Search Results (658)

Background/Objectives: Diffuse large B-cell lymphoma (DLBCL) remains clinically heterogeneous despite standard first-line immunochemotherapy. We evaluated whether machine learning (ML) models using routinely available diagnostic variables could predict primary refractory DLBCL. Materials and Methods: We performed a retrospective single-center study of 369 patients with DLBCL treated between 2015 and 2023. Primary refractory disease was defined as failure to achieve at least a partial response after first-line therapy. Logistic regression, random forest, gradient boosting, support vector machine with radial basis function kernel (SVM-RBF), and multilayer perceptron models were trained using baseline clinical and laboratory predictors. Performance was assessed using a stratified 80/20 holdout split, nested cross-validation, repeated random splits, and sensitivity analysis with complete hyperparameter retuning. Results: Primary refractory disease occurred in 111 patients (30.1%). In the holdout test set (n = 73), IPI achieved the highest discrimination (AUC 0.692; 95% CI 0.545–0.828). Among ML models, gradient boosting performed best (AUC 0.658; 95% CI 0.503–0.801), followed by SVM-RBF (AUC 0.619; 95% CI 0.471–0.760). DeLong comparisons showed no significant differences between ML models and IPI. In internal validation, gradient boosting showed the highest nested CV AUC (0.712 ± 0.049). Feature importance identified IPI as the dominant predictor. A weighted ML-derived clinical score identified a high-risk group with the highest refractory rate (52.9%), although the trend was not statistically significant (p = 0.063). Conclusions: ML models showed comparable but not superior performance to IPI for predicting primary refractory DLBCL. These findings support further external validation and development of multimodal clinically interpretable prediction frameworks for risk-adapted management. Full article

Background: Attention-Deficit/Hyperactivity Disorder (ADHD) affects an estimated 6% of adults in the United States and contributes to a significant economic burden. Telehealth has emerged as a vital tool in the management of ADHD, offering improved access to care, especially for individuals in underserved communities. Despite its growing role, there remain critical gaps in understanding how social determinants of health (SDOH) are associated with disparities in telehealth utilization for ADHD treatment. Objectives and Methods: This study analyzed data from the National Center for Health Statistics (NCHS) Rapid Surveys System (RSS) Round 2: ADHD (October–November 2023), a nationally fielded survey of U.S. adults. Respondents were classified into three groups: never diagnosed, previously diagnosed, and currently diagnosed with ADHD. The study aimed to (1) compare the distribution of SDOH across ADHD status groups and the general adult population to identify factors associated with ADHD diagnosis; (2) assess the homogeneity of SDOH distributions across ADHD groups; (3) evaluate telehealth utilization among adults currently diagnosed with ADHD; and (4) examine the relationship between SDOH and telehealth use for ADHD treatment. Multivariable logistic regression (MVLR) served as a benchmark model, while machine learning (ML) models—including regularized linear regression, support vector machine (SVM), random forest (RF), LightGBM, multilayer perceptron (MLP), and Few-Shot Learning (FSL)—were trained to identify key predictors. Results: A total of 7009 survey responses were analyzed: 124 had a past diagnosis, 444 were currently diagnosed, and the remainder had never been diagnosed with ADHD, corresponding to a current ADHD prevalence of 6.3%. Adults with current ADHD were more likely to be male, single, younger, white, non-homeowners, and frequent users of online health resources. They also reported lower education, income, and financial security. About 70% used telehealth for counseling and prescriptions; insurance covered telehealth visits for 82.32% of users, yet 38.76% reported no coverage of ADHD-related diagnostic or treatment costs. Nineteen SDOH elements across four domains—demographic, socioeconomic, neighborhood/built environment, and healthcare access—were identified as predictors. ML models outperformed MVLR, with SVM and FSL achieving the highest F1 (both 0.63), and FSL the highest recall (0.69). Age, race, marital status, difficulty paying bills, home ownership, education, and household size were the most consistently important variables. Limitations: This study is limited by a cross-sectional design, reliance on self-reported ADHD diagnoses, and a lack of genetic or family-history measures. Additionally, the omission of complex sampling weights limits the national representativeness of these findings. Finally, the small effective sample size poses risks of model overfitting, and the generalizability of the models could not be externally validated due to the unavailability of comparable independent datasets. Conclusions: Despite widespread internet access, disparities in telehealth use for ADHD persist. Among 19 SDOH predictors, age (aOR = 0.56), difficulty paying medical bills (aOR = 2.52), and race (aOR = 1.37) were significantly associated with telehealth use, and all ML models outperformed the MVLR benchmark, though bootstrap CIs overlapped. Future research should incorporate inclusive data collection and stratified modeling to better represent disadvantaged populations and inform equitable access strategies. Full article

