complex MRI images but also significantly improves the classification accuracy of brain tumors. Our approach distinguishes itself by meticulously integrating attention mechanisms that systematically enhance feature extraction, thereby achieving superior performance in detecting a broad spectrum of brain tumors. Demonstrated through extensive experiments on a large public dataset, our model achieves an exceptional high-test accuracy of 99.76%, setting a new benchmark in MRI-based brain tumor classification. Moreover, the incorporation of Grad-CAM visualization techniques sheds light on the model’s decision-making process, offering transparent and interpretable insights that are invaluable for clinical assessment. By addressing the limitations inherent in previous models, this study not only advances the field of medical imaging analysis but also highlights the pivotal role of attention mechanisms in enhancing the interpretability and accuracy of deep learning models for brain tumor diagnosis. This research sets the stage for advanced CADx systems, enhancing patient care and treatment outcomes.

The Superiority of Fine-tuning over Full-training for the Efficient Diagnosis of COPD from CXR Images

This research investigates the use of deep learning for diagnosing lung diseases like Chronic Obstructive Pulmonary Disease (COPD) using Chest X-rays (CXR). The study compares the impact of deep learning on improving these diagnoses by comparing the performance of models trained from the scratch with those enhanced through fine-tuning established architectures like InceptionV3, ResNet50, and VGG-19. The study revealed that fine-tuning pre-trained models offers significant benefits: faster convergence, improved stability, and increased accuracy. Data augmentation techniques were found to be particularly useful when dealing with limited or unbalanced datasets. A custom CNN model, Iyke-Net, showed promising results when fine-tuned. Interestingly, it was observed that models using grayscale images outperformed those using colour images in disease classification, suggesting that colour information might be less critical than previously thought for certain diagnostic procedures. The study emphasizes the importance of balancing model complexity with computational efficiency and diagnostic accuracy. It advocates for refining existing deep learning models for COPD diagnosis from CXR images, paving the way for further innovations in AI-enhanced medical diagnostics.

A Compression and Encryption Based Heart Disease Diagnosis with Deep Learning through ECG Signals

Electrocardiogram (ECG) monitoring models are commonly employed for diagnosing heart diseases. Since ECG signals are normally acquired for a longer time duration with high resolution, there is a need to compress the ECG signals for transmission and storage. So, a novel compression technique is essential in transmitting the signals to the telemedicine center to monitor and analyses the data. In addition, the protection of ECG signals poses a challenging issue, which encryption techniques can resolve. The existing Encryption-Then-Compression (ETC) models for multimedia data fail to properly maintain the trade- off between compression performance and signal quality. In this view, this study presents a new ETC with a diagnosis model for ECG data, called the ETC-ECG model. The proposed model involves four major processes, namely, pre-processing, encryption, compression, and classification. Once the ECG data of the patient are gathered, Discrete Wavelet Transform (DWT) with a Thresholding mechanism is used for noise removal. In addition, the chaotic map-based encryption technique is applied to encrypt the data. Moreover, the Burrows-Wheeler Transform (BWT) approach is employed for the compression of the encrypted data. Finally, a Deep Neural Network (DNN) is applied to the decrypted data to diagnose heart disease. The detailed experimental analysis takes place to ensure the effective performance of the presented model to assure data security, compression, and classification performance for ECG data

Development and Assessment of a Prediction Model for Alzheimer's Disease Diagnosis Based on Thermoregulation-Related Genes.

Alzheimer's disease (AD) is a prevalent neurodegenerative condition among the elderly population and the most common form of dementia, however, we lack potent interventions to arrest its inherent pathogenic vectors. Robust evidence indicates thermoregulatory perturbations during and before the onset of symptoms. Therefore, temperature-regulated biomarkers may offer clues to therapeutic targets during the presymptomatic stage. The purpose of this study is to develop and assess a thermoregulation-related gene prediction model for Alzheimer's Disease diagnosis. This study aims to utilize microarray bioinformatic analysis to identify the potential biomarkers of AD by analyzing four microarray datasets (GSE48350, GSE5281, GSE122063, and GSE181279) of AD patients. Furthermore, thermoregulation-associated hub genes were identified, and the expression patterns in the brain were explored. In addition, we explored the infiltration of immune cells with thermoregulation-related hub genes. Diagnostic marker validation was then performed at the single-cell level. Finally, the prediction of targeted drugs was performed based on the hub genes. Through the analysis of four datasets pertaining to AD, a total of five genes associated with temperature regulation were identified. Notably, CCK, CXCR4, SLC27A4, and SLC17A6 emerged as diagnostic markers indicative of AD-related brain injury. Furthermore, in the examination of peripheral blood samples from AD patients, SLC27A4 and CXCR4 were identified as pivotal diagnostic indicators. Regrettably, animal experimentation was not pursued to validate the data; rather, an assessment of temperature regulation-related genes was conducted. Future investigations will be undertaken to establish the correlation between these genes and AD pathology. Overall, CCK, CXCR4, SLC27A4, and SLC17A6 can be considered pivotal biomarkers for diagnosing the pathogenesis and molecular functions of AD.

