Test F1 Score Research Articles

Efficacy of automated machine learning models and feature engineering for diagnosis of equivocal appendicitis using clinical and computed tomography findings

This study evaluates the diagnostic efficacy of automated machine learning (AutoGluon) with automated feature engineering and selection (autofeat), focusing on clinical manifestations, and a model integrating both clinical manifestations and CT findings in adult patients with ambiguous computed tomography (CT) results for acute appendicitis (AA). This evaluation was compared with conventional single machine learning models such as logistic regression(LR) and established scoring systems such as the Adult Appendicitis Score(AAS) to address the gap in diagnostic approaches for uncertain AA cases. In this retrospective analysis of 303 adult patients with indeterminate CT findings, the cohort was divided into appendicitis (n = 115) and non-appendicitis (n = 188) groups. AutoGluon and autofeat were used for AA prediction. The AutoGluon-clinical model relied solely on clinical data, whereas the AutoGluon-clinical-CT model included both clinical and CT data. The area under the receiver operating characteristic curve (AUROC) and other metrics for the test dataset, namely accuracy, sensitivity, specificity, PPV, NPV, and F1 score, were used to compare AutoGluon models with single machine learning models and the AAS. The single ML models in this study were LR, LASSO regression, ridge regression, support vector machine, decision tree, random forest, and extreme gradient boosting. Feature importance values were extracted using the “feature_importance” attribute from AutoGluon. The AutoGluon-clinical model demonstrated an AUROC of 0.785 (95% CI 0.691–0.890), and the ridge regression model with only clinical data revealed an AUROC of 0.755 (95% CI 0.649–0.861). The AutoGluon-clinical-CT model (AUROC 0.886 with 95% CI 0.820–0.951) performed better than the ridge model using clinical and CT data (AUROC 0.852 with 95% CI 0.774–0.930, p = 0.029). A new feature, exp(-(duration from pain to CT)3 + rebound tenderness), was identified (importance = 0.049, p = 0.001). AutoML (AutoGluon) and autoFE (autofeat) enhanced the diagnosis of uncertain AA cases, particularly when combining CT and clinical findings. This study suggests the potential of integrating AutoML and autoFE in clinical settings to improve diagnostic strategies and patient outcomes and make more efficient use of healthcare resources. Moreover, this research supports further exploration of machine learning in diagnostic processes.

Meta-model structural monitoring with cutting-edge AAE-VMD fusion alongside optimized machine learning methods

Transfer learning significantly enhances machine learning by leveraging knowledge from one dataset to boost performance on another, which is particularly beneficial when labelled data ares limited or costly. Sensor fusion, an essential technique in structural health monitoring, improves the effectiveness of transfer learning by combining data from multiple sensors to extract more informative features. This article proposes a novel meta-model structural monitoring using a new data fusion method named the adversarial autoencoder (AAE)–variational mode decomposition (VMD) algorithm, which integrates optimization algorithms, transfer learning, and machine learning techniques for damage detection tasks. The proposed meta-model combines transfer learning with an optimized machine learning framework for training and employs pretrained models for testing across diverse datasets. First, the tensors are fused using the AAE approach into 300 data points, reducing noise and outliers, performing dimensionality reduction, and enriching the training and test datasets. Then, a preprocessing step involves decomposing and denoising tensors using the VMD algorithm, followed by selecting the most informative intrinsic mode functions (IMFs) based on their variance. These selected IMFs are concatenated, and 13 statistical features are extracted from them and used as inputs for machine learning models. Various optimization algorithms are employed to fine-tune the hyperparameters of the machine learning models for optimal classification results. Validation of this meta-model utilizes the dataset collected from a steel grandstand structure, available in benchmark dataset format. For decomposed fused tensors, both particle swarm optimization and covariance matrix adaptation evolution strategy emerge as equally effective optimization techniques for K-nearest neighbours (KNN), consistently achieving the highest mean test accuracy and F1 score of 99.5%. Conversely, KNN stands out as a robust and reliable classification algorithm for denoised fused tensors in transfer learning classification problems, consistently demonstrating perfect accuracy and an F1 score of 1.0 ± 0.0 across all optimization techniques.

