AUC Score Research Articles

Multi-type stroke lesion segmentation: comparison of single-stage and hierarchical approach.

Stroke, a major cause of death and disability worldwide, can be haemorrhagic or ischaemic depending on the type of bleeding in the brain. Rapid and accurate identification of stroke type and lesion segmentation is critical for timely and effective treatment. However, existing research primarily focuses on segmenting a single stroke type, potentially limiting their clinical applicability. This study addresses this gap by exploring multi-type stroke lesion segmentation using deep learning methods. Specifically, we investigate two distinct approaches: a single-stage approach that directly segments all tissue types in one model and a hierarchical approach that first classifies stroke types and then utilises specialised segmentation models for each subtype. Recognising the importance of accurate stroke classification for the hierarchical approach, we evaluate ResNet, ResNeXt and ViT networks, incorporating focal loss and oversampling techniques to mitigate the impact of class imbalance. We further explore the performance of U-Net, U-Net++ and DeepLabV3 models for segmentation within each approach. We use a comprehensive dataset of 6650 images provided by the Ministry of Health of the Republic of Türkiye. This dataset includes 1130 ischaemic strokes, 1093 haemorrhagic strokes and 4427 non-stroke cases. In our comparative experiments, we achieve an AUC score of 0.996 when classifying stroke and non-stroke slices. For lesion segmentation task, while the performance of different architectures is comparable, the hierarchical training approach outperforms the single-stage approach in terms of intersection over union (IoU). The performance of the U-Net model increased significantly from an IoU of 0.788 to 0.875 when the hierarchical approach is used. This comparative analysis aims to identify the most effective approach and deep learning model for multi-type stroke lesion segmentation in brain CT scans, potentially leading to improved clinical decision-making, treatment efficiency and outcomes.

Exploring Factors Influencing Patient Delay Behavior in Oral Cancer: The Development of a Risk Prediction Model in Western China

Background and Aims: To study the unknown influencing factors of delayed medical treatment behavior in oral cancer patients in western China and to develop a prediction model on the risk of delayed medical treatment in oral cancer patients. Method: We investigated oral cancer patients attending a tertiary Grade A dental hospital in western China from June 2022 to July 2023. The logistic regression and four machine learning models (nearest neighbors, the RBF SVM, random forest, and QDA) were used to identify risk factors and establish a risk prediction model. We used the established model to predict the data before and after the COVID-19 pandemic and test whether the prediction effect can still remain stable and accurate under the interference of COVID-19. Result: Out of the 495 patients included in the study, 122 patients (58.65%) delayed seeking medical treatment before the lifting of the restrictions of the pandemic, while 153 patients (53.13%) did so after the lifting of restrictions. The logistic regression model revealed that living with adult children was a protective factor for patients in delaying seeking medical attention, regardless of the implementation of pandemic control measures. After comparing each model, it was found that the statistical indicators of the random forest algorithm such as the AUC score (0.8380) and specificity (0.8077) ranked first, with the best prediction performance and stable performance. Conclusions: This study systematically elucidates the critical factors influencing patient delay behavior in oral cancer diagnosis and treatment, employing a comprehensive risk prediction model that accurately identifies individuals at an elevated risk of delay. It represents a pioneering large-scale investigation conducted in western China, focusing explicitly on the multifaceted factors affecting the delayed medical treatment behavior of oral cancer patients. The findings underscore the imperative of implementing early intervention strategies tailored to mitigate these delays. Furthermore, this study emphasizes the pivotal role of robust social support systems and positive family dynamics in facilitating timely access to healthcare services for oral cancer patients, thereby potentially improving outcomes and survival rates.

