Introduction: Acute ischemic stroke (AIS) is a leading cause of global mortality and disability worldwide. Machine learning (ML) models enhance prognostic accuracy by analysing complex, multidimensional clinical data. The aim of this systematic review and meta-analysis is to identify the gaps in the current ML models, along with methodological and performance outcomes in AIS. Further, the study objective was to identify the most frequently used algorithms and compare their relative effectiveness, thereby supporting future research to develop novel ML-based predictive models for stroke care management. Methods: The systematic review followed PRISMA guidelines with PROSPERO registration. A comprehensive search was performed in PubMed, Scopus, and Web of Science using MeSH keywords. Data extraction captured study characteristics, ML algorithms, and outcome metrics. We used the PROBAST and TRIPOD-AI to assess the qualities and bias of included studies. Meta-analysis of AUC values across ML models were conducted to synthesize model performance used a random-effects model to summarize and analyse the data and assessed heterogeneity ( I ² ) statistic using SPSS-29 and R-Studio-4.2.0. Results: A total of 14 studies were included in the systematic review, with 12 eligible for meta-analysis. The pooled AUC of ML models was 0.87 (95% CI, 0.83–0.91), demonstrating strong predictive performance despite substantial heterogeneity ( I ² = 99%). Random forest (RF) (AUC = 0.85) and SVM (AUC = 0.82) outperformed logistic regression (LR) (AUC = 0.75), while XGBoost showed stable performance (AUC = 0.82); heterogeneity was mainly driven by study design, publication year, and algorithm type ( p < 0.001). Conclusion: ML-based models show potential for improving prognostic assessment in AIS; however, substantial heterogeneity and methodological limitations across studies limit the generalizability of pooled performance estimates. Systematic review registration: https://www.crd.york.ac.uk/PROSPERO/view/CRD420251033217 , (Registration number: CRD420251033217).

Background: Invasive and mucosal infections caused by Candida species continue to pose a significant global health burden, particularly due to the species’ increasing resistance to conventional antifungal agents. This systematic review evaluates the antifungal potential of pyrrolidine-based derivatives, focusing on structure–activity relationships, mechanisms of action, and activity against Candida species. Methods: A systematic literature search was conducted in PubMed, Scopus, and Web of Science for studies published between January 2015 and January 2026, following PRISMA guidelines and registered in PROSPERO (CRD420261279035). Studies reporting in vitro, in vivo, or in silico evaluation of pyrrolidine derivatives against Candida species were included. Data extraction and risk-of-bias assessment were performed using predefined criteria. Results: Twelve studies met the inclusion criteria, describing diverse pyrrolidine-based scaffolds, including spirooxindole, dispiro, triazole-linked, tetrazole, and quinoline-fused derivatives. The compounds demonstrated antifungal activity against multiple Candida species, including resistant isolates with minimum inhibitory concentrations ranging from approximately 0.5 to 16 µg/mL. Several derivatives showed comparable activity to standard antifungal agents under the reported experimental conditions. Mechanistic investigations indicated inhibition of biofilm formation, disruption of fungal cell wall and membrane integrity, suppression of hyphal transition, and modulation of virulence-associated pathways. Multi-mechanism antifungal effects were reported across different structural classes. Conclusions: Pyrrolidine-based derivatives represent promising antifungal scaffolds with potent activity against Candida species and associated virulence factors. However, limited in vivo validation and insufficient pharmacokinetic and toxicity data remain major barriers to clinical translation. Further optimization of structure–activity relationships and comprehensive preclinical evaluation are required to advance these scaffolds toward therapeutic development.

Heart disease is one of the major non-communicable disease and leading cause of mortality in the world. According to WHO heart disease is taking about nearly 17.9 million lives of people each year. Its mortality forecasts indicate a rise in global annual deaths to 20.5 million in 2020 and as high as 24.2 million by 2030. Risk factors are one of the most powerful predictors of heart disease. The study includes modified and non-modified risk factors that contribute to the disease such as Age, Gender, Family history, Hypertension, Diabetics, Obesity, Blood Pressure, Smoking, Alcohol intake, Exercise and Heart rate. Machine learning is one of the most useful techniques that can help researchers, entrepreneurs, and individuals for extracting valuable information from sets of data. The objective of this study is to highlight the utility and application of machine learning techniques for the prediction of heart disease to facilitate experts in the healthcare domain. A total of 336 patients were examined and their personal and medical data were collected in JSS hospital. This prospective study was consisting of 55% patients are free from the heart disease and 45% have heart disease. From the result, it has been determined that males are more likely to develop the heart diseases than females and very common in elderly persons. The accuracy of the Naive Bayes model is found to be 94%, Obesity plays a vital role in getting the disease followed by hypertension, alcohol intake, smoking, exercise and age has more impact on developing the heart disease.

