International Journal of Healthcare Education & Medical Informatics (ISSN: 2455-9199)

AI-Based Prediction and Detection of Glaucoma Using Fundus Imaging: A Review of Machine and Deep Learning Approaches

Satyam Sharma, Dr Vipul Sharma — Thu, 22 Jan 2026 00:00:00 +0000

Glaucoma is an acquired chronic neuropathy characterized by damage to the optic nerve head and retinal nerve fiber layer. It is a leading cause of irreversible blindness worldwide. Our paper presents a systematic review of recent machine learning (ML) and deep learning (DL) approaches for glaucoma diagnosis from retinal fundus images. We survey available datasets, preprocessing methods, network architectures, and evaluation metrics. The review highlights automated methods for optic nerve segmentation and glaucoma classification, many achieving high accuracy. Results are synthesized to discuss the strengths and limitations of current AI methods and suggest directions for future research.

Applications of Nature-Inspired Metaheuristic Algorithms for Disease diagnosis in medical imaging

Priya Thakur, Sunaina, Baljit Kaur, Navreet Kaur — Thu, 22 Jan 2026 00:00:00 +0000

Nature-Inspired Metaheuristics Algorithms (NIMHs) have also been given attention in recent years in the field of medical imaging to diagnose diseases because they can efficiently deal with complex optimization problems. These Algorithms are motivated by natural phenomena and natural evolution. This survey emphasizes recent progress in using algorithms like particle swarm optimization (PSO), grey wolf optimizer (GWO), whale optimization algorithm (WOA), Harris Hawks Optimization (HHO), Salp Swarm Optimization (SSO)and hybrid metaheuristics towards disease diagnosis across image modalities, including MRI, CT and X-ray. When they are merged with contemporary architecture, e.g., U-net, vision transformer (ViT), the techniques enhance diagnostic accuracy and efficiency to identify diseases like COVID-19 classification, tumours and Parkinson's disease. The current review integrates recent developments in the area, yet also emphasizes persisting challenges including increased computational cost, poor generalizability, and absence of interpretability. And the directions for the future are elaborated, including developing effective hybrid models, explainable AI, multi-objective optimization, and clinically validated frameworks on various datasets.

A Review of Deep Learning Fusion based Multimodal for Disease Diagnosis and Classification.

Baljit Kaur, Navreet Kaur, Sunaina, Priya Thakur — Thu, 22 Jan 2026 00:00:00 +0000

Deep Fusion multimodal learning, have revolutionized early disease detection and prediction. Deep Fusion multimodal integrates data from different sources like clinical records, medical imaging, genomic data, clinical records and come up with optimal results of patients. Recent approaches includes Convolution Neural Network(CNNs) for feature extraction ,Vision Transformers(ViTs) for global attention, self-supervised multimodal transformers, self-attention, cross-attention and Hand Crafted Features authorize more accurate and efficient predictions. This enables early detection of diseases like Alzheimer’s, tumor growth before it becomes visible. While challenges occurs in data standardization, interpretability and clinical validation.We believe that the multimodal robustness can be enhanced by developing more interpretable and generalized model which enable accurate monitoring early disease diagnosis and classification disease prediction years before clinical onset.

COVID-19 Detection Using Machine Learning: A Dataset-Centric Review

Ravneet Kaur, Vipul Sharma — Thu, 22 Jan 2026 00:00:00 +0000

The COVID-19 pandemic has posed unprecedented challenges to global healthcare systems, necessitating rapid and accurate diagnostic strategies. Machine learning and deep learning approaches have emerged as powerful tools for analyzing diverse datasets, including clinical records, imaging data, audio signals, and multimodal sources, to detect and predict COVID-19 infection and severity. This review systematically examines studies utilizing these datasets, highlighting the predictive performance of various models, including convolutional neural networks, support vector machines, recurrent neural networks, and ensemble methods. Clinical datasets provide critical insights for risk stratification and mortality prediction, imaging datasets enable precise assessment of pulmonary involvement, and audio datasets offer non-invasive, rapid screening opportunities. Multimodal approaches integrating these diverse sources demonstrate superior predictive accuracy and robustness. Despite significant advancements, challenges such as dataset heterogeneity, class imbalance, limited sample sizes, and model interpretability persist. Future research directions include attention-based fusion, self-supervised and contrastive learning, and federated learning to improve generalization and facilitate real-world deployment. This review emphasizes the importance of dataset-driven machine learning strategies in advancing COVID-19 diagnostics and provides a framework for future AI-based approaches to infectious disease detection.

Multi-Modal Artificial Intelligence for Cardiovascular Risk Prediction: Integrating ECG, Imaging, Genomics, and Wearable Data

Aashna Sagar, Dr. Kiranbir Kaur, Dr. Prabhpreet Kaur, Dr. Amandeep Kaur — Thu, 22 Jan 2026 00:00:00 +0000

Cardiovascular diseases remain the biggest killers. Early detection makes a real difference in stopping and handling treatment right. Pulling together data from all sorts of places, like ECGs and medical images, genomics, plus from wearable devices, it paints this complete
view of heart health. Basically, it mixes help predict risks way better. It catches
issues early on, and it customizes care by blending the electrical signals with
structural looks, genetic details, and everyday people's habits.