Application of Bayesian networks based on Sequential Monte Carlo simulation and physical model in fault diagnosis of horizontal three-phase separator system

In offshore production platforms, horizontal three-phase separator is common process equipment. Its main function is to complete the dehydration and degassing of crude oil. Separator system is more complex, and its failure may cause significant economic losses and disastrous consequences. Therefore, it is critical to accurately and quickly identify where and why faults occur in the separator system. In this study, separator fault diagnosis model based on Bayesian networks is developed. Moreover, Sequential Monte Carlo simulation and physical model are introduced to overcome field problems such as missing separator failure data and the inability of experts to provide accurate empirical knowledge. Using this model, 13 faults in a separator in an offshore crude oil processing system are successfully diagnosed. Meanwhile, the proposed model is compared with deep neural network, convolutional neural network, and deep residual network, with accuracy rates of 100%, 91.34%, 87.99%, and 94.62%, respectively. Then, the diagnostic accuracy of each model for different faults is also compared in this paper under various signal-to-noise ratios. The results show that the method proposed in this paper has better noise immunity compared to the other three models. Therefore, the accuracy and robustness of the proposed model is further demonstrated. Finally, to analyze the fault-tolerance of the proposed model, 2–3 error evidence is randomly entered. The results show that the proposed model has better fault tolerance compared to data-driven Bayesian networks.

Construction of ferroptosis-related prediction model for pathogenesis, diagnosis and treatment of ruptured abdominal aortic aneurysm.

Abdominal aortic aneurysm (AAA) is a dangerous cardiovascular disease, which often brings great psychological burden and economic pressure to patients. If AAA rupture occurs, it is a serious threat to patients' lives. Therefore, it is of clinical value to actively explore the pathogenesis of ruptured AAA and prevent its occurrence. Ferroptosis is a new type of cell death dependent on lipid peroxidation, which plays an important role in many cardiovascular diseases. In this study, we used online data and analysis of ferroptosis-related genes to uncover the formation of ruptured AAA and potential therapeutic targets. We obtained ferroptosis-related differentially expressed genes (Fe-DEGs) from GSE98278 dataset and 259 known ferroptosis-related genes from FerrDb website. Enrichment analysis of differentially expressed genes (DEGs) was performed by gene ontology (GO) and Kyoto encyclopedia of genes and genomes (KEGG). Receiver Operating characteristic (ROC) curve was employed to evaluate the diagnostic abilities of Fe-DEGs. Transcription factors and miRNAs of Fe-DEGs were identified through PASTAA and miRDB, miRWalk, TargetScan respectively. Single-sample gene set enrichment analysis (ssGSEA) was used to observe immune infiltration between the stable group and the rupture group. DGIdb database was performed to find potential targeted drugs of DEGs. GO and KEGG enrichment analysis found that DEGs mainly enriched in "cellular divalent inorganic cation homeostasis," "cellular zinc ion homeostasis," "divalent inorganic cation homeostasis," "Mineral absorption," "Cytokine - cytokine receptor interaction," "Coronavirus disease - COVID-19." Two up-regulated Fe-DEGs MT1G and DDIT4 were found to further analysis. Both single and combined applications of MT1G and DDIT4 showed good diagnostic efficacy (AUC = 0.8254, 0.8548, 0.8577, respectively). Transcription factors STAT1 and PU1 of MT1G and ARNT and MAX of DDIT4 were identified. Meanwhile, has_miR-548p-MT1G pairs, has_miR-53-3p/has_miR-181b-5p/ has_miR-664a-3p-DDIT4 pairs were found. B cells, NK cells, Th2 cells were high expression in the rupture group compared with the stable group, while DCs, Th1 cells were low expression in the rupture group. Targeted drugs against immunity, GEMCITABINE and INDOMETHACIN were discovered. We preliminarily explored the clinical significance of Fe-DEGs MT1G and DDIT4 in the diagnosis of ruptured AAA, and proposed possible upstream regulatory transcription factors and miRNAs. In addition, we also analyzed the immune infiltration of stable and rupture groups, and found possible targeted drugs for immunotherapy.