Intelligent risk identification for drilling lost circulation incidents using data-driven machine learning

In drilling operations, lost circulation (LC) poses a significant challenge, potentially leading to severe accidents such as overflow or blowouts if not accurately identified and controlled. This study introduces a method for identifying LC risk severity using data-driven machine learning and statistical algorithms, specifically demonstrated in the Ying-Qiong Basin of the South China Sea. The method begins with variance filtering to eliminate invalid data, followed by the application of the Pearson correlation coefficient to remove redundant data. This process results in the selection of 12 logging parameters out of the initial 38. Combined with indirect judgments of LC severity based on relevant prior knowledge, the data is labeled to construct the original dataset. A feature extraction and optimization method is proposed, which employs sliding time windows to extract 21 features. These features are then selected and optimized using a random forest algorithm to construct the optimal feature set. To enhance the controllability of the Extreme Learning Machine (ELM) model, the sparrow search algorithm is integrated. Additionally, several fitness functions are introduced for both regression and classification models, resulting in the development of the improved ELM (IELM) model. The dataset is split into training and test sets, and the performance of the IELM model is compared to that of the standard ELM and BP neural network models. The results indicate that the IELM model outperforms the other two, achieving an impressive test F1 score of 97.22 % for accurately identifying LC severity. Moreover, the model trained using the optimal feature set demonstrates higher accuracy and faster convergence. The proposed feature extraction and optimization method effectively increases the amount of information contained in the data, thereby enhancing the model's performance.

Predicting TCM patterns in PCOS patients: An exploration of feature selection methods and multi-label machine learning models

BackgroundTraditional Chinese Medicine (TCM) offers individualized treatment for Polycystic Ovary Syndrome (PCOS) through pattern differentiation, but the subjectivity of TCM diagnoses can lead to inconsistent outcomes. Integrating machine learning (ML) offers an objective basis to support TCM diagnoses. This study aims to evaluate various feature selection techniques and multi-label ML algorithms to develop an effective predictive model for classifying TCM patterns in PCOS patients, thereby enhancing diagnostic standardization and treatment personalization. MethodsThe study utilized a dataset comprising 432 patients with PCOS, exhibiting one or more of five TCM patterns. Feature selection began with Variance Thresholding (VT), followed by a comparison of five advanced techniques: Statistical Analysis Test, Recursive Feature Elimination with Cross-Validation (RFECV), Least Absolute Shrinkage and Selection Operator Regression, BorutaShap, and ReliefF. To ascertain the most effective model for predicting PCOS TCM patterns, four ML algorithms—Support Vector Machine, Logistic Regression, Extreme Gradient Boosting (XGBoost), and Artificial Neural Networks—were evaluated against the identified feature set. ResultsVT reduced the feature count from 224 to 174. RFECV emerged as the most effective feature selection method, identifying 67 key features. XGBoost emerged as the top-performing model, demonstrating superior testing accuracy (0.7870), F1 score (0.9519), and Hamming loss (0.0481) with RFECV-optimized features. ConclusionsThe RFECV-XGBoost model proved effective for classifying TCM patterns in PCOS. It emphasizes the necessity of precise feature selection and the significant capabilities of ML in advancing TCM pattern diagnostics, marking a significant step toward enhancing precise and personalized healthcare in biomedical studies.

