Classification Model Research Articles

Evaluation of artificial intelligence-powered screening for sexually transmitted infections-related skin lesions using clinical images and metadata

BackgroundSexually transmitted infections (STIs) pose a significant global public health challenge. Early diagnosis and treatment reduce STI transmission, but rely on recognising symptoms and care-seeking behaviour of the individual. Digital health software that distinguishes STI skin conditions could improve health-seeking behaviour. We developed and evaluated a deep learning model to differentiate STIs from non-STIs based on clinical images and symptoms.MethodsWe used 4913 clinical images of genital lesions and metadata from the Melbourne Sexual Health Centre collected during 2010–2023. We developed two binary classification models to distinguish STIs from non-STIs: (1) a convolutional neural network (CNN) using images only and (2) an integrated model combining both CNN and fully connected neural network (FCN) using images and metadata. We evaluated the model performance by the area under the ROC curve (AUC) and assessed metadata contributions to the Image-only model.ResultsOur study included 1583 STI and 3330 non-STI images. Common STI diagnoses were syphilis (34.6%), genital warts (24.5%) and herpes (19.4%), while most non-STIs (80.3%) were conditions such as dermatitis, lichen sclerosis and balanitis. In both STI and non-STI groups, the most frequently observed groups were 25–34 years (48.6% and 38.2%, respectively) and heterosexual males (60.3% and 45.9%, respectively). The Image-only model showed a reasonable performance with an AUC of 0.859 (SD 0.013). The Image + Metadata model achieved a significantly higher AUC of 0.893 (SD 0.018) compared to the Image-only model (p < 0.01). Out of 21 metadata, the integration of demographic and dermatological metadata led to the most significant improvement in model performance, increasing AUC by 6.7% compared to the baseline Image-only model.ConclusionsThe Image + Metadata model outperformed the Image-only model in distinguishing STIs from other skin conditions. Using it as a screening tool in a clinical setting may require further development and evaluation with larger datasets.

Intelligent diagnostic model for pterygium by combining attention mechanism and MobileNetV2

AIM: To evaluate the application of an intelligent diagnostic model for pterygium. METHODS: For intelligent diagnosis of pterygium, the attention mechanisms—SENet, ECANet, CBAM, and Self-Attention—were fused with the lightweight MobileNetV2 model structure to construct a tri-classification model. The study used 1220 images of three types of anterior ocular segments of the pterygium provided by the Eye Hospital of Nanjing Medical University. Conventional classification models—VGG16, ResNet50, MobileNetV2, and EfficientNetB7—were trained on the same dataset for comparison. To evaluate model performance in terms of accuracy, Kappa value, test time, sensitivity, specificity, the area under curve (AUC), and visual heat map, 470 test images of the anterior segment of the pterygium were used. RESULTS: The accuracy of the MobileNetV2+Self-Attention model with 281 MB in model size was 92.77%, and the Kappa value of the model was 88.92%. The testing time using the model was 9ms/image in the server and 138ms/image in the local computer. The sensitivity, specificity, and AUC for the diagnosis of pterygium using normal anterior segment images were 99.47%, 100%, and 100%, respectively; using anterior segment images in the observation period were 88.30%, 95.32%, and 96.70%, respectively; and using the anterior segment images in the surgery period were 88.18%, 94.44%, and 97.30%, respectively. CONCLUSION: The developed model is lightweight and can be used not only for detection but also for assessing the severity of pterygium.

A Multimorbidity Analysis of Hospitalized Patients With COVID-19 in Northwest Italy: Longitudinal Study Using Evolutionary Machine Learning and Health Administrative Data.

