Explore the vast range of titles available.

Background/Objectives: Diabetes is one of the most familiar and common diseases among people currently, and is a type of metabolic disease that is caused due to high levels of sugar in the blood for longer periods of time. If the disease is predicted at an earlier stage, the severity and risks associated with diabetes are significantly reduced, which helps to save the lifespan of people. In earlier investigations, various kinds of automated models based on artificial intelligence (AI) were developed for this purpose. However, key issues still revolve around the lack of robustness, dependability, and precise prediction. The motivation behind the proposed study is to design and develop an automated tool for the diagnosis of chronic disease with the use of novel AI methodology. Methods: For this purpose, a new detection framework is introduced, known as the Brass Optimized Learning-Based Diabetes Prediction (BOLD) model for remote healthcare applications. By using this kind of optimization-integrated deep learning technique, the overall performance and efficiency of the diabetes detection system are maximized. This framework preprocesses the input diabetes dataset before performing the data splitting, normalization, and cleaning activities. Next, the best attributes for improving the prognostic performance of the classifier are chosen using the Brassy Pelican Optimization (BPO) procedure. The Hunting Optimized Recurrent Neural Network—Long Short-Term Memory (RNN-LSTM) method is used to categorize the people into those who are diabetic and those who are not based on the chosen attributes. The approach employs a Deer Hunting Optimization (DHO) method to choose the hyperparameters needed to make an informed choice. A variety of parameters have been employed to confirm the results, which are evaluated for performance verification using the PIDD, Indonesia diabetic database, and kidney disease dataset. Results: The BOLD framework is successful to the extent that it has been able to achieve several metrics of comparably good results, such as an RMSE value of 0.015, a Cohen’s Kappa measure of 0.99, a precision of 0.991, a recall of 0.99, an accuracy equal to 0.996, and an AUC equal to 0.99. Conclusions: It is also remarkable that a very short time of 0.8 s was enough for it to deliver this kind of performance, making it a neat combination of both time and power efficiency.

Diabetes is one of the most rapidly spreading diseases in the world, resulting in an array of significant complications, including cardiovascular disease, kidney failure, diabetic retinopathy, and neuropathy, among others, which contribute to an increase in morbidity and mortality rate. If diabetes is diagnosed at an early stage, its severity and underlying risk factors can be significantly reduced. However, there is a shortage of labeled data and the occurrence of outliers or data missingness in clinical datasets that are reliable and effective for diabetes prediction, making it a challenging endeavor. Therefore, we introduce a newly labeled diabetes dataset from a South Asian nation (Bangladesh). In addition, we suggest an automated classification pipeline that includes a weighted ensemble of machine learning (ML) classifiers: Naive Bayes (NB), Random Forest (RF), Decision Tree (DT), XGBoost (XGB), and LightGBM (LGB). Grid search hyperparameter optimization is employed to tune the critical hyperparameters of these ML models. Furthermore, missing value imputation, feature selection, and K-fold cross-validation are included in the framework design. A statistical analysis of variance (ANOVA) test reveals that the performance of diabetes prediction significantly improves when the proposed weighted ensemble (DT + RF + XGB + LGB) is executed with the introduced preprocessing, with the highest accuracy of 0.735 and an area under the ROC curve (AUC) of 0.832. In conjunction with the suggested ensemble model, our statistical imputation and RF-based feature selection techniques produced the best results for early diabetes prediction. Moreover, the presented new dataset will contribute to developing and implementing robust ML models for diabetes prediction utilizing population-level data.