Leveraging protein language model embeddings and logistic regression for efficient and accurate in-silico acidophilic proteins classification

The increasing demand for eco-friendly technologies in biotechnology necessitates effective and sustainable catalysts. Acidophilic proteins, functioning optimally in highly acidic environments, hold immense promise for various applications, including food production, biofuels, and bioremediation. However, limited knowledge about these proteins hinders their exploration. This study addresses this gap by employing in silico methods utilizing computational tools and machine learning. We propose a novel approach to predict acidophilic proteins using protein language models (PLMs), accelerating discovery without extensive lab work. Our investigation highlights the potential of PLMs in understanding and harnessing acidophilic proteins for scientific and industrial advancements. We introduce the ACE model, which combines a simple Logistic Regression model with embeddings derived from protein sequences processed by the ProtT5 PLM. This model achieves high performance on an independent test set, with accuracy (0.91), F1-score (0.93), and Matthew's correlation coefficient (0.76). To our knowledge, this is the first application of pre-trained PLM embeddings for acidophilic protein classification. The ACE model serves as a powerful tool for exploring protein acidophilicity, paving the way for future advancements in protein design and engineering.

Deep learning classification of pediatric spinal radiographs for use in large scale imaging registries.

The purpose of this study is to develop and apply an algorithm that automatically classifies spine radiographs of pediatric scoliosis patients. Anterior-posterior (AP) and lateral spine radiographs were extracted from the institutional picture archive for patients with scoliosis. Overall, there were 7777 AP images and 5621 lateral images. Radiographs were manually classified into ten categories: two preoperative and three postoperative categories each for AP and lateral images. The images were split into training, validation, and testing sets (70:15:15 proportional split). A deep learning classifier using the EfficientNet B6 architecture was trained on the spine training set. Hyperparameters and model architecture were tuned against the performance of the models in the validation set. The trained classifiers had an overall accuracy on the test set of 1.00 on 1166 AP images and 1.00 on 843 lateral images. Precision ranged from 0.98 to 1.00 in the AP images, and from 0.91 to 1.00 on the lateral images. Lower performance was observed on classes with fewer than 100 images in the dataset. Final performance metrics were calculated on the assigned test set, including accuracy, precision, recall, and F1 score (the harmonic mean of precision and recall). A deep learning convolutional neural network classifier was trained to a high degree of accuracy to distinguish between 10 categories pre- and postoperative spine radiographs of patients with scoliosis. Observed performance was higher in more prevalent categories. These models represent an important step in developing an automatic system for data ingestion into large, labeled imaging registries.

Transfer-Learning Approach for Enhanced Brain Tumor Classification in MRI Imaging

Background: Intracranial neoplasm, often referred to as a brain tumor, is an abnormal growth or mass of tissues in the brain. The complexity of the brain and the associated diagnostic delays cause significant stress for patients. This study aims to enhance the efficiency of MRI analysis for brain tumors using deep transfer learning. Methods: We developed and evaluated the performance of five pre-trained deep learning models—ResNet50, Xception, EfficientNetV2-S, ResNet152V2, and VGG16—using a publicly available MRI scan dataset to classify images as glioma, meningioma, pituitary, or no tumor. Various classification metrics were used for evaluation. Results: Our findings indicate that these models can improve the accuracy of MRI analysis for brain tumor classification, with the Xception model achieving the highest performance with a test F1 score of 0.9817, followed by EfficientNetV2-S with a test F1 score of 0.9629. Conclusions: Implementing pre-trained deep learning models can enhance MRI accuracy for detecting brain tumors.

A Novel Intelligent Condition Monitoring Framework of Essential Service Water Pumps

