Search Results (982)

Background/Objectives: Lung cancer recurrence, particularly in NSCLC, remains a major challenge, with 30–70% of patients relapsing post-treatment. Traditional predictors like TNM staging and histopathology fail to account for tumor heterogeneity and immune dynamics. This review evaluates AI models integrating gene biomarkers (TP53, KRAS, FOXP3, PD-L1, and CD8) to enhance the recurrence prediction and improve the personalized risk stratification. Methods: Following the PRISMA guidelines, we systematically reviewed AI-driven recurrence prediction models for lung cancer, focusing on genomic biomarkers. Studies were selected based on predefined criteria, emphasizing AI/ML approaches integrating gene expression, radiomics, and clinical data. Data extraction covered the study design, AI algorithms (e.g., neural networks, SVM, and gradient boosting), performance metrics (AUC and sensitivity), and clinical applicability. Two reviewers independently screened and assessed studies to ensure accuracy and minimize bias. Results: A literature analysis of 18 studies (2019–2024) from 14 countries, covering 4861 NSCLC and small cell lung cancer patients, showed that AI models outperformed conventional methods. AI achieved AUCs of 0.73–0.92 compared to 0.61 for TNM staging. Multi-modal approaches integrating gene expression (PDIA3 and MYH11), radiomics, and clinical data improved accuracy, with SVM-based models reaching a 92% AUC. Key predictors included immune-related signatures (e.g., tumor-infiltrating NK cells and PD-L1 expression) and pathway alterations (NF-κB and JAK-STAT). However, small cohorts (41–1348 patients), data heterogeneity, and limited external validation remained challenges. Conclusions: AI-driven models hold potential for recurrence prediction and guiding adjuvant therapies in high-risk NSCLC patients. Expanding multi-institutional datasets, standardizing validation, and improving clinical integration are crucial for real-world adoption. Optimizing biomarker panels and using AI trustworthily and ethically could enhance precision oncology, enabling early, tailored interventions to reduce mortality. Full article

Gastroesophageal reflux disease (GERD) is a widespread condition that requires reliable and non-invasive diagnostic methods to minimize patient discomfort. This study presents a radiofrequency spectrophotometry sensor specifically designed to detect esophageal liquid flow and ionicity in real time without disrupting the patient’s daily life. The sensor operates by measuring dielectric properties and ionic conductivity through the thoracic plexus, eliminating the need for invasive probes or prolonged monitoring. A study conducted on 49 participants demonstrated the sensor’s ability to differentiate between various liquid media and identify beta dispersion relaxation as a biomarker for esophageal tissue damage, a key indicator of GERD progression. Additionally, alpha dispersion conductivity effectively distinguished reflux episodes, proving the sensor’s high sensitivity. Unlike traditional diagnostic techniques such as endoscopy or pH monitoring, this radiofrequency spectrophotometry sensor enables continuous, real-time reflux detection, allowing patients to maintain a normal lifestyle during assessment. The results validate its potential as an innovative alternative for GERD diagnosis and monitoring, with future research focused on clinical validation, optimization, and integration into long-term patient monitoring systems. Full article

Endometrial organoids (EOs) have emerged as a powerful three-dimensional (3D) model for studying the human endometrium, offering new insights into infertility and reproductive disorders. These self-organizing miniature structures closely mimic the cellular composition, hormonal responsiveness, and functional characteristics of the endometrium, making them valuable preclinical tools for investigating implantation failure, endometrial receptivity, and disease pathophysiology. This review explores the role of EOs in reproductive medicine, with a focus on their applications in infertility research, environmental toxicology, and regenerative therapies. Traditional 2D cell cultures fail to capture the complexity of these physiological and pathological interactions, whereas organoids provide a physiologically relevant system for studying implantation mechanisms. Additionally, co-culture models incorporating stromal and immune cells have further enhanced our understanding of the maternal–fetal interface. Beyond modeling infertility, EOs hold significant promise for therapeutic applications. Advances in organoid transplantation have demonstrated potential for treating endometrial dysfunction-related infertility, including conditions such as Asherman’s syndrome and thin endometrium. Moreover, these models serve as a platform for drug screening and biomarker discovery, paving the way for personalized reproductive medicine. Despite their transformative potential, limitations remain, including the need for improved extracellular matrices, vascularization, and immune system integration. This review emphasizes the significant contributions of EOs to the field of infertility treatment and reproductive biology by examining recent advancements and emerging research. The continued refinement of these models would offer a paradigm for improving assisted reproductive technologies (ARTs) and regenerative medicine outcomes, offering new hope for individuals facing infertility challenges. Full article

