Lung cancer remains the leading cause of cancer-related mortality worldwide. Early detection of pulmonary nodules is crucial for timely diagnosis and effective treatment. Conventional computer-aided detection systems have shown limitations, including high false-positive rates and low sensitivity. Recent advances in deep learning, particularly convolutional neural networks (CNNs), have shown great potential in improving the accuracy and reliability of nodule detection and classification. This study aimed to develop and evaluate an automatic method for lung nodule detection and classification using a CNN-based architecture applied to computed tomography images from the publicly available LIDC-IDRI database.

This retrospective study was conducted on 82 patients (10,496 computed tomography slices) selected from the LIDC-IDRI database. The proposed method consists of five main steps: image preprocessing, lung parenchyma segmentation using Otsu’s thresholding and morphological operations, detection of nodule candidates, feature extraction, and classification using a CNN model. The CNN architecture includes two convolutional layers (20 and 30 filters, 3×3 kernel), ReLU activation, max-pooling layers, and a Softmax output layer. The network was trained with a mini-batch size of 32 for 50 epochs using the Stochastic Gradient Descent with Momentum optimizer (learning rate = 0.001, momentum = 0.9). Model performance was evaluated in terms of sensitivity, specificity, precision, and accuracy.

The proposed CNN model successfully detected pulmonary nodules and achieved accurate classification between benign and malignant nodules. On the LIDC-IDRI dataset, the model achieved a sensitivity of 98.7%, specificity of 97.5%, precision of 97.9%, and accuracy of 98.4%. Comparative analysis with recent studies, including hybrid CNN-long short-term memory and ResNet-based models, demonstrated that the proposed method provides competitive performance while maintaining lower computational complexity. The classification of nodule subtypes (solid, partially frosted, totally frosted) showed satisfactory discrimination results.

The proposed CNN-based system demonstrates the feasibility and robustness of deep learning for automatic lung nodule detection and classification. Despite strong results, the study acknowledges limitations such as single-database validation and a relatively small training size. Future work will focus on validating the model across other datasets (e.g., ELCAP, NELSON) and optimizing multi-class classification performance to enhance generalizability and clinical applicability.

Organoids are derived from self-organizing stem cells and form three-dimensional structures that are structurally and functionally similar to in vivo tissues. With the ability to replicate the in vivo microenvironment and maintain genetic stability, organoids have become a powerful tool for elucidating developmental mechanisms, accurately modeling disease processes, and efficiently screening drug candidates, and have also demonstrated significant value in the field of traditional Chinese medicine (TCM)-including applications in screening active components of TCM, studying TCM pharmacodynamic mechanisms, evaluating TCM safety, and verifying the effects of traditional non-pharmacological therapies such as acupuncture and yoga. Organoids can be cultured using air-liquid interface systems, bioreactors, and vascularization techniques. They are widely used in drug screening, disease modeling, precision medicine, and toxicity assessment. However, current limitations include high costs, difficulty in accurately replicating the microenvironment, and ethical concerns. In this review, we systematically retrieve, synthesize, and analyze relevant literature to elucidate the culture methods of organoid technology, its diverse applications across various fields, and the challenges it faces. In the future, integration with artificial intelligence may provide new insights and strategies for drug development and disease research and the modernization of TCM.

To support clinicians in making informed decisions regarding the diagnosis and management of inherited hyperbilirubinemia, including Gilbert syndrome, Crigler-Najjar syndrome, Dubin-Johnson syndrome, and Rotor syndrome, the Inherited and Metabolic Liver Disease Collaboration Group of the Hepatology Branch of the Chinese Medical Association convened a panel of Chinese experts in this field. This multidisciplinary consortium developed the present expert consensus by integrating the latest advances in both clinical practice and basic research.

