Fatma Hilal Yagin

Molecular subtypes from multi-omic profiling have refined the biological characterization of clear cell renal cell carcinoma (ccRCC), but whether they add prognostic information to clinicopathological variables already in use is unclear. We evaluated the incremental prognostic value of proteomically assigned CPTAC consensus subtypes (NMF1–NMF3) against stage and grade, and asked whether subtype identity is carried by a biologically specific set of proteins. Subtypes were predicted from tumor proteomes in 211 patients under nested cross-validation and a locked hold-out design, and the analysis was repeated using methylation subtypes defined without proteomic input. A transcriptome classifier was transferred to 533 TCGA-KIRC tumors, and the transferred subtypes entered nested Cox models containing age, stage and Fuhrman grade. A curated set of 139 metabolic enzymes was compared against 500 random protein sets of the same size and against random sets additionally matched on abundance, missingness, variance and co-regulation. Classification reached a macro-average AUROC of 0.901 (95% CI 0.871–0.933) under cross-validation and 0.862 in the untouched expansion cohort; methylation subtypes were classified with comparable accuracy (0.905). Subtype proportions in TCGA-KIRC differed from CPTAC by at most 2.5 percentage points. Among 518 patients with complete clinical data, grade improved a model containing age and stage (p = 0.001), whereas subtype added nothing once grade was included (p = 0.703; change in C-index +0.0019, 95% CI −0.0023 to +0.0116); with 171 deaths, the study could detect a hazard ratio of 1.64 at 80% power, so small effects remain possible. The metabolic panel did not outperform size-matched (p = 0.649) or covariate-matched random sets (p = 0.762), whereas a housekeeping set performed significantly worse. CPTAC consensus subtype identity is highly predictable from the proteome but redundantly encoded rather than concentrated in a functional class, and adds no measurable prognostic information beyond stage and grade in this cohort. High classification accuracy for a molecular label is not evidence of clinical utility; these conclusions apply to the CPTAC NMF scheme as evaluated here and should not be extended to proteomic subtyping in general.

Background: Erythrocyte proteins released into plasma carry oxidation-related annotations and can be read as evidence of oxidative stress. We examined whether this applies to an oxidative-stress enrichment reported in a plasma proteomic study of obstructive sleep apnoea (OSA). Methods: In a secondary analysis of public data (PXD073409; men; 15 non-OSA, 15 mild OSA, 15 severe OSA; 422 proteins), erythrocyte, platelet and coagulation quality marker indices were computed from the panels of Geyer et al.; the erythrocyte panel was only partly quantified (15 of 29 entries). The original differential and over-representation analyses were repeated with panel members excluded, with adjustment for the erythrocyte index, and with leave-one-protein-out indices. A second public dataset (PXD069503; 15 severe OSA, 15 mild-to-moderate OSA, 15 controls) was used for directional comparison. Clinical covariates were not available. Results: The erythrocyte index was higher in mild (ratio of geometric means 1.74, 95% CI 1.04 to 2.80) and severe OSA (2.43, 1.68 to 3.47) than in non-OSA participants. Six of the 13 proteins that are increased in severe OSA were erythrocyte panel members, and all nine enriched terms consisted of panel members only, including hydrogen peroxide catabolic process (HBA1, HBB, HBD, PRDX2). After adjustment, PRDX2 was accounted for by erythrocyte content, whereas the haemoglobin chains remained elevated and carried seven of the terms. The index alone separated severe- from non-OSA participants (AUROC 0.858); the data could not show whether all 422 proteins (AUROC 0.969) add to it (difference +0.111, 95% CI −0.009 to +0.268). In the second dataset the index was higher in severe OSA than in controls (1.55, 1.06 to 2.35). Conclusions: The reported oxidative-stress enrichment rests on erythrocyte-associated proteins and, on these data, is not evidence of altered oxidative activity in plasma. Whether this content arises before or after venepuncture cannot be determined. Quality marker indices should be reported alongside plasma proteomic biomarker results.

