Kidney stones, in particular those from crystallising calcium oxalate, are a major healthcare issue. They must be accurately and promptly located to ensure effective treatment. Traditional diagnostic modalities including imaging studies and biochemical analysis can be expensive, invasive, and ineffective in prognosticating disease course. In this study, the authors propose HQIT-Net (Hybrid Quantum-Inspired Transformer Network), a new deep learning system for accurately and non-invasively predicting kidney stones by using biochemical indicators in urine and CT image. The novelty of HQIT-Net is that QCNNs and ViT are employed in combination to handle CT images, as well as the application of Bi-Directional LSTM with Attention in order to capture sequential patterns from numerical urine data. The unique incorporation of these modes is the key innovation in this framework, which provides a holistic view of kidney stone formation—structurally and biochemically. The model is trained on two datasets: (1) the dataset of “Physical Characteristics of Urines with and Without Crystals” consisting of scarce urine samples categorized as per six vital attributes (specific gravity, pH, osmolarity, conductivity, urea concentration and calcium concentration); and (2) the PACS CT Kidney dataset(Dhaka), to detect crystallization at kidneys and kidney without stone. To ensure data privacy and improve generalization performance, HQIT-Net adopts a Federated Self-Supervised Learning (FSSL) architecture that supports decentralized training over hospitals without sharing raw data. Experimental results show that HQIT-Net outperforms the state-of-the-art models, such as Swin Transformer, ConvNeXt, EfficientNetV2, DeepLabV3 + and GNNs with an accuracy of 99.1%, sensitivity of 98.6%, specificity of 99.3% and AUC-ROC of 0.998 respectively. HQIT-Net will establish a new benchmark for real-time privacy-preserving detection of kidney stone, which integrates quantum-inspired AI, attention-based learning and multimodal data fusion.

Pharmacogenomics are increasingly used in precision medicine for the development of targeted drug therapy to personalize treatment to enhance treatment outcomes and minimize adverse drug reactions (ADRs). In this study, we introduced an AI-based multi-omics model that integrates and amalgamates different data types including genomics, transcriptomics, epigenomics, and clinical data as predictors of patient-specific score of drug response. The included PharmGKB source of drug response offered the opportunity to use GNNs, advanced multi-modal data fusion, and dimensionality reduction to model complex biological interactions. Predictive supervised learning models were trained on a high number of features with high predictive accuracy, while reinforcement learning and digital twin through in silico validation were mapped to simpler personalized dose optimization. The hybrid model showed excellent capacity with 97.2% prediction accuracy, AUC 0.97, and full interpretability (the best-performing model of existing high-performing models at the time of submission). These empirical results provide evidence of the framework’s capacity to interrogate key pharmacogenetic features and effectively stratify patients into groups so as to develop a more effective and safer drug regimen. To summarize, the integrative AI platform supports a framework for the implementation of precision pharmacotherapy, allowing for a higher degree of data-driven decision making and treatment optimization based on personalized parameters, all judged to be credible by the patient.

The design of human-machine interfaces is more precise and demanding in the medical and healthcare industries. Medical monitoring equipment demands more consistent and effective interpretation, as well as fast and straightforward operation due to its monitoring and reference functions. Consequently, it is crucial to consider how people interact with computers when designing the interface for medical monitoring devices. Nowadays people are giving more importance to health than anything in the world. Therefore, as it is related to peoples’ safety, the architecture of human-computer communication must be carefully considered in the studies and development of high-end medical equipment. The price of training physicians and other medical professionals is rising dramatically. Most of the countries have stepped forward from the traditional medical teaching system to a more human computer interactive teaching and learning environment with innovative technologies. This article focuses on the related researches, existing HCI applications for healthcare and the application of deep neural network for disease classification. The proposed work is to develop a healthcare learning platform to offer healthcare education to both medical practitioners and also for common people. This can be implemented as Mobile apps using human-computer interface technology and also as a website with Artificial Intelligence and Machine Learning Techniques. This proposal’s primary goal is to provide anytime, everywhere access to healthcare education for physiological and medical teaching courses, consequently advancing national health care.