Neurodegenerative diseases (NDs) represent a major global health challenge in aging populations, with their incidence continuing to rise worldwide. Although substantial progress has been made in elucidating the clinical features and molecular underpinnings of these disorders, the precise mechanisms driving neurodegeneration remain incompletely understood. This review examines the increasing significance of the gut–brain–immune triad in the pathogenesis of NDs, with particular attention to Alzheimer’s disease, Parkinson’s disease, amyotrophic lateral sclerosis, and multiple sclerosis. It explores how disruptions in gut microbiota composition and function influence neuroinflammation, blood–brain barrier integrity, and immune modulation through microbial-derived metabolites, including short-chain fatty acids, lipopolysaccharides, and bacterial amyloids. In both Alzheimer’s and Parkinson’s diseases, a reduced abundance of short-chain fatty acid-producing bacterial taxa has been consistently associated with heightened pro-inflammatory signaling, thereby facilitating disease progression. Although detailed mechanistic understanding remains limited, experimental evidence—primarily from rodent models—indicates that microbial metabolites derived from a dysbiotic gut may initiate or aggravate central nervous system dysfunctions, such as neuroinflammation, synaptic dysregulation, neuronal degeneration, and disruptions in neurotransmitter signaling via vagal, humoral, and immune-mediated pathways. The review further highlights how gut microbiota alterations in amyotrophic lateral sclerosis and multiple sclerosis contribute to dysregulated T cell polarization, glial cell activation, and central nervous system inflammation, implicating microbial factors in disease pathophysiology. In addition to identifying critical knowledge gaps, the review emphasizes the need for sustained, multifactorial research efforts, including the development of physiologically relevant brain–gut organoid models and the implementation of standardized experimental protocols. A major limitation in the field remains the difficulty of establishing causality, as clinical manifestations often arise after extended preclinical phases—lasting years or decades—during which aging, dietary patterns, pharmacological exposures, environmental factors, and comorbidities collectively modulate the gut microbiome. Finally, the review discusses how microbial influences on host epigenetic regulation may offer innovative avenues for modulating neuroimmune dynamics, underscoring the therapeutic potential of targeted microbiome-based interventions in neurodegenerative diseases.

Harlequin ichthyosis, one of the rarest and most severe skin disorders, is mainly characterized by extreme hyperkeratosis, severely impairing the natural barrier function of the skin. This congenital disease results from a mutation in the ABCA12 gene responsible for lipid transport, whereby healthy skin development is assured. Harlequin ichthyosis is an autosomal recessive condition that requires parents to carry a defective gene copy for the disorder to manifest in their offspring. Babies born with Harlequin ichthyosis have thick skin plates that crack and flake off; they easily become dehydrated, infected, and may suffer from respiratory complications. With new improvements in neonatal care and systemic therapy, notably retinoid therapy, infants’ survival rates have improved. This review provides an inclusive overview of the pathophysiology, clinical features, diagnostic methods, management, and potential future therapies for Harlequin ichthyosis. In addition, a discussion on genetic counseling and its importance in managing family risk factors is also included, as well as a look into cutting-edge research focused on gene therapy and potential curative treatments.

The global integration of traditional medicine (TM) and modern medicine reflects a fundamental shift in healthcare aimed at delivering more holistic, culturally sensitive, and patient-centered care. With over 80% of the global population relying on some form of TM, especially in Asia, Africa, and Latin America, there is growing momentum to institutionalize TM alongside evidence-based biomedicine. Countries like India, China, and Korea have led integration through formal education, government-supported research, and clinical frameworks, while high-income countries are increasingly adopting complementary and integrative medicine models. However, this convergence faces substantial challenges, including differences in epistemology, regulatory standards, evidence hierarchies, and practitioner training. Limited clinical trials, quality assurance concerns, and issues related to intellectual property rights and biopiracy further complicate harmonization. Despite these barriers, the World Health Organization’s Traditional Medicine Strategy (2014–2023) and its newly established Global Centre for Traditional Medicine (India) underscore a growing international commitment to evidence-based integration. Opportunities lie in promoting collaborative research, strengthening regulatory frameworks, enhancing digital health platforms for TM documentation, and fostering intercultural dialogue between health systems. If guided ethically and scientifically, integration can improve access to care, reduce treatment costs, and offer personalized health solutions for chronic and lifestyle-related diseases. This review explored global integration models, evaluated emerging challenges, and identified strategies to support an inclusive, pluralistic, and sustainable healthcare future that respects both traditional wisdom and modern science.

With the widespread application of systemic treatments for hepatocellular carcinoma, liver injury caused by molecular targeted drugs and immune checkpoint inhibitors has become a common clinical problem. The Chinese Society of Hepatology, Chinese Medical Association, organized domestic experts to summarize and analyze adverse liver reactions, as well as advances in the diagnosis and treatment related to systemic therapy for liver cancer, both domestically and internationally. Based on this work, we formulated the “Consensus on the Management of Liver Injury Associated with Targeted Drugs and Immune Checkpoint Inhibitors for Hepatocellular Carcinoma”, aiming to provide practical recommendations and decision-making guidance for clinicians in hepatology and related specialties. This guidance focuses on the monitoring, diagnosis, prevention, and treatment of liver injury during targeted and immune checkpoint inhibitor therapy, ultimately helping more liver cancer patients benefit from targeted immunotherapy.

