Saved Queries

Missense single nucleotide variants (SNVs) represent one of the most common forms of genetic variation and account for a substantial proportion of variants of uncertain significance in clinical databases. Accurate computational classification of these variants remains an important challenge in precision medicine and genomic research. In this study, we present PathoPredictor, an interpretable machine-learning framework designed to distinguish pathogenic from benign missense variants using curated clinical variant data and functional annotations. High-confidence variants were obtained from the November 2023 ClinVar release and annotated using dbNSFP v5.1 (GRCh37). After data filtering, imputation, and normalization, 59,302 expert-reviewed missense variants were retained for model development. Six machine-learning algorithms were evaluated under identical cross-validation conditions applied to the training set. Among the evaluated models, LightGBM demonstrated the strongest overall performance and was selected as the final PathoPredictor classifier, achieving a mean ROC–AUC of 0.93 ± 0.004, accuracy of 0.90 ± 0.006, and Matthew’s correlation coefficient of 0.80 ± 0.008 across five cross-validation folds. Model interpretability was examined using SHAP (SHapley Additive exPlanations), enabling both global feature ranking and variant-level explanation of predictions. Temporal validation using ClinVar variants submitted after November 2023 showed consistent predictive performance on previously unseen submissions within the same database ecosystem (ROC–AUC = 0.91). While the framework demonstrates strong discrimination and structured interpretability, potential limitations include training data bias and partial circularity associated with the inclusion of existing meta-predictors. Overall, PathoPredictor provides a reproducible and interpretable computational framework for integrating functional annotations in missense variant prioritization, supporting research and genomic analysis workflows. Full article

►▼ Show Figures

Figure 1

37 pages, 1511 KB

Open AccessArticle

Economics of Production Diseases at the Individual Animal Level in German Dairy Farms

by Adriana Wöckel, Wolf Wippermann, Benno Waurich, Erik Bannert, Julia Wittich, Christina Felgentreu, Franz Fröhlich, Fanny Rachidi, Peter Hufe, Detlef May, Sven Dänicke, Hermann H. Swalve, Alexander Starke and Melanie Schären-Bannert

Dairy 2026, 7(2), 26; https://doi.org/10.3390/dairy7020026 (registering DOI) - 24 Mar 2026

Abstract

Production diseases in dairy cattle impose economic and welfare burdens, yet few studies quantify costs using on-farm cases. This study aimed to estimate costs and lost revenues at the individual-animal level in 10 German dairy farms (average of 592 cows; 9694 kg marketed milk/cow/year; 32.9% culling rate). Each farm was visited for three weeks; diseased cows and calves were examined by a trained veterinarian. Diagnoses, treatments, labour times, and outcomes were recorded, and costs calculated for labour, products, veterinary and orthopaedic services, discarded milk, decreased milk yield, culling, book loss, and reduced carcass value. In total, 1272 single-animal cases were included: 68% were stand-alone diseases, 11% involved multiple diagnoses within one organ system, and 21% affected several organ systems. When several diseases occurred in the same animal, total costs and lost revenues were greater than the sum of stand-alone cases, indicating compounding effects. High-impact conditions included mastitis, claw disorders, left displaced abomasum, and multimorbidity; per-case losses ranged from €43 (digital dermatitis) to >€1200 (left displaced abomasum with complications). Labour and culling-related costs were higher than reported, and productivity losses exceeded treatment costs in many cases. Findings support farm-level decision-making, prevention, and parameterization of future dynamic models. Full article

►▼ Show Figures

Figure 1

23 pages, 3318 KB

Open AccessArticle

Assessing Membership Inference Privacy Risks in Medical Diffusion Models via Discrete Encoding-Based Inference

by Fei Kong, Hao Cheng, Tianlong Chen, Xiaoshuang Shi and Chenxi Yuan

Appl. Sci. 2026, 16(7), 3140; https://doi.org/10.3390/app16073140 (registering DOI) - 24 Mar 2026

Abstract

The rapid adoption of diffusion models in medical imaging has raised significant concerns regarding data privacy, especially their susceptibility to Membership Inference Attacks (MIAs). However, the privacy risks associated with diffusion models in the medical domain remain underexplored compared to natural images. In this study, we propose a novel grey-box attack framework, termed the Discrete Encoding-Based Membership Inference Attack (DEB), inspired by Denoising Diffusion Codebook Models (DDCM). DEB injects semantically meaningful noise via a discrete codebook strategy and identifies training samples by analyzing the model’s output trajectory under this discrete encoding, specifically measuring the average of intermediate predictions across selected time steps. We conduct an evaluation of MIAs across natural images and five representative datasets from the MedMNIST collection. Our experiments reveal that the susceptibility of diffusion models is highly dependent on the data modality; for instance, while certain datasets exhibit near-complete vulnerability, others like PathMNIST demonstrate strong inherent resistance to MIAs. Furthermore, DEB demonstrates superior performance compared to existing baselines (e.g., SecMI, PIA, SimA), particularly on challenging datasets. For example, DEB achieves a True Positive Rate at 1% False Positive Rate (TPR @ 1% FPR) of 60.3