Advances in Artificial Intelligence for Lung Cancer Detection: A Review of Imaging and Computational Approaches

Prabhjot Kaur, Dr. Prabhpreet Kaur , Dr. Kiranbir kaur , Dr. Amandeep Kaur — Thu, 22 Jan 2026 00:00:00 +0000

Lung cancer is the leading cause of cancer-related deaths worldwide, and early detection significantly improves survival. Artificial intelligence (AI), particularly deep learning and convolutional neural networks (CNNs), has emerged as a powerful tool in thoracic imaging and diagnostics. Recent research has demonstrated that AI is capable of accurately detecting, categorizing, and segmenting lung nodules on chest radiographs, low-dose CT (LDCT), and histology, often matching or outperforming radiologists in this regard. AI also makes it easier to predict histological subtypes, characterize non-invasive tumors, and integrate prognostic information with clinical data. However, problems like limited dataset generalizability, high false-positive rates, and restricted clinical

Optimising Deep Feature Maps using Genetic Algorithm for Efficient Breast Mass Classification in Mammogram Images

Navreet kaur, Rahul Hans — Thu, 22 Jan 2026 00:00:00 +0000

Breast cancer is the most prominent cause of death of women worldwide, highlighting the importance of precise and effective diagnostic tools. Deep convolutional neural networks have already achieved substantial success. in medical image analysis but run into redundancy and computational cost problems with high-dimensional feature flattening. This paper provides a hybrid deep learning and metaheuristic approach to optimising deep feature maps prior to flattening. From the CBIS-DDSM breast cancer dataset, feature maps are drawn from the ReLU5 layer of AlexNet, and global average pooling (GAP) compresses them into a single representative value without changing size or losing information. A Genetic Algorithm (GA) is employed for optimisation at the channel level to determine the most informative and relevant channels to classify. The subset of features optimised is then fed into a softmax classifier to classify finally. This method avoids redundant calculations, accelerates convergence, and decreases training time. Experiments show that the designed model performs better than the conventional AlexNet framework in both accuracy in classification and efficiency in computations. Notably, at 40 epochs, GA_AlexNet achieved a 72.51% accuracy, surpassing AlexNet by 8.44%.

Integrating Artificial Intelligence in Structural Health Monitoring: A Path Toward Climate Resilient Infrastructure

Riti Mahajan, Kulwinder Kaur, Vivek Gupta, Subham Sharma — Fri, 16 Jan 2026 00:00:00 +0000

This paper reviews the evolution and advancements in structural health monitoring(SHM). The traditional methods relied on sensor-based measurements and statistical modeling for anomaly detection. The introduction of wireless smart sensor networks improved scalability and deployment. Recent changes in technologies, with the integration of Artificial Intelligence (AI), Machine Learning (ML), and IoT, have enabled real-time monitoring to be more productive and predictive. Core techniques include vibration analysis, fibre optics, non-destructive testing, and image-based methods.AI models such as Random forests, CNNs, RNNs, and SVMs enhance fault detection and damage classification. Applications extend to bridges, buildings, aerospace, offshore platforms, and smart cities. SHM benefits include improved safety, automation, and scalability, reduced cost, etc. Key challenges remain in data heterogeneity, sensor reliability, and model interpretability. Future research emphasizes hybrid AI-IoT frameworks and sustainable solutions for resilient infrastructure

Role of AI in the Food & Beverage Industry

Kanwal Nain Thakur, Karambir Kaur — Tue, 27 Jan 2026 00:00:00 +0000

This article starts by discussing the technologies currently used in the food and beverage industry. It highlights the progress AI is making in analytics, improving quality, and predictive maintenance. This paper examines the various roles of AI in the food and beverage sector. It examines its uses in food production, quality assurance, optimising the supply chain, customer service, personalisation, and managing waste. The article also considers the ethical issues, challenges, and future possibilities. As the food and beverage (F&B) industry evolves due to shifting consumer tastes and operational challenges, AI plays a crucial role in driving innovation and efficiency.

A Review of Methods for Detecting Calcium Carbide Induced Ripening in Fruits

Gurbhit Chaurakoti, Harshit Kumar , Hani Kumar , Anurag Singh — Tue, 27 Jan 2026 00:00:00 +0000

The use of calcium carbide (CaC₂) as a ripening agent for fruits is banned in most countries across the world, including India (under the prevention of Food Adulteration Act (PFA: 44 AA), 1955 and Food Safety and Standards Regulation Act, 2011). Yet, in our country; it is a common practice to use industrial-grade Calcium Carbide for ripening of climacteric fruits like mango, banana, papaya etc. which leaves behind traces of arsenic and phosphorus, along with heavy metals like Fe, Co, Hg, Pb etc. CaC₂ reacts with moisture to produce acetylene gas, which accelerates the ripening process, but the byproducts of this process pose a severe threat to human health. Hence, there is a need of accessible and economically feasible methods for detecting CaC₂ induced ripening in fruits, for all stakeholders in the fruit supply chain, especially the end consumer. This review investigates the utility, limitations, and underlying principles of key methods. While laboratory-based techniques like gas chromatography-mass spectrometry are highly accurate, they are time-consuming and destructive. Sensor-based and colorimetric methods target residues of CaC₂, arsenic, and the VOC (volatile organic compound) profile of fruit. Spectroscopy based methods have been explored, including the more accurate hyperspectral imaging and the low-cost, portable sensors in the visible-near infrared wavelength band, which show potential for hand-held applications.