Background/Objectives: Cutaneous melanoma caused over 331,000 new cases and 58,000 deaths worldwide in 2022, with five-year survival falling from 99.4% in localised disease to 35.6% after distant metastasis. Most dermoscopic deep learning studies report headline accuracy without addressing data leakage, calibration, or how their comparisons are constructed. This study asks how much of that performance survives a protocol designed to remove the optimism. Materials and Methods: Six classification architectures were trained on HAM10000/ISIC 2018 (10,015 images, seven classes) at a fixed resolution and with fixed ImageNet-1k pretraining, the architecture confounding with neither. Five segmentation networks were trained alongside MedSAM and evaluated separately under reference-derived and fully automatic box prompts. Lesion-level StratifiedGroupKFold prevented duplicate-lesion leakage; temperature scaling used an inner-validation partition, never the test fold. Models were compared across outer folds (N = 5), saliency localisation against a fixed centred-disc baseline, and generalisation on BCN20000 (15,172 images). Results: The six configurations were statistically indistinguishable (Friedman χ² = 7.057, p = 0.216; balanced accuracy 0.664–0.700), so no best architecture could be identified. MedSAM ranked first with reference-derived prompts (Dice 0.9547) and last with automatic prompts (0.7729), 16.7 points below a plain U-Net, its advantage reflecting prompt provenance rather than the model. All three class activation methods scored below the fixed disc on mask-IoU (0.2531–0.3512 against 0.4745). Externally, balanced accuracy fell 25 points and the ranking reversed, while AUC held at 0.80–0.84; recalibration helped only two of six models. Conclusions: Under a protocol that isolates each compared factor, the differences that such studies report do not survive. Cross-cohort loss is large and not reliably repaired by recalibration; the leverage lies in evaluation methodology, not architectural novelty.

Background/Objectives: The period between 12 and 16 years of age coincides with peak pubertal change, declining habitual physical activity, and the consolidation of lifelong behavioral patterns, making it a critical window for understanding how fitness develops and how stable (or unstable) it is over time. This review aims to synthesize longitudinal evidence addressing how HRPF changes and tracks in adolescents aged approximately 12 to 16 years, the sex- and maturation-related modifiers of these patterns, the methodological approaches used to assess them, and the secular and behavioral context within which they occur. Methods: A structured narrative review was conducted searching four electronic databases—Google Scholar, PubMed, Web of Science, and Scopus—using terms combining concepts of adolescence, health-related physical fitness, and longitudinal study design published up to April 2026. Reference lists of retrieved systematic reviews and meta-analyses were snowball-searched. Eligible studies employed longitudinal or repeated-measures designs in samples overlapping the 12–16-year age range; no formal risk-of-bias appraisal or quantitative pooling was undertaken, consistent with the narrative-review design. Findings were synthesized narratively by HRPF component and thematic domain. Results: Cardiorespiratory fitness rises through early adolescence before plateauing or declining from approximately age 15 in one longitudinal cohort, more markedly in boys; muscular power and strength diverge increasingly by sex, a pattern consistent with androgen-mediated gains in lean mass in boys, although this mechanism was not directly tested here; flexibility remains the most stable component; and body composition acts as both an outcome and a determinant of other fitness test performance. Within-adolescence tracking is moderate-to-high for most components in the single available 3-year cohort of adolescent girls that reported component-specific tracking coefficients (e.g., lower-limb power β = 0.98, aerobic endurance β = 0.75, trunk muscular endurance β = 0.51), and substantially stronger than tracking from childhood into adolescence. Secular trends indicate population-level fitness has declined in many countries over recent decades, with adolescents showing greater decline than children. Conclusions: Early-to-mid adolescence appears to be a critical and time-limited opportunity to consider for fitness-promoting intervention: fitness rank is still somewhat malleable, but shows progressively stronger tracking with age—a pattern of rank stability that should not itself be read as evidence about responsiveness to intervention. Methodological heterogeneity in test batteries, follow-up duration, and tracking statistics limits direct comparability across studies. Future research should incorporate maturity-status indicators, multi-wave designs, and harmonized assessment protocols.

Pancreatic ductal adenocarcinoma (PDAC) has two principal molecular subtypes—classical and basal-like—with divergent prognosis and chemotherapy response, yet transcriptomic classifiers rarely generalize across cohorts or quantify per-patient uncertainty. We trained a classical-versus-basal-like classifier on CPTAC-PDAC (n = 140) and externally validated it on histology-filtered TCGA-PAAD (n = 150). Twelve algorithms were benchmarked under stratified nested cross-validation with four-method consensus feature selection; domain adaptation (naive transfer, CORAL, and ComBat), four conformal procedures (split, weighted, CV+, and Conformal Risk Control), and a four-method consensus explainable-AI framework (SHAP, LIME, permutation importance, and decision-curve ablation) with pathway enrichment were then evaluated. Top models reached a cross-validated AUROC ≈ 0.96 and external AUROC 0.913–0.938 (top-3 ensemble 0.961); batch correction did not improve transfer, indicating minimal residual batch effect. Consensus explainability recovered keratinization biology and nominated five candidate genes (GSDMC, A2ML1, PIP5K1B, IL20RB, and AKR7L) beyond the Moffitt signature. All four conformal procedures plateaued near 0.85 coverage at α = 0.05 under zero-shot transfer, whereas local recalibration on a small target sample restored nominal coverage. We present a transparent, externally validated, uncertainty-aware and TRIPOD+AI-compliant PDAC subtype classifier, best deployed as a calibrated decision-support tool with site-specific recalibration.

Myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) is a debilitating multisystem illness characterised by post-exertional malaise, non-restorative sleep, and cognitive impairment, yet no objective diagnostic biomarkers have been established. Untargeted plasma metabolomics provides a broad view of the biochemical disturbances underlying ME/CFS; however, the high dimensionality of omics datasets and the limited interpretability of conventional classifiers nevertheless hinder translation into clinical practice. This study evaluates three ensemble classifiers—Explainable Boosting Machine (EBM), XGBoost, and LightGBM—for binary ME/CFS classification using plasma metabolomic and lipidomic profiles from 197 participants (106 ME/CFS; 91 healthy controls; 888 features). Feature dimensionality was reduced using a Pareto-Guided Recursive Neural Network (PRNN) pipeline. Model performance was assessed via 50-repeat stratified hold-out validation. EBM achieved the highest accuracy (0.909; 95% CI: 0.868–0.949) and area under the receiver operating characteristic curve (AUC: 0.940; 95% CI: 0.909–0.983), with XGBoost and LightGBM performing comparably. Interpretability analyses revealed that pairwise metabolite interaction terms—particularly proline & indole-3-lactate, tyrosine & N-acetylornithine, and maleic acid & arachidic acid—contributed the greatest discriminative signal. An ablation analysis comparing the full interaction-augmented EBM (AUC = 0.940) with a main-effects-only EBM (AUC = 0.882) confirmed that pairwise metabolite co-variation contributes additional discriminative value beyond individual metabolite levels, implicating amino acid catabolism, tryptophan–kynurenine pathway dysregulation, mitochondrial energy impairment, and lipid remodelling as central pathophysiological features. Global and instance-level explanations jointly demonstrated population-level metabolic signatures alongside individual heterogeneity, highlighting the added clinical value of explainable artificial intelligence (XAI) in metabolomics. These findings support EBM-based metabolomic profiling as an internally validated approach for ME/CFS classification, subject to external validation, calibration assessment, and prospective testing.

Colorectal cancer (CRC) remains one of the leading causes of cancer-related mortality worldwide, highlighting the critical need for non-invasive, accurate, and interpretable diagnostic tools. Metabolomic profiling of fecal microbial extracellular vesicles (EVs) offers a promising yet underexplored avenue for biomarker discovery when integrated with explainable machine learning (ML) frameworks. This study aimed to identify stool-derived microbial EV metabolite biomarkers that discriminate CRC patients from healthy controls and to develop interpretable ML classifiers for non-invasive CRC detection. Metabolomic profiles of fecal microbial EVs from 76 age- and sex-comparable participants (36 CRC, 40 controls) were obtained using LC/QTOFMS and GC/TOFMS. Three ML classifiers (TPOT, LightGBM, XGBoost) were trained and evaluated through 100-repeat stratified hold-out and nested 5-fold cross-validation, with SHAP and LIME applied for global and local interpretability. Fourteen metabolites were significantly dysregulated between the CRC and control groups (adjusted p < 0.05), with 13 upregulated and one (aminoisobutyric acid) downregulated. Furoic acid exhibited perfect diagnostic discrimination, followed by palmitic acid and tyramine. Nested cross-validation demonstrated robust performance: TPOT achieved AUC = 0.997 ± 0.005, sensitivity = 0.973 ± 0.022, and MCC = 0.957 ± 0.033. Hold-out validation corroborated these findings (AUC = 0.998 ± 0.008). SHAP analysis identified furoic acid, palmitic acid, and tyramine as the dominant predictive features, while aminoisobutyric acid exhibited a distinctive protective pattern. LIME analysis corroborated these findings at the individual prediction level. The identified fecal EV-derived metabolite panel—particularly furoic acid, palmitic acid, and tyramine—shows strong potential to predict CRC in a non-invasive, interpretable manner; however, given the modest sample size, these findings should be considered hypothesis-generating and require validation in larger, prospective, multi-center cohorts before clinical translation.