Essential service water pumps are necessary safety devices responsible for discharging waste heat from containments through seawater; their condition monitoring is critical for the safe and stable operation of seaside nuclear power plants. However, it is difficult to directly apply existing intelligent methods to these pumps. Therefore, an intelligent condition monitoring framework is designed, including the parallel implementation of unsupervised anomaly detection and fault diagnosis. A model preselection algorithm based on the highest validation accuracy is proposed for anomaly detection and fault diagnosis model selection among existing models. A novel information integration algorithm is proposed to fuse the output of anomaly detection and fault diagnosis. According to the experimental results of modules, a kernel principal component analysis using mean fusion processing multi-channel data (AKPCA (fusion)) is selected, and a support vector machine using mean fusion processing multi-channel data (SVM (fusion)) is selected. The overall test accuracy and false negative rate of AKPCA (fusion) are 0.83 and 0.144, respectively, and the overall test accuracy and f1-score of SVM (fusion) are 0.966 and 1, respectively. The test results of AKPCA (fusion), SVM (fusion), and the proposed information integration algorithm show that the information integration algorithm successfully avoids a lack of abnormal status information and misdiagnosis. The proposed framework is a meaningful attempt to achieve the intelligent condition monitoring of complex equipment.

Deep transfer learning for detection of breast arterial calcifications on mammograms: a comparative study

IntroductionBreast arterial calcifications (BAC) are common incidental findings on routine mammograms, which have been suggested as a sex-specific biomarker of cardiovascular disease (CVD) risk. Previous work showed the efficacy of a pretrained convolutional network (CNN), VCG16, for automatic BAC detection. In this study, we further tested the method by a comparative analysis with other ten CNNs.Material and methodsFour-view standard mammography exams from 1,493 women were included in this retrospective study and labeled as BAC or non-BAC by experts. The comparative study was conducted using eleven pretrained convolutional networks (CNNs) with varying depths from five architectures including Xception, VGG, ResNetV2, MobileNet, and DenseNet, fine-tuned for the binary BAC classification task. Performance evaluation involved area under the receiver operating characteristics curve (AUC-ROC) analysis, F1-score (harmonic mean of precision and recall), and generalized gradient-weighted class activation mapping (Grad-CAM++) for visual explanations.ResultsThe dataset exhibited a BAC prevalence of 194/1,493 women (13.0%) and 581/5,972 images (9.7%). Among the retrained models, VGG, MobileNet, and DenseNet demonstrated the most promising results, achieving AUC-ROCs > 0.70 in both training and independent testing subsets. In terms of testing F1-score, VGG16 ranked first, higher than MobileNet (0.51) and VGG19 (0.46). Qualitative analysis showed that the Grad-CAM++ heatmaps generated by VGG16 consistently outperformed those produced by others, offering a finer-grained and discriminative localization of calcified regions within images.ConclusionDeep transfer learning showed promise in automated BAC detection on mammograms, where relatively shallow networks demonstrated superior performances requiring shorter training times and reduced resources.Relevance statementDeep transfer learning is a promising approach to enhance reporting BAC on mammograms and facilitate developing efficient tools for cardiovascular risk stratification in women, leveraging large-scale mammographic screening programs.Key points• We tested different pretrained convolutional networks (CNNs) for BAC detection on mammograms.• VGG and MobileNet demonstrated promising performances, outperforming their deeper, more complex counterparts.• Visual explanations using Grad-CAM++ highlighted VGG16’s superior performance in localizing BAC.Graphical

Sunflower Origin Identification Based on Multi-Source Information Fusion Technique of Kernel Extreme Learning Machine