Machine learning (ML) algorithms can be used to extract clinically meaningful information from movement data captured by inertial measurement units (IMUs), but many human activity recognition (HAR) pipelines are developed on large laboratory datasets that may not reflect small, heterogeneous, real-world samples. The purpose of this study is to systematically compare the accuracy of multiple ML models, feature sets (both simple and expanded), class balancing strategies, null and transition period handling techniques, and sensor configurations for recognizing a set of four everyday activities extracted from IMU time series data from an age-diverse population. Six ML classifiers were trained and tested: multilayer perceptron, random forest, k-nearest neighbors, logistic regressor, CatBoost, and gaussian naive bayes. These approaches were used in a pipeline with differing sampling techniques including the synthetic minority oversampling technique or random undersampling, and feature handling steps including principal component analysis or a Select-From-Model metatransformer. Additionally, two deep learning methods, DeepConvLSTM and ResGCNN, were trained and tested. Accuracy, precision, recall, and area under the receiver operating characteristic curve were compared to a dummy classifier as a benchmark approximation to chance performance. All pipelines performed better than the dummy classifier, with model accuracy ranging between 0.427 and 0.644. This study demonstrated the ability of several ML algorithms to properly recognize a set of functional activities using limited IMU data from both children and adults. Full article

Undiagnosed diabetes and prediabetes are common among trauma patients and increase perioperative complication rates, yet routine glycemic screening at hospital admission is rarely performed. We compared 10 supervised machine learning (ML) algorithms for early detection of impaired glucose metabolism in 1789 trauma surgery patients (1095 normal; 694 prediabetes/diabetes) using questionnaire data and preoperative laboratory values within a nested cross-validation framework with hyperparameter optimization. On the combined feature set, XGBoost achieved the highest area under the receiver operating characteristic curve (ROC-AUC; 0.815), followed by multilayer perceptron (0.814) and Gradient Boosting (0.813); adding blood parameters significantly improved performance for nine of ten algorithms (DeLong’s test, p < 0.05). SHapley Additive exPlanations (SHAP) and XGBoost feature gains identified six overlapping predictors, yielding a simplified model with comparable mean discrimination. Inter-model differences were small, and a fully interpretable logistic regression model remained within one percentage point of XGBoost. The best-performing model demonstrated strong calibration and a higher net benefit than either universal testing or no testing across the evaluated threshold probabilities. In routine trauma practice, such a model could identify patients who would benefit from confirmatory glycated hemoglobin (HbA1c) testing, enabling earlier detection of dysglycemia, risk-stratified glucose management, and timely referral for lifestyle intervention in patients with prediabetes. Full article

The application of Machine Learning (ML) to bridge Structural Health Monitoring (SHM) is constrained by a lack of diverse and labelled datasets. Obtaining high-quality training data from operational infrastructure is inherently difficult because critical assets are typically repaired immediately upon the detection of defects, preventing the collection of data describing diverse failure modes. To address this scarcity and enable the prototyping of robust algorithms, this study presents a framework for generating synthetic modal frequencies using a calibrated Finite Element (FE) model of the S101 bridge. Aleatory uncertainties and environmental variability are incorporated through the stochastic variation of material properties and thermal loads derived from a 20-year climate record. Analysis of the generated dataset revealed that simulated thermal loads induced frequency shifts that often exceeded those caused by minor structural damage, confirming the necessity of training on environmentally representative data. The primary contribution of this work is an open-access, FAIR-compliant (Findable, Accessible, Interoperable, Reusable) synthetic dataset, intended to serve as a standardised benchmark for the SHM research community under conditions of combined structural and environmental uncertainty. To demonstrate the utility of the generated data, the performance of a supervised multi-layer perceptron and an unsupervised k-means clustering algorithm are evaluated, with the supervised approach achieving a maximum classification accuracy of 1.00. However, the framework also reveals a fundamental modelling limitation: the linear FE approach failed to replicate the physical response under pier settlement, producing frequency shifts an order of magnitude below those observed experimentally. Full article