Multimorbidity is a significant public health concern, characterized by the coexistence and interaction of multiple preexisting medical conditions. This complex condition has been associated with an increased risk of COVID-19. Individuals with multimorbidity who contract COVID-19 often face a significant reduction in life expectancy. The postpandemic period has also highlighted an increase in frailty, emphasizing the importance of integrating existing multimorbidity details into epidemiological risk assessments. Managing clinical data that include medical histories presents significant challenges, particularly due to the sparsity of data arising from the rarity of multimorbidity conditions. Also, the complex enumeration of combinatorial multimorbidity features introduces challenges associated with combinatorial explosions. This study aims to assess the severity of COVID-19 in individuals with multiple medical conditions, considering their demographic characteristics such as age and sex. We propose an evolutionary machine learning model designed to handle sparsity, analyzing preexisting multimorbidity profiles of patients hospitalized with COVID-19 based on their medical history. Our objective is to identify the optimal set of multimorbidity feature combinations strongly associated with COVID-19 severity. We also apply the Apriori algorithm to these evolutionarily derived predictive feature combinations to identify those with high support. We used data from 3 administrative sources in Piedmont, Italy, involving 12,793 individuals aged 45-74 years who tested positive for COVID-19 between February and May 2020. From their 5-year pre-COVID-19 medical histories, we extracted multimorbidity features, including drug prescriptions, disease diagnoses, sex, and age. Focusing on COVID-19 hospitalization, we segmented the data into 4 cohorts based on age and sex. Addressing data imbalance through random resampling, we compared various machine learning algorithms to identify the optimal classification model for our evolutionary approach. Using 5-fold cross-validation, we evaluated each model's performance. Our evolutionary algorithm, utilizing a deep learning classifier, generated prediction-based fitness scores to pinpoint multimorbidity combinations associated with COVID-19 hospitalization risk. Eventually, the Apriori algorithm was applied to identify frequent combinations with high support. We identified multimorbidity predictors associated with COVID-19 hospitalization, indicating more severe COVID-19 outcomes. Frequently occurring morbidity features in the final evolved combinations were age>53, R03BA (glucocorticoid inhalants), and N03AX (other antiepileptics) in cohort 1; A10BA (biguanide or metformin) and N02BE (anilides) in cohort 2; N02AX (other opioids) and M04AA (preparations inhibiting uric acid production) in cohort 3; and G04CA (Alpha-adrenoreceptor antagonists) in cohort 4. When combined with other multimorbidity features, even less prevalent medical conditions show associations with the outcome. This study provides insights beyond COVID-19, demonstrating how repurposed administrative data can be adapted and contribute to enhanced risk assessment for vulnerable populations.

Fully and Weakly Supervised Deep Learning for Meniscal Injury Classification, and Location Based on MRI.

Meniscal injury is a common cause of knee joint pain and a precursor to knee osteoarthritis (KOA). The purpose of this study is to develop an automatic pipeline for meniscal injury classification and localization using fully and weakly supervised networks based on MRI images. In this retrospective study, data were from the osteoarthritis initiative (OAI). The MR images were reconstructed using a sagittal intermediate-weighted fat-suppressed turbo spin-echo sequence. (1) We used 130 knees from the OAI to develop the LGSA-UNet model which fuses the features of adjacent slices and adjusts the blocks in Siam to enable the central slice to obtain rich contextual information. (2) One thousand seven hundred and fifty-six knees from the OAI were included to establish segmentation and classification models. The segmentation model achieved a DICE coefficient ranging from 0.84 to 0.93. The AUC values ranged from 0.85 to 0.95 in the binary models. The accuracy for the three types of menisci (normal, tear, and maceration) ranged from 0.60 to 0.88. Furthermore, 206 knees from the orthopedic hospital were used as an external validation data set to evaluate the performance of the model. The segmentation and classification models still performed well on the external validation set. To compare the diagnostic performances between the deep learning (DL) models and radiologists, the external validation sets were sent to two radiologists. The binary classification model outperformed the diagnostic performance of the junior radiologist (0.82-0.87 versus 0.74-0.88). This study highlights the potential of DL in knee meniscus segmentation and injury classification which can help improve diagnostic efficiency.