SmartRecoNet is a deep learning-based hybrid framework designed to deliver intelligent, personalized smartphone recommendations by leveraging diverse data sources and user-specific factors. The system integrates user reviews, smartphone specifications, real-time trends, individual preferences, budget constraints, and demographic information to generate ranked suggestions tailored to each user. By combining the strengths of multiple deep learning models, SmartRecoNet delivers recommendations that are not only accurate but also contextually relevant and timely. The framework incorporates sentiment understanding through advanced natural language processing, trend forecasting using time-series modeling, feature encoding for device specifications, and personalized preference profiling using collaborative filtering. A hybrid recommendation engine synthesizes these components to provide a comprehensive and user-aware ranking of smartphones. One of the key strengths of SmartRecoNet lies in its adaptability. It continuously learns from real-time user feedback such as clicks and purchases, ensuring that the recommendation quality evolves with changing user behavior. Additionally, the system incorporates periodic updates of its core models to remain aligned with current market dynamics and consumer sentiment. A/B testing is employed during deployment to validate performance and user satisfaction. By unifying sentiment, behavior, preferences, and specifications, SmartRecoNet offers a scalable and intelligent solution for users seeking the best smartphones aligned with their personal needs and market trends. The system demonstrates clear advantages in terms of personalization, accuracy, diversity, and responsiveness, making it a valuable tool for enhancing the smartphone shopping experience.

With the increased computational efficiency, Deep Neural Network gained more importance in the area of medical diagnosis. Nowadays many researchers have noticed the security concerns of various deep neural network models used for the clinical applications. However an efficient model misbehaves frequently when it confronted with intentionally modified data samples, called adversarial examples. These adversarial examples generated with some imperceptible perturbations, but can fool the DNNs to give false predictions. Thus, various adversarial attacks and defense methods certainly stand out from both AI and security networks and have turned into a hot exploration point lately. Adversarial attacks can be expected in various applications of deep learning model especially in healthcare area for disease prediction or classification. It should be properly handled with effective defensive mechanisms or else it may be a great threat to human life. This literature work will help to notice various adversarial attacks and defensive mechanisms. In the field of clinical analysis, this paper gives a detailed research on adversarial approaches on deep neural networks. This paper starts with the speculative establishments, various techniques, and utilization of adversarial attacking strategies. The contributions by the various researchers for the defensive mechanisms against adversarial attacks were also discussed. A few open issues and difficulties are accordingly discussed about, which might incite further exploration endeavors.

Multi-label disease classification algorithms help to predict various chronic diseases at an early stage. Diverse deep neural networks are applied for multi-label classification problems to foresee multiple mutually non-exclusive classes or diseases. We propose a federated approach for detecting the chest diseases using DenseNets for better accuracy in prediction of various diseases. Images of chest X-ray from the Kaggle repository is used as the dataset in the proposed model. This new model is tested with both sample and full dataset of chest X-ray, and it outperforms existing models in terms of various evaluation metrics. We adopted transfer learning approach along with the pre-trained network from scratch to improve performance. For this, we have integrated DenseNet121 to our framework. DenseNets have a few focal points as they help to overcome vanishing gradient issues, boost up the feature propagation and reuse and also to reduce the number of parameters. Furthermore, gradCAMS are used as visualization methods to visualize the affected parts on chest X-ray. Henceforth, the proposed architecture will help the prediction of various diseases from a single chest X-ray and furthermore direct the doctors and specialists for taking timely decisions.

Water is the vital component in a human body. Healthy body should be hydrated enough for the proper functioning of various organs. Water has major roles in the physical functioning of a human. Water plays a major role in the metabolic activities in the body. The various nutrients formed in the human body are transferred to different organs through water. Intake of water and water discharge should be controlled to maintain the water balance. Requirements of water in the human body may not meet through the food items or beverages and also not possible to get from metabolic activities. Sometimes the present dehydration level may be life threatening. There should be a proper mechanism to calculate the severity level of dehydration. If the severity of dehydration could be calculated, it is possible to take proper remedies. Dehydration may lead to different chronic diseases like kidney failure, coma, heart related illness, electrolyte abnormalities etc. The intake of plain water is required to maintain the water balance in the human body for better health. It is inevitable to meet the daily water requirements as the deficiency of water in human being may lead to various chronic diseases. Deep learning methods can be used to develop a predictive model for the early diagnosis of chronic diseases with a proper dataset which indudes not only the test results but also the hydration level in human body.