Search Results (1,335)

Background/Objective: Highly palatable foods are pleasurable and motivational stimuli that activate the brain’s reward system and can induce overeating in the absence of physiological needs. This study investigated how different access patterns to a cafeteria diet influence food intake, body weight-related parameters, and metabolic and neurobehavioral outcomes. Methods: At postnatal day 31, forty male Wistar rats were assigned to a standard diet or a cafeteria diet with continuous, predictable intermittent, or unpredictable intermittent access. After 10 weeks, the open-field and sucrose-preference tests assessed exploratory and anxiety-like behaviors and reward-related responses, respectively. Body composition, serum biochemical parameters, neurotransmitter content, and mRNA and protein levels were analyzed in reward-related brain regions. Results: Intermittent access increased food intake on cafeteria days compared with continuous access, with unpredictable access yielding the highest intake. Continuous-access rats exhibited higher final body weight and fat accumulation than chow-fed Control rats. Despite similar body weight, both intermittent-access groups had higher visceral adiposity, obesity indices, and adverse metabolic outcomes than the Control group. All cafeteria-fed rats displayed anxiety-like behavior, and all groups preferred sucrose except the continuous-access group. Molecular analyses revealed region-specific differences in gene expression related to neuroplasticity, stress response, and epigenetic regulation that varied with access pattern and predictability. Conclusions: Our results suggest that, beyond diet composition, the pattern and predictability of food access are key determinants of feeding behavior. Intermittent access increases the motivational value of the cafeteria diet, promoting overeating and driving reward- and stress-related neuroadaptations with potential metabolic and mental health implications. Full article

Background/Objectives: Although early institutionalization has been linked to socioemotional difficulties, its relationship with interoception in early childhood remains unclear. This study examined differences in interoception, emotion regulation, and prosocial behavior between institutionalized preschool children (IPC) and noninstitutionalized preschool children (NIPC) and explored the associations among these domains. Methods: In total, 51 children aged 4–6 years (26 IPC, 25 NIPC) participated in this study. Interoceptive accuracy (IAc) was assessed using an adapted Jumping Jack Paradigm that combined subjective reports and objective heart rate measures. Interoceptive sensitivity was evaluated using the iBEAT task based on gaze duration toward synchronous and asynchronous stimuli. Cooperation was measured using a joint fishing task, and emotion regulation was assessed using a delayed gratification task and the Early Emotion Regulation Behavior Questionnaire. Group differences were analyzed using one-way analysis of variance. Regression analyses were performed to explore the associations among variables. Results: Both groups had IAc values close to zero, indicating overall correspondence between subjective and objective signals. However, IPC showed more negative values, indicating underestimation, whereas NIPC showed more positive values, indicating overestimation. No significant differences in interoceptive sensitivity were found, and no evidence of discrimination between synchronous and asynchronous stimuli emerged. Compared with the IPC, the NIPC exhibited greater cooperation. No group differences were found in inhibitory control, although differences were observed in specific emotion regulation strategies. Regression analyses indicated that institutionalization and interoceptive sensitivity predicted IAc, whereas emotion regulation strategies and synchronous preference predicted cooperation. Conclusions: The results suggest that early institutionalization may induce changes in interoception, emotion regulation, and cooperation. Full article

