Search Results (912)

Background: Plant-based protein supplementation in supporting muscle recovery following resistance exercise remains an area of growing interest, particularly among vegan athletes, as a potential alternative to animal-based proteins. This systematic review aimed to evaluate the effectiveness of plant-based proteins on recovery from resistance exercise-induced muscle damage in healthy young adults. Methods: A systematic and comprehensive search was administered in eight databases up to 1 May 2025, identifying 1407 articles. Following deduplication and screening, 24 studies met the eligibility criteria, including 22 randomized controlled trials and 2 non-randomized studies, with the majority from high income western countries. Results: Interventions primarily involved soy, pea, rice, hemp, potato, and blended plant protein sources, with doses ranging from 15 to 50 g, typically administered post resistance exercise. Outcomes assessed included muscle protein synthesis (MPS), delayed-onset muscle soreness (DOMS), inflammatory biomarkers, muscle function, and fatigue. The review findings reaffirm that single-source plant proteins generally offer limited benefits compared to animal proteins such as whey, particularly in acute recovery settings, a limitation well-documented consistently in the literature. However, our synthesis highlights that well-formulated plant protein blends (e.g., combinations of pea, rice, and canola) can stimulate MPS at levels comparable to whey when consumed at adequate doses (≥30 g with ~2.5 g leucine). Some studies also reported improvements in subjective recovery outcomes and reductions in muscle damage biomarkers with soy or pea protein. However, overall evidence remains limited by small sample sizes, moderate to high risk of bias, and heterogeneity in intervention protocols, protein formulations, and outcome measures. Risk of bias assessments revealed concerns related to detection and reporting bias in nearly half the studies. Due to clinical and methodological variability, a meta-analysis was not conducted. Conclusion: plant-based proteins particularly in the form of protein blends and when dosed appropriately, may support muscle recovery in resistance-trained individuals and offer a viable alternative to animal-based proteins. However, further high-quality, long-term trials in vegan populations are needed to establish definitive recommendations for plant protein use in sports nutrition. Full article

Circadian rhythms are intrinsic 24 h cycles that regulate metabolic processes across multiple tissues, with skeletal muscle emerging as a central node in this temporal network. Muscle clocks govern gene expression, fuel utilisation, mitochondrial function, and insulin sensitivity, thereby maintaining systemic energy homeostasis. However, circadian misalignment, whether due to behavioural disruption, nutrient excess, or metabolic disease, impairs these rhythms and contributes to insulin resistance, and the development of obesity, and type 2 diabetes mellitus. Notably, the muscle clock remains responsive to non-photic cues, particularly exercise, which can reset and amplify circadian rhythms even in metabolically impaired states. This work synthesises multi-level evidence from rodent models, human trials, and in vitro studies to elucidate the role of skeletal muscle clocks in circadian metabolic health. It explores how exercise entrains the muscle clock via molecular pathways involving AMPK, SIRT1, and PGC-1α, and highlights the time-of-day dependency of these effects. Emerging data demonstrate that optimally timed exercise enhances glucose uptake, mitochondrial biogenesis, and circadian gene expression more effectively than time-agnostic training, especially in individuals with metabolic dysfunction. Finally, findings are integrated from multi-omic approaches that have uncovered dynamic, time-dependent molecular signatures that underpin circadian regulation and its disruption in obesity. These technologies are uncovering biomarkers and signalling nodes that may inform personalised, temporally targeted interventions. By combining mechanistic insights with translational implications, this review positions skeletal muscle clocks as both regulators and therapeutic targets in metabolic disease. It offers a conceptual framework for chrono-exercise strategies and highlights the promise of multi-omics in developing precision chrono-medicine approaches aimed at restoring circadian alignment and improving metabolic health outcomes. Full article