This study proposes a novel brain-region-level aging assessment paradigm based on Shapley value interpretation, aiming to overcome the interpretability limitations of traditional brain age prediction models. Although deep-learning-based brain age prediction models using neuroimaging data have become crucial tools for evaluating abnormal brain aging, their unidimensional brain age–chronological age discrepancy metric fails to characterize the regional heterogeneity of brain aging. Meanwhile, despite Shapley additive explanations having demonstrated potential for revealing regional heterogeneity, their application in complex deep learning algorithms has been hindered by prohibitive computational complexity. To address this, we innovatively developed a computational framework featuring efficient Shapley value approximation through a novel multi-stage computational strategy that significantly reduces complexity, thereby enabling an interpretable analysis of deep learning models. By establishing a reference system based on standard Shapley values from healthy populations, we constructed an anatomically specific Regional Brain Aging Deviation Index (RBADI) that maintains age-related validity. Experimental validation using UK Biobank data demonstrated that our framework successfully identified the thalamus (THA) and hippocampus (HIP) as core contributors to brain age prediction model decisions, highlighting their close associations with physiological aging. Notably, it revealed significant correlations between the insula (INS) and alcohol consumption, as well as between the inferior frontal gyrus opercular part (IFGoperc) and smoking history. Crucially, the RBADI exhibited superior performance in the tri-class classification of prodromal neurodegenerative diseases (HCs vs. MCI vs. AD: AUC = 0.92; HCs vs. pPD vs. PD: AUC = 0.86). This framework not only enables the practical implementation of Shapley additive explanations in brain age prediction deep learning models but also establishes anatomically interpretable biomarkers. These advancements provide a novel spatial analytical dimension for investigating brain aging mechanisms and demonstrate significant clinical translational value for early neurodegenerative disease screening, ultimately offering a new methodological tool for deciphering the neural mechanisms of aging. Full article

Early detection of cancer is crucial for improving patient outcomes. Traditional modalities such as mammography and low-dose computed tomography are effective but exhibit inherent limitations, including radiation exposure and accessibility challenges. This review explores innovative, non-invasive cancer screening methods, focusing on liquid biopsy and volatile organic compound (VOC)-based detection platforms. Liquid biopsy analyzes circulating tumor DNA and other biomarkers in bodily fluids, offering potential for early detection and monitoring of treatment response. VOC-based detection leverages unique metabolic signatures emitted by cancer cells, detectable in exhaled breath or other bodily emissions, providing a rapid and patient-friendly screening option. We provide a comprehensive overview of these advanced multi-cancer detection techniques to enhance diagnostic accuracy, accessibility, and patient adherence, and ultimately enhance survival rates and patient outcomes. Full article

This review explores recent advances in data processing for atomic force microscopy (AFM) nanoindentation on soft samples, with a focus on “apparent” or “average” Young’s modulus distributions used for cancer diagnosis and treatment monitoring. Young’s modulus serves as a potential key biomarker, distinguishing normal from cancerous cells or tissue by assessing stiffness variations at the nanoscale. However, user-independent, reproducible classification remains challenging due to assumptions in traditional mechanics models, particularly Hertzian theory. To enhance accuracy, depth-dependent mechanical properties and polynomial corrections have been introduced to address sample heterogeneity and finite thickness. Additionally, AFM measurements are affected by tip imperfections and the viscoelastic nature of biological samples, requiring careful data processing and consideration of loading conditions. Furthermore, a quantitative approach using distributions of mechanical properties is suitable for tissue classification and for evaluating treatment-induced changes in nanomechanical properties. As part of this review, the use of AFM-based mechanical properties as a tool for monitoring treatment outcomes—including treatments with antifibrotic drugs and photodynamic therapy—is also presented. By analyzing nanomechanical property distributions before and after treatment, AFM provides insights for optimizing therapeutic strategies, reinforcing its role in personalized cancer care and expanding its applications in research and clinical settings. Full article