Objective: Cerebral ischemia/reperfusion (I/R) injury triggers oxidative stress, neuroinflammation, neuronal degeneration, and white matter damage not only in directly affected cerebral regions but also in remote brain areas such as the cerebellum. Skimmianine, a naturally occurring furoquinoline alkaloid, has been reported to possess antioxidant and anti-inflammatory properties. This study investigated the protective effects of skimmianine pretreatment against secondary cerebellar injury following experimental cerebral I/R. Materials and Methods: Thirty-two female Wistar rats were randomly assigned to sham, Skimmianine, I/R, and I/R + Skimmianine groups (n = 8/group). Cerebral I/R was induced by transient middle cerebral artery occlusion for 60 min followed by 23 h reperfusion. Skimmianine (40 mg/kg/day, intraperitoneally) was administered for 14 days before ischemia induction. Oxidative stress markers, neuroinflammatory mediators, histopathological alterations, behavioral outcomes, and ultrastructural changes were evaluated. In addition, network pharmacology and molecular docking analyses were performed to explore potential molecular mechanisms. Results: Cerebral I/R significantly decreased TAS levels compared with sham (0.89 ± 0.15 vs. 1.52 ± 0.18 mmol Trolox Eq/L) and increased TOS (15.60 ± 3.03 vs. 6.80 ± 1.41 µmol H₂O₂ Eq/L), OSI (17.48 ± 0.50 vs. 4.43 ± 0.47), TNF-α (68.4 ± 10.2 vs. 18.6 ± 4.4 pg/mL), Iba1 (41.3 ± 9.7 vs. 11.7 ± 1.6 pg/mL), and GFAP levels (334.5 ± 12.5 vs. 87.7 ± 9.5 ng/mL; all p < 0.001). I/R also impaired motor performance, as shown by increased beam crossing time (11.7 ± 2.2 vs. 4.8 ± 0.7 s) and grid foot fault rate (18.6 ± 4.0% vs. 3.4 ± 1.1%). Skimmianine pretreatment significantly improved these alterations, increasing TAS to 1.29 ± 0.20 mmol Trolox Eq/L and reducing TOS, OSI, TNF-α, Iba1, and GFAP levels to 9.20 ± 2.04, 7.07 ± 0.47, 34.9 ± 7.4, 24.2 ± 6.9, and 237.0 ± 7.9, respectively, compared with the untreated I/R group. Histopathological scores for Purkinje cell loss, edema, vascular congestion, and TNF-α expression were also significantly reduced by skimmianine. Quantitative TEM analysis showed that I/R reduced myelin thickness (0.29 ± 0.05 vs. 0.53 ± 0.07 µm), increased G-ratio values (0.75 ± 0.05 vs. 0.63 ± 0.04), and increased vacuolized fibers (24.70 ± 4.20% vs. 3.20 ± 1.10%), whereas skimmianine partially restored myelin thickness (0.42 ± 0.07 µm), reduced the G-ratio (0.68 ± 0.05), and decreased vacuolized fibers (11.20 ± 2.80%; p < 0.05 vs. I/R). Molecular docking demonstrated favorable binding between skimmianine and TNF-α, with a predicted binding energy of −6.953 kcal/mol. Conclusions: These findings indicate that skimmianine exerts neuroprotective effects against secondary cerebellar injury following cerebral I/R through coordinated modulation of oxidative stress, systemic neuroinflammatory responses, astroglial injury-associated pathways, and inflammation-related mechanisms. Full article

Algorithmic prediction models are increasingly used to support decision-making in high-stakes environments, including emergency departments (ED). However, aggregate performance metrics may obscure systematic differences in classification errors or calibration across subgroups. This study presents a stage-wise, multi-metric, and interpretable fairness auditing framework for ED prediction. The framework compares mitigation strategies across data-, model-, and decision-level interventions, evaluates subgroup fairness using complementary classification and calibration criteria including equalized odds difference (EOD) and expected calibration error (ECE) disparity, and incorporates interpretability analyses based on SHapley Additive exPlanations (SHAP) and the calibration adjustment difference (CAD) to characterize changes in feature-contribution patterns and subgroup-specific probability adjustments after mitigation. The framework was applied to 126,819 ED encounters from MIMIC-IV-ED using measurements recorded within the first 2 h after arrival, and penalized logistic regression and random forest models were compared under reweighting, reduction, and multicalibration. Baseline AUROC values were 0.748 ± 0.028 for random forest and 0.746 ± 0.028 for penalized logistic regression. Reduction and multicalibration largely preserved discrimination performance, whereas reweighting was associated with reduced AUROC and AUPRC. Reweighting most clearly reduced EOD-based classification disparity, particularly for age, yielding reductions of 80.6% in random forest and 86.4% in penalized logistic regression. By contrast, multicalibration most consistently reduced ECE-based calibration disparity for sex and age but did not consistently improve EOD-based classification disparity. In the interpretability analyses, SHAP indicated that data- and model-level mitigation altered feature-contribution patterns, whereas CAD showed that decision-level mitigation produced subgroup-specific probability adjustments that varied in direction and magnitude across groups. These findings reveal trade-offs among discrimination performance, classification fairness, and calibration fairness, indicating that fairness mitigation should be guided by a clearly defined target fairness objective. Pre-deployment fairness auditing should therefore combine complementary fairness metrics with interpretability analyses to evaluate both subgroup-level outcomes and unintended changes in model behavior. Full article