Miniaturized spatial electric field sensors often exhibit insufficient front-end charge coupling because of their limited sensing area. To address this material-level bottleneck, KH550-functionalized graphene composite films were developed as candidate electrode materials for spatial electric-field sensing. Single-layer and multilayer graphene powders were modified with the silane coupling agent KH550 and dispersed in a waterborne polyurethane/PVP matrix to fabricate composite films. The sensing mechanism was analyzed from the Maxwell–Wagner–Sillars interfacial polarization and electrode-equivalent capacitance perspectives. The modified materials were characterized by SEM, EDS, Raman spectroscopy, FTIR spectroscopy, low-frequency dielectric measurements, and broadband high-frequency impedance measurements. KH550 functionalization introduced Si- and N-containing surface species and increased disorder or sp³-related structural features while retaining the layered graphene structure. The film formulation selected through qualitative visual screening contained 0.16 g of graphene, 10 mL of waterborne polyurethane, and 0.05 g of PVP. Under AC excitation, the relative permittivity of the composite film containing KH550-functionalized multilayer graphene was approximately 18% higher than that of its unmodified counterpart. Broadband measurements showed material-dependent changes in the reflection and impedance responses of the electrode–fixture configurations. The modified multilayer-graphene electrode exhibited a different distribution of reflection minima, resistance maxima, and capacitive–inductive transitions from the unmodified and copper electrodes. Because the measured response includes contributions from the coating, substrate, fixture, and parasitic elements, these results are interpreted as comparative system-level responses. These results indicate that interfacial engineering of graphene composite films can enhance electrode-level dielectric response and charge-coupling capability, providing a material basis for non-contact electric field sensing electrodes. Full article

Background/Objectives: Oral solid dosage forms of traditional Chinese and ethnic medicines are currently undergoing modernisation. The objective of this study is to explore the scope for formulation variation arising from batch-to-batch fluctuations in intermediates, and to identify the factors influencing key quality attributes of honey-containing tablets. In this regard, a machine-learning-based predictive model is being formulated that will integrate and analyse formulation factors and the results characterised by the SeDeM expert system. Utilising the SeDeM index as a mediating variable, the study endeavours to establish a comprehensible and predictable stepwise research pathway to provide a foundation for industrial-scale upscaling. Methods: Twelve SeDeM expert systems were utilised to characterise honey-containing granules for formulation screening, to evaluate their suitability for use in traditional Chinese medicine honey-containing tablet systems, and to identify key limiting factors and the feasibility space affecting the quality of the final product; Based on the QBD philosophy, a TriAD (Tri-criterion Adaptive Design) design scheme was proposed, integrating the horizontal balance of orthogonal designs, the spatial coverage of uniform designs, and the parameter estimation efficiency of D-optimal designs into the experimental layout of the formulation feasibility space; Through further data aggregation, a multi-layer feature set comprising four formulation factors, six SeDeM indicators, and three critical quality attributes (CQAs) was constructed. The mediating effects of the SeDeM indicators were revealed through different pathways involving 37 combinations of simple, linear, and Bootstrap models. Furthermore, 180 linear and non-linear machine learning models (comprising 12 categories of algorithms) were trained to predict formulation and CQA outcomes, ultimately completing the design space mapping and validation. Results: The results show that the SeDeM parameters effectively bridge the CQA results of different honey formulations, with these indicators acting as selective mediators between formulation factors and CQAs. Compared with a pure data model relying solely on raw formulation variables, the introduction of SeDeM knowledge, combined with high-information-content samples obtained via TriAD, improved the predictive performance and robustness of the SeDeM–ML hybrid model in terms of disintegration time and hardness; its R²_LOO increased by 0.267 and 0.510, respectively, and the overall predictive space was significantly expanded. Experimental validation was conducted using formulations within the design space predicted by the optimal model; the results showed that both the prediction bias and the relative standard deviation were less than 5 percent. Conclusions: The present study demonstrates that SeDeM can not only be used to evaluate formulations of honey-containing TCM tablets but also serves as an intermediary bridge linking formulation factors, granule-mechanism variables, and tablet quality outcomes. TriAD, in turn, further translates the QbD philosophy into an actionable formulation space design, thereby providing a development pathway for honey-containing tablets that combines interpretability, predictability, and QbD consistency, and offers new insights for the industrial application of oral TCM preparations. Full article