Aims/hypothesisIdentifying the metabolite profile of individuals with normal fasting glucose (NFG [<5.55 mmol/l]) who progressed to type 2 diabetes may give novel insights into early type 2 diabetes disease interception and detection.MethodsWe conducted a population-based prospective study among 1150 Framingham Heart Study Offspring cohort participants, age 40–65 years, with NFG. Plasma metabolites were profiled by LC-MS/MS. Penalised regression models were used to select measured metabolites for type 2 diabetes incidence classification (training dataset) and to internally validate the discriminatory capability of selected metabolites beyond conventional type 2 diabetes risk factors (testing dataset).ResultsOver a follow-up period of 20 years, 95 individuals with NFG developed type 2 diabetes. Nineteen metabolites were selected repeatedly in the training dataset for type 2 diabetes incidence classification and were found to improve type 2 diabetes risk prediction beyond conventional type 2 diabetes risk factors (AUC was 0.81 for risk factors vs 0.90 for risk factors + metabolites, p = 1.1 × 10−4). Using pathway enrichment analysis, the nitrogen metabolism pathway, which includes three prioritised metabolites (glycine, taurine and phenylalanine), was significantly enriched for association with type 2 diabetes risk at the false discovery rate of 5% (p = 0.047). In adjusted Cox proportional hazard models, the type 2 diabetes risk per 1 SD increase in glycine, taurine and phenylalanine was 0.65 (95% CI 0.54, 0.78), 0.73 (95% CI 0.59, 0.9) and 1.35 (95% CI 1.11, 1.65), respectively. Mendelian randomisation demonstrated a similar relationship for type 2 diabetes risk per 1 SD genetically increased glycine (OR 0.89 [95% CI 0.8, 0.99]) and phenylalanine (OR 1.6 [95% CI 1.08, 2.4]).Conclusions/interpretationIn individuals with NFG, information from a discrete set of 19 metabolites improved prediction of type 2 diabetes beyond conventional risk factors. In addition, the nitrogen metabolism pathway and its components emerged as a potential effector of earliest stages of type 2 diabetes pathophysiology.

Aims/hypothesisIslet autoimmunity usually starts with the appearance of autoantibodies against either insulin (IAA) or GAD65 (GADA). This categorises children with preclinical type 1 diabetes into two immune phenotypes, which differ in their genetic background and may have different aetiology. The aim was to study whether Coxsackievirus group B (CVB) infections, which have been linked to the initiation of islet autoimmunity, are associated with either of these two phenotypes in children with HLA-conferred susceptibility to type 1 diabetes.MethodsAll samples were from children in the Finnish Type 1 Diabetes Prediction and Prevention (DIPP) study. Individuals are recruited to the DIPP study from the general population of new-born infants who carry defined HLA genotypes associated with susceptibility to type 1 diabetes. Our study cohort included 91 children who developed IAA and 78 children who developed GADA as their first appearing single autoantibody and remained persistently seropositive for islet autoantibodies, along with 181 and 151 individually matched autoantibody negative control children, respectively. Seroconversion to positivity for neutralising antibodies was detected as the surrogate marker of CVB infections in serial follow-up serum samples collected before and at the appearance of islet autoantibodies in each individual.ResultsCVB1 infections were associated with the appearance of IAA as the first autoantibody (OR 2.4 [95% CI 1.4, 4.2], corrected p = 0.018). CVB5 infection also tended to be associated with the appearance of IAA, however, this did not reach statistical significance (OR 2.3, [0.7, 7.5], p = 0.163); no other CVB types were associated with increased risk of IAA. Children who had signs of a CVB1 infection either alone or prior to infections by other CVBs were at the highest risk for developing IAA (OR 5.3 [95% CI 2.4, 11.7], p < 0.001). None of the CVBs were associated with the appearance of GADA.Conclusions/interpretationCVB1 infections may contribute to the initiation of islet autoimmunity being particularly important in the insulin-driven autoimmune process.