Orofacial pain (OFP) includes a broad spectrum of odontogenic and non-odontogenic conditions with overlapping clinical features that often limit diagnostic accuracy, driving increasing interest in artificial intelligence (AI) as a tool to enhance diagnostic precision and support clinical decision-making. A narrative review was conducted using PubMed/MEDLINE, Scopus, and Web of Science to identify studies (2016–2026) applying AI to the diagnosis, classification, or prediction of OFP in adults. Eligible studies reported at least two diagnostic performance metrics and were thematically grouped into odontogenic and non-odontogenic categories, the latter including musculoskeletal, neurovascular, and neuropathic pain. Twenty studies were included. Neurovascular pain, particularly migraine, showed the most consistent and highest diagnostic performance, likely due to the greater availability of structured clinical data and standardized diagnostic criteria. Musculoskeletal pain, especially temporomandibular disorders, also demonstrated high and reproducible performance. In contrast, odontogenic pain showed lower and more heterogeneous performance, with better results mainly in imaging-based models, while signal- and behavior-based approaches were less robust. Neuropathic pain exhibited moderate to high performance in selected radiomics studies, but overall results remained inconsistent due to phenotypic variability and limited objective biomarkers. Currently, AI shows promising potential in OFP diagnosis, especially for neurovascular and musculoskeletal pain, but clinical translation is limited by data heterogeneity and lack of validation. Progress in clinical practice depends on multimodal datasets and multicenter studies to ensure robust, generalizable tools. Full article

Electric vehicle (EV) charging behaviors exhibit significant heterogeneity in terms of price sensitivity, time-of-day preference, and weekend charging habits, creating challenges for charging demand prediction and service management. To address this issue, this paper proposes a three-variable charging response framework that jointly considers electricity price, time-of-day preference, and weekend preference. Using real charging-order data from a public charging platform, four behavioral parameters, namely baseline charging demand (Q₀), price sensitivity (α), time preference (β), and weekend preference (γ), are estimated through nonlinear least squares (NLS). Based on the extracted parameter vectors, K-means clustering is employed to identify five representative user groups: Commuting-Dominant, elastic energy-saving, Weekend-Switching, Night-Preferential, and discount-sensitive users. The results reveal substantial behavioral heterogeneity among users. To validate the proposed framework, both parameter interpretability analysis and benchmark comparisons are conducted. Compared with the best baseline model, the proposed method reduces the test RMSE from 11.5 kWh to 8.3 kWh (27.8%), decreases the test MAPE from 25.3% to 18.7% (26.1%), and improves the test R² from 0.70 to 0.80. The proposed framework provides an interpretable approach for EV charging behavior modeling and user segmentation, offering practical support for differentiated pricing, charging demand management, and intelligent charging service operation. Full article

Experiences of discrimination and/or microaggressions may negatively affect mental health among university students. We assessed the association between experiences of discrimination, microaggressions, and combined exposure on poor behavioral health (PBH) among university students in Spring 2023 (N = 45,386) using cross-sectional data from the American College Health Association’s National College Health Assessment III. PBH (an index of severe psychological distress and substance use risk) was reported by 42.9% of students. More than half of sexual and gender minority (SGM) youth reported PBH, and had a high prevalence of discrimination and microaggressions. Among racial/ethnic groups, Black/African American students had the highest prevalence of experiences of discrimination and microaggressions. Minoritized groups who experienced discrimination or microaggressions consistently reported a higher prevalence of PBH compared to their counterparts not reporting these experiences; the opposite pattern was observed among cisgender, heterosexual, and White participants. In the logistic regression models, experiences of both discrimination and microaggressions were associated with an over 2-fold increase in odds of PBH, controlling for demographic variables, compared to those experiencing neither. Interaction effects revealed that experiences of microaggressions did not consistently and differentially predict PBH across subgroups of minority youth. Efforts to increase resilience on university campuses may improve behavioral health. Full article