Background: Sepsis remains a leading cause of mortality in emergency and intensive care settings, with early diagnosis representing a critical determinant of patient outcomes. Despite advances in biomarker discovery, integrating platelet-derived metabolic signatures with explainable machine learning frameworks for sepsis prediction remains underexplored. The clinical adoption of predictive models has been hindered by the “black box” nature of conventional algorithms, limiting clinician trust and understanding. Objective: This study aimed to evaluate and validate an interpretable machine learning model utilizing platelet metabolomics data for accurate sepsis prediction while providing clinically meaningful explanations of the underlying metabolic disturbances that could inform therapeutic decision-making. Methods: We analyzed metabolomics data, comprising 25 sepsis patients diagnosed according to Sepsis-3 criteria and 14 age- and gender-matched non-sepsis from the emergency department. Platelet metabolite profiles were obtained via quantitative ¹H-NMR spectroscopy. Five machine learning algorithms were evaluated: Explainable Boosting Machine (EBM), Support Vector Machine (SVM), Logistic Regression (LR), Gradient Boosting Machine (GBM), and AdaBoost. Three biologically motivated metabolite ratios (adenosine triphosphate/adenosine diphosphate (ATP/ADP), ATP/adenosine monophosphate (AMP), Glutamine/Glutamate) were derived as additional features, yielding 22 candidate variables. Models were evaluated using a fully nested leave-one-out cross-validation (LOOCV) framework in which log transformation, KNN imputation, BorderlineSMOTE class balancing, and hyperparameter optimisation were performed exclusively within each training fold. Global and local interpretability analyses were performed to identify discriminative metabolites. Results: EBM achieved the highest ROC-AUC (0.864; 95% CI: 0.736–1.000), the highest PR-AUC (0.902; 95% CI: 0.783–0.997), and the best Brier score (0.189; 95% CI: 0.130–0.258) among all evaluated models, with sensitivity 0.880 (95% CI: 0.640–1.000; TP = 22/25) and specificity 0.714 (95% CI: 0.357–1.000; TN = 10/14). Global feature importance identified Carnitine, myo-Inositol, ADP, and O-Phosphoethanolamine as the leading single-feature predictors, alongside three pairwise interaction terms reflecting non-additive energy–amino acid metabolic relationships. Local explanations demonstrated that the ADP–Creatine interaction, Glutamine, and myo-Inositol drove correct sepsis classification in a representative true positive case. Conclusions: The EBM model demonstrated the highest discriminative performance and best calibration among all evaluated models, providing transparent mechanistic insights through global feature importance, and patient-level local explanations. These findings position the proposed framework as a proof-of-concept warranting external validation in larger, multi-centre cohorts before any clinical application is considered.

Background: Problematic smartphone use among adolescents is a growing public health concern closely associated with psychological distress and loneliness. Effective, culturally grounded, school-based interventions are needed. Objective: The aim of this study was to assess the effects of a 12-week program combining traditional social sports games and mental exercises on smartphone addiction, nomophobia, psychological distress, and loneliness in adolescents. Methods: In this randomized controlled trial, 69 school-recruited Tunisian adolescents (aged 14-16 years) with clinically elevated smartphone addiction scores were assigned to an experimental group (n=36, 52.2%) or a control group (n=33, 47.8%). The experimental group received a 12-week intervention comprising 4 weekly sessions integrating traditional social sports games with mental exercises, whereas the control group continued standard physical education. Outcomes (smartphone addiction, nomophobia, psychological distress, and loneliness) were assessed at baseline and after the intervention using scales validated in Arabic. Results: Linear mixed-effects models adjusted for age, sex, and BMI revealed significant group × time interactions of moderate magnitude across all outcomes ( P <.05 in all cases) favoring the experimental group. Adjusted postintervention comparisons confirmed significantly lower scores in the experimental group for smartphone addiction, nomophobia, psychological distress, and loneliness ( P <.05 in all cases; partial η _p ² =0.08‐0.12). Mediation analysis indicated that reductions in loneliness accounted for 34.4% of the intervention’s effect on smartphone addiction, consistent with partial mediation. Conclusions: A culturally adapted, school-based intervention combining traditional social sports games and mental exercises significantly reduced problematic smartphone use and improved psychological well-being. The partial mediation through reduced loneliness highlights the critical role of social connectedness in adolescent digital health interventions.

Introduction: Studies have demonstrated that insults during development increase the risk for developing diseases later in life, including hypertension, ischemic heart disease, stroke, respiratory disease, diabetes, cancer, as well as psychiatric disorders. Hence, as mitochondrial dysfunction-induced oxidative stress has been proposed to be a central molecular hub linking metabolic and oxidative stress pathways, the serotonin modulation-related mitochondrial boost might mitigate such impairments. Thus, the present study investigates the effects of serotonina modulation by uoxetine on oxidative stress and mitochondrial biogenesis biomarkers in the brainstem and heart of male rats that were overfed during lactation period. Methods: Normo and overfed animals received uoxetine (FX, SSRI) or saline from postnatal day 39 to postnatal day 59, wherein tissues were collected 24 hours later. Results and discussion: Overfeeding increased body weight and induced lipid peroxidation and protein oxidation in both tissues, while genes related to mitochondrial dynamics (PGC1a and TFAM) were speci cally modulated, suggesting a targeted effect of uoxetine on mitochondrial biogenesis pathways by overfeeding across the tissues. Together, our results suggest that early life overfeeding deregulates oxidative balance and mitochondrial biogenesis, wherein FX administration acts toward molecular normalization both in heart and brainstem of male offspring. These ndings shed light on the potential of serotonin modulation to mitigate the effects of overnutrition during developmental periods.