Abstract 4116410: A Novel Deep Learning Approach for Prediction of Right Heart Failure After Left Ventricular Assist Device Implantation using Pulmonary Artery Pressure Tracings

Introduction: Left ventricular assist device (LVAD) offers a lifeline for advanced heart failure patients, but ~30% experience post-operative right heart failure (RHF) with significant morbidity and mortality. Current methods for predicting RHF risk have limited accuracy. This study is the first of its kind to explore the feasibility of using a convolutional neural network (CNN) deep learning model with pulmonary artery pressure (PAP) tracings acquired during pre-operative hemodynamic assessment to identify patients at risk for early RHF. Methods: A CNN model was pre-trained on PAP tracings from the MIMIC-III Waveform Database to leverage transferable knowledge and improve model performance. The model learned general features and temporal relationships in hemodynamic tracing morphology for RHF prediction. It was then adapted for classification by modifying the output layers. Post-LVAD RHF was definitively adjudicated for each instance included from our 246 patient single center LVAD database. RHF was adjudicated using the 2020 Academic Research Consortium defintion. The database included 205 non-RHF instances and 41 RHF instances. We developed a novel signal processing method utilizing computer vision to extract PAP waveform data from pre-operative right heart catheterization reports. Data was reviewed to ensure accurate pressure tracing representation. SMOTE-ENN (synthetic oversampling) and class weighting addressed dataset imbalance during training to enhance model generalizability and RHF prediction accuracy. Results: The model achieved strong performance in classifying RHF from non-RHF outcomes, as evidenced by consistent AUC scores of 0.87 and 0.85 on validation and unseen test data, respectively. These findings indicate the potential for hemodynamic tracings to predict RHF after LVAD implantation. Notably, the model maintained its performance on unseen data, highlighting its generalizability. Conclusions: This study explored the feasibility of using a deep learning model for RHF risk stratification in patients with LVADs. The model, pre-trained on PAP tracings, achieved promising classification performance assessed by AUC. Further validation with larger, more diverse datasets will refine model performance and enhance generalizability for clinical application. Leveraging hemodynamic tracings within a deep learning framework holds promise for improved clinical outcome prediction.

NIMG-40. RADIOMICS-BASED DIFFERENTIATION OF GLIOBLASTOMA AND METASTATIC DISEASE: DOES DIFFERENCE IN TYPE OF T1-CONTRAST ENHANCED SEQUENCE MATTER?

Abstract BACKGROUND To evaluate the radiomics-based model performance for differentiation between glioblastoma (GB) and intracranial metastatic disease (IMD) using magnetization prepared rapid gradient echo (MPRAGE) and volumetric interpolated breath-hold examination (VIBE) T1-contrast enhanced sequences. MATERIALS AND METHODS T1-CE MPRAGE and VIBE sequences acquired in 108 patients (31 GBs and 77 IMD) during the same MRI session were retrospectively evaluated. Post standardized image pre-processing and segmentation, radiomics features were extracted from necrotic and enhancing tumor components. A total of 90 machine learning (ML) pipelines were evaluated using a five-fold cross-validation. Performance was measured by mean AUC, Log-loss, and Brier scores. Pearson correlation analysis of radiomics features from tumor subcomponents was also performed. RESULTS The mean AUC across the top-ten pipelines varied between 0.890-0.851 with T1-CE MPRAGE and 0.907-0.869 with T1-CE VIBE sequence. Top performing models for the MPRAGE sequence commonly used support vector machines, while those for VIBE sequence used either support vector machines or random forest. Common feature reduction methods for top-performing models included linear combination filter and least absolute shrinkage and selection operator (LASSO) for both sequences. Only three of the top ten models used the same combination of feature reduction-ML algorithm pipeline. A feature-wise comparison showed that the radiomic features between sequences were strongly correlated, with the highest correlation for shape-based features. CONCLUSION Radiomics features derived from T1-CE MPRAGE and VIBE sequences may have similar overall classification performance for differentiating GB from IMD, albeit often using different feature selection-ML algorithm pipelines.

Deep Learning-Based Classification of Macrofungi: Comparative Analysis of Advanced Models for Accurate Fungi Identification

This study focuses on the classification of six different macrofungi species using advanced deep learning techniques. Fungi species, such as Amanita pantherina, Boletus edulis, Cantharellus cibarius, Lactarius deliciosus, Pleurotus ostreatus and Tricholoma terreum were chosen based on their ecological importance and distinct morphological characteristics. The research employed 5 different machine learning techniques and 12 deep learning models, including DenseNet121, MobileNetV2, ConvNeXt, EfficientNet, and swin transformers, to evaluate their performance in identifying fungi from images. The DenseNet121 model demonstrated the highest accuracy (92%) and AUC score (95%), making it the most effective in distinguishing between species. The study also revealed that transformer-based models, particularly the swin transformer, were less effective, suggesting room for improvement in their application to this task. Further advancements in macrofungi classification could be achieved by expanding datasets, incorporating additional data types such as biochemical, electron microscopy, and RNA/DNA sequences, and using ensemble methods to enhance model performance. The findings contribute valuable insights into both the use of deep learning for biodiversity research and the ecological conservation of macrofungi species.