This study constructs a model for the rapid identification of the origins of edible sunflower (Helianthus) using Kernel Extreme Learning Machine (KELM) with multi-source information fusion technology. Near-infrared spectroscopy (NIRS) and nuclear magnetic resonance spectroscopy (NMRS) were utilized to analyze 180 sunflower samples from the Xinjiang, Heilongjiang, and Inner Mongolia regions. Initially, the identification models for the origin of sunflowers using NIR and NMR data were compared between two algorithms: the Extreme Learning Machine (ELM) and KELM, combined with various spectral preprocessing methods. The experiment found that the NIR spectral model preprocessed with standard normal variate (SNV) using the KELM algorithm was the most accurate, achieving accuracies of 98.7% in the training set and 97.2% in the test set. The spin-echo NMR spectral model preprocessed with non-local means (NLMs) using the KELM algorithm was the second best, with accuracies of 98.4% in the training set and 96.4% in the test set. To further improve the accuracy of the identification models, innovative sunflower origin identification models were developed based on data layer fusion and feature layer fusion using NIRS and NMRS. In the data layer fusion model, the KELM algorithm model was optimal, achieving a test set accuracy and F1 score of 98.2% and 98.18%, respectively, an improvement of 1.0% over the best single data source model. In the feature layer fusion model, four types of feature-layer information-fusion identification models were established using two feature extraction algorithms, Competitive Adaptive Reweighted Sampling (CARS) and Variable Importance Projection (VIP), combined with joint feature and simple merging feature strategies. The CARS-KELM algorithm combined with the joint feature method was found to be the best, achieving 100% accuracy in both the training and test sets, an improvement of 2.8% over the best single data source model. Identifying the origin of edible sunflower using NIRS and NMRS is demonstrated as feasible by the results. The best single-spectrum sunflower origin identification model was achieved using the KELM algorithm with SNV preprocessing. The feature layer fusion method combining NIRS and NMRS data is suitable for handling the task of sunflower origin identification. This method significantly improves the recognition accuracy of the model compared to a single model, achieving fast and accurate origin identification of edible sunflowers. The research results provide a new method for rapid identification of sunflower origin.

Natural Language Processing-Driven Artificial Intelligence Models for the Diagnosis of Lumbar Disc Herniation with L5 and S1 Radiculopathy: A Preliminary Evaluation

To develop and validate natural language processing-driven artificial intelligence (AI) models for the diagnosis of lumbar disc herniation (LDH) with L5 and S1 radiculopathy using electronic health records (EHRs). EHRs of patients undergoing single-level percutaneous endoscopic lumbar discectomy for the treatment of LDH at the L4/5 or L5/S1 level between June 1, 2013, and December 31, 2021, were collected. The primary outcome was LDH with L5 and S1 radiculopathy, which was defined as nerve root compression recorded in the operative notes. Datasets were created using the history of present illness text and positive symptom text with radiculopathy (L5 or S1), respectively. The datasets were randomly split into a training set and a testing set in a 7:3 ratio. Two machine learning models, the long short-term memory network and Extreme Gradient Boosting, were developed using the training set. Performance evaluation of the models on the testing set was done using measures such as the receiver operating characteristic curve, area under the curve, accuracy, recall, F1-score, and precision. The study included a total of 1681 patients, with 590 patients having L5 radiculopathy and 1091 patients having S1 radiculopathy. Among the 4 models developed, the long short-term memory model based on positive symptom text showed the best discrimination in the testing set, with precision (0.9054), recall (0.9405), accuracy (0.8950), F1-score (0.9226), and area under the curve (0.9485). This study provides preliminary validation of the concept that natural language processing-driven AI models can be used for the diagnosis of lumbar disease using EHRs. This study could pave the way for future research that may develop more comprehensive and clinically impactful AI-driven diagnostic systems.

Prediction of Protein-DNA Interface Hot Spots Based on Empirical Mode Decomposition and Machine Learning.

Protein-DNA complex interactivity plays a crucial role in biological activities such as gene expression, modification, replication and transcription. Understanding the physiological significance of protein-DNA binding interfacial hot spots, as well as the development of computational biology, depends on the precise identification of these regions. In this paper, a hot spot prediction method called EC-PDH is proposed. First, we extracted features of these hot spots' solid solvent-accessible surface area (ASA) and secondary structure, and then the mean, variance, energy and autocorrelation function values of the first three intrinsic modal components (IMFs) of these conventional features were extracted as new features via the empirical modal decomposition algorithm (EMD). A total of 218 dimensional features were obtained. For feature selection, we used the maximum correlation minimum redundancy sequence forward selection method (mRMR-SFS) to obtain an optimal 11-dimensional-feature subset. To address the issue of data imbalance, we used the SMOTE-Tomek algorithm to balance positive and negative samples and finally used cat gradient boosting (CatBoost) to construct our hot spot prediction model for protein-DNA binding interfaces. Our method performs well on the test set, with AUC, MCC and F1 score values of 0.847, 0.543 and 0.772, respectively. After a comparative evaluation, EC-PDH outperforms the existing state-of-the-art methods in identifying hot spots.