Water-soluble viscosity-modifying admixtures (VMAs) were initially introduced into cementitious materials to enhance cohesion, stability and resistance to bleeding and segregation. With the development of self-compacting concrete, underwater concrete, grouting materials and 3D-printed cementitious materials, VMAs have become increasingly important for regulating rheological behavior, workability retention, shape retention and construction processability. Recent studies further indicate that VMAs can affect not only fresh-state properties, but also hydration kinetics, early-age microstructure evolution, mechanical performance, transport behavior and long-term durability. This review systematically summarizes the types, action mechanisms, and performance effects of water-soluble VMAs in cementitious materials. Particular emphasis is placed on the relationships among the molecular structure, liquid phase viscosity enhancement, particle adsorption and bridging, polymer-chain entanglement, ion-responsiveness, admixture compatibility, and microstructure evolution. The review shows that the effects of VMAs are not governed solely by admixture type or dosage, but depend strongly on molecular mass, functional groups, substituent composition, charge characteristics, binder chemistry, and the pore solution environment. Finally, current research gaps and future directions are discussed, including quantitative structure–mechanism–performance relationships, applicability in low-carbon binders, service-life prediction, and application-oriented VMA design. Full article

The South-to-North Water Diversion Project (SNWDP) in China involves a vast number of resettlers with far-reaching impacts. As a crucial carrier of resettlers’ daily lives, the indoor thermal comfort of resettlement housing directly affects their physical and mental health. However, existing empirical and field studies have paid limited attention to the thermal comfort and thermal adaptation of the resettlers. This study focuses on resettlers of the SNWDP, employing a combination of questionnaires and on-site measurements to analyze thermal benchmarks and thermal adaptation behavior data. The study introduces the concept of relative deprivation theory from social psychology, compares the correlations between vertical and horizontal deprivation and thermal perception across different relocation modes, and validates the predictive performance of commonly used thermal comfort models. The results show that as the relocation distance increases, the summer indoor thermal neutral temperature rises sequentially, and both the sensitivity to temperature changes and the width of the comfort zone also increase. Regarding thermal adaptation behaviors, the short-distance group primarily relies on passive adjustments such as using electric fans and reducing clothing, while the long-distance group significantly shifts toward active mechanical cooling like air conditioning. The sense of relative deprivation has a significant impact on the thermal comfort of medium- and long-distance resettlers, and its correlation even exceeds that of physical factors such as air temperature and black globe temperature. Among all groups, the ePMV and ePTS models modified by the expectancy factor exhibit the best predictive performance, with the smallest average deviation from the actual Thermal Sensation Vote (TSV), making them the optimal evaluation models for indoor thermal comfort of resettlers in the SNWDP. The findings provide theoretical guidance for creating healthy and comfortable indoor thermal environments in resettlement areas and for the sustainable development of subsequent phases of the SNWDP. Full article

Urban fire prevention is shifting from reactive response to proactive risk governance, yet current approaches often overlook risk-type heterogeneity, spatial dependencies, and underlying behavioral mechanisms, especially equitable risk distribution among vulnerable groups. To address this, this study integrates the Pressure–State–Response (PSR) model with environmental criminology theories (Routine Activity Theory (RAT) and Crime Pattern Theory (CPT)) to couple macro social causal chains with micro behavioral–spatial mechanisms. Using data from the digital urban management system of Shenzhen’s Guangming District in 2019, four fire risk event types are examined: electric bike charging violations (EB), unauthorized power wiring (PW), water heater misuse (WH), and aging gas pipelines (GP). Spatial error models explain 82–89% of the variance across fire risk event types, and spatial 5-fold cross-validation shows minimal performance decline (ΔR² = 0.03–0.08), confirming robust prediction without overfitting. Key findings include: (1) elderly proportion is significantly positively associated with WH and PW (coefficients = 2.64 and 3.06, p < 0.01); (2) restaurant density has a consistently positive association with all four risk types (coefficients = 0.24–0.60, p < 0.01); (3) functional diversity and connectivity exhibit dual patterns, showing negative associations with more visible, easily detectable violations (PW, GP) but positive relationships with relatively concealed behaviors (EB); (4) reported safety deficiencies display strong positive associations with all fire risk event types and can therefore serve as an effective early-warning indicator for broader fire risk. These results support risk-specific, equity-oriented prevention strategies that prioritize vulnerable groups and high-risk environments. The validated PSR–RAT/CPT framework provides a novel theoretical basis for targeted fire risk governance and advances safe, resilient, inclusive cities aligned with Sustainable Development Goal 11. Full article