Machine Learning Approaches for Microorganism Identification, Virulence Assessment, and Antimicrobial Susceptibility Evaluation Using DNA Sequencing Methods: A Systematic Review.

Microbial infections pose a substantial global health challenge, particularly impacting immunocompromised individuals and exacerbating the issue of antimicrobial resistance (AMR). High virulence of pathogens can lead to severe infections and prolonged antimicrobial treatment, increasing the risk of developing resistant strains. Integrating machine-learning (ML) with DNA sequencing technologies offers potential solutions by enhancing microbial identification, virulence assessment, and antimicrobial susceptibility evaluation. This review explores recent advancements in these integrated approaches, addressing current limitations and identifying gaps in the literature. A comprehensive literature search was conducted across databases including PubMed, Scopus, Web of Science, and IEEE Xplore, covering publications from January 2014 to June 2024. Using a detailed Boolean search string, relevant studies focusing on ML applications in microorganism identification, antimicrobial susceptibility testing, and microbial virulence were included. The screening process involved a two-stage review of titles, abstracts, and full texts, with data extraction and critical appraisal performed using the QIAO tool. Data were analyzed through narrative synthesis to identify common themes and innovations. Out of 1,650 initially identified records, 19 studies met the inclusion criteria. These studies primarily focused on AMR, with additional research on microbial virulence and identification. Machine learning algorithms such as Random Forest, Support Vector Machines, and Convolutional Neural Networks, combined with DNA sequencing techniques like Whole Genome Sequencing and Metagenomic Sequencing, demonstrated significant advancements in predictive accuracy and efficiency. High-quality studies achieved impressive performance metrics, including F1-scores up to 0.88 and AUC scores up to 0.96. The integration of ML and DNA sequencing technologies has significantly enhanced microbial analysis, improving the identification of pathogens, assessment of virulence, and evaluation of antimicrobial susceptibility. Despite advancements, challenges such as data quality, high costs, and model interpretability persist. This review highlights the need for continued innovation and provides recommendations for future research to address these limitations and improve disease management and public health strategies. The systematic review is registered with PROSPERO (CRD42024571347).

Establishing an AI model and application for automated capsule endoscopy recognition based on convolutional neural networks (with video).

Although capsule endoscopy (CE) is a crucial tool for diagnosing small bowel diseases, the need to process a vast number of images imposes a significant workload on physicians, leading to a high risk of missed diagnoses. This study aims to develop an artificial intelligence (AI) model and application based on convolutional neural networks that can automatically recognize various lesions in small bowel capsule endoscopy. Three small bowel capsule endoscopy datasets were used for AI model training, validation, and testing, encompassing 12 categories of images. The model's performance was evaluated using metrics such as AUC, sensitivity, specificity, precision, accuracy, and F1 score to select the best model. A human-machine comparison experiment was conducted using the best model and endoscopists with varying levels of experience. Model interpretability was analyzed using Grad-CAM and SHAP techniques. Finally, a clinical application was developed based on the best model using PyQt5 technology. A total of 34,303 images were included in this study. The best model, MobileNetv3-large, achieved a weighted average sensitivity of 87.17%, specificity of 98.77%, and an AUC of 0.9897 across all categories. The application developed based on this model performed exceptionally well in comparison with endoscopists, achieving an accuracy of 87.17% and a processing speed of 75.04 frames per second, surpassing endoscopists of varying experience levels. The AI model and application developed based on convolutional neural networks can quickly and accurately identify 12 types of small bowel lesions. With its high sensitivity, this system can effectively assist physicians in interpreting small bowel capsule endoscopy images.Future studies will validate the AI system for video evaluations and real-world clinical integration.