Machine learning assisted classification between diabetic polyneuropathy and healthy subjects using plantar pressure and temperature data: a feasibility study

Automated and early detection of diabetics with polyneuropathy in an ambulatory health monitoring setup may reduce the major risk factors for diabetic patients. Increased and localized plantar pressure associated with impaired pain and temperature is a combination of developing foot ulcers in subjects with polyneuropathy. Although many interesting research works have been reported in this area, most of them emphasize on signal acquisition process and plantar pressure distribution in the foot region. In this work, a machine learning assisted low complexity technique was developed using plantar pressure and temperature signals which will classify between diabetic polyneuropathy and healthy subjects. Principal component analysis (PCA) and maximum relevance minimum redundancy (mRMR) methods were used for feature extraction and selection respectively followed by k-NN classifier for binary classification. The proposed technique was evaluated with 100 min of publicly available annotated data from 43 subjects and provides blind test accuracy, sensitivity, precision, F1-score, and area under curve (AUC) of 99.58%, 99.50%, 99.44%, 99.47% and 99.56% respectively. A low resource hardware implementation in ARM v6 controller required an average memory usage of 81.2 kB and latency of 1.31 s to process 9 s pressure and temperature data collected from 16 sensor channels for each of the foot region.

AI powered Cyberbullying Detection Model

Cyberbullying has arisen as an unavoidable and concerning issue via virtual entertainment stages, influencing the psychological well-being and prosperity of people around the world. To resolve this issue, this study proposes a cyberbullying recognition framework utilizing the K-SVM calculation. Utilizing the force of AI, the framework means to consequently distinguish and signal occurrences of cyberbullying progressively web-based entertainment content. The improvement of the location framework starts with the assortment and naming of a thorough dataset containing instances of cyberbullying and non-cyberbullying posts or remarks. After pre-handling the text information by eliminating unessential data, changing message over completely to lowercase, and tokenizing it, significant highlights are removed utilizing the pack of-words or TF-IDF methods. These changed element vectors act as contributions for preparing the K-SVM classifier, which tries to find the ideal hyper plane for successfully recognizing cyberbullying from non-cyberbullying content. The exhibition of the K-SVM model is assessed utilizing a different testing dataset, with measurements, for example, exactness, accuracy, review, F1-score, and ROC-AUC broke down to survey its viability in distinguishing cyberbullying cases. Model calibrating is led through trial and error with different K-SVM hyper boundaries and cross-approval methods to upgrade the framework's exhibition. Keywords: Cyberbullying, social media, Online harassment

Optimizing echo state networks for continuous gesture recognition in mobile devices: A comparative study

Continuous gesture recognition can be used to enhance human-computer interaction. This can be accomplished by capturing human movement with the use of the Inertial Measurement Units in smartphones and using machine learning algorithms to predict the intended gestures. Echo State Networks (ESNs) consist of a fixed internal reservoir that is able to generate rich and diverse nonlinear dynamics in response to input signals that capture temporal dependencies within the signal. This makes ESNs well-suited for time series prediction tasks, such as continuous gesture recognition. However, their application has not been rigorously explored, with regard to gesture recognition. In this study, we sought to enhance the efficacy of ESN models in continuous gesture recognition by exploring diverse model structures, fine-tuning hyperparameters, and experimenting with various training approaches. We used three different training schemes that used the Leave-one-out Cross-validation (LOOCV) protocol to investigate the performance in real-world scenarios with different levels of data availability: Leaving out data from one user to use for testing (F1-score: 0.89), leaving out a fraction of data from all users to use in testing (F1-score: 0.96), and training and testing using LOOCV on a single user (F1-score: 0.99). The obtained results outperformed the Long Short-Term Memory (LSTM) performance from past research (F1-score: 0.87) while maintaining a low training time of approximately 13 seconds compared to 63 seconds for the LSTM model. Additionally, we further explored the performance of the ESN models through behaviour space analysis using memory capacity, Kernel Rank, and Generalization Rank. Our results demonstrate that ESNs can be optimized to achieve high performance on gesture recognition in mobile devices on multiple levels of data availability. These findings highlight the practical ability of ESNs to enhance human-computer interaction.