Evaluation of children's oral diagnosis and treatment using imaging examination using AI based Internet of Things.

Although cone beam computed tomography (CBCT) plays an important role in the diagnosis and treatment of oral diseases, its image segmentation method needs to be further improved, and there are still objections about the clinical application effect of general anesthesia (GA) on children's dental fear (CDF). This study aimed to investigate the application value of CBCT based on intelligent computer segmentation model in oral diagnosis and treatment of children in the context of biomedical signals, and to analyze the alleviating effect of GA on CDF. Based on the regional level set (CV) algorithm, the local binary fitting (LBF) model was introduced to optimize it, and the tooth CBCT image segmentation model CV-LBF was established to compare the segmentation accuracy (SA), maximum symmetric surface distance (MSSD), average symmetric surface distance (ASSD), over segmentation rate (OR), and under segmentation rate (UR) between these model and other algorithms. 82 children with CDF were divided into general anesthesia group (GAG) (n= 38) and controls (n= 44) according to the voluntary principle of their families. Children in GAG were treated with GA and controls with protective fixed intervention. Children's fear survey schedule-dental subscale (CFSS-DS) and Venham scores were counted before intervention in the two groups. CFSS-DS scores were recorded at 2 hours after intervention and after recovery in children in GAG. CFSS-DS and Venham scores were performed in all children 1 week after surgery. The results showed that the S⁢A value of CV-LBF algorithm was higher than that of region growing algorithm (P< 0.05). OR, UR, MSSD, and ASSD values of CV-LBF algorithm were evidently lower than those of other algorithms (P< 0.05). CFSS-DS scores were lower in GAG than in controls 2 hours after intervention and at return visits after 1 week of intervention (P< 0.001), and Venham scores were lower in GAG than in controls after intervention (P< 0.001). After intervention, the proportion of children with Venham grade 0, 1, 2, and 3 was obviously higher in GAG than in controls (P< 0.001), while the proportion of children with Venham grade 4 and 5 was clearly higher in controls than in GAG (P< 0.001). The results revealed that the computer intelligent segmentation model CV-LBF has potential application value in CBCT image segmentation of children's teeth, and GA can effectively alleviate anxiety of children with CDF and can be used as biomedical signals.

Explainable machine learning approach for cancer prediction through binarilization of RNA sequencing data.

In recent years, researchers have proven the effectiveness and speediness of machine learning-based cancer diagnosis models. However, it is difficult to explain the results generated by machine learning models, especially ones that utilized complex high-dimensional data like RNA sequencing data. In this study, we propose the binarilization technique as a novel way to treat RNA sequencing data and used it to construct explainable cancer prediction models. We tested our proposed data processing technique on five different models, namely neural network, random forest, xgboost, support vector machine, and decision tree, using four cancer datasets collected from the National Cancer Institute Genomic Data Commons. Since our datasets are imbalanced, we evaluated the performance of all models using metrics designed for imbalance performance like geometric mean, Matthews correlation coefficient, F-Measure, and area under the receiver operating characteristic curve. Our approach showed comparative performance while relying on less features. Additionally, we demonstrated that data binarilization offers higher explainability by revealing how each feature affects the prediction. These results demonstrate the potential of data binarilization technique in improving the performance and explainability of RNA sequencing based cancer prediction models.