Background/Objectives: Cardiac surgery involves unique complexities that differ from those of general ICU populations. Traditional scoring systems often underperform due to the significant class imbalance between survival and mortality. This study utilized the MIMIC-IV database, integrating machine learning (ML) and feature engineering to develop an in-hospital mortality prediction model specifically for open-heart surgery patients. Methods: We included 6941 cases (mortality: 76, 1.095%). Sixty-eight variables from the first ICU day were extracted. Following data preprocessing and imputation, four ML models—logistic regression, random forest (RF), XGBoost, and multilayer perceptron (MLP)—were constructed using stratified 10-fold cross-validation. SMOTE was applied to address class imbalance. A streamlined 17-variable model was developed and compared against the Sequential Organ Failure Assessment (SOFA) and the Oxford Acute Severity of Illness Score (OASIS). Results: Among the 68-variable models, RF achieved the highest area under the receiver operating characteristic curve (AUROC) of 0.915 (95% CI, 0.855–0.966). For the 17-variable models, MLP performed best (AUROC: 0.920; 95% CI, 0.865–0.964), significantly outperforming SOFA (0.688) and OASIS (0.690). Regarding the area under the precision-recall curve (AUCPR), the 17-variable MLP also yielded the highest score (0.203; 95% CI, 0.060–0.389) compared with SOFA (0.161) and OASIS (0.046). SHapley Additive exPlanations (SHAP) analysis identified bicarbonate levels, mechanical ventilation, and mean pulmonary arterial pressure as the top predictors, consistent with clinical expectations. Conclusions: The streamlined MLP model significantly outperforms traditional scoring systems and may serve as a useful tool for early postoperative risk stratification after open-heart surgery. Full article

Vertical farming (VF) offers a smart way to grow crops in stacked layers inside controlled indoor environments. By doing so, it uses far less land and water than traditional open-field agriculture, making it a promising solution for cities with limited space and resources. In recent years, artificial intelligence (AI), machine learning (ML), and Internet of Things (IoT) technologies have begun to transform vertical farming. These tools are moving the industry away from rigid, rule-based systems toward more flexible, data-driven operations that can adapt in real time. This paper presents a systematic review of 208 peer-reviewed studies from 2015 to 2025. It explores how AI, ML, and IoT are applied across the VF ecosystem, focusing on key areas such as computer vision for disease detection, crop growth and yield prediction, smart climate control, and precision nutrient and irrigation management. This review examines the performance of different algorithms, including Convolutional Neural Networks (CNNs), Random Forest, XGBoost, and LSTMs across hydroponic, aeroponic, and aquaponic systems. The review also covers IoT setups with multi-sensor networks, edge-cloud computing, and automated control systems. Commercial farms have shown real gains in resource efficiency and shorter supply chains. However, challenges remain: high energy use (especially from LED lighting, which makes up 40–60% of costs), expensive setup, scattered datasets, and limited real-world testing. Many high-accuracy claims (>95%) come from lab conditions and need better validation in actual farms. Overall, AI-powered vertical farming has strong potential to support resilient urban food systems. Future work should focus on lightweight edge AI models, improved data standards, explainable AI, and robust life cycle assessments to ensure the benefits outweigh the environmental and economic costs. Full article