Comparative Analysis of Machine Learning Models for Music Recommendation

Abstract. This study is inspired by the Kaggle competition WSDM - KKBoxs Music Recommendation Challenge. The study focuses on doing a comparative study on music recommendation models. Based on the requirements and the given dataset from the Kaggle competition, the problem can be transferred to a classification problem, and therefore, we chose three classification models for the comparative study. The three models are K Nearest Neighbors (KNN), Random Forest, and Light Gradient Boosting Machine (LightGBM). We also did data analysis and data preparation before applying the model and used the handout method and cross-validation method for the validation. For the evaluation, the AUC score is applied to the results and the empirical results show that LightGBM is the best model among these three.

Sleep apnea test prediction based on Electronic Health Records

The identification of Obstructive Sleep Apnea (OSA) is done by a Polysomnography test which is often done in later ages. Being able to notify potential insured members at earlier ages is desirable. For that, we develop predictive models that rely on Electronic Health Records (EHR) and predict whether a person will go through a sleep apnea test after the age of 50. A major challenge is the variability in EHR records in various insured members over the years, which this study investigates as well in the context of controls matching, and prediction. Since there are many temporal variables, the RankLi method was introduced for temporal variable selection. This approach employs the t-test to calculate a divergence score for each temporal variable between the target classes. We also investigate here the need to consider the number of EHR records, as part of control matching, and whether modeling separately for subgroups according to the number of EHR records is more effective. For each prediction task, we trained 4 different classifiers including 1-CNN, LSTM, Random Forest, and Logistic Regression, on data until the age of 40 or 50, and on several numbers of temporal variables. Using the number of EHR records for control matching was found crucial, and using learning models for subsets of the population according to the number of EHR records they have was found more effective. The deep learning models, particularly the 1-CNN, achieved the highest balanced accuracy and AUC scores in both male and female groups. In the male group, the highest results were also observed at age 50 with 100 temporal variables, resulting in a balanced accuracy of 90% and an AUC of 93%.

Enhancing the differential diagnosis of small pulmonary nodules: a comprehensive model integrating plasma methylation, protein biomarkers, and LDCT imaging features

BackgroundAccurate differentiation between malignant and benign pulmonary nodules, especially those measuring 5–10 mm in diameter, continues to pose a significant diagnostic challenge. This study introduces a novel, precise approach by integrating circulating cell-free DNA (cfDNA) methylation patterns, protein profiling, and computed tomography (CT) imaging features to enhance the classification of pulmonary nodules.MethodsBlood samples were collected from 419 participants diagnosed with pulmonary nodules ranging from 5 to 30 mm in size, before any disease-altering procedures such as treatment or surgical intervention. High-throughput bisulfite sequencing was used to conduct DNA methylation profiling, while protein profiling was performed utilizing the Olink proximity extension assay. The dataset was divided into a training set and an independent test set. The training set included 162 matched cases of benign and malignant nodules, balanced for sex and age. In contrast, the test set consisted of 46 benign and 49 malignant nodules. By effectively integrating both molecular (DNA methylation and protein profiling) and CT imaging parameters, a sophisticated deep learning-based classifier was developed to accurately distinguish between benign and malignant pulmonary nodules.ResultsOur results demonstrate that the integrated model is both accurate and robust in distinguishing between benign and malignant pulmonary nodules. It achieved an AUC score 0.925 (sensitivity = 83.7%, specificity = 82.6%) in classifying test set. The performance of the integrated model was significantly higher than that of individual methylation (AUC = 0.799, P = 0.004), protein (AUC = 0.846, P = 0.009), and imaging models (AUC = 0.866, P = 0.01). Importantly, the integrated model achieved a higher AUC of 0.951 (sensitivity = 83.9%, specificity = 89.7%) in 5–10 mm small nodules. These results collectively confirm the accuracy and robustness of our model in detecting malignant nodules from benign ones.ConclusionsOur study presents a promising noninvasive approach to distinguish the malignancy of pulmonary nodules using multiple molecular and imaging features, which has the potential to assist in clinical decision-making.Trial registration: This study was registered on ClinicalTrials.gov on 01/01/2020 (NCT05432128). https://classic.clinicaltrials.gov/ct2/show/NCT05432128.