Fault diagnosis of drone motors driven by current signal data with few samples

Multi rotor unmanned aerial vehicles (UAVs) are extensively utilized across various domains, and the motor constitutes a pivotal element in the UAV power system. The majority of UAV failures and crashes stem from motor malfunctions, underscoring the imperative need for comprehensive research on fault diagnosis in UAV motors to ensure the stable and reliable execution of flight tasks. This study focuses on quadrotor UAVs as the research subject and devises targeted fault simulation experiments based on the structural features and operational characteristics of the DC brushless motor used in quadrotor UAVs, specifically examining the stator, rotor, and bearings. To address challenges related to the UAV’s own loads, limited space for redundant parts, and the high cost and difficulty associated with installing sensors for traditional fault diagnostic signals such as vibration and temperature, this study opts to use current signals as a substitute. This approach resolves the issue of challenging data collection for UAVs and investigates a current signal based fault diagnosis method for UAV motors. Lastly, in response to the limited training samples available for fault data due to the UAV’s highly sensitive characteristics regarding the health status of its components and flight stability, traditional machine learning and deep learning methods encounter difficulties in identifying representative features with a small number of training samples, leading to the risk of overfitting and reduced model accuracy in fault diagnosis. To overcome this challenge, we propose a hybrid neural network fault diagnosis model that incorporates a width learning system and a convolutional neural network (CNN). The width learning system eliminates temporal characteristics from the original current signal, capturing more comprehensive and representative sample features in the width feature space. Subsequently, the CNN is employed for feature extraction and classification tasks. In empirical small sample fault diagnosis experiments using current signal data for UAV motors, our proposed model outperforms other models used for comparison.

A rolling bearing fault diagnosis method based on interactive generative feature space oversampling-based autoencoder under imbalanced data

With the rapid development of railroads and the yearly increase in the scale of operation, the safe operation and maintenance of rail trains have become particularly important. Among them, deep learning-based bearing fault diagnosis methods have attracted more and more attention in rail train operation and maintenance. However, rail trains usually operate normally. Collecting complete fault data for deep learning model training is often difficult. Such scenarios with a large difference between the number of normal data and fault data usually affect the performance of fault diagnosis models. Here, an interactive generative feature space oversampling-based autoencoder (IGFSO-AE) is proposed to realize fault sample generation under imbalanced data. First, the original vibration signal is converted into a semantically stable amplitude–frequency signal by fast Fourier transform and input into the autoencoder; second, the order of the hidden layer space features of the autoencoder is randomly exchanged, and the interactive sample generation learning strategy trains the autoencoder; then, interpolation oversampling is used to interpolate samples in the hidden layer space where the Euclidean distance between samples is large, and is input into the decoder, the generated samples are mixed with the original samples to form a new training set, which is used to train the intelligent fault diagnosis model and output the diagnosis results. Finally, the performance of the proposed method is evaluated using the publicly available bearing dataset and the bogie-bearing fault simulation bench in our lab. The experimental results show that IGFSO-AE can generate diverse samples with incremental information and exhibits robustness and superiority in different imbalanced proportions of data.

SPOTTING OF CYBERBULLYING ON SOCIAL MEDIA USING MACHINE LEARNING

Cyberbullying occurs when someone harasses, threatens, or mistreats someone else online or on social media. Cyberbullying leads to threats, public embarrassment, and reprimands. Cyberbullying has caused a rise in youth suicide and mental health issues. It has lowered my self-esteem and escalated my suicidal thoughts. If cyberbullying continues, an entire generation of young adults will suffer from low self-esteem and mental health issues. Many machine learning algorithms are used to automatically identify social media cyberbullying. Social media monitoring allows this. These models don't account for all the factors that could make a comment or post bullying. Bullying is still ambiguous. This study presents a cyberbullying diagnosis model based on several factors. Cyberbully is a misuse of technology advantage to bully a person. This project is used Dataset namely,’ Cyberbullying-tweets’. This project used Machine Learning Classifiers such as Support Vector Machine (SVM), Random Forest (RF), Naïve Bayes (NB), and Neural Networks (NN), Logistic Regression(LR) Algorithms and calculated performance results for comparing the performance for dataset. Keywords: Cyberbullying Detection, Social Media Analysis, Machine Learning Models, Natural Language Processing (NLP), Text Classification , Feature Extraction, Sentiment Analysis, Textual Data Mining, Online Harassment, User Profiling, Toxic Language Detection, Hate Speech Detection, Content Moderation, Multi-Layer Perceptron (MLP), Support Vector Machine (SVM), Neural Network Algorithms, Lexicon-based Features, Syntactic Features, N-gram Analysis, Arabic Social Media (if focusing on Arabic language),User Behavior Analysis, Feature Engineering, Cross- Platform Analysis, Real-time Monitoring, Social Network Analysis

