Richa Gupta

Diabetic retinopathy (DR), an eye disease that is a threatening cause of irreversible blindness, always challenging to detect and diagnose on time. There are many ophthalmic invasive procedures which exist in medical science for the diagnosis of oculi (eyes). These all require highly skilled medical practitioners with operational knowledge of diagnosing sensitive organs like the retina and its tiny vessels. Due to the dearth of retinal specialists, the eye’s organs’ sensitivity, and the complexity of retinal therapy, invasive procedures are time-consuming, costly, and have slow progress. The fundus images are the visual information of the rear part of the retina. The progression of lesions around the retinal tissue’s surface causes the electric signals to not able to reach at the visual cortex, thus causing blurry vision or vision loss experienced by patients. The older methods using retinal fundus images for diagnosing lesions and symptoms of DR take time, causing delays in treatment and hence reducing the chance of success. Therefore, for early diagnosis, using fundus or retinal images can save the required effort and time of both doctors and patients. Artificial intelligence (AI) techniques have the capability to learn the tissue structures of the eye’s anatomy and to provide an analysis of the disease through the retinal fundus images. This process consists of operations, first apply the image preprocessing techniques followed by segmentation and filtering, then classify the disease using the artificial intelligence-based model. The proposed model trained over a dataset of DR images, for the prediction of accurate results, followed by deciding if the diagnosis by the model is correctly classified or not using the Explainable AI (XAI) algorithm. The rapid growth and better outcome of machine learning and deep learning algorithms are reasons to adopt, enhance the early diagnosis and treatments of patients.

CRISPR-Cas systems have transformed genome engineering with their exceptional precision, programmability, and affordability. Although they originate from microbial defense mechanisms, expanding their use, especially in therapeutics, requires a chemically oriented framework that allows for tunable, reversible, and safe gene editing. This review offers a multidisciplinary look at recent progress in the structural, synthetic, and computational aspects of CRISPR-Cas technologies. Structural analyses examine the domain architectures of Cas enzymes, including the recognition (REC), nuclease (HNH and RuvC), and PAM-interacting domains, emphasizing the catalytic importance of divalent metal ions. Comparative insights into Cas9, Cas12, and Cas13 demonstrate functional diversity across DNA- and RNA-targeting systems, supported by high-resolution structural data on guide RNA pairing and conformational dynamics. The review highlights advances in chemical modulation, such as anti-CRISPR proteins, small-molecule inhibitors, and stimuli-responsive switches, focusing on structure–activity relationships. Additionally, bioorganic delivery systems like lipid nanoparticles, polymers, and cell-penetrating peptides are discussed for their role in improving in vivo delivery through formulation chemistry. Computational chemistry methods—molecular docking, molecular dynamics simulations, and virtual screening—are identified as critical tools for discovering and optimizing modulators. The use of AI-driven tools is proposed as a promising direction for rational CRISPR design. Overall, this chemistry-focused perspective emphasizes the importance of molecular control in developing the next generation of programmable and safe CRISPR-based therapies.

Computational and machine learning approaches play a pivotal role in identifying, characterizing, and targeting noncanonical DNA structures, including G-quadruplexes, Z-DNA, hairpins, and triplexes. These configurations play critical roles in maintaining genomic stability, facilitating DNA repair, and regulating chromatin organization. Although the human genome predominantly adopts the B DNA conformation, evidence indicates that non-B DNA forms exert significant influence on gene expression and disease development. This highlights the need for dedicated computational frameworks to systematically investigate these alternative structures. Machine learning model, encompassing supervised and unsupervised algorithms such as K Nearest Neighbors, Support Vector Machines, and deep learning architectures including Convolutional Neural Networks, have shown considerable potential in predicting sequence motifs predisposed to forming non-B DNA conformations. These predictive tools contribute to identifying genomic regions associated with disease susceptibility. Complementary bioinformatics platforms and molecular docking tools, notably Auto Dock, along with chemical libraries like ZINC, facilitate the virtual screening of small molecules targeting specific DNA structures. Stabilizers of G quadruplexes, exemplified by CX 5461, have demonstrated therapeutic promise in BRCA-deficient cancers, highlighting the translational impact of computational methods on drug discovery. Anticipating DNA structural shifts opens new avenues in personalized medicine for complex diseases, with computational chemistry and machine learning deepening our understanding of DNA topology and guiding smarter ligand design. The integrated approach proposed in this review addresses the previous studies performed in this field and highlights the current limitations in structural genomics and advances the development of precision therapeutics aligned with individual genomic profiles.