Background/Objectives: Chronological age (CA) is commonly used in clinical decision-making, yet it may not accurately reflect biological aging. Recent advances in artificial intelligence (AI) allow estimation of electrocardiogram (ECG)-derived heart age, which may serve as a non-invasive biomarker for physiological aging. This study aimed to develop and validate a deep learning model to predict ECG-heart age in individuals with no structural heart disease. Methods: We trained a convolutional neural network (DenseNet-121) using 12-lead ECGs from 292,484 individuals (mean age: 51.4 ± 13.8 years; 42.3% male) without significant cardiac disease. Exclusion criteria included missing age data, age <18 or >90 years, and structural abnormalities. CA was used as the target variable. Model performance was evaluated using the coefficient of determination (R²), Pearson correlation coefficient (PCC), mean absolute error (MAE), and root mean square error (RMSE). External validation was conducted using 1191 independent ECGs. Results: The model demonstrated strong predictive performance (R² = 0.783, PCC = 0.885, MAE = 5.023 years, RMSE = 6.389 years). ECG-heart age tended to be overestimated in younger adults (≤30 years) and underestimated in older adults (≥70 years). External validation showed consistent performance (R² = 0.703, PCC = 0.846, MAE = 5.582 years, RMSE = 7.316 years). Conclusions: The proposed AI-based model accurately estimates ECG-heart age in individuals with structurally normal hearts. ECG-derived heart age may serve as a reliable biomarker of biological aging and support future risk stratification strategies. Full article

Paper-based colorimetric biosensors represent a promising class of low-cost diagnostic tools that do not require external instrumentation. However, their broader applicability is limited by the environmental concerns associated with conventional metal-based nanomaterials and the subjectivity of visual interpretation. To address these challenges, this study introduces a proof-of-concept platform—using CA19-9 as a model biomarker—that integrates naturally derived melanin nanoparticles (MNPs) with machine learning-based image analysis to enable environmentally sustainable and analytically robust colorimetric quantification. Upon target binding, MNPs induce a concentration-dependent color transition from yellow to brown. This visual signal was quantified using a machine learning pipeline incorporating automated region segmentation and regression modeling. Sensor areas were segmented using three different algorithms, with the U-Net model achieving the highest accuracy (average IoU: 0.9025 ± 0.0392). Features extracted from segmented regions were used to train seven regression models, among which XGBoost performed best, yielding a Mean Absolute Percentage Error (MAPE) of 17%. Although reduced sensitivity was observed at higher analyte concentrations due to sensor saturation, the model showed strong predictive accuracy at lower concentrations, which are especially challenging for visual interpretation. This approach enables accurate, reproducible, and objective quantification of colorimetric signals, thereby offering a sustainable and scalable alternative for point-of-care diagnostic applications. Full article

Background: RiBi is integral to cell proliferation, and its dysregulation is increasingly recognized as a hallmark of aggressive cancers. We sought to develop and validate a composite “PanRibo-515 score” reflecting RiBi activity across multiple tumor types, assess its prognostic significance, and explore its relationship with immune checkpoint therapy outcomes. Methods: We curated 515 RiBi–associated genes (PanRibo-515) and used a LASSO regression-based strategy on a training dataset (GSE202203) to select the prognostically most relevant subset of 68 genes (OncoRibo-68). Directionality (positive or negative impact on survival) was assigned based on the sign of the LASSO coefficients. We integrated a forward selection approach to identify a refined subset of genes for computing the OncoRibo-68 score. For validation, patients in The Cancer Genome Atlas (TCGA) were stratified into high or low OncoRibo-68 score groups for survival analyses. Additional validation for immunotherapy response was conducted using bioinformatic platforms used for immunotherapy response analysis. Results: A higher OncoRibo-68 score consistently correlated with poorer overall and progression-free survival across multiple cancers. Elevated OncoRibo-68 score was linked to an immunosuppressive tumor microenvironment, but interestingly to increased response to checkpoint inhibitors. Conclusions: Our findings highlight RiBi as an important determinant of tumor aggressiveness and identify the OncoRibo-68 score as a promising biomarker for risk stratification and therapy selection. Future research may evaluate whether targeting RiBi pathways could enhance treatment efficacy, particularly in combination with immunotherapy. Full article

