Chronic Kidney Disease (CKD) affects 697.5 million people globally, with \~{}115 million in India. Early detection is clinically challenging as the disease remains asymptomatic through stages 1–3, particularly in resource-limited rural settings like Madhya Pradesh. While high-accuracy black-box models (SVM, Random Forest, DNN) achieve 91.5–98% accuracy on the UCI CKD benchmark, they lack interpretability—creating a Transparency Gap that hinders clinical adoption. This paper proposes ANFIS-PSO, a Particle Swarm Optimization-tuned Adaptive Neuro-Fuzzy Inference System for early CKD diagnosis. A five-stage pipeline incorporating KNN imputation and Min-Max normalization was applied to the... More >

Mental health disorders pose a significant global burden, yet integrated non-invasive tools for simultaneous neurodiagnosis and therapy remain limited. This paper introduces IRENIC, a wearable prototype integrating an EEG skull cap for real-time brain monitoring, pre-stored SPECT/PET databases, AR visualization, psychometric tools, AI algorithms — including CNNs and reinforcement learning — that correlate EEG with neuroimaging data including brain stimulation games, cognitive therapy, calming music, and yoga mudras. The validated conceptual design enables EEG acquisition, AI-powered multi-modal correlation, psychometric evaluation, and closed-loop therapy delivery within a single platfor... More >

Accurate brain tumor classification from MRI remains essential for computer-assisted diagnosis, yet manual interpretation is time-consuming and variable. This study presents an EfficientNet-B0-based convolutional neural network for multi-class classification of glioma, meningioma, pituitary tumors, and no-tumor cases. The model was trained and evaluated on a public MRI dataset of 7023 images using a strict patient-level split to ensure unbiased assessment. A fixed EfficientNet-B0 backbone with a lightweight classification head reduces overfitting while maintaining stable learning. Performance was assessed via accuracy, precision, recall, F1-score, and specificity. The model achieved class-wi... More >

Environmental exposure biomarkers (EEBs) reflect the internal burden of pollutants, yet the joint effects of multiple exposures on biological aging and chronic disease risk remain insufficiently characterized. We analyzed 8,582 adults from the 2013-2016 National Health and Nutrition Examination Survey (NHANES). Mixed exposure was characterized using 74 EEBs. Phenotypic age acceleration and biological age acceleration were used as aging outcomes. Weighted quantile sum (WQS) regression, Bayesian kernel machine regression (BKMR), and LASSO regression were applied to identify key exposure components associated with aging acceleration. Logistic and Cox regression models were then used to evaluate... More >

Parkinson’s disease (PD) is the second most common neurodegenerative disorder worldwide, predominantly affecting older adults. Early detection is crucial, as subtle motor and non-motor symptoms frequently overlap with other conditions, often resulting in delayed diagnosis. Many existing models rely on costly and less accessible imaging modalities such as MRI or PET scans, limiting their applicability in resource-constrained settings where only routine clinical data are available. This study develops interpretable AI models for early PD detection using structured clinical variables, incorporating feature selection techniques. Feature selection was conducted via Random Forest (RF) importance... More >

Tongue diagnosis is a core component of Traditional Chinese Medicine (TCM) with important clinical application value, yet its standardization is severely hampered by the subjectivity of manual interpretation and the lack of unified imaging acquisition protocols. Worse still, the scarcity of large-scale annotated datasets has become a key bottleneck restricting the development of artificial intelligence (AI)-assisted TCM tongue diagnosis technology. To address these critical issues, this study constructs a high-quality standardized dataset dedicated to AI-driven TCM tongue diagnosis research. The dataset contains 6,719 high-resolution tongue images collected under strictly standardized condit... More >

Saliency Object Detection-Based Medical Image Fusion concentrates on the most prominent anatomical parts that naturally attract attention. The process begins with a two-step pipeline. First, it identifies the salient regions those structures most critical to a diagnostic decision. These highlighted areas are then fed into a guided-filtering framework. This work blends them with complementary information from a second imaging modality, such as CT and MRI. The method uses total variation regularization to suppress noise while preserving edges. A saliency-based weighting scheme ensures that every key detail is retained. The result is a single, high-quality image that carries the full diagnostic... More >

Early diagnosis plays a critical role in the successful skin cancer treatment. To classify skin lesions as benign or malignant, this study suggested a deep learning-enabled method that combines a Transformer module with ResNet50. At first ResNet50, a powerful convolutional neural network, to extract the image features and then enhance the model with a Transformer layer to improve the model accuracy is used. The final model is fine-tuned to achieve better accuracy. This approach shows improved classification results compared to the traditional model. The results signify that combining CNN-based feature extraction with Transformer-enabled global attention suggestively improves skin lesion clas... More >