Sentiment analysis with machine learning for drug reviews

In the treatment of the disease, the fact that individuals use drugs independently from doctors without appropriate consultation causes their health status to become worse than normal. This article aims to conduct a sentiment analysis over the comments of individuals about the drug in case they use drugs without consultation. Within the scope of this study, patients' comments about drugs were vectorized using Bow and TF-IDF algorithms, sentiment analysis was made, and the predicted sentiments were; it was evaluated with precision, recall, f1score, accuracy and AUC score. As a result of the evaluations, the most successful result was obtained in the TF-IDF method. This result is the result of the Linear Support Vector Classifier algorithm with an Accuracy value of 93%.

Prediction of mental health risk in adolescents via a smartphone app: a feasibility pilot study

Abstract Background The prevalence of mental health problems in adolescents is a global public health concern. Machine learning (ML) can analyse multidimensional data collected by phone sensors (passive tracking) and symptom self-reporting (active tracking) to model and predict mental health states. However, research in adolescents is lacking. This study investigated the feasibility of using ML to predict mental health in a non-clinical population of adolescents from active and passive data collected through the Mindcraft mobile app. Methods We recruited 103 secondary students (aged 14-18) who first completed the Strengths and Difficulties Questionnaire (SDQ) and then used the Mindcraft app for two weeks. The app integrates sensor data (location, steps, noise, light, battery, app usage) and self-reports. We extracted 85 sensor-based features and 19 from questionnaires to develop a gradient-boosted ensemble ML model. This model identifies students with abnormal SDQ scores and was evaluated using leave-one-out cross-validation. Results All students completed the active questionnaires; 67 also provided passive sensor data. 31 had abnormal SDQ scores. Using passive data, the ML model reached a balanced accuracy of 0.64 and an AUC score of 0.57. Incorporating both data types improved accuracy to 0.67 and AUC to 0.70. Feature importance scores showed step count and questionnaire on racing thoughts and hopefulness as most significant. Conclusions Our findings affirm the potential of integrating passive and active data collection to monitor mental health in real-world settings. Our ML model demonstrated moderate accuracy in predicting adolescents’ mental health risk measured with a behavioural screening questionnaire. This study will guide the development of a ML-driven, personalised mobile intervention for early symptom detection and mental health self-management, which might constitute an innovative and scalable tool for mental health prevention and intervention in adolescents. Key messages • This study shows the feasibility of using active and passive data to predict mental health risk in adolescents. • This study informs the development of a personalised machine learning-driven mobile intervention.

Deep learning detection of subclinical cardiovascular dysfunction in type 2 diabetes through retinal photography

Abstract Background Type 2 diabetes (T2D) is associated with excess atherosclerotic coronary disease and heart failure risk, with several cardiac abnormalities described in asymptomatic patients. Routine digital retinal photography performed for screening of diabetic retinopathy (DR) has the potential to identify patients with underlying cardiovascular disease (CVD). We aimed to determine whether features extracted from digital retinal photographs could detect subclinical cardiovascular dysfunction in asymptomatic people with T2D. Methods We prospectively enrolled adults with T2D and no history or symptoms of CVD to undergo extensive phenotyping with multiparametric stress perfusion cardiac MRI and CT coronary artery calcium scoring. Digital retinal photographs acquired for routine diabetic eye screening and performed within one year of cardiac evaluation were interrogated for retinopathy grading and using four deep learning (DL) models (Xception, Inception, EfficientNet, and MobileNet) to capture complex patterns within the retinal vasculature. Each subject had four retinal photographs (two of each eye) for DL analysis. Cardiac image analysis was performed blinded to participant details and independent of retinal images. Subjects with and without DR were compared. Participants were divided into training (80%) and validation datasets (20%) prior to DL analysis. DL models employed to predict from retinal images: presence or absence of coronary artery calcium on non-contrast CT, myocardial perfusion reserve <2.5, left ventricular (LV) global longitudinal strain <16%, absolute stress and rest myocardial blood flood (mL/g/min) used as continuous variables. AUC was used to assess the ability of DL models to discriminate between those without and without subclinical CVD. Results An initial 254 subjects (comprising 1,016 retinal photographs) were included in the analysis: 212 (83%) with no DR, 42 (17%) with grade 1 (mild background) DR. Key cardiac imaging parameters in subjects with and without DR are displayed in Table 1. The groups were well matched for age, sex, body mass index and blood pressure. Overall, those with grade 1 DR had higher atheroma burden, evidence of increased LV filling pressures (E/e’) and poorer systolic function, but no differences in stress and rest myocardial blood flow or myocardial perfusion reserve. However, all four DL models failed to achieve sufficient discrimination of any of the evaluated cardiac imaging parameters, with the majority achieving AUC scores below 50% for all cardiac parameters. Conclusion Asymptomatic adults with grade 1 DR exhibit more subclinical atherosclerosis and cardiovascular dysfunction than those without DR. However, DL transfer models could not discriminate between subjects with and without cardiovascular disease. Further work is needed to better define whether retinal screening may be used to identify those people with T2D most at risk of underlying cardiovascular disease.Subjects demographics