Diabetes Diagnosis Using Deep Learning

Hyperglycemia is a complication of diabetes (high blood sugar). This condition causes biochemical alterations in the cells of the body, which may lead to structural and functional problems throughout the body, including the eye. Diabetes retinopathy (DR) is a type of retinal degeneration induced by long-term diabetes that may lead to blindness. propose our deep learning method for the early detection of retinopathy using an efficient net B1 model and using the APTOS 2019 dataset. we used the Gaussian filter as one of the most significant image-processing algorithms. It recognizes edges in the dataset and reduces superfluous noise. We will enlarge the retina picture to 224×224 (the Efficient Net B1 standard) and utilize data augmentation methods to enhance the dataset photographs, and balance the dataset (which was quite uneven), to avoid overfitting. By using Transfer learning we save training time by using a previously learned deep CNN and transfer learning weights. In this research, EfficientNetB1 is compared against Xception, InceptionV3, MobileNet, and ResNet50 as a deep transfer learning model. The proposed model's accuracy, precision, recall, and f1-score are all examined. The EfficientNetB1 model outperforms all others in terms of overall testing accuracy (86.1%), sensitivity (87.24%), precision (97.6%), and F1-Score (89.32 percent). This approach might help physicians diagnose Diabetic Retinopathy earlier.

Diabetes prediction using feature engineering and machine learning algorithms with security

The prevalence of diabetes has been steadily increasing, necessitating accurate prediction models to assist in early diagnosis and proactive management. In this paper, a hybrid machine learning-based diabetes prediction model has been proposed. To evaluate the model, the dataset was subsequently divided into training and testing subsets. We used the Random Forest Classifier, Light Gradient Boosting Mechanism Classifier, Gradient Boosting Classifier, Logistic Regression, K-Nearest Neighbours (KNN) Classifier, Naive Bayes Gaussian, Decision Tree Classifier, XGBoost Classifier, and Support Vector Classifier as nine different classifiers. Several metrics were used to evaluate the models, including testing accuracy, recall score, F1 score, and precision score. We have evaluated our model on the “Pima Indian Diabetes Database”[1], which served as the main dataset, for diabetes prediction. The proposed model serves as a practical framework for researchers and practitioners interested in leveraging machine learning techniques for diabetes prediction.

ViT-ILD: A Vision Transformer-based Neural Network for Detection of Interstitial Lung Disease from CT Images

Interstitial Lung Disease (ILD) is a lung illness characterized by inflammation and scarring. Identifying and categorizing ILD patterns using chest Computed Tomography (CT) images is crucial for diagnosis and treatment planning. Deep learning and computer vision advancements offer the potential for automating medical image examination, such as the transformer model, which identifies intricate dependencies and relationships in data. Chest CT scans provide valuable information for ILD pattern classification and diagnosis. The Vision Transformer (ViT) based Multi-Head Self Attention (MHSA) architecture detects local and global spatial dependencies, focusing on relevant regions and considering contextual interactions. The ViT-based model architecture aims to categorize ILD patterns using MHSA mechanisms. The proposed ViT-ILD model improves the performance by modifying hyperparameters, attention heads, and hidden units. It also utilises techniques of residual connections, layer normalization, and positional encoding for improvement. The proposed method ViT-ILD has achieved comparable training, validation and test accuracy of 100%, 98%, and 82.75% respectively for the 4-class classification with a healthy lung, hypersensitivity pneumonitis, pulmonary fibrosis, and tuberculosis from the MedGift CT dataset. It is observed that the proposed ViT-ILD model has achieved test accuracy, recall, precision, and f1-score of 82.75%, 74.15%, 100%, and 82.35%.