Molecular property prediction is a fundamental task in drug discovery and materials design. While graph neural networks (GNNs) and SMILES-based Transformers have made significant strides, the former are often limited by local message-passing bottlenecks such as over-squashing, while the latter frequently lack explicit topological constraints and suffer from severe vocabulary imbalance. In this work, we revisit the granularity of molecular modeling and propose a representation learning framework built upon bond-level sequences. Our framework models molecules as sequences of directed bond tokens and introduces a structure-aware hybrid attention mechanism. By imposing hard topological constraints on a subset of attention heads to reinforce local connectivity while preserving global receptive fields in the remaining heads, the design is intended to separate short-range chemical bonding from long-range contextual dependencies. For pre-training, we implemented a multi-scale consistency learning paradigm, which utilizes an atom-centric group masking strategy to induce a hierarchical loss of local structural information and employs contrastive and triplet losses to ensure identity consistency across varying scales of structural degradation. Furthermore, by incorporating macro-scale physicochemical descriptors (e.g., LogP, TPSA) as global anchors, we examined how the inclusion of global attribute bias can provide weak physicochemical priors during pre-training, while its effect during downstream fine-tuning remains task-dependent. Experimental results demonstrate that our lightweight model, with approximately 3.5 million parameters, exhibits a dataset-dependent performance profile across MoleculeNet benchmarks and shows promising behavior on selected topology-sensitive tasks, particularly MUV. Ablation studies further analyze the contribution of bond-level connectivity, the stage-dependent dynamics of global attribute bias, structured masking, and pre-training configurations. Ultimately, this work provides an alternative representation design for molecular modeling, offering a parameter-efficient option for future molecular learning systems alongside traditional SMILES-based and graph-based formulations. Full article

The scientific literature lacks sufficient data on the transport of various toxic pollutants by polymer particles. Investigating how the structure of microplastic particles formed during the degradation of polymeric materials affects pollutant sorption processes will improve our ability to predict environmental behavior. General-purpose polystyrene, expanded polystyrene, ABS plastic (acrylonitrile–butadiene–styrene) and crosslinked polystyrene are produced on an industrial scale. Copolymers of styrene with divinylbenzene are used on a large scale as sorbents for gel permeation chromatography (Styragel brand sorbents), in the production of catalysts on a polymer substrate or ion-exchange resins. In this study, non-spherical, crosslinked polystyrene microparticles with varying polystyrene chain packing densities were used as model microplastic particles representative of crosslinked polystyrene. It was shown that the adsorption of a hazardous chemical rhodamine B was influenced by both the packing density of the polystyrene chains and the presence of ionic functional groups, i.e., the “degree of aging” of the microplastic particles. The sorption capacities of these model microparticles were compared with those of natural origin (silicon dioxide, quartz powder, and microcrystalline cellulose). A viability assay using HEK293 and HeLa cell lines exposed to leachates from both pristine and rhodamine B-loaded microparticles revealed that all unmodified microparticles, regardless of their nature, exhibited no cytotoxicity at concentrations up to 1000 μg/mL. In contrast, microparticles with adsorbed rhodamine B significantly reduced cell viability to 20–40% at concentrations of 100 μg/mL. Full article

Steel pipelines for oil and gas transportation serve as the lifeline of energy conveyance, and their long-term safe operation constitutes a crucial safeguard for energy security. Nevertheless, in complex service environments, local defects formed on the inner pipe wall due to medium corrosion have emerged as a prominent hidden danger endangering pipeline integrity. Accurate evaluation of the residual strength of pipelines with corrosion defects is not only the technical foundation for ensuring the safe operation of pipelines, but also the key basis for formulating scientific maintenance strategies and prolonging the service life of pipelines. Taking three grades of steel pipelines (X52, X65 and X80), which represent the typical strength grades commonly used in long-distance oil and gas transmission pipelines, as the research objects, this paper establishes a three-dimensional finite element model of single-point uniform corrosion defects considering the nonlinear material behavior, and systematically investigates the influence laws of geometric parameters (depth, length and width) of corrosion defects on the failure pressure of pipelines under the action of monotonic internal pressure load. The accuracy of the proposed finite element model is verified by comparison with the test data from thirteen groups of full-scale burst experiments. On the basis of parametric analysis results, an explicit and high-precision predictive model for failure pressure is developed. The research findings reveal that corrosion depth acts as the dominant factor affecting pipeline failure pressure with a distinctly nonlinear influence characteristic: the load-bearing capacity of pipelines drops drastically when the relative depth d/t exceeds 0.6, where d is the corrosion depth and t is the pipe wall thickness. There exists a critical value for the impact of corrosion length, beyond which its weakening effect on failure pressure tends to level off. Within the commonly encountered engineering range (20~100°), corrosion width exerts a negligible influence on pipeline failure pressure and thus can be overlooked in engineering evaluation. In comparison with conventional industry assessment methods such as ASME B31G, DNV RP-F101, PCORRC and SY/T 6151, the newly established predictive model features higher prediction accuracy and broader applicability, which provides on-site engineers with a powerful theoretical tool and practical formula for the rapid and accurate evaluation of the residual strength of corroded pipelines. Full article