ECG-image-kit: a synthetic image generation toolbox to facilitate deep learning-based electrocardiogram digitization

Abstract Objective: Cardiovascular diseases are a major cause of mortality globally, and electrocardiograms (ECGs) are crucial for diagnosing them. Traditionally, ECGs are stored in printed formats. However, these printouts, even when scanned, are incompatible with advanced ECG diagnosis software that require time-series data. Digitizing ECG images is vital for training machine learning models in ECG diagnosis, leveraging the extensive global archives collected over decades. Deep learning models for image processing are promising in this regard, although the lack of clinical ECG archives with reference time-series data is challenging. Data augmentation techniques using realistic generative data models provide a solution.&amp;#xD;&amp;#xD;Approach: We introduce ECG-Image-Kit, an open-source toolbox for generating synthetic multi-lead ECG images with realistic artifacts from time-series data, aimed at automating the conversion of scanned ECG images to ECG data points. The tool synthesizes ECG images from real time-series data, applying distortions like text artifacts, wrinkles, and creases on a standard ECG paper background.&amp;#xD;&amp;#xD;Main results: As a case study, we used ECG-Image-Kit to create a dataset of 21,801 ECG images from the PhysioNet QT database. We developed and trained a combination of a traditional computer vision and deep neural network model on this dataset to convert synthetic images into time-series data for evaluation. We assessed digitization quality by calculating the signal-to-noise ratio (SNR) and compared clinical parameters like QRS width, RR, and QT intervals recovered from this pipeline, with the ground truth extracted from ECG time-series. The results show that this deep learning pipeline accurately digitizes paper ECGs, maintaining clinical parameters, and highlights a generative approach to digitization.&amp;#xD;&amp;#xD;Significance: The toolbox has broad applications, including model development for ECG image digitization and classification. The toolbox currently supports data augmentation for the 2024 PhysioNet Challenge, focusing on digitizing and classifying paper ECG images.

HAMMF: Hierarchical attention-based multi-task and multi-modal fusion model for computer-aided diagnosis of Alzheimer’s disease

Alzheimer’s disease (AD) is a progressive neurodegenerative condition, and early intervention can help slow its progression. However, integrating multi-dimensional information and deep convolutional networks increases the model parameters, affecting diagnosis accuracy and efficiency and hindering clinical diagnostic model deployment. Multi-modal neuroimaging can offer more precise diagnostic results, while multi-task modeling of classification and regression tasks can enhance the performance and stability of AD diagnosis. This study proposes a Hierarchical Attention-based Multi-task Multi-modal Fusion model (HAMMF) that leverages multi-modal neuroimaging data to concurrently learn AD classification tasks, cognitive score regression, and age regression tasks using attention-based techniques. Firstly, we preprocess MRI and PET image data to obtain two modal data, each containing distinct information. Next, we incorporate a novel Contextual Hierarchical Attention Module (CHAM) to aggregate multi-modal features. This module employs channel and spatial attention to extract fine-grained pathological features from unimodal image data across various dimensions. Using these attention mechanisms, the Transformer can effectively capture correlated features of multi-modal inputs. Lastly, we adopt multi-task learning in our model to investigate the influence of different variables on diagnosis, with a primary classification task and a secondary regression task for optimal multi-task prediction performance. Our experiments utilized MRI and PET images from 720 subjects in the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset. The results show that our proposed model achieves an overall accuracy of 93.15% for AD/NC recognition, and the visualization results demonstrate its strong pathological feature recognition performance.

Stacking with Recursive Feature Elimination-Isolation Forest for classification of diabetes mellitus.

Diabetes Mellitus is one of the oldest diseases known to humankind, dating back to ancient Egypt. The disease is a chronic metabolic disorder that heavily burdens healthcare providers worldwide due to the steady increment of patients yearly. Worryingly, diabetes affects not only the aging population but also children. It is prevalent to control this problem, as diabetes can lead to many health complications. As evolution happens, humankind starts integrating computer technology with the healthcare system. The utilization of artificial intelligence assists healthcare to be more efficient in diagnosing diabetes patients, better healthcare delivery, and more patient eccentric. Among the advanced data mining techniques in artificial intelligence, stacking is among the most prominent methods applied in the diabetes domain. Hence, this study opts to investigate the potential of stacking ensembles. The aim of this study is to reduce the high complexity inherent in stacking, as this problem contributes to longer training time and reduces the outliers in the diabetes data to improve the classification performance. In addressing this concern, a novel machine learning method called the Stacking Recursive Feature Elimination-Isolation Forest was introduced for diabetes prediction. The application of stacking with Recursive Feature Elimination is to design an efficient model for diabetes diagnosis while using fewer features as resources. This method also incorporates the utilization of Isolation Forest as an outlier removal method. The study uses accuracy, precision, recall, F1 measure, training time, and standard deviation metrics to identify the classification performances. The proposed method acquired an accuracy of 79.077% for PIMA Indians Diabetes and 97.446% for the Diabetes Prediction dataset, outperforming many existing methods and demonstrating effectiveness in the diabetes domain.