This study presents a non-invasive approach to monitoring post-harvest fruit quality by applying CO₂ laser photoacoustic spectroscopy (CO₂LPAS) to study the respiration of “Conference” pears from local and commercially stored (supermarket) sources. Concentrations of ethylene (C₂H₄), ethanol (C₂H₆O), and ammonia (NH₃) were continuously monitored under shelf-life conditions. Our results reveal that ethylene emission peaks earlier in supermarket pears, likely due to post-harvest treatments, while ethanol accumulates over time, indicating fermentation-related deterioration. Significantly, ammonia levels increased during the late stages of senescence, suggesting its potential role as a novel biomarker for fruit degradation. The application of CO₂LPAS enabled highly sensitive, real-time detection of trace gases without damaging the fruit, offering a powerful alternative to traditional monitoring methods. Additionally, artificial intelligence (AI) models, particularly convolutional neural networks (CNNs), were explored to enhance data interpretation, enabling early detection of ripening and spoilage patterns through volatile compound profiling. This study advances our understanding of post-harvest physiological processes and proposes new strategies for improving storage and distribution practices for climacteric fruits. Full article

Background. Postoperative pancreatic fistula (POPF) remains one of the most relevant complications following pancreaticoduodenectomy (PD), significantly impacting short-term outcomes and delaying adjuvant therapies. Current predictive models offer limited accuracy, often failing to incorporate early postoperative data. This retrospective study aimed to develop and validate machine learning (ML) models to predict the absence and severity of POPF using clinical, surgical, and early postoperative variables. Methods. Data from 216 patients undergoing PD were analyzed. A total of twenty-four machine learning (ML) algorithms were systematically evaluated using the Matthews Correlation Coefficient (MCC) and AUC-ROC metrics. Among these, the GradientBoostingClassifier consistently outperformed all other models, demonstrating the best predictive performance, particularly in identifying patients at low risk of postoperative pancreatic fistula (POPF) during the early postoperative period. To enhance transparency and interpretability, a SHAP (SHapley Additive exPlanations) analysis was applied, highlighting the key role of early postoperative biomarkers in the model predictions. Results. The performance of the GradientBoostingClassifier was also directly compared to that of a traditional logistic regression model, confirming the superior predictive performance over conventional approaches. This study demonstrates that ML can effectively stratify POPF risk, potentially supporting early drain removal and optimizing postoperative management. Conclusions. While the model showed promising performance in a single-center cohort, external validation across different surgical settings will be essential to confirm its generalizability and clinical utility. The integration of ML into clinical workflows may represent a step forward in delivering personalized and dynamic care after pancreatic surgery. Full article

Background/Objectives: This study investigates the application of machine learning (ML) techniques in diagnosing speech sound disorders (SSDs) in Saudi Arabic-speaking children, with a specific focus on phonological biomarkers, particularly Infrequent Variance (InfrVar), to improve diagnostic accuracy. SSDs are a significant concern in pediatric speech pathology, affecting an estimated 10–15% of preschool-aged children worldwide. However, accurate diagnosis remains challenging, especially in linguistically diverse populations. Traditional diagnostic tools, such as the Percentage of Consonants Correct (PCC), often fail to capture subtle phonological variations. This study explores the potential of machine learning models to enhance diagnostic accuracy by incorporating culturally relevant phonological biomarkers like InfrVar, aiming to develop a more effective diagnostic approach for SSDs in Saudi Arabic-speaking children. Methods: Data from 235 Saudi Arabic-speaking children aged 2;6 to 5;11 years were analyzed using several machine learning models: Random Forest, Support Vector Machine (SVM), XGBoost, Logistic Regression, K-Nearest Neighbors, and Naïve Bayes. The dataset was used to classify speech patterns into four categories: Atypical, Typical Development (TD), Articulation, and Delay. Phonological features such as Phonological Variance (PhonVar), InfrVar, and Percentage of Consonants Correct (PCC) were used as key variables. SHapley Additive exPlanations (SHAP) analysis was employed to interpret the contributions of individual features to model predictions. Results: The XGBoost and Random Forest models demonstrated the highest performance, with an accuracy of 91.49% and an AUC of 99.14%. SHAP analysis revealed that articulation patterns and phonological patterns were the most influential features for distinguishing between Atypical and TD categories. The K-Means clustering approach identified four distinct subgroups based on speech development patterns: TD (46.61%), Articulation (25.42%), Atypical (18.64%), and Delay (9.32%). Conclusions: Machine learning models, particularly XGBoost and Random Forest, effectively classified speech development categories in Saudi Arabic-speaking children. This study highlights the importance of incorporating culturally specific phonological biomarkers like InfrVar and PhonVar to improve diagnostic precision for SSDs. These findings lay the groundwork for the development of AI-assisted diagnostic tools tailored to diverse linguistic contexts, enhancing early intervention strategies in pediatric speech pathology. Full article