Missing Risk Factor Prediction in Cardiovascular Disease Using a Blended Dataset and Optimizing Classification With a Stacking Algorithm

ABSTRACTMachine learning is important in the treatment of heart disease because it is capable of analyzing large amounts of patient data, such as medical records, imaging tests, and genetic information, in order to identify patterns and predict the risk of developing heart disease. However, most ML algorithms require more accurate data in order to build an accurate prediction model and do not tolerate missing values. Handling missing risk factors is critical during dataset preprocessing and becomes more difficult when the risk factors are completely missing. Removing this completely missing feature may result in the loss of critical information, but there are no readily available imputation methods, which presents a significant challenge. To overcome this difficulty, in this study, we take an attempt to impute using statistical multiple linear regression and Huber regression (HR) methods using four blended datasets (Statlog, Cleveland, Hungarian, and Switzerland) sourced from the UCI ML repository. The entire dataset comprises 14 attributes, including one target variable; however, in the Switzerland dataset, one feature value (“serum cholesterol”) is entirely missing. Missing “serum cholesterol” is recognized as a predisposing factor including “chest pain,” “supreme heartbeat rate,” “type of defect,” “exercise induced ST stress related to rest,” and “exercise generated angina” in the proposed imputation methods. We also proposed applying the majority voting ensemble technique in an individual's and integrated dataset using ML algorithms as part of the risk factor identification strategy. The results show that our proposed stacked algorithm for the combined dataset with the ensemble features significantly improved accuracy by 93.47%, and an AUC score of 94.50% demonstrated more accurate and early prediction than the previous research and also provided the model's diversity, resilience, generalization, and adaptability to varied datasets.

Cough2COVID-19 detection using an enhanced multi layer ensemble deep learning framework and CoughFeatureRanker

In response to the pressing requirement for precise and easily accessible COVID-19 detection methods, we present the Cough2COVID-19 framework, which is cost-effective, non-intrusive, and widely accessible. The conventional diagnostic methods, notably the PCR test, are encumbered by limitations such as cost and invasiveness. Consequently, the exploration of alternative solutions has gained momentum. Our innovative approach employs a multi-layer ensemble deep learning (MLEDL) framework that capitalizes on cough audio signals to achieve heightened efficiency in COVID-19 detection. This study introduces the Cough2COVID-19 framework, effectively addressing these challenges through AI-driven analysis. Additionally, this study proposed the CoughFeatureRanker algorithm, which delves into the robustness of pivotal features embedded within cough audios. The CoughFeatureRanker algorithm selects the most prominent features based on their optimal discriminatory performance from 15 features to detect COVID-19. The effectiveness of the CoughFeatureRanker algorithm within the ensemble framework is scrutinized, confirming its favorable influence on the accuracy of COVID-19 detection. The Cough2COVID-19 (MLEDL) framework achieves remarkable outcomes in COVID-19 detection through cough audio signals, boasting a specificity of 98%, sensitivity of 97%, accuracy of 98%, and an AUC score of 0.981. Our framework asserts its supremacy in precise non-invasive screening through an exhaustive comparison with cutting-edge methodologies. This groundbreaking innovation holds the potential to enhance urban resilience by transforming disease diagnosis, offering a significant approach to curtailing transmission risks and facilitating timely interventions in the ongoing battle against the pandemic.