Revolutionizing anemia detection: integrative machine learning models and advanced attention mechanisms

This study addresses the critical issue of anemia detection using machine learning (ML) techniques. Although a widespread blood disorder with significant health implications, anemia often remains undetected. This necessitates timely and efficient diagnostic methods, as traditional approaches that rely on manual assessment are time-consuming and subjective. The present study explored the application of ML – particularly classification models, such as logistic regression, decision trees, random forest, support vector machines, Naïve Bayes, and k-nearest neighbors – in conjunction with innovative models incorporating attention modules and spatial attention to detect anemia. The proposed models demonstrated promising results, achieving high accuracy, precision, recall, and F1 scores for both textual and image datasets. In addition, an integrated approach that combines textual and image data was found to outperform the individual modalities. Specifically, the proposed AlexNet Multiple Spatial Attention model achieved an exceptional accuracy of 99.58%, emphasizing its potential to revolutionize automated anemia detection. The results of ablation studies confirm the significance of key components – including the blue-green-red, multiple, and spatial attentions – in enhancing model performance. Overall, this study presents a comprehensive and innovative framework for noninvasive anemia detection, contributing valuable insights to the field.

Enhancing intrusion detection: a hybrid machine and deep learning approach

The volume of data transferred across communication infrastructures has recently increased due to technological advancements in cloud computing, the Internet of Things (IoT), and automobile networks. The network systems transmit diverse and heterogeneous data in dispersed environments as communication technology develops. The communications using these networks and daily interactions depend on network security systems to provide secure and reliable information. On the other hand, attackers have increased their efforts to render systems on networks susceptible. An efficient intrusion detection system is essential since technological advancements embark on new kinds of attacks and security limitations. This paper implements a hybrid model for Intrusion Detection (ID) with Machine Learning (ML) and Deep Learning (DL) techniques to tackle these limitations. The proposed model makes use of Extreme Gradient Boosting (XGBoost) and convolutional neural networks (CNN) for feature extraction and then combines each of these with long short-term memory networks (LSTM) for classification. Four benchmark datasets CIC IDS 2017, UNSW NB15, NSL KDD, and WSN DS were used to train the model for binary and multi-class classification. With the increase in feature dimensions, current intrusion detection systems have trouble identifying new threats due to low test accuracy scores. To narrow down each dataset’s feature space, XGBoost, and CNN feature selection algorithms are used in this work for each separate model. The experimental findings demonstrate a high detection rate and good accuracy with a relatively low False Acceptance Rate (FAR) to prove the usefulness of the proposed hybrid model.

G-SAM: GMM-based segment anything model for medical image classification and segmentation

G-SAM: GMM-based segment anything model for medical image classification and segmentation

HyperGCN – a multi-layer multi-exit graph neural network to enhance hyperspectral image classification

ABSTRACT Graph neural networks (GNNs) have recently garnered significant attention due to their exceptional performance across various applications, including hyperspectral (HS) image classification. However, most existing GNN-based models for HS image classification are limited depth models and often suffer from performance degradation as model depth increases. This study introduces HyperGCN, an exclusive GNN-based model designed with multiple graph convolutional layers to exploit the rich spectral information inherent in HS images, thereby enhancing classification performance. To address performance degradation, HyperGCN incorporates techniques resistant to oversmoothing into its architecture. Additionally, multiple-side exit branches are integrated into the intermediate layers of HyperGCN, enabling dynamic management of the complexity of HS images. Less complex HS images are processed by fewer layers, exiting early via attached branches, while more complex images traverse multiple layers until reaching the final output layer. Extensive experiments on four benchmark HS datasets (Indian Pines, Pavia University, Salinas, and Botswana) demonstrate HyperGCN’s superior performance over basic GNN-based models. Notably, HyperGCN outperforms or performs comparably to the CNN-GNN combined model in classifying HS images. Furthermore, the superior performance of multi-exit HyperGCN over its single-exit counterpart emphasizes the effectiveness of incorporating side exit branches in GNN-based HS image classification. Compared to state-of-the-art models, multi-exit HyperGCN demonstrates competitive performance, highlighting its effectiveness in handling complex spectral information in HS images while maintaining an acceptable balance between accuracy and computational efficiency.