Traumatic brain injury (TBI) remains a critical global health issue with limited effective treatments. Traditional care of TBI patients focuses on stabilization and symptom management without regenerating damaged brain tissue. In this review, we analyze the current state of treatment of TBI, with focus on novel therapeutic approaches aimed at reducing secondary brain injury and promoting recovery. There are few innovative strategies that break away from the traditional, biological target-focused treatment approaches. Precision medicine includes personalized treatments based on biomarkers, genetics, advanced imaging, and artificial intelligence tools for prognosis and monitoring. Stem cell therapies are used to repair tissue, regulate immune responses, and support neural regeneration, with ongoing development in gene-enhanced approaches. Nanomedicine uses nanomaterials for targeted drug delivery, neuroprotection, and diagnostics by crossing the blood–brain barrier. Brain–machine interfaces enable brain-device communication to restore lost motor or neurological functions, while virtual rehabilitation and neuromodulation use virtual and augmented reality as well as brain stimulation techniques to improve rehabilitation outcomes. While these approaches show great potential, most are still in development and require more clinical testing to confirm safety and effectiveness. The future of TBI therapy looks promising, with innovative strategies likely to transform care. Full article

Metastatic colorectal cancer (mCRC) remains a major cause of cancer-related mortality worldwide and requires the development of new biomarkers to improve patient management. Traditional markers, such as RAS mutations and microsatellite instability (MSI), have revolutionized therapeutic decisions, but emerging evidence underlines the importance of integrating multi-omics sciences for a deeper understanding of tumor biology and therapeutic resistance. Although these omics technologies hold great promise for the advancement of precision oncology, significant challenges remain. However, the integration of multi-omics data is opening the way to more accurate diagnostics, personalized therapies, and improved outcomes for mCRC patients. This review provides an in-depth description of the various omics sciences and explores their advantages and critical issues. Full article

Mucin, a heavily glycosylated glycoprotein, serves an important function in forming protective and immune defense barriers against the exterior environment on epithelial surfaces. While secreted-type mucins are involved in mucous production, transmembrane mucins, which contain O-glycosylated tandem repeats, play a pivotal role in cellular signaling, especially in immune modulation and mediating inflammatory response. However, dysregulation in mucin expressions, such as MUC1, MUC2, MUC4, MUC5AC, and MUC16, have been observed in many cancer cells. More specifically, alterations in the expression and glycosylation of MUC1 have been associated with the upregulation of pathways involving the cell proliferation, angiogenesis, migration, and invasion of cancer cells. With mucin’s extensive involvement in cancer biology, several mucin biomarkers, such as CA125, CA19-9, and CEA, have been utilized as diagnostic and prognostic monitoring biomarkers in ovarian, pancreatic, and colon cancer. Vaccines and antibody therapy against abnormal mucin glycosylation have also been investigated for potential therapy for mucin-related cancers that are resistant to traditional chemotherapy agents. Despite the lack of specificity in mucin biomarkers and challenges in efficient drug delivery systems, the current advancement in mucin-targeted immunotherapy highlighted the pivotal potential in developing therapeutic targets to improve cancer prognosis. Full article

