Shivani Singh

Pica is a clinically significant and often overlooked feeding and eating disorder in which individuals have a persistent urge to eat or chew non-nutritious or non-food items and is linked to nutritional, hematological, behavioral, and environmental issues. Human studies have regularly found links between pica and iron deficiency and anemia, as well as between changes in hematological parameters, decreased ferritin, and decreased zinc concentrations; toxic-element exposure may also be a part of certain behaviors (like geophagia). The review critically summarises the potential use of multimodal artificial intelligence (AI) and machine learning (ML) to support predictive risk stratification, early detection, and clinical management of pica, highlighting the importance of combining etiological and pathophysiological biomarkers, clinical, behavioural, toxicological and electronic health-record data. Biomarker evidence also indicates human exposure to multiple biomarkers together may be a more complete risk profile than single biomarkers, since there are human data from which to draw conclusions. AI and natural language processing could be used to identify undetected pica-related behaviors and track changes over time to clinical and laboratory data. However, there are still limitations in the development and validation of pica-specific AI models, and existing evidence from related conditions mainly methodologically supports the use of AI. Further studies are needed on large, prospective, diverse human cohorts, standardized pica phenotyping, longitudinal assessment of biomarkers, explainable AI, external validation, and prospective clinical assessment. Finally, multimodal AI should be used as a clinically interpretable decision support system, not as an independent diagnostic system.

Leptospirosis or commonly referred to as Weil’s disease is an emerging neglected zoonotic bacterial infection that poses great challenges globally due to its complicated epidemiology, varied presentations, and increased prevalence linked with climate change, urbanization, and environmental pollution. Despite advancements in the diagnostic procedures and treatment options with antibiotics, delayed diagnosis and inadequate surveillance systems still hinder disease control efforts. This review provides current information about the disease with regard to the causative agents, pathogenesis, epidemiology, bio-screening techniques, and therapies of leptospirosis together with new developments in artificial intelligence (AI), machine learning (ML), modeling, geospatial analysis, three-dimensional (3D) fingerprinting, digital pathology, and precision medicine. Some of the emerging technologies such as explainable AI, deep learning (DL), Geographic Information System (GIS), Bayesian, and Long Short-Term Memory (LSTM) model, biomarker-based diagnostics, and AI -based drug discovery have demonstrated significant potential in the context of disease surveillance, prediction of outbreaks, prognosis, and personalization of clinical interventions. This review further addresses aspects like vaccine development, digital health, and the difficulties of transitioning these technologies into practice. The integration of intelligent computing techniques and molecular diagnostics in conjunction with One Health surveillance may offer a promising approach to achieve early detection, precise treatment, and preparedness in leptospirosis.

These rare facial diseases, which include hemifacial microsomia, Parry–Romberg syndrome, Moebius syndrome, Treacher Collins syndrome, Apert syndrome, and Crouzon syndrome, among others, pose considerable difficulties in diagnosis and treatment due to their clinical variability, rare occurrence, and complex genetic etiology. This review highlights the increasing potential of artificial intelligence (AI) and machine learning (ML) technologies in the better diagnosis, phenotyping, genotyping, and clinical management of these rare disorders. In this review, the applications of AI to facial phenotyping, three-dimensional (3D) imaging, radiomics, multimodal learning, and explainable AI have been highlighted. It also points out some latest developments in the field of bioinformatics, genome editing, RNA therapies, patient-derived models, and digital twin technology for precision medicine and translational research. Presently, there is sufficient evidence indicating the benefits of AI in increasing the accuracy in diagnosis, objective craniofacial evaluation, and customized treatment plans, whereas computational therapy is still experimental. However, various barriers such as data limitations, variability in phenotype, bias in the algorithms, external validation, ethical issues, and regulation prevent its widespread adoption in clinical practice. Future studies need to concentrate on multicenter data sharing, multimodal explainable AI, precision genomics, and translational framework to speed up the adoption of AI in rare craniofacial medicine.