Obesity is a major public health concern because of its high prevalence and association with cardiometabolic comorbidities. This study compared nine ensemble and meta-ensemble learning models for multiclass obesity-status classification using the Obesity Dataset, comprising 1610 records, 14 predictors, and four body-weight status classes. To ensure a leakage-aware evaluation, all preprocessing and resampling steps were embedded within the validation workflow. Standardization, one-hot encoding, and RandomOverSampler were applied only within the training folds; SMOTE and no-resampling configurations were retained as configurable alternatives but were not used to generate the reported results. Model performance was assessed using complementary classification, discrimination, agreement, and calibration metrics, including accuracy, balanced accuracy, weighted F1-score, macro F1-score, weighted ROC-AUC, Matthews correlation coefficient, Brier score, and multiclass expected calibration error. Overall, the ensemble models achieved strong discriminative performance, with eight of nine classifiers exceeding 82% accuracy and obtaining weighted ROC-AUC values close to or above 94%. LightGBM showed the strongest mean metric-based profile, with an accuracy of 85.41 ± 2.85%, weighted F1-score of 85.25 ± 2.88%, weighted ROC-AUC of 95.58 ± 1.52%, and MCC of 0.779 ± 0.042. Random Forest and Stacking achieved comparable classification performance, although Stacking presented poorer calibration. The Friedman test detected significant global differences among classifiers, χ² = 38.7733, p = 0.000005. However, the Nemenyi post hoc test indicated that Stacking, Random Forest, LightGBM, Voting, Gradient Boosting, and Extra Trees belonged to the same high-performance statistical group. Therefore, LightGBM was selected as the final model based on its practical balance of predictive performance, calibration behavior, stability, and implementation feasibility, rather than on unequivocal statistical superiority. On the independent holdout set, LightGBM maintained strong generalization, achieving accuracy = 0.8447, weighted F1-score = 0.8435, MCC = 0.7653, and weighted ROC-AUC = 0.9464. Calibration was moderate, with Brier score = 0.2575 and multiclass ECE = 0.1070, indicating that predicted probabilities should be interpreted cautiously when used to support threshold-based decisions. Full article

Sustainability education establishes a better understanding for students who study sustainability, yet fails to create observable changes in student conduct. This study presents an adaptive machine learning-based educational framework that predicts student sustainability topic comprehension and provides customized learning resources to enhance academic performance and environmental sustainability practices. A synthetic dataset of 9600 records and 21 attributes was generated to simulate student interaction with eight sustainability topics, including climate change, carbon footprint, recycling, water conservation, renewable energy, sustainable transport, food waste, and green buildings. The dataset contained student demographic information, together with their academic performance indicators, their participation metrics, their quiz results, and their conduct assessment scores, which were collected before and after their educational process. The Random Forest classifier was developed to forecast three different levels of comprehension, which included low comprehension, medium comprehension, and high comprehension. The model achieved an accuracy of 0.999, precision of 0.999, recall of 0.999, and F1-score of 0.9989. Students in the adaptive group increased their quiz scores by an average of 15.21 points while students in the control group improved their scores by 6.08 points. The adaptive group showed a mean behavior change of 12.02 points while the control group displayed a 3.54-point change. The greatest improvements occurred among students who began with limited knowledge because the adaptive group attained 17.93 points in quiz improvement and 13.80 points in behavior change. The results demonstrate that the adaptive learning framework successfully simulates personalized sustainability education paths that proceed through controlled testing environments. The synthetic dataset testing showed that the framework created distinct learning patterns, which proved that academic performance and sustainability behavior enhancements showed better results than the fixed learning method. The findings demonstrate proof-of-concept results that show that adaptive machine learning can be successfully integrated into sustainability education, but they do not demonstrate actual educational effectiveness in real-world settings. Full article