This research presents a predictive model aimed at estimating the progression of Amyotrophic Lateral Sclerosis (ALS) based on clinical features collected from a dataset of 50 patients. Important features included evaluations of speech, mobility, and respiratory function. We utilized an XGBoost regression model to forecast scores on the ALS Functional Rating Scale (ALSFRS-R), achieving a training mean squared error (MSE) of 0.1651 and a testing MSE of 0.0073, with R² values of 0.9800 for training and 0.9993 for testing. The model demonstrates high accuracy, providing a useful tool for clinicians to track disease progression and enhance patient management and treatment strategies.

Alzheimer’s disease (AD) is a progressive neurodegenerative disorder characterized by cognitive decline and memory impairment. Early and accurate detection of AD is crucial for timely intervention and effective treatment. Biomarkers such as amyloid-beta and tau proteins, genetic markers like the APOE genotype, and neuroimaging findings are essential for AD diagnosis and prognosis, but their complex interactions require advanced analytical tools. AI has emerged as a transformative tool in healthcare, offering advanced computational techniques to analyze complex biomarker data with enhanced precision. This review paper explores the advancements in diagnosing Alzheimer’s disease (AD) using artificial intelligence (AI) techniques. In the paper, we discuss the importance of diagnosing AD accurately and the potential benefits of using AI techniques for the early and accurate detection of AD. We emphasize the significance of AI in optimizing biomarker analysis for AD detection, discussing the challenges in their implementation and future implications. AI technologies can transform AD detection by significantly improving diagnostic imaging techniques, identifying key biomarkers, and standardizing the analysis of complex neuroimaging data. In this paper, we also highlight the critical role of AI in addressing challenges associated with integrating new technologies into clinical practice and providing effective solutions for consistent and reliable AD detection techniques.

Background: Stressors have a huge impact on ones well-being. It affects individual mental and physical health, if untreated. The response to these stresses is termed as a stress response. Based on the type and severity of the stimulus, stress can affect the various actions and functioning of the body called stress. This explains how important it becomes to detect the level of stress and treat it well. The best treatment for stress is to identify the factors causing stress and eliminate it in the initial stage. Various methods have been proposed to detect the level of stress. One of the common methods is by using wearable devices to capture EEG signals and use various proposed algorithms to detect the level of stress. However, there are cases where stress cannot be captured by non-invasive technologies. Besides, these technologies cannot determine the stress-causing factors. This paper proposes a methodology to cater to such cases and identify the factors causing stress in the patient. It can also act as a front line methodology to detect if the candidate is suffering from anxiety or stress. The use of fuzzy logic in various healthcare areas has become very evident. This is because it deals with a range of values. While, Petri nets is a network where the arc runs from place to transition and not between places and transitions. It is the best model to use in dynamic and concurrent activities of the system. Thus, combination of these 2 logics can provide an extremely competent basis for the implementation of computing reasoning processes and the modeling of systems with uncertainty. Thus, came Fuzzy Petri Nets (FPN). This paper proposes the use of FPN in designing a methodology for factors responsible for causing stress and furthers the level of stress in the patient. The methodology is developed by observing the process of food transfer in plants. The authors have also discussed afferent and efferent stress paths. Method: This methodology proposed in this paper uses Fuzzy Petri Net. The algorithm designed in this paper has been named as the Sprouting tree algorithm by the authors. Designing the fault tree is the first and very important step for the correct determination of the level of the stress. The score generated using the Hamilton scale is fed as input to the AND/OR gate system to receive the value of stressor and thus drawing a fault tree. The transformation rules are applied to convert fault tree into the FPN. Then, we derive production rules and reachability matrix. These rules helps in normalizing the value obtained via fault tree so that they lie in range of fuzzy logic. FPN calculates the certainty factor (CF), which represents the state of stress in an individual. Therefore, the values obtained from FPN will finally build a tree which is named as Sprouting tree. Conclusions: The methodology proposed in this paper is absolutely new to detect the stress. The future of this work is to observe the accuracy of the proposed algorithm by implementing it with real data, which is under process.

Breast cancer, the most prevalent cancer in women worldwide, demands effective screening for early identification and improved treatment outcomes. Recent advances in artificial intelligence (AI) have resulted in dramatic developments in a variety of fields, including healthcare. In this review paper, we look at how AI approaches can be used in breast cancer screening to improve diagnostic accuracy and provide deeper molecular insights. We dig into the complex terrain of breast cancer treatment, which has transformed as a result of the discovery of prognostic and predictive biomarkers, allowing for personalised therapeutic methods based on molecular subgroups. We emphasise the importance of AI-driven approaches in optimising screening procedures and providing quick and exact findings. The potential of AI to revolutionise breast cancer screening is highlighted, including its applications in diagnostic imaging, lesion identification, and standardised imaging data interpretation. The analysis highlights AI’s critical role in tackling issues associated with the integration of new technologies, providing solutions for worldwide standardisation in cancer detection.