Rare appendix malignancies, such as mucinous adenocarcinoma, goblet cell adenocarcinoma, signet-ring cell carcinoma, and appendiceal neuroendocrine tumors, are rare gastrointestinal cancers with diagnostic and treatment challenges due to their histological and molecular diversity. This study presents an explainable Artificial Intelligence (AI)-based approach that integrates digital histological biopsy images, molecular markers, and patient data to enhance disease classification and prediction of response to treatment. A quantitative methodology was used, based on an anonymized dataset of 200 patients with rare appendix malignancies. The performance of machine learning algorithms, such as Logistic Regression, Random Forest, XGBoost, and LightGBM, was compared using Accuracy, Precision, Recall, F1 score, and ROC-AUC metrics, while SHAP and Grad-CAM methods increased model interpretability. LightGBM outperformed all other methods and achieved the highest accuracy (96.2%), F1-score (95.5%), and ROC-AUC (0.987). KRAS, Ki-67, and TP53 were determined to be the most significant predictors from the biomarker analysis and the overall treatment response prediction accuracy of the combined model was found to be 95.1%. These results show that combining digital histopathology, biomarkers, and explainable AI (XAI) can enhance diagnosis accuracy, treatment response predictions, and clinical decision-making in rare appendiceal malignancies.

VEXAS syndrome (Vacuoles, E1 enzyme, X-linked, Autoinflammatory, Somatic syndrome) is a more recently described, acquired somatic mutation in the UBA1 gene, and is an autoinflammatory disorder of adults. Its clinical features include systemic inflammation, clonal hematopoiesis, abnormalities of the bone marrow and various hematological, rheumatological and dermatologic changes. This review discusses the molecular pathogenesis of VEXAS syndrome with emphasis on the UBA1 mutations, immune dysfunction and disease pathogenesis. In addition, it emphasizes the importance of artificial intelligence, next generation sequencing (NGS), integration of multi-omics and three-dimensional (3D) genomic fingerprinting in the improvement of diagnosis and molecular characterization. The current therapeutic options such as the use of corticosteroids, JAK inhibitors, azacitidine and biologic agents, as well as novel stem cell-based therapies are reviewed. Special focus is on the most promising potentially curative therapy, namely, allogeneic hematopoietic stem cell transplantation (HSCT). Although genomic medicine and precision diagnostics has come a long way, there are still issues to be addressed, particularly with respect to diagnosis at an early stage and longer-term management. The synergy of genomics, artificial intelligence (AI), and regenerative medicine could have a profound impact on the care of VEXAS syndrome patients in the future.

Lassa fever and septic fever are important infectious diseases which cause high morbidity, mortality and healthcare burden, especially in resource-limited areas. The clinical features of both diseases are so similar, and include fever, hypotension, respiratory failure, and multi-organ failure, that early diagnosis and treatment are challenging. The clinical features, epidemiological features, risk factors, early clinical predictors and biomarkers of disease severity and mortality are analyzed. Prognosis assessment and therapeutic monitoring is an important role of a number of biomarkers, such as lactate, procalcitonin, cystatin-C, and inflammatory cytokines. The review also notes that artificial intelligence, machine learning, 3D imaging technologies and epidemiological surveillance systems are increasingly playing a key role in the prediction, monitoring and clinical decision-making of diseases. The combination of biomarker-based diagnostics, AI-driven predictive modelling, and digital healthcare technologies could greatly enhance the management of infectious diseases and the preparedness of healthcare systems. The multidisciplinary research and international co-operation continue to be critical to decrease the global burden of severe infectious diseases.