Objectives: College life introduces psychological stressors such as academic pressure, social adaptation, and lifestyle changes, often impacting eating behaviours. Emotional or stress-induced eating marked by increased consumption of high-calorie, sugary foods is increasingly prevalent among young adults and has been linked to adverse health outcomes. Gender differences further influence coping mechanisms, with females more prone to emotional eating due to biological and psychosocial factors. The study aimed to explore gender-based patterns in stress-induced eating among college students in Karnataka, Kerala, and Andhra Pradesh. Material and Methods: A total of 555 students participated in the study, comprising 200 from Karnataka, 151 from Kerala, and 204 from Andhra Pradesh. The survey captured demographic data, anthropometric data, emotional well-being, dietary habits, and medical history. Descriptive statistics and Chi-square tests were used to assess gender-based differences in stress-related eating behaviour and associated health outcomes. Data were entered in Microsoft Excel and analysed using IBM SPSS version 22.0. Results: Gender and regional variations were observed in stress-induced eating behaviours. Female students in Kerala and Karnataka reported higher tendencies toward emotional eating, while males in Andhra Pradesh showed significant stress-related behavioural changes. BMI distribution also differed, with Kerala students exhibiting greater variability across underweight, overweight, and obesity categories. Gender was significantly associated with BMI in Andhra Pradesh ( p = 0.004). Stress-related eating was linked with changes in appetite, cravings, coping strategies, and physical health indicators such as blood sugar fluctuations and digestive issues, with notable gender-specific differences across states. Conclusion: The study findings underscore the need for targeted, gender-sensitive interventions to support emotional well-being and promote healthy dietary habits in academic settings.

Objectives: Coronavirus disease 2019 (COVID-19), caused by the SARS-CoV-2, is a contagious infectious disease. The aim of the present study is to identify the most effective biochemical parameters associated with COVID-19 severity. Early identification of these parameters is crucial for rapid risk stratification of patients and for initiating timely clinical management. Material and Methods: A total of 584 patients with COVID-19 admitted to a tertiary care hospital in Mysuru, Karnataka, were included in the study. The routinely measured biochemical parameters obtained after hospital admission were evaluated for their association with the study outcome. Descriptive statistics, independent sample t -test, Pearson’s correlation analysis, binary logistic regression, and receiver operating characteristic (ROC) curve analysis were performed at a 5% level of significance using IBM SPSS Statistics version 22. Results: Demographic and clinical characteristics showed that male patients, 427 (73%) and older adults aged 60–80 years, 157 (48.5%), constituted the largest proportion of hospitalised patients with COVID-19. A higher proportion of male patients was observed in both the ICU 16 (2.74%) and non-ICU 411 (70.38%) groups. Correlation analysis demonstrated mild to moderate associations among selected biochemical markers. In the multivariable logistic regression analysis, serum creatinine was the only biochemical parameter significantly associated with the study outcome (OR = 0.265; p = 0.027) and also demonstrated acceptable discriminatory performance in the ROC analysis. Conclusion: Early identification of biochemical abnormalities improves clinical prognosis by enabling timely risk stratification and appropriate therapeutic intervention. These findings support the routine assessment of biochemical parameters as part of the initial evaluation of patients with COVID-19.

Background: Breast cancer is the most common malignancy among women worldwide and a leading cause of cancer-related mortality. Despite advances in diagnosis and treatment, accurately predicting 5-year survival remains challenging because of disease heterogeneity. This study systematically evaluated the performance of machine learning (ML) models for predicting 5-year breast cancer survival and synthesised their overall discriminative performance. Methods: A systematic search of PubMed, Scopus, and Web of Science (2010–2024) identified studies developing ML models for 5-year survival prediction. Study quality was assessed using PROBAST. Logit-transformed area under the receiver operating characteristic curve (AUC) estimates were quantitatively synthesised using a random-effects meta-analysis with the restricted maximum likelihood (REML) estimator. Heterogeneity was assessed using Cochran’s Q and I² statistics, publication bias using funnel plots and Egger’s regression test, and subgroup analyses according to study characteristics. Statistical analyses were performed using IBM SPSS version 29.0 and R version 4.6.1. Results: Fifteen studies were included. A wide range of ML models, including Random Forest, Random Survival Forest, and gradient boosting methods, was evaluated. The pooled analysis demonstrated good discriminative performance, with an overall AUC of 0.83 (95% CI: 0.80–0.86). Substantial heterogeneity was observed across studies. Ensemble-based models generally showed consistent performance. Publication bias was detected, and several studies exhibited moderate-to-high risk of bias. Conclusions: ML models show strong potential for predicting 5-year breast cancer survival and may support early risk stratification and clinical decision-making. However, greater methodological standardisation, rigorous external validation, and improved reporting are required before widespread clinical implementation.