Celiac disease is a chronic, immune-mediated enteropathy precipitated by gluten exposure in genetically predisposed individuals, with a global prevalence of approximately 1%. Though diagnostic workflows incorporate serologic techniques with both histologic and genetic evaluation, each approach carries key pitfalls that contribute to diagnostic inaccuracy. Serology testing is limited by selective immunoglobulin A deficiency and low-titer antibodies, in addition to interlaboratory variability of calibration standards and specimen concentrations. While duodenal biopsy is considered the gold standard for celiac diagnosis, patchy villous atrophy (e.g., ultrashort celiac disease) mimics other enteropathies, and the inherent subjectivity of histologic interpretation can compromise accuracy. Furthermore, celiac predisposition is highly correlated with two human leukocyte antigen (HLA) alleles, HLA-DQ2 and HLA-DQ8. However, nearly 30–40% of the general population expresses one of these alleles, thus introducing the risk of overdiagnosis and limiting the practical implications of genetic testing. There exist special celiac presentations, such as seronegative or potential celiac disease, overlap syndromes, and enteropathy-associated T-cell lymphoma, that introduce additional challenges to diagnostic success. The serologic-histologic discordance and nonspecific symptoms associated with these cases may require divergence from the traditional workflow, as well as supplemental investigations, such as a gluten challenge or breath testing, to confirm a celiac diagnosis. These challenges in celiac diagnosis have driven research into novel biomarkers and molecular assays that can not only enable earlier, more accurate detection but also provide longitudinal disease monitoring. Such markers include intestinal fatty acid-binding proteins, specific microRNA expression, and microbiome signatures that are strongly linked to celiac disease, which may one day serve as adjunctive screening tools to optimize diagnostic yield. This narrative review identifies the key pitfalls in adult celiac disease diagnosis — from pre-analytic serology issues to patchy histology and overinterpretation of HLA — and proposes a guideline-aligned, stepwise algorithm (with emerging biomarkers) to enhance accuracy and reduce missed or delayed cases. Ultimately, continued refinement of a comprehensive, multimodal diagnostic strategy that can integrate with emerging molecular tools is necessary for overcoming the current limitations of individual approaches to celiac diagnosis.

Nutrition plays a pivotal role in the prevention and management of gastrointestinal and hepatic diseases, yet dietary guidance remains generic, limiting its effectiveness. Conditions such as inflammatory bowel disease, irritable bowel syndrome, metabolic dysfunction-associated steatotic liver disease, celiac disease, and gastroesophageal reflux disease are significantly influenced by dietary factors. Personalized nutrition has emerged as a promising strategy to tailor interventions, but conventional approaches fail to account for individual metabolic, genetic, and microbiome variability, limiting their clinical impact. The rapid rise of artificial intelligence (AI) has transformed precision nutrition by integrating genomics, microbiome profiles, metabolic markers, and real-time dietary tracking to generate individualized recommendations. AI-driven systems are advancing dietary assessment, condition-specific nutrition optimization, and continuous monitoring through tools such as wearable devices and natural language processing-based diet analysis. These innovations hold transformative potential in gastroenterology and hepatology, offering dynamic, patient-specific strategies that may enhance clinical outcomes. However, challenges remain, including the lack of standardized AI-driven protocols, ethical concerns such as bias and data privacy, limited clinical validation, and the underrepresentation of nutrition in many current AI applications. Opportunities for progress include developing federated learning models, expanding real-world validation studies, and designing regulatory and ethical frameworks for safe implementation. This narrative review synthesizes literature published between 2015 and 2025 across five databases, highlighting key applications, limitations, and future directions of AI-driven personalized nutrition in gastroenterology and hepatology. It provides insights into how AI could reshape patient-centered care through more individualized, effective, and scalable dietary strategies.

Identifying patients at high risk for poor bowel preparation preceding a colonoscopy is critical to successful colorectal cancer screening. High-risk patients, such as those who are obese, diabetic, opioid users, or former smokers, often have comorbidity, medication, and sociodemographic factors that lead to suboptimal bowel preparation even when following protocol. Suboptimal preparation results in missed lesions, longer procedure times, and increased healthcare costs. Optimal visualization of the colon mucosa is achieved through effective bowel preparation. Polyethylene glycol (PEG) solutions are preferred for their safety, especially in patients with kidney or cardiac disease. Split-dose PEG regimens with a low-residue diet are recommended by the American Gastroenterological Association to promote cleansing and patient tolerance. Tailored regimens can be employed in high-risk patients, including those with chronic constipation, opioid dependence, or diabetes. Educational interventions, such as written and verbal instructions, patient navigators, and mobile device reminders, improve compliance. Medical strategies include split-dose PEG-electrolyte lavage solution with bisacodyl, additional purgatives for select patients, and avoidance of sodium phosphate in elderly or renally impaired individuals. Open-access colonoscopy services have expanded following the COVID-19 pandemic to manage backlogs and improve access. Improving education, simplifying regimens, and targeting interventions can reduce repeat procedures and enhance colorectal cancer detection. This narrative review summarizes patient-, medication-, and system-level risk factors for inadequate bowel preparation in high-risk populations and synthesizes practical, evidence-based strategies to optimize colonoscopy quality, including in open-access settings.