In Industry 4.0 manufacturing, predictive maintenance has emerged as a key focus to ensure the reliability of operations, minimize downtime, and contribute to equipment safety. This study proposes a predictive maintenance framework for additive manufacturing systems (AMSs) using an explainable artificial intelligence (XAI) and machine learning (ML) approach, which is supported by real-time multi-sensor monitoring and is synchronized with a digital twin architecture. A heterogeneous dataset of over 10,000 observations and 13 sensor attributes was gathered from a sensing architecture with ESP32 cameras designed to handle heterogeneous signals from thermal, environmental, mechanical and safety-related sensors. Domain-aware feature engineering was done to gain insights into operation indicators such as temperature instability, vibration degradation, smoke risk, humidity anomalies and aggregated maintenance risk scores. Multiple predictive models, such as the Random Forest model, XGBoost model, Logistic Regression model, K-Nearest Neighbours classifier, Multi-Layer Perceptron model, and ARIMA forecast model, were comparatively assessed under highly imbalanced maintenance conditions. The results showed that ensemble learning methods, especially XGBoost and MLP, had better recall and ROC-AUC for fault detection of maintenance-critical problems. SHAP and LIME analyses then showed that a number of physically meaningful indicators, including thermal instability, vibration anomalies, smoke-related features, and aggregated risk scores, have a significant impact on maintenance predictions and hence provide better operational interpretability and maintenance transparency. Full article

The purpose of the present study was to evaluate the effects of zirconia material type, substructure color, cement color, and aging (before and after aging) on the color change of laminate veneers (LVs) prepared from different multilayer translucent zirconia ceramics. LV preparation was performed on a phantom tooth, and the preparation was digitized to produce resin abutments in two shades (light: A1/B1; medium: A2/A3) to simulate different tooth colors. LVs were designed using dental design software and fabricated from three multilayer zirconia ceramics (multilayered super-high-translucent 5Y-TZP zirconia, multilayered high-translucent 4Y-TZP zirconia, and multilayered ultra-translucent 5Y-TZP zirconia), resulting in 12 experimental groups (n = 10). They were then cemented with either clear or white resin cement and subsequently subjected to 10,000 cycles of thermal aging. The color parameters were measured at three time points (before cementation, before aging, and after aging), and the color change values (ΔE₀₀) were calculated. The data were statistically analyzed, and the results were compared with the perceptibility threshold (ΔE₀₀ = 0.8) and the clinical acceptability threshold (ΔE₀₀ = 1.8). Four-way ANOVA revealed an interaction among zirconia material, substructure color, cement shade, and measurement time (p = 0.02). Color change values after cementation (ΔE₀₀-1) across all groups showed a statistically significant difference between the white and clear cement groups. Before aging, the color change values observed in the 4Y-TZP (DD Cube One ML)-medium abutment–white cement (ΔE₀₀-1 = 1 ± 0.2) and 5Y-TZP (Katana UTML)-medium abutment–white cement (ΔE₀₀-1 = 1.6 ± 0.7) groups were above the perceptible threshold value but were clinically acceptable (0.8 < ΔE₀₀ < 1.8). The color change values observed after aging (ΔE₀₀-2) across all experimental groups were clinically unacceptable (ΔE₀₀ > 1.8). The color changeof ultra-translucent zirconia LVs was influenced by zirconia material type, cement shade, substructure color, and aging, with the effect of the zirconia material itself being less pronounced. Aging further reduced color stability, resulting in increased ΔE₀₀ values and clinically unacceptable color differences. Full article

Localization is a fundamental requirement for autonomous mobile robot navigation. Several localization techniques exist, but they often require extensive installation of beacons, careful parameter tuning, high computational requirements, or an immense amount of training data. Environmental (e.g., indoor)/resource constraints, sensor degradation, and sudden pose discontinuities can make such methods unreliable. This creates a critical gap: the lack of a simple, lightweight localization method that can operate as a primary localization method or in parallel with other classical systems and provide reliable pose estimates during primary localization system failures. Thus, this paper proposes a lightweight, deep learning (DL)-based, two-dimensional LiDAR localization method. The approach combines LiDAR scan range data with eleven proposed handcrafted geometric features to train a Convolutional Multi-Layer Perceptron (ConvMLP) regression model for predicting the two-dimensional location of a robot, which is further smoothed by an augmented recursive Extended Kalman filter (EKF). The overall system is validated in three real-world environments. The results are compared against various existing machine learning (ML) models and other well-known localization techniques. The experimental results demonstrate a 280 Hz pose-update rate, achieving a 13 cm Root Mean Square Error (RMSE) using the ConvMLP model alone, which further reduces to 5 cm when fused with the recursive EKF. Full article