Ulcerative colitis (UC) is a chronic inflammatory bowel disease associated with disrupted lipid metabolism. This study aimed to uncover novel molecular subtypes and biomarkers by integrating sphingolipid metabolism-related genes (SMGs) with machine learning approaches. Using data from the GEO and GeneCards databases, 29 UC-related SMGs were identified. Consensus clustering was employed to define distinct molecular subtypes of UC, and a diagnostic model was developed through various machine learning algorithms. Further analyses—including functional enrichment, transcription factor prediction, single-cell localization, potential drug screening, molecular docking, and molecular dynamics simulations—were conducted to investigate the underlying mechanisms and therapeutic prospects of the identified genes in UC. The analysis revealed two molecular subtypes of UC: C1 (metabolically dysregulated) and C2 (immune-enriched). A diagnostic model based on three key genes demonstrated high accuracy in both the training and validation cohorts. Moreover, the transcription factor FOXA2 was predicted to regulate the expression of all three genes simultaneously. Notably, mebendazole and NVP-TAE226 emerged as promising therapeutic agents for UC. In conclusion, SMGs are integral to UC molecular subtyping and immune microenvironment modulation, presenting a novel framework for precision diagnosis and targeted treatment of UC. Full article

Posterior capsule opacification (PCO), a frequent complication of cataract surgery, arises from dysregulated wound healing and fibrotic transformation of residual lens epithelial cells. While transcriptomic and machine learning (ML) approaches have elucidated fibrosis-related pathways in other tissues, the molecular divergence between regenerative and fibrotic outcomes in the lens remains unclear. Here, we used an ex vivo chick lens injury model to simulate post-surgical conditions, collecting RNA from lenses undergoing either regenerative wound healing or fibrosis between days 1–3 post-injury. Bulk RNA sequencing data were normalized, log-transformed, and subjected to univariate filtering prior to training LASSO, SVM, and RF ML models to identify discriminatory gene signatures. Each model was independently validated using a held-out test set. Distinct gene sets were identified, including fibrosis-associated genes (VGLL3, CEBPD, MXRA7, LMNA, gga-miR-143, RF00072) and wound-healing-associated genes (HS3ST2, ID1), with several achieving perfect classification. Gene Set Enrichment Analysis revealed divergent pathway activation, including extracellular matrix remodeling, DNA replication, and spliceosome associated with fibrosis. RT-PCR in independent explants confirmed key differential expression levels. These findings demonstrate the utility of supervised ML for discovering lens-specific fibrotic and regenerative gene features and nominate biomarkers for targeted intervention to mitigate PCO. Full article

Purpose: Predicting colorectal cancer liver metastasis (CRLM) is essential for prognostic assessment. This study aims to develop and validate an interpretable multimodal machine learning framework based on multiparametric MRI for predicting CRLM, and to enhance the clinical interpretability of the model through SHapley Additive exPlanations (SHAP) analysis and deep learning visualization. Methods: This multicenter retrospective study included 463 patients with pathologically confirmed colorectal cancer from two institutions, divided into training (n = 256), internal testing (n = 111), and external validation (n = 96) sets. Radiomics features were extracted from manually segmented regions on axial T2-weighted imaging (T2WI) and diffusion-weighted imaging (DWI). Deep learning features were obtained from a pretrained ResNet101 network using the same MRI inputs. A least absolute shrinkage and selection operator (LASSO) logistic regression classifier was developed for clinical, radiomics, deep learning, and combined models. Model performance was evaluated by AUC, sensitivity, specificity, and F1-score. SHAP was used to assess feature contributions, and Grad-CAM was applied to visualize deep feature attention. Results: The combined model integrating features across the three modalities achieved the highest performance across all datasets, with AUCs of 0.889 (training), 0.838 (internal test), and 0.822 (external validation), outperforming single-modality models. Decision curve analysis (DCA) revealed enhanced clinical net benefit from the integrated model, while calibration curves confirmed its good predictive consistency. SHAP analysis revealed that radiomic features related to T2WI texture (e.g., LargeDependenceLowGrayLevelEmphasis) and clinical biomarkers (e.g., CA19-9) were among the most predictive for CRLM. Grad-CAM visualizations confirmed that the deep learning model focused on tumor regions consistent with radiological interpretation. Conclusions: This study presents a robust and interpretable multiparametric MRI-based model for noninvasively predicting liver metastasis in colorectal cancer patients. By integrating handcrafted radiomics and deep learning features, and enhancing transparency through SHAP and Grad-CAM, the model provides both high predictive performance and clinically meaningful explanations. These findings highlight its potential value as a decision-support tool for individualized risk assessment and treatment planning in the management of colorectal cancer. Full article