MEF-AlloSite: an accurate and robust Multimodel Ensemble Feature selection for the Allosteric Site identification model

A crucial mechanism for controlling the actions of proteins is allostery. Allosteric modulators have the potential to provide many benefits compared to orthosteric ligands, such as increased selectivity and saturability of their effect. The identification of new allosteric sites presents prospects for the creation of innovative medications and enhances our comprehension of fundamental biological mechanisms. Allosteric sites are increasingly found in different protein families through various techniques, such as machine learning applications, which opens up possibilities for creating completely novel medications with a diverse variety of chemical structures. Machine learning methods, such as PASSer, exhibit limited efficacy in accurately finding allosteric binding sites when relying solely on 3D structural information.Scientific ContributionPrior to conducting feature selection for allosteric binding site identification, integration of supporting amino-acid–based information to 3D structural knowledge is advantageous. This approach can enhance performance by ensuring accuracy and robustness. Therefore, we have developed an accurate and robust model called Multimodel Ensemble Feature Selection for Allosteric Site Identification (MEF-AlloSite) after collecting 9460 relevant and diverse features from the literature to characterise pockets. The model employs an accurate and robust multimodal feature selection technique for the small training set size of only 90 proteins to improve predictive performance. This state-of-the-art technique increased the performance in allosteric binding site identification by selecting promising features from 9460 features. Also, the relationship between selected features and allosteric binding sites enlightened the understanding of complex allostery for proteins by analysing selected features. MEF-AlloSite and state-of-the-art allosteric site identification methods such as PASSer2.0 and PASSerRank have been tested on three test cases 51 times with a different split of the training set. The Student’s t test and Cohen’s D value have been used to evaluate the average precision and ROC AUC score distribution. On three test cases, most of the p-values (<0.05\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$< 0.05$$\\end{document}) and the majority of Cohen’s D values (>0.5\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$> 0.5$$\\end{document}) showed that MEF-AlloSite’s 1–6% higher mean of average precision and ROC AUC than state-of-the-art allosteric site identification methods are statistically significant.

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

Polycystic Ovary Syndrome (PCOS) is a widespread endocrinological dysfunction impacting women of reproductive age, categorized by excess androgens and a variety of associated syndromes, consisting of acne, alopecia, and hirsutism. It involves the presence of multiple immature follicles in the ovaries, which can disrupt normal ovulation and lead to hormonal imbalances and associated health complications. Routine diagnostic methods rely on manual interpretation of ultrasound (US) images and clinical assessments, which are time-consuming and prone to errors. Therefore, implementing an automated system is essential for streamlining the diagnostic process and enhancing accuracy. By automatically analyzing follicle characteristics and other relevant features, this research aims to facilitate timely intervention and reduce the burden on healthcare professionals. The present study proposes an advanced automated system for detecting and classifying PCOS from ultrasound images. Leveraging Artificial Intelligence (AI) based techniques, the system examines affected and unaffected cases to enhance diagnostic accuracy. The pre-processing of input images incorporates techniques such as image resizing, normalization, augmentation, Watershed technique, multilevel thresholding, etc. approaches for precise image segmentation. Feature extraction is facilitated by the proposed CystNet technique, followed by PCOS classification utilizing both fully connected layers with 5-fold cross-validation and traditional machine learning classifiers. The performance of the model is rigorously evaluated using a comprehensive range of metrics, incorporating AUC score, accuracy, specificity, precision, F1-score, recall, and loss, along with a detailed confusion matrix analysis. The model demonstrated a commendable accuracy of \\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$96.54\\%$$\\end{document} when utilizing a fully connected classification layer, as determined by a thorough 5-fold cross-validation process. Additionally, it has achieved an accuracy of \\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$97.75\\%$$\\end{document} when employing an ensemble ML classifier. This proposed approach could be suggested for predicting PCOS or similar diseases using datasets that exhibit multimodal characteristics.

Improving Clinical Preparedness: Community Health Nurses and Early Hypoglycemia Prediction in Type 2 Diabetes Using Hybrid Machine Learning Techniques.