Fruit-In-Sight: A deep learning-based framework for secondary metabolite class prediction using fruit and leaf images.

Fruits produce a wide variety of secondary metabolites of great economic value. Analytical measurement of the metabolites is tedious, time-consuming, and expensive. Additionally, metabolite concentrations vary greatly from tree to tree, making it difficult to choose trees for fruit collection. The current study tested whether deep learning-based models can be developed using fruit and leaf images alone to predict a metabolite's concentration class (high or low). We collected fruits and leaves (n = 1045) from neem trees grown in the wild across 0.6 million sq km, imaged them, and measured concentration of five metabolites (azadirachtin, deacetyl-salannin, salannin, nimbin and nimbolide) using high-performance liquid chromatography. We used the data to train deep learning models for metabolite class prediction. The best model out of the seven tested (YOLOv5, GoogLeNet, InceptionNet, EfficientNet_B0, Resnext_50, Resnet18, and SqueezeNet) provided a validation F1 score of 0.93 and a test F1 score of 0.88. The sensitivity and specificity of the fruit model alone in the test set were 83.52 ± 6.19 and 82.35 ± 5.96, and 79.40 ± 8.50 and 85.64 ± 6.21, for the low and the high classes, respectively. The sensitivity was further boosted to 92.67± 5.25 for the low class and 88.11 ± 9.17 for the high class, and the specificity to 100% for both classes, using a multi-analyte framework. We incorporated the multi-analyte model in an Android mobile App Fruit-In-Sight that uses fruit and leaf images to decide whether to 'pick' or 'not pick' the fruits from a specific tree based on the metabolite concentration class. Our study provides evidence that images of fruits and leaves alone can predict the concentration class of a secondary metabolite without using expensive laboratory equipment and cumbersome analytical procedures, thus simplifying the process of choosing the right tree for fruit collection.

Detection and classification of brain tumor using hybrid deep learning models

Accurately classifying brain tumor types is critical for timely diagnosis and potentially saving lives. Magnetic Resonance Imaging (MRI) is a widely used non-invasive method for obtaining high-contrast grayscale brain images, primarily for tumor diagnosis. The application of Convolutional Neural Networks (CNNs) in deep learning has revolutionized diagnostic systems, leading to significant advancements in medical imaging interpretation. In this study, we employ a transfer learning-based fine-tuning approach using EfficientNets to classify brain tumors into three categories: glioma, meningioma, and pituitary tumors. We utilize the publicly accessible CE-MRI Figshare dataset to fine-tune five pre-trained models from the EfficientNets family, ranging from EfficientNetB0 to EfficientNetB4. Our approach involves a two-step process to refine the pre-trained EfficientNet model. First, we initialize the model with weights from the ImageNet dataset. Then, we add additional layers, including top layers and a fully connected layer, to enable tumor classification. We conduct various tests to assess the robustness of our fine-tuned EfficientNets in comparison to other pre-trained models. Additionally, we analyze the impact of data augmentation on the model's test accuracy. To gain insights into the model's decision-making, we employ Grad-CAM visualization to examine the attention maps generated by the most optimal model, effectively highlighting tumor locations within brain images. Our results reveal that using EfficientNetB2 as the underlying framework yields significant performance improvements. Specifically, the overall test accuracy, precision, recall, and F1-score were found to be 99.06%, 98.73%, 99.13%, and 98.79%, respectively.