Background: Swimming coaches search for the most efficient training approach and stimuli for swimmers’ improvement. High-intensity interval training (HIIT) is a well-established training approach used by coaches to accelerate swimmers’ improvement. A HIIT variation, which has lately been discussed by many coaches about its possible effectiveness on performance, is Ultra Short Race Pace Training (USRPT). The present case study aimed to examine the effect of a faster-than-race pace test set (FRPtS) on the performance of a middle-distance (MD) swimmer at the freestyle events. Methods: This case study included a 21-year-old national-level MD swimmer with 16 years of swimming experience. The swimmer followed 11 weeks of FRPtS sets in a 17-week training intervention. The FRPtS sets were repeated two to three times per week, the volume ranged from 200 m to 1200 m, and the distances that were used were 25 m, 50 m, and 100 m at a faster pace than the 400 m. Descriptive statistics were implemented, recording the average with standard deviation (number in parentheses), the sum, and the percentages (%). Results: According to the results, the swimmer improved his personal best (PB) and season best (SB) performance in the events of 200 m and 400 m freestyle. Specifically, the improvement from his PB performance was 2.9% (−3.49 s) and 1.0% (−2.55 s), whereas in his SB performance it was 2.9% (−3.53 s) and 4.4% (−11.43 s) for the 200 and 400 m freestyle, respectively. Conclusions: Concluding, FRPtS is assumed to have beneficial effects on the swimming performance of MD events. However, further crossover or parallel studies on different swimming events with more participants and biomarkers must be conducted to clarify the effects of that kind of training on swimming performance. Full article

Background: Mild Cognitive Impairment (MCI) represents an intermediate stage between normal cognitive aging and Alzheimer’s Disease (AD). Early and accurate identification of MCI is crucial for implementing interventions that may delay or prevent further cognitive decline. This study aims to develop a machine learning-based model for differentiating between Cognitively Normal (CN) individuals and MCI patients using data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). Methods: An ensemble classification approach was designed by integrating Extra Trees, Random Forest, and Light Gradient Boosting Machine (LightGBM) algorithms. Feature selection emphasized clinically relevant biomarkers, including Amyloid-β 42, phosphorylated tau, diastolic blood pressure, age, and gender. The dataset was split into training and held-out test sets. A probability thresholding strategy was employed to flag uncertain predictions for potential deferral, enhancing model reliability in borderline cases. Results: The final ensemble model achieved an accuracy of 83.2%, a recall of 80.2%, and a precision of 86.3% on the independent test set. The probability thresholding mechanism flagged 23.3% of cases as uncertain, allowing the system to abstain from low-confidence predictions. This strategy improved clinical interpretability and minimized the risk of misclassification in ambiguous cases. Conclusions: The proposed AI-driven ensemble model demonstrates strong performance in classifying MCI versus CN individuals using multimodal ADNI data. Incorporating a deferral mechanism through uncertainty estimation further enhances the model’s clinical utility. These findings support the integration of machine learning tools into early screening workflows for cognitive impairment. Full article

Machine learning algorithms are commonly employed for classification and interpretation of high-dimensional data. The classification task is often broken down into two separate procedures, and different methods are applied to achieve accurate results and produce interpretable outcomes. First, an effective subset of high-dimensional features must be extracted and then the selected subset will be used to train a classifier. Gradient Boosted Trees (GBT) is an ensemble model and, particularly due to their robustness, ability to model complex nonlinear interactions, and feature interpretability, they are well suited for complex applications. XGBoost (eXtreme Gradient Boosting) is a high-performance implementation of GBT that incorporates regularization, parallel computation, and efficient tree pruning that makes it a suitable efficient, interpretable, and scalable classifier with potential applications to medical data analysis. In this study, a Monte Carlo Gradient Boosted Trees (MCGBT) model is proposed for both feature reduction and classification. The proposed MCGBT method was applied to a lung cancer dataset for feature identification and classification. The dataset contains 107 radiomics which are quantitative imaging biomarkers extracted from CT scans. A reduced set of 12 radiomics were identified, and patients were classified into different cancer stages. Cancer staging accuracy of 90.3% across 100 independent runs was achieved which was on par with that obtained using the full set of 107 radiomics, enabling lean and deployable classifiers. Full article