The aim of the study was to analyze the data of diabetic patients regarding warning signs of hypoglycemia to predict it at an early stage using various novel machine learning (ML) algorithms. Individual interviews with diabetic patients were conducted over 6 months to acquire information regarding their experience with hypoglycemic episodes. This information included warning signs of hypoglycemia, such as incoherent speech, exhaustion, weakness, and other clinically relevant cases of low blood sugar. Researchers used supervised, unsupervised, and hybrid techniques. In supervised techniques, researchers applied regression, while in hybrid classification ML techniques were used. In a 5-fold cross-validation approach, the prediction performance of seven models was examined using the area under the receiver operating characteristic curve (AUROC). We analyzed the data of 290 diabetic patients with low blood sugar episodes. Our investigation discovered that gradient boosting and neural networks performed better in regression, with accuracies of 0.416 and 0.417, respectively. In classification models, gradient boosting, AdaBoost, and random forest performed better overall, with AUC scores of 0.821, 0.814, and 0.821, individually. Precision values were 0.779, 0.775, and 0.776 for gradient boosting, AdaBoost, and random forest, respectively. AdaBoost and Gradient Boosting models, in particular, outperformed all others in predicting the probability of clinically severe hypoglycemia. These techniques enable community health nurses to predict hypoglycemia at an early stage and provide the necessary therapies to patients to prevent complications resulting from hypoglycemia.

Administration Route Differentiation of Altrenogest via the Metabolomic LC-HRMS Analysis of Equine Urine.

Altrenogest, also known as allyltrenbolone, is a synthetic form of progesterone used therapeutically to suppress unwanted symptoms of estrus in female horses. Altrenogest affects the system by decreasing levels of endogenous gonadotrophin and luteinizing and follicle-stimulating hormones, which in turn decreases estrogen and mimics the increase of progesterone production. This results in more manageable mares for training and competition alongside male horses while improving the workplace safety of riders and handlers. However, when altrenogest is administered, prohibited steroid impurities such as trendione, trenbolone, and epitrenbolone can be detected. It has been assumed that greater concentrations of these steroid impurities are present in injectable preparations and, therefore, pose a greater risk of causing anabolic effects when administered. For this reason, and due to the necessity of this therapeutic substance for the safety of thoroughbred racing participants, a metabolomic approach investigating the differentiation of two main administration routes was conducted. Liquid chromatography high-resolution mass spectrometry analysis of equine urine samples found five sulfated compounds, estrone sulfate, testosterone sulfate, 2-methoxyestradiol sulfate, pregnenolone sulfate, and cortisol sulfate, with the potential to differentiate between oral and intramuscularly administered altrenogest using a random forest classification model. The best model results, comparing two horses' administration normalized peak area datasets, gave an AUC score of 0.965 with a confidence level of 95% (between 0.931 and 0.995). Identifications of these compounds were confirmed with assistance from the Shimadzu Insight Explore Assign feature, together with MS/MS spectrum and retention time matching of purchased and synthesized reference standards. This study proposes a new potential application for metabolomic multi-tool workflows and machine learning models in a forensic toxicological context.

A hybrid feature fusion deep learning framework for multi-source medical image analysis

Despite the widespread adoption of deep learning to enhance image classification, significant obstacles remain. First, multisource data with diverse sizes and formats is a great challenge for most current deep learning models. Second, lacking manual labeled data for model training limits the application of deep learning. Third, the widely used CNN-based methods shows their limitations in extracting global features and yield poor performance for image topology. To address these issues, we propose a Hybrid Feature Fusion Deep Learning (HFFDL) framework for image classification. This framework consists of an automated image segmentation module, a two-stream backbone module, and a classification module. The automatic image segmentation module utilizes the U-Net model and transfer learning to detect region of interest (ROI) in multisource images; the two-stream backbone module integrates the Swin Transformer architecture with the Inception CNN, with the aim of simultaneous extracting local and global features for efficient representation learning. We evaluate the performance of HFFDL framework with two publicly available image datasets: one for identifying COVID-19 through X-ray scans of the chest (30,386 images), and another for multiclass skin cancer screening using dermoscopy images (25,331 images). The HFFDL framework exhibited greater performance in comparison to many cutting-edge models, achieving the AUC score 0.9835 and 0.8789, respectively. Furthermore, a practical application study conducted in a hospital, identifying viable embryos using medical images, revealed the HFFDL framework outperformed embryologists.