Precision agriculture and sustainable farming practices require autonomous environmental monitoring systems capable of operating in remote areas with limited energy and connectivity. However, the high cost of existing professional technology remains a significant barrier to widespread adoption. This study presents the development of a solar-powered smart sensing node designed for autonomous operation that integrates TinyML and dual-mode wireless connectivity via LoRaWAN and Wi-Fi for intelligent monitoring. The system features a custom-designed cup anemometer and multispectral sensing capabilities integrated into a compact single-tower architecture. All structural components, including radiation shields and a modular PVC frame, were designed for low-cost manufacturing and mass production. A single hermetic housing protects the core control electronics and is designed to improve durability in harsh outdoor environments. A Multi-Layer Perceptron model was implemented on the edge to enable intelligent data fusion and compensation, while a dynamic sampling strategy optimized power consumption. Experimental results demonstrate the feasibility of the proposed architecture through adaptive spectral acquisition over a daily illumination cycle, embedded MLP-based sensor fusion, and telemetry-oriented data compression that substantially reduces the number of transmitted samples. The main contribution of this work is a system-level architecture that integrates sensing, embedded intelligence, solar-energy harvesting, hybrid wireless communication, and telemetry optimization into a compact, low-cost, and field-deployable prototype IoT platform for sustainable precision agriculture. Full article

Outsourcing Internet-of-Things (IoT) data and computation to cloud and fog infrastructure exposes both the data and the access-control process to integrity, confidentiality, and privacy risks. Attribute-based encryption (ABE) provides fine-grained access control but, as deployed today, suffers from single-authority bottlenecks, expensive policy updates, weak auditability, and exposure to secret-key leakage, classical primitives are additionally threatened by future quantum adversaries. This paper does not propose a new cryptographic scheme. Instead, it contributes a conceptual reference architecture that systematizes how a set of existing, standardized primitives can be composed into a single access-control framework for IoT outsourcing, and it makes the resulting design precise enough to reason about. Concretely, we (i) define a system model and a threat model covering passive, active, colluding, bounded-leakage, and harvest-now-decrypt-later quantum adversaries; (ii) instantiate each layer with a named construction decentralized multi-authority ABE, attribute-based proxy re-encryption for policy updates, a bounded leakage resilient key model, ASCON lightweight AEAD, and ML-KEM/ML-DSA post-quantum primitives, together with a permissioned, on-chain digest/off-chain payload logging layer; (iii) specify the end-to-end data flow and module interfaces; and (iv) give a goal-by-goal security rationale and an analytical evaluation based only on standardized parameter sizes and asymptotic complexity. We are explicit about what is inherited from prior work, what remains to be proven for the composed system, and that a measured prototype evaluation remains future work. The intended value of this paper is to provide a clear, composable, and honestly scoped design that subsequent implementation studies can build upon. Full article

In this article, machine learning (ML) is proposed as a solution to detect and classify false message injection attacks in autonomous ground navigation. First, multiple trajectories are designed and simulated to collect authentic feature samples offered by the odometry and inertial measurement unit (IMU) of an autonomous ground vehicle (UGV). Then, a dataset comprising these samples and other injected samples that simulate two cyberattacks, namely path modification (PM) and velocity drift (VD), is created to train, validate, and benchmark various ML classification models. These include decision tree (DT), k-nearest neighbors (KNN), multi-layer perceptron (MLP), random forest (RF), and support vector machine (SVM). The optimum classification model is experimentally evaluated using a UGV platform, and results suggest that the proposed solution allows the detection of authentic and attacked messages with more than 98% average accuracy and sub-millisecond prediction time. Thus, this solution is ideal for real-time classification, especially in fixed-route applications, e.g., public transportation. Full article