Classification Model for Real-Time Monitoring of Machining Status of Turned Workpieces

Classification Model for Real-Time Monitoring of Machining Status of Turned Workpieces

Prioritising deteriorating patients using time-to-event analysis: prediction model development and internal–external validation

BackgroundBinary classification models are frequently used to predict clinical deterioration, however they ignore information on the timing of events. An alternative is to apply time-to-event models, augmenting clinical workflows by ranking patients by predicted risks. This study examines how and why time-to-event modelling of vital signs data can help prioritise deterioration assessments using lift curves, and develops a prediction model to stratify acute care inpatients by risk of clinical deterioration.MethodsWe developed and validated a Cox regression for time to in-hospital mortality. The model used time-varying covariates to estimate the risk of clinical deterioration. Adult inpatient medical records from 5 Australian hospitals between 1 January 2019 and 31 December 2020 were used for model development and validation. Model discrimination and calibration were assessed using internal–external cross validation. A discrete-time logistic regression model predicting death within 24 h with the same covariates was used as a comparator to the Cox regression model to estimate differences in predictive performance between the binary and time-to-event outcome modelling approaches.ResultsOur data contained 150,342 admissions and 1016 deaths. Model discrimination was higher for Cox regression than for discrete-time logistic regression, with cross-validated AUCs of 0.96 and 0.93, respectively, for mortality predictions within 24 h, declining to 0.93 and 0.88, respectively, for mortality predictions within 1 week. Calibration plots showed that calibration varied by hospital, but this can be mitigated by ranking patients by predicted risks.ConclusionTime-varying covariate Cox models can be powerful tools for triaging patients, which may lead to more efficient and effective care in time-poor environments when the times between observations are highly variable.

Altered insular functional activity among electronic cigarettes users with nicotine dependence

Electronic cigarettes (e-cigs) use, especially among youngsters, has been on the rise in recent years. However, little is known about the long-term effects of the use of e-cigs on brain functional activity. We acquired the resting-state functional magnetic resonance imaging (rs-fMRI) data from 93 e-cigs users with nicotine dependence and 103 health controls (HC). The local synchronization was analyzed via the regional homogeneity (ReHo) method at voxel-wise level. The functional connectivity (FC) between the nucleus accumbens (NAcc), the ventral tegmental area (VTA), and the insula was calculated at ROI-wise level. The support vector machining classification model based on rs-fMRI measures was used to identify e-cigs users from HC. Compared with HC, nicotine-dependent e-cigs users showed increased ReHo in the right rolandic operculum and the right insula (p < 0.05, FDR corrected). At the ROI-wise level, abnormal FCs between the NAcc, the VTA, and the insula were found in e-cigs users compared to HC (p < 0.05, FDR corrected). Correlation analysis found a significant negative correlation between ReHo in the left NAcc and duration of e-cigs use (r = −0.273, p = 0.008, FDR corrected). The following support vector machine model based on significant results of rs-fMRI successfully differentiates chronic e-cigs users from HC with an accuracy of 73.47%, an AUC of 0.781, a sensitivity of 67.74%, and a specificity of 78.64%. Dysregulated spontaneous activity and FC of addiction-related regions were found in e-cigs users with nicotine dependence, which provides crucial insights into the prevention of its initial use and intervention for quitting e-cigs.

The synergy of morphokinetic parameters and sHLA-G in cleavage embryo enhancing implantation rates

Objective: This study aimed to assess the relationship between implantation and soluble HLA-G (sHLA-G) expression in cleavage embryo culture medium (ECM) in conjunction with early developmental kinetics determined by time-lapse imaging (TLI).Methods: A retrospective, single-center study was conducted involving 238 embryos from 165 patients who underwent Frozen-thawed embryo transfer (FET) using autologous oocytes, with either single or double embryo transfer. TLI morphokinetic parameters (t2, t3, t4, t5, t6, t7, t8, cc2, s2, cc3, s3) of embryos were analyzed, and sHLA-G levels in D3 ECM were measured using an enzyme-linked immunosorbent assay (ELISA). A hierarchical classification model was developed to categorize embryos into five groups (A, B, C, D, E). The correlation between sHLA-G levels, TLI classification of embryos, and embryo implantation was investigated to establish a non-invasive method for evaluating implantation potential. Multivariate logistic regression analysis was performed to identify potential influencing factors, and receiver operating characteristic (ROC) curves were used to evaluate the predictive value for implantation.Results: Multivariate unconditional logistic regression analysis indicated that TLI parameters t5 and s3 and sHLA-G level in ECM were independent risk factors affecting embryo implantation. The implantation rate decreased from TLI classification A to E. The proposed classification model effectively assessed the implantation potential of embryos. The implantation rate was higher in the sHLA-G positive group compared to the sHLA-G negative group (p &amp;lt; 0.001). The expression of sHLA-G in D3 ECM, combined with the TLI classification model, accurately evaluated the implantation potential of embryos with an AUC of 0.876.Conclusion: The integration of cleavage kinetics and embryonic sHLA-G expression could reliably identify embryos with a high likelihood of successful implantation.