A Systematic Review on Deep Learning Model in Computer-aided Diagnosis for Anterior Cruciate Ligament Injury.

In developing Computer-Aided Diagnosis (CAD), a Convolutional Neural Network (CNN) has been commonly used as a Deep Learning (DL) model. Although it is still early, DL has excellent potential in implementing computers in medical diagnosis. This study reviews the use of DL for Anterior Cruciate Ligament (ACL) tear diagnosis. A comprehensive search was performed in PubMed, Embase, and Web of Science databases from 2018 to 2024. The included study criteria used MRI images to evaluate ACL tears, and the diagnosis of ACL tears was performed using the DL model. We summarized the paper by reporting their model accuracy, model comparison with arthroscopy, and explainable. AI implementation in tabular format; we conclude that many medical professionals believe that arthroscopic diagnosis is the most reliable method for diagnosing ACL tears. However, due to its intrusive treatment, CAD is projected to be able to produce similar outcomes from MRI scan results. To gain the trust of physicians and meet the demand for reliable knee injury detection systems, an algorithm for CAD should also meet several criteria, such as being transparent, interpretable, explainable, and easy to use. Therefore, future works should consider creating an Explainable DL model for ACL tear diagnosis. It is also essential to evaluate the performance of this Explainable DL model compared to the gold standard of arthroscopy diagnosis. There are issues regarding the need for Explainable DL in CAD to increase confidence in its result while also highlighting the importance of the involvement of medical practitioners in system design. There is no funding for this work.

A knowledge-driven graph convolutional network for abnormal electrocardiogram diagnosis

The electrocardiogram (ECG) signal comprising P-, Q-, R-, S-, and T-waves is an indispensable noninvasive diagnostic tool for analyzing physiological conditions of the heart. In general, traditional ECG intelligent diagnosis methods gradually extract features of the signal from input data until they can classify the ECG signal. However, the decision-making process of ECG intelligence models is implicit to clinicians. Clinical experts rely on clear and specific features extracted from ECG data to diagnose cardiac diseases effectively. Inspired by this clinical diagnosis mechanism, we propose an ECG knowledge graph (ECG-KG) framework primarily to improve ECG classification by presenting knowledge of ECG clinical diagnosis. In particular, the ECG-KG framework contains an ECG semantic feature extraction module, a knowledge graph construction module, and an ECG classification module. First, the ECG semantic feature extraction module locates the key points using the difference value method and further calculates the ECG attribute features. Further, the knowledge graph construction module utilizes attribute features to design entities and relationships for constructing abnormal ECG triples. The triples vectorize ECG abnormalities through the strategy of knowledge graph embedding strategy. Finally, the ECG classification module combines the ECG knowledge graph with the graph convolutional network model and adequately integrates expert knowledge to identify ECG abnormalities. Experiments conducted on the benchmark QT, the CPSC-2018, and the ZZU-ECG datasets show that the ECG-KG framework considerably outperforms other ECG diagnosis models, indicating the effectiveness of the ECG-KG framework for ECG abnormality diagnosis.

Towards Improved Radiological Diagnostics: Investigating the Utility and Limitations of GPT-3.5 Turbo and GPT-4 with Quiz Cases.