Background/Objectives: Peripheral artery disease (PAD) impacts more than 200 million individuals globally and leads to mortality and morbidity secondary to progressive limb dysfunction and amputation. However, clinical management of PAD remains suboptimal, in part because of the lack of standardized biomarkers to predict patient outcomes. Growth differentiation factor 15 (GDF15) is a stress-responsive cytokine that has been studied extensively in cardiovascular disease, but its investigation in PAD remains limited. This study aimed to use explainable statistical and machine learning methods to assess the prognostic value of GDF15 for limb outcomes in patients with PAD. Methods: This prognostic investigation was carried out using a prospectively enrolled cohort comprising 454 patients diagnosed with PAD. At baseline, plasma GDF15 levels were measured using a validated multiplex immunoassay. Participants were monitored over a two-year period to assess the occurrence of major adverse limb events (MALE), a composite outcome encompassing major lower extremity amputation, need for open/endovascular revascularization, or acute limb ischemia. An Extreme Gradient Boosting (XGBoost) model was trained to predict 2-year MALE using 10-fold cross-validation, incorporating GDF15 levels along with baseline variables. Model performance was primarily evaluated using the area under the receiver operating characteristic curve (AUROC). Secondary model evaluation metrics were accuracy, sensitivity, specificity, negative predictive value (NPV), and positive predictive value (PPV). Prediction histogram plots were generated to assess the ability of the model to discriminate between patients who develop vs. do not develop 2-year MALE. For model interpretability, SHapley Additive exPlanations (SHAP) analysis was performed to evaluate the relative contribution of each predictor to model outputs. Results: The mean age of the cohort was 71 (SD 10) years, with 31% (n = 139) being female. Over the two-year follow-up period, 157 patients (34.6%) experienced MALE. The XGBoost model incorporating plasma GDF15 levels and demographic/clinical features achieved excellent performance for predicting 2-year MALE in PAD patients: AUROC 0.84, accuracy 83.5%, sensitivity 83.6%, specificity 83.7%, PPV 87.3%, and NPV 86.2%. The prediction probability histogram for the XGBoost model demonstrated clear separation for patients who developed vs. did not develop 2-year MALE, indicating strong discrimination ability. SHAP analysis showed that GDF15 was the strongest predictive feature for 2-year MALE, followed by age, smoking status, and other cardiovascular comorbidities, highlighting its clinical relevance. Conclusions: Using explainable statistical and machine learning methods, we demonstrated that plasma GDF15 levels have important prognostic value for 2-year MALE in patients with PAD. By integrating clinical variables with GDF15 levels, our machine learning model can support early identification of PAD patients at elevated risk for adverse limb events, facilitating timely referral to vascular specialists and aiding in decisions regarding the aggressiveness of medical/surgical treatment. This precision medicine approach based on a biomarker-guided prognostication algorithm offers a promising strategy for improving limb outcomes in individuals with PAD. Full article

Respiratory diseases represent a persistent global health challenge, underscoring the need for intelligent, accurate, and personalized diagnostic and therapeutic systems. Existing methods frequently suffer from limitations in diagnostic precision, lack of individualized treatment, and constrained adaptability to complex clinical scenarios. To address these challenges, our study introduces a modular AI-powered framework that integrates an audio-based disease classification model with simulated molecular biomarker profiles to evaluate the feasibility of future multimodal diagnostic extensions, alongside a synthetic-data-driven prescription recommendation engine. The disease classification model analyzes respiratory sound recordings and accurately distinguishes among eight clinical classes: bronchiectasis, pneumonia, upper respiratory tract infection (URTI), lower respiratory tract infection (LRTI), asthma, chronic obstructive pulmonary disease (COPD), bronchiolitis, and healthy respiratory state. The proposed model achieved a classification accuracy of 99.99% on a holdout test set, including 94.2% accuracy on pediatric samples. In parallel, the prescription module provides individualized treatment recommendations comprising drug, dosage, and frequency trained on a carefully constructed synthetic dataset designed to emulate real-world prescribing logic.The model achieved over 99% accuracy in medication prediction tasks, outperforming baseline models such as those discussed in research. Minimal misclassification in the confusion matrix and strong clinician agreement on 200 prescriptions (Cohen’s $\kappa$ = 0.91 [0.87–0.94] for drug selection, 0.78 [0.74–0.81] for dosage, 0.96 [0.93–0.98] for frequency) further affirm the system’s reliability. Adjusted clinician disagreement rates were 2.7% (drug), 6.4% (dosage), and 1.5% (frequency). SHAP analysis identified age and smoking as key predictors, enhancing model explainability. Dosage accuracy was 91.3%, and most disagreements occurred in renal-impaired and pediatric cases. However, our study is presented strictly as a proof-of-concept. The use of synthetic data and the absence of access to real patient records constitute key limitations. A trialed clinical deployment was conducted under a controlled environment with a positive rate of satisfaction from experts and users, but the proposed system must undergo extensive validation with de-identified electronic medical records (EMRs) and regulatory scrutiny before it can be considered for practical application. Nonetheless, the findings offer a promising foundation for the future development of clinically viable AI-assisted respiratory care tools. Full article