Background Diabetes, the fastest growing health emergency, has created several life-threatening challenges to public health globally. It is a metabolic disorder and triggers many other chronic diseases such as heart attack, diabetic nephropathy, brain strokes, etc. The prime objective of this work is to develop a prognosis tool based on the PIMA Indian Diabetes dataset that will help medical practitioners in reducing the lethality associated with diabetes. Methods Based on the features present in the dataset, two prediction models have been proposed by employing deep learning (DL) and quantum machine learning (QML) techniques. The accuracy has been used to evaluate the prediction capability of these developed models. The outlier rejection, filling missing values, and normalization have been used to uplift the discriminatory performance of these models. Also, the performance of these models has been compared against state-of-the-art models. Results The performance measures such as precision, accuracy, recall, F 1 score, specificity, balanced accuracy, false detection rate, missed detection rate, and diagnostic odds ratio have been achieved as 0.90, 0.95, 0.95, 0.93, 0.95, 0.95, 0.03, 0.02, and 399.00 for DL model respectively, However for QML, these measures have been computed as 0.74, 0.86, 0.85, 0.79, 0.86, 0.86, 0.11, 0.05, and 35.89 respectively. Conclusion The proposed DL model has a high diabetes prediction accuracy as compared with the developed QML and existing state-of-the-art models. It also uplifts the performance by 1.06% compared to reported work. However, the performance of the QML model has been found as satisfactory and comparable with existing literature.

Diabetes is an acute disease that happens when the pancreas cannot produce enough insulin. It can be fatal if undiagnosed and untreated. If diabetes is revealed early enough, it is possible, with adequate treatment, to live a healthy life. Recently, researchers have applied artificial intelligence techniques to the forecasting of diabetes. As a result, a new SMOTE-based deep LSTM system was developed to detect diabetes early. This strategy handles class imbalance in the diabetes dataset, and its prediction accuracy is measured. This article details investigations of CNN, CNN-LSTM, ConvLSTM, and deep 1D-convolutional neural network (DCNN) techniques and proposed a SMOTE-based deep LSTM method for diabetes prediction. Furthermore, the suggested model is analyzed towards machine-learning, and deep-learning approaches. The proposed model’s accuracy was measured against the diabetes dataset and the proposed method achieved the highest prediction accuracy of 99.64%. These results suggest that, based on classification accuracy, this method outperforms other methods. The recommendation is to use this classifier for diabetic patients’ clinical analysis.

Type 2 diabetes (T2D) is a growing global health crisis, affecting over 537 million people as of 2021. Early prediction remains particularly challenging in low- and middle-income countries due to missing data, class imbalance, and population-specific risk factors. This study presents a four-stage predictive framework— Feature-Weighted Class-Adaptive Generative Imputation Network-Weighted Classifier Aggregation Ensemble (FW-CAGIN-WCAE)—designed to address these limitations. First, Zero-Threshold Feature Removal (ZTFR) is applied to eliminate low-quality variables. Second, missing values are imputed FW-CAGIN, a novel class-aware and feature-weighted GAN model that accounts for both class and feature importance. Third, a performance-weighted ensemble of 15 machine and deep learning algorithms is constructed. Finally, SHAP analysis is used to uncover population-specific risk indicators. The proposed method was evaluated on three benchmark datasets—PIDD, FHGDD, and BDD—and their combinations, using nested five-fold cross-validation. The model achieved a peak AUC of 0.936 ± 0.018 in PIDD-BDD combination and reduced the imputation mean absolute error (MAE) from 0.8028 to 0.0033. It also lowered AUC variability by 36.3% and improved the diagnostic odds ratio (DOR) to 68.4 ± 20.5. SHAP analysis identified as a key predictive feature across both Asian and European populations. These findings demonstrate that the proposed framework offers an accurate, interpretable, and population-sensitive solution for early T2D detection, especially in resource-limited healthcare settings.

