Clinical decision support systems (CDSS) can improve medication safety, yet implementation remains limited in some Philippine hospitals. This study examined hospital pharmacists' perceived usefulness of CDSS, willingness to adopt, trust requirements, and anticipated barriers in non-implementing hospitals in Rizal Province, Philippines. A convergent mixed-methods, cross-sectional survey was conducted among 84 licensed hospital pharmacists using a content-validated 15-item Likert questionnaire and six open-ended questions, analysed descriptively and thematically. Across perceived-usefulness items, 88.10%–92.86% agreed that CDSS could improve medication safety, risk detection, and efficiency.... More >

Mechanistic tumor-response models that are transparent and updatable with patient data are important for model-informed precision radiotherapy. This study presents a reproducible computational framework integrating an explicit mathematical derivation, numerical solver, clinical protocol-derived parameters, and three-dimensional visualization to simulate simplified lung tumor regression during radiotherapy for non-small cell lung cancer (NSCLC). A first-order Taylor approximation, equivalent to the forward Euler method, is derived from Taylor's formula with integral remainder, with local truncation error of order $h^2$. The resulting update rule is applied to a first-order regression model wi... More >

Rehearsal-based continual learning in Medical IoT (MIoT) autoencoders requires replaying latent codes of past clinical tasks to prevent catastrophic forgetting. When these latent codes are derived from patient data, each replay constitutes a fresh privacy query, and existing differential privacy (DP) composition theorems-designed for finite, pre-specified query sequences-fail to bound cumulative privacy leakage over an unbounded task horizon. This paper presents PRISM-DP, a Privacy-Resilient Infinite-Sequence Memory framework that introduces a martingale-based DP composition theorem for unbounded replay sequences. PRISM-DP proves that a geometrically decaying per-task privacy schedule combin... More >

Contemporary medicine is shifting from reactive, symptom-based treatment toward proactive, preventive intervention, yet endocrine and metabolic disorders frequently progress through subtle, subclinical phases that are overlooked during routine primary-care encounters, delaying diagnosis and increasing the longitudinal cost of care. This paper presents EndocrineAI, a full-stack, high-integrity clinical decision support system (CDSS) for early-stage endocrine and metabolic risk screening. The platform adopts a hybrid architecture that synthesizes deterministic, rule-based clinical logic with probabilistic Machine Learning (ML) inference and Generative AI summarization. An eight-stage processin... More >

Polycystic Ovary Syndrome (PCOS) is a prevalent endocrine disorder affecting reproductive-age women, leading to infertility, hormonal imbalance, insulin resistance, and cardiovascular complications. Early diagnosis remains challenging due to heterogeneous manifestations, overlapping symptoms, and lack of automated screening tools. To address these issues, this study presents a comprehensive comparative framework for PCOS prediction using machine learning and deep learning on a public dataset of 541 patient records. The framework incorporates missing value imputation, feature standardization, SMOTE class balancing, and correlation-based feature selection. Five machine learning algorithms (Dec... More >

Dengue is a major public health concern in tropical and subtropical regions worldwide. The World Health Organization (WHO) classifies dengue as an endemic disease in more than 125 countries, with approximately 75% of the affected population residing in the Asia-Pacific region, including the Philippines. This study aimed to compare and analyze the four-dengue virus (DENV) serotypes in terms of gene and protein sequence alignment, structural modeling, and identification of candidate epitopes within envelope protein domain III (E-DIII). The DENV E-DIII region plays a critical role in host-cell interaction and is considered a promising immunogenic target for the development of dengue subunit vac... More >

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 >