Immunotherapy for cancer treatment has proved to be a very useful technique that helps to boost the immune responses of the host against cancer cells. In this study, the effectiveness of atezolizumab is assessed in Programmed Death-Ligand 1(PD-L1) Positive advanced cancers of Indians. This study was performed using a retrospective analysis on the clinical data of 120 patients that received atezolizumab treatment between 2021 and 2025. Patients with advanced solid malignancies such as non-small cell lung carcinoma (NSCLC), hepaticellular carcinoma (HCC), and triple-negative breast cancer (TNBC) were included in this study. The RECIST 1.1 criteria and CTCAE Version 5.0 recommendations were used to assess the response to therapy, progression-free survival, overall survival, and adverse events linked to the immune system, respectively. Kaplan-Meier survival analysis, chi-square testing, and descriptive statistics were all part of the statistical package. The results demonstrated that patients exhibiting elevated levels of PD-L1 had a substantially better chance of surviving. In total, 76.6% of people were able to keep the sickness at bay, whereas only 48.3% responded. Treatment response is strongly correlated with PD-L1 over-expression (χ² = 9.64, p = 0.002). Adverse reactions experienced by subjects in this study were mostly mild-to-moderate. It was concluded in this study that atezolizumab is an effective and safe immunotherapy drug for treating PD-L1-positive malignancies in Indians.

The mpox virus (MPXV), which is an emergent orthopoxvirus with zoonotic transmission capability, represents a growing public health threat on a global scale due to the recently reported outbreaks in multiple countries after 2022. In view of the rising prevalence of genetically heterogeneous strains, such as Clade I and Clade II, there has been a growing research focus on the molecular aspects of pathogenesis, evolution, transmission, and epidemiology of MPXV clades. The current review focuses on the genome structure, mutations, viral fitness, immune evasiveness, and human-to-human transmission rate associated with MPXV clades. The comparative pathogenicity between the Clade I and Clade II variants is also discussed, with emphasis on the increased virulence and mortality related to Clade I and increased transmissibility of Clade II variants, including Clade IIb. Recent genomic studies have shown that hypermutations caused by the APOBEC3 enzymes, single-nucleotide polymorphism, and adaptive evolution contribute to viral persistence, immune escape, and epidemic spread. Furthermore, the review explains how epidemiologic surveillance efforts, molecular diagnostic tools, genomics techniques, and public health issues related to mpox epidemic response are managed. This information highlights the crucial role of genomics surveillance, timely diagnostics, vaccines, and the One Health approach in future prevention of mpox outbreaks.

The human aging process can be characterized by progressive cellular degeneration, mitochondria malfunctioning, inflammatory responses, epigenetics modifications, and loss of tissue regenerative ability. The recent progress made in the field of longevity has revealed several promising treatment opportunities for prolonging a healthy lifespan in humans through epigenetics regulation, senolytics application, NAD+ precursors' intake, telomerase activation, and regenerative treatments. This review considers evidence from human studies about the impact of DNA methylation, cell senescence elimination, mitochondria recovery, enhanced immunity, tissue renewal, and cognitive reserve increase in human aging biology. According to findings based on human research, interventions involving senolytic compounds, Nicotinamide Riboside (NR), Nicotinamide Mononucleotide (NMN), and telomerase-linked regenerative treatment have the ability to contribute to improved metabolism, vascular functions, immunological resilience, and cognitive efficiency while reducing inflammatory processes and decreasing the number of senescent cells in a human body. In addition, comprehensive longevity approaches consisting of the mentioned interventions seem to possess combined benefits in terms of human longevity improvement. However, there are certain drawbacks that must be addressed when applying these interventions into clinical practice; namely, small sample sizes used in studies, lack of long-term safety testing, ethical issues, and inadequate biomarkers. Future directions in the research are discussed.

The investigation assessed the potential applications of LLMs, EEG neurofeedback, HRV analysis, DORAS systems, and VRH in the development of AI-powered hypnotherapy solutions for pain therapy. The results proved that AI-based hypnotherapy platforms had higher levels of customization, ability to monitor the states of trance, maintain consistency of sessions, and promote physiological adaptations compared to conventional hypnotherapy approaches based on human hypnotherapists. The quantitative analysis revealed that hypnotherapy sessions assisted by VRH delivered the most effective pain relief outcomes, whereas the EEG and HRV assessments revealed enhanced levels of autonomic relaxation and emotional control in the context of hypnotherapy. The researchers found that despite obvious strengths in terms of scalability, incorporation of neurofeedback, and responsiveness to individual conditions of patients, AI systems lack some qualities inherent to humans such as emotional empathy and rapport building. Overall, it can be concluded that future hypnotherapy systems are more likely to become hybrid human-AI solutions.