A brain tumor diagnosis approach based on deep separable convolutional networks and attention mechanisms

Brain tumors rank among the most lethal types of tumors. Magnetic Resonance Imaging (MRI) technology can clearly display the position, size, and borders of the tumors. Hence, MRI is frequently used in clinical diagnostics to detect brain tumors. Deep learning and related methods have been widely used in computer vision research recently for diagnosis and classification of MRI images of brain tumors. One trend is to achieve better performance by increasing model complexity. However, at the same time, the trainable parameters of the model increases accordingly. Too many parameters will lead to more difficult model training and optimization, and are prone to overfitting. To address this problem, this study constructs a model that incorporates a depthwise separable convolution technique and an attention mechanism to balance model performance and complexity. The model achieves 97.41% accuracy in the brain tumor classification task, which exceeds the 96.72% accuracy of the pre-trained model MobileNetV2, and shows good image classification ability. Future work could test the model's classification results on noisy images and investigate how to optimize the model's generalization ability.

Radiograph recognition of COVID-19 based on DenseNet

This paper presents a neural network approach for pneumonia image classification. Utilizing thousands of actual X-ray images from both pneumonia patients and healthy individuals, a classification model is developed. This neural network model, a prevalent machine learning technique, is employed as an adjunct tool to aid pneumonia diagnosis and pre-screening. The algorithms utilized in the study are comprehensively analyzed and detailed. Through an examination of the network's architecture, several effective methods for enhancing the model are proposed, leading to improved model structure and classification performance. The novel model structure proposed in this study is demonstrated and evaluated. The final training accuracy exceeds 95%, demonstrating the model's proficiency in learning from the training data. Moreover, the test accuracy hovers around 92%, indicating the model's robust performance in generalizing to unseen data.

Development and validation of an Adaboost model for breast cancer classification

The mutation of breast cells leads to breast cancer,a lump causing illnesses .A large amount of women who have the concern of cancer are suffering from mutation in their breast cells. Early diagnosis of breast cancer can significantly improve the survival rate of patients by allowing them to receive timely clinical treatment. Accurate classification from tumor data prevents patients from receiving unnecessary treatment. Therefore, correctly diagnosing breast cancer and classifying patients into malignant or benign groups is a hot topic. In this study, the Adaboost algorithm is used to sort breast cancer depending on whether it is benign or malignant by combining the one-hot coding approach and imbalance learning. The one-hot coding approach overcomes the bias caused by the LabelEncoder coding approach, and the synthetic minority over-sampling technique, which improves the classification performance of Adaboost by augmenting the categorization balanced data structure with more minority class samples, so that its diagnosis of breast cancer reaches 99% accuracy, which is better than other machine learning models, we propose this model can be used for the diagnosis of breast cancer, providing a more accurate and faster way to classify breast cancer.

Development of a Robust CNN Model for Mango Leaf Disease Detection and Classification: A Precision Agriculture Approach

Development of a Robust CNN Model for Mango Leaf Disease Detection and Classification: A Precision Agriculture Approach

Designing efficient brain tumor classifier using hybrid EfficientNet-faster R-CNN deep learning model