Whether young, old, type 1, type 2, gestational, newly diagnosed, long-time sufferer, caretaker or loved one, millions of people are afflicted and affected by diabetes. The World Health Organization (WHO) predicts that by 2030, diabetes will be the 7th leading cause of death in the world, and estimated more than 422 million adults of the population worldwide are living with diabetes, with millions of people with prediabetes. Machine learning models have shown promising results in the correct identification of the presence of diabetes, which is essential for providing efficient treatment; however, their decision-making process is often considered a “black box” that lacks transparency and interpretability. In this project, we explored the use of Shapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME), two popular explainable AI techniques, to generate local and global explanations for machine learning models. All the datasets used for the study were gathered from Kaggle and split into training and test sets using different kinds of machine learning algorithms, which would boost the success rate of therapy. Along with Categorical Boosting (CatBoost), Extreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), Random Forest (RF), Adaptive Boosting (AdaBoost), Logistic Regression (LR), Light Gradient Boosting Machine (LightGBM), and Decision Trees (DT) are well-known models for predicting diabetes and managing therapy. Explainable AI techniques were then applied to generate explanations of the model’s predictions on the test sets. Our results demonstrated that SHAP and LIME can effectively identify patterns in the symptoms of patients and suggest a potential diagnosis or recommend further courses of action. In addition, this study also presents a comparative analysis of these algorithms based on various performance metrics, such as accuracy, recall, AUC-ROC, and F1 score, achieving the highest values on the test set, indicating the potential of combining machine learning and explainable AI for improving diabetes diagnosis and treatment.

AimsStudies to prevent gestational diabetes (GDM) have shown the best results when lifestyle measures have been applied early in pregnancy. We aimed to investigate whether first-trimester fasting plasma glucose (FPG) could predict GDM risk and adverse pregnancy outcomes. MethodsA retrospective analysis of prospectively collected data from singleton pregnancies who were attended at our hospital between 2008 and 2018 (n = 27,198) was performed. We included patients with a recorded first-trimester FPG and complete pregnancy data (n = 6845). Patients under 18, with pregestational diabetes or reproductive techniques, were excluded. First-trimester FPG was evaluated as a continuous variable and divided into quartiles. GDM was diagnosed by NDDG criteria. The relationship between first- and second-trimester glucose > 92 mg/dL was also investigated. The relationship between FPG and pregnancy outcomes was assessed in 6150 patients who did not have GDM.ResultsMaternal age was 34.2 ± 3.9 years, BMI 23.1 ± 3.7 kg/m2 and mean FPG 83.0 ± 7.3 mg/dL. Glucose quartiles were: ≤ 78, 79–83, 84–87 and ≥ 88 mg/dL. First-trimester FPG predicted the risk of GDM (7%, 8%, 10.2% and 16% in each quartile, p < 0.001) and the risk of second-trimester glucose > 92 mg/dL (2.6%, 3.8%, 6.3% and 11.4% in each quartile, p < 0.001). FPG was significantly associated with LGA (8.2%, 9.3%, 10% and 11.7% in each quartile, p = 0.011) but not with other obstetrical outcomes. In a multivariate analysis including age, BMI, tobacco use, number of pregnancies and weight gained during pregnancy, first-trimester FPG was an independent predictor of LGA. ConclusionsFirst-trimester FPG is an early marker of GDM and LGA.

The objective of this research was to develop a highly accurate model for predicting diabetes, with the intention of offering a data-based approach for early detection in clinical settings. The study was based on the Zhoupu Hospital 2022-2024 physical examination dataset, which included 62 features including biochemical indicators, physical examination, etc. Ten key predictive features including urinary glucose (GLU_), urinary protein (PRO), etc., were identified through a combination of screening by the variance threshold method, ANOVA, and Pearson’s correlation coefficient method. And SHAP (SHapley Additive exPlanations) values were used for interpretability analysis of feature importance. The study compared six machine learning models, and after 5-fold cross-validation and grid search tuning, the Random Forest model performed optimally, with average prediction metrics of 0.9412±0.0237 recall, F1 score=0.9212±0.0181, AUC value of 0.9691±0.0145, Mathews correlation coefficient (MCC) of 0.8402±0.0365, and Equilibrium accuracy was 0.9195±0.0183 and specificity was 0.8978±0.0251. The results of the study suggest that the random forest model can be an effective tool for early warning of diabetes. The SHAP interpretation provides a quantitative basis for the analysis of pathological mechanisms, effectively enhances the transparency and credibility of the diabetes prediction model in clinical applications, and helps healthcare professionals to understand the logic of the model and assist in diagnostic and therapeutic decisions.