Background: Pathological complete response (pCR) serves as a prognostic surrogate endpoint for long-term clinical outcomes in breast cancer patients receiving neoadjuvant systemic therapy (NAST). This study aims to develop and evaluate machine learning-based biomarkers for predicting pCR and recurrence-free survival (RFS). Methods: This retrospective monocentric study included 235 women (mean age 46 ± 11 years) with non-metastatic breast cancer treated with NAST. We developed various machine learning models using clinical features (age, genetic mutations, TNM stage, hormonal receptor expression, HER2 status, and histological grade), along with morphological features (size, T2 signal, and surrounding edema) and radiomics data extracted from pre-treatment MRI. Patients were divided into training and test groups with different MRI models. A customized machine learning pipeline was implemented to handle these diverse data types, consisting of feature selection and classification components. Results: The models demonstrated superior prediction ability using radiomics features, with the best model achieving an AUC of 0.72. Subgroup analysis revealed optimal performance in triple-negative breast cancer (AUC of 0.80) and HER2-positive subgroups (AUC of 0.65). Conclusion: Machine learning models incorporating clinical, qualitative, and radiomics data from pre-treatment MRI can effectively predict pCR in breast cancer patients receiving NAST, particularly among triple-negative and HER2-positive breast cancer subgroups. Full article

Background and Objectives: Despite significant advances in surgical techniques and perioperative care, major adverse cardiovascular events (MACE) remain a leading cause of postoperative morbidity and mortality in patients undergoing coronary artery bypass grafting and/or aortic valve replacement. Accurate preoperative risk stratification is essential yet often limited by models that overlook atrial mechanics and underutilized biomarkers. Materials and Methods: This study aimed to develop an interpretable machine learning model for predicting perioperative MACE by integrating clinical, biochemical, and echocardiographic features, with a particular focus on novel physiological markers. A retrospective cohort of 131 patients was analyzed. An Extreme Gradient Boosting (XGBoost) classifier was trained on a comprehensive feature set, and SHapley Additive exPlanations (SHAPs) were used to quantify each variable’s contribution to model predictions. Results: In a stratified 80:20 train–test split, the model initially achieved an AUC of 1.00. Acknowledging the potential for overfitting in small datasets, additional validation was performed using 10 independent random splits and 5-fold cross-validation. These analyses yielded an average AUC of 0.846 ± 0.092 and an F1-score of 0.807 ± 0.096, supporting the model’s stability and generalizability. The most influential predictors included total atrial conduction time, mitral and tricuspid annular orifice areas, and high-density lipoprotein (HDL) cholesterol. These variables, spanning electrophysiological, structural, and metabolic domains, significantly enhanced discriminative performance, even in patients with preserved left ventricular function. The model’s transparency provides clinically intuitive insights into individual risk profiles, emphasizing the significance of non-traditional parameters in perioperative assessments. Conclusions: This study demonstrates the feasibility and potential clinical value of combining advanced echocardiographic, biochemical, and machine learning tools for individualized cardiovascular risk prediction. While promising, these findings require prospective validation in larger, multicenter cohorts before being integrated into routine clinical decision-making. Full article