Abstract Purpose: Brain tumors have historically posed a significant risk to individuals, potentially leading to fatality. However, in contemporary times, they have emerged as one of the most dangerous health issues affecting both children and adults. The effects of this phenomenon result in the unregulated proliferation of brain cells. Within the field of biological image processing, the utilisation of deep learning algorithms offers a distinct and unparalleled experience. The Convolutional Neural Network (CNN) is a pivotal component in brain tumor categorization applications. However, a notable limitation of CNNs is their extensive execution time, primarily attributed to the substantial number of trainable parameters involved. &amp;#xD;Methods: This study proposes a hybrid model for brain tumor classification that combines faster R-CNN and EfficientNet. The objective is to minimise the time required for classification without compromising accuracy. The data collection from Figshare was employed during the model's development.&amp;#xD;Results and Conclusion: The hybrid model proposed in this study demonstrates a notable accuracy of 98.96% during the training phase and 99.2% during the testing phase, surpassing the performance of both the EfficientNet model and the Faster R-CNN model when employed individually. The aforementioned findings were derived through a comparative analysis of the Hybrid model, the EfficientNet model, and the Faster R-CNN model.

Comprehensive analysis of pathological and biochemical data of prostate tumors based on multiple machine learning models

This study conducts a comprehensive analysis of global prostate tumor cases, employing various machine learning models for classification. The research focuses on data preprocessing, feature selection, and model training, utilizing effective techniques for handling biochemical and pathological data. In model training, a range of algorithms such as XGBoost, Random Forest, LightGBM, and CatBoost were explored, ultimately achieving an 89% test accuracy through a Stacking model. For pathological data, strategies included addressing missing values, text cleaning, and segmentation, combining CountVectorizer with multiple algorithms. LightGBM demonstrated optimal performance with an accuracy of 82%. The Bert model, post-segmentation and Focal loss optimization, achieved an accuracy of 80.39%. In summary, this research leverages machine learning to provide a convenient approach for diagnosing and treating prostate tumors, offering robust model support for predicting related diseases.

Lung Sound Classification for Respiratory Disease Identification Using Deep Learning: A Survey

Integrating artificial intelligence (AI) into lung sound classification has markedly improved respiratory disease diagnosis by analysing intricate patterns within audio data. This study is driven by the widespread issue of lung diseases, which affect around 500 million people globally. Early detection of respiratory diseases is crucial for delivering timely and effective treatment. Our study consists of a comprehensive survey of lung sound classification methodologies, exploring the advancements made in leveraging AI to identify and classify respiratory diseases. This survey thoroughly investigates lung sound classification models, along with data augmentation, feature extraction, explainable techniques and support tools to improve systems for diagnosing respiratory conditions. Our goal is to provide meaningful insights for healthcare professionals, researchers and technologists who are dedicated to developing methodologies for the early detection of pulmonary diseases. The paper provides a summary of the current status of lung sound classification research, highlighting both advancements and challenges in the use of AI for more accurate and efficient diagnostic methods in respiratory healthcare.

An improved efficientnet B7 underwater marine organism image classification model based on the spatial group enhancement attention mechanisms

In this paper, we adopt the Efficientnet B7 model, which is an excellent performer in deep learning algorithms, and improve it by combining with the Spatial Group Enhancement attention mechanism to provide an innovative method for underwater biological image classification. After a reasonable division of the dataset, we introduced the improved Efficientnet B7 model for training. By observing the change of the loss curve on the training set, it can be seen that the loss value of the model gradually decreases from 0.6 to 0.05 and tends to be stable, which indicates that the classification prediction of the model is gradually close to the real result, and it can classify the underwater marine organisms images effectively. The accuracy on the training set gradually increases from the initial 80.12% to 98.31%, and the recall also grows from 75.82% to 98.93%, showing that the model predicts well. The performance on the test set shows an accuracy of 84.86%, a recall of 82.40%, and an F1 value of 80.2%, indicating that the model has good generalisation ability. This means that our proposed improved methods and ideas have achieved significant results in the task of underwater biological image classification, providing a useful reference for research in related fields. By comparing the experimental results, it can be seen that the optimisation of the Efficientnet B7 model by introducing the Spatial Group Enhancement attention mechanism achieves better performance in the underwater marine organisms image classification task, which lays the foundation for the future application of deep learning in underwater environments. This study is of positive significance for the promotion of underwater biology research, marine protection and other fields, and provides new ideas and methods for carrying out more in-depth related research.