The rise of large language models such as generative pre-trained transformers (GPTs) has sparked significant interest in radiology, especially in interpreting radiological reports and image findings. While existing research has focused on GPTs estimating diagnoses from radiological descriptions, exploring alternative diagnostic information sources is also crucial. This study introduces the use of GPTs (GPT-3.5 Turbo and GPT-4) for information retrieval and summarization, searching relevant case reports via PubMed, and investigates their potential to aid diagnosis. From October 2021 to December 2023, we selected 115 cases from the "Case of the Week" series on the American Journal of Neuroradiology website. Their Description and Legend sections were presented to the GPTs for the two tasks. For the Direct Diagnosis task, the models provided three differential diagnoses that were considered correct if they matched the diagnosis in the diagnosis section. For the Case Report Search task, the models generated two keywords per case, creating PubMed search queries to extract up to three relevant reports. A response was considered correct if reports containing the disease name stated in the diagnosis section were extracted. McNemar's test was employed to evaluate whether adding a Case Report Search to Direct Diagnosis improved overall accuracy. In the Direct Diagnosis task, GPT-3.5 Turbo achieved a correct response rate of 26% (30/115 cases), whereas GPT-4 achieved 41% (47/115). For the Case Report Search task, GPT-3.5 Turbo scored 10% (11/115), and GPT-4 scored 7% (8/115). Correct responses totaled 32% (37/115) with three overlapping cases for GPT-3.5 Turbo, whereas GPT-4 had 43% (50/115) of correct responses with five overlapping cases. Adding Case Report Search improved GPT-3.5 Turbo's performance (p = 0.023) but not that of GPT-4 (p = 0.248). The effectiveness of adding Case Report Search to GPT-3.5 Turbo was particularly pronounced, suggesting its potential as an alternative diagnostic approach to GPTs, particularly in scenarios where direct diagnoses from GPTs are not obtainable. Nevertheless, the overall performance of GPT models in both direct diagnosis and case report retrieval tasks remains not optimal, and users should be aware of their limitations.ABBREVIATIONS: AI = Artificial Intelligence, GPT = generative pretrained transformer, LLM = large language model.

A Hierarchical Fault Diagnosis Model for Planetary Gearbox with Shift-invariant Dictionary and OMPAN

Abstract Planetary gearbox has been widely applied in the mechanical transmission system, and the failure types of planetary gearbox are more and more diversified. The conventional fault diagnosis methods focus on identifying the faults in the fault library, but ignored the faults outside the fault library. However, it is impossible to build a fault library for all failure types. Targeting the problem of identifying the faults outside the fault library, a hierarchical fault diagnosis method for planetary gearbox with shift-invariant dictionary and orthogonal matching pursuit with adaptive noise (OMPAN) is proposed in this paper. By k-means singular value decomposition (K-SVD) dictionary learning method and shift-invariant strategy, a shift-invariant dictionary is constructed so that the normal modulation components of signals can be completed decomposed. OMPAN algorithm is proposed, which uses the white Gaussian noise to improve the solution method of the orthogonal matching pursuit (OMP) algorithm so that it can separate the modulation components in the signal more accurately. The fault feature extraction is developed via shift-invariant dictionary and OMPAN. A hierarchical classifier is proposed with 3 sub-classifiers so that both the faults in the fault library and the faults outside the fault library are identified. The effectiveness of the proposed hierarchical fault diagnosis method is validated by a planetary gearbox experiment. Result show that the proposed shift-invariant dictionary and OMPAN method has achieved a superior performance in highlighting fault features compared with other two sparse decomposition methods. The proposed hierarchical fault diagnosis approach has achieved a good performance both in classification of the faults in the fault library and identification of the faults outside the fault library.

Enhancing Wind Farm Reliability: A Field of View Enhanced Convolutional Neural Network-Based Model for Fault Diagnosis and Prevention

Wind farms play a crucial role in renewable energy generation, but their reliability is often compromised by complex environmental and equipment conditions. This study proposes a field of view enhanced convolutional neural network (CNN) model for fault diagnosis and prevention in wind farms. The model is developed by collecting and processing wind farm fault data and compared with support vector machine (SVM) and k-nearest neighbor (KNN) models. The results showed that the proposed CNN model outperformed the other models in terms of convergence speed (17 iterations to reach the minimum loss), fault diagnosis accuracy (99.3% and 99.2% for inner and outer circle faults, respectively), and stable power output improvement. The model’s application to maintenance scheduling and economic benefit analysis in a real wind farm case demonstrated its high consistency and accuracy in fault prediction and maintenance optimization. The proposed approach has the potential to enhance wind farm reliability, efficiency, and economy by enabling accurate fault diagnosis, early warning, and preventive maintenance.