The female genital microbiota plays a critical role in reproductive health and has recently emerged as a key factor influencing the outcomes of Assisted Reproductive Techniques (ARTs). Beyond traditional concerns about vaginal dysbiosis and infections such as bacterial vaginosis or mycoses, recent evidence highlights the broader impact of genital microbial communities, including the vaginal, cervical, and endometrial niches, on ART success rates. New findings suggest that specific bacterial profiles, as well as shifts in the virome and mycobiome, can significantly affect implantation and pregnancy outcomes. Non-invasive biomarkers such as menstrual blood have also been proposed for assessing endometrial receptivity. Furthermore, growing attention has been directed towards methodological challenges such as contamination risks during microbiota sampling which may influence study reliability. This review synthesizes the latest data on the relationship between the female genital microbiota and ART outcomes, with a focus on standardized microbiological analysis techniques and specific patient populations such as those experiencing recurrent implantation to optimize ART success based on microbiota profiling. Full article

Background: Copper dyshomeostasis has been implicated in a subset of Alzheimer’s disease (AD) patients, characterized by elevated non-ceruloplasmin-bound copper (non-Cp Cu). However, traditional methods for estimating non-Cp Cu are indirect and analytically imprecise. This study introduces and validates a direct assay for exchangeable copper (ExcCu) by inductively coupled plasma-mass spectrometry (ICP-MS), compliant with Clinical and Laboratory Standards Institute (CLSI) guidelines. Methods: We performed analytical validation of the ExcCu assay following CLSI protocols (EP5, EP6, EP7, EP9, EP15, and EP28). ExcCu and other copper-related biomarkers were quantified in serum samples from 154 healthy controls, 82 AD patients, and 10 patients with Wilson disease (WD). Diagnostic performance was evaluated via receiver operating characteristic (ROC) curve analysis, and inter-method agreement was assessed using Bland–Altman plots. Results: The ExcCu assay demonstrated excellent linearity, precision (CV < 6%), and inter-laboratory reproducibility. Among AD patients, ExcCu levels were significantly elevated compared to controls (p < 0.001). ExcCu distinguished AD from controls with an AUC of 0.80 and a specificity of 95%. Compared to non-Cp Cu, ExcCu yielded no negative values and showed reduced bias. The relative exchangeable copper (REC) index was more effective in differentiating AD from WD (AUC = 0.88). Conclusions: The validated ExcCu assay overcomes the limitations of the traditional non-Cp Cu calculation, offering a reliable biomarker for copper-related AD subtypes. Its high specificity supports its use in patient stratification, potentially contributing to personalized approaches in AD diagnosis and therapy. Full article

Background: Mild traumatic brain injury (mTBI), commonly known as concussion, is a major public health issue characterized by subtle neuronal damage that traditional imaging techniques such as computed tomography (CT) and magnetic resonance imaging (MRI) often fail to detect. Fluid biomarkers have emerged as promising diagnostic and prognostic tools for mTBI. Objectives: This umbrella meta-analysis aims to evaluate the diagnostic accuracy and clinical utility of the key fluid biomarkers, S100B, glial fibrillary acidic protein (GFAP), ubiquitin carboxy-terminal hydrolase L1 (UCH-L1, neurofilament light chain (NfL)) and tau protein, in detecting mTBI and to clarify their roles as screening, confirmatory, and complementary indicators. Methods: A systematic review was performed using PubMed, Web of Science, Scopus, and Cochrane to identify the published meta-analyses that assessed the biomarkers in mTBI. Sensitivity, specificity, and diagnostic odds ratios were then calculated using random-effects models. Heterogeneity was evaluated with the I² statistic, and publication bias was assessed via funnel plots. The results of S100B demonstrated high sensitivity (91.6%) but low specificity (42.4%), making it an effective rule-out biomarker to minimize unnecessary CT scans. In contrast, GFAP exhibited moderate sensitivity (84.5%) with improved specificity (61.0%), supporting its role in confirming mTBI diagnoses. UCH-L1 revealed a sensitivity of 86.7% alongside low specificity (37.3%), indicating its potential as a complementary marker. Additionally, the NfL levels were notably elevated in sports-related concussions, while the diagnostic utility of tau protein remains inconclusive due to limited available data. Conclusions: The findings underscore the clinical promise of fluid biomarkers in the management of mTBI. S100B and GFAP are particularly valuable as screening and confirmatory markers, respectively. Nonetheless, further standardization of biomarker thresholds and additional longitudinal studies are necessary to validate the roles of UCH-L1, NfL, and Tau protein. The integration of these biomarkers into a multimodal diagnostic panel may enhance mTBI detection accuracy and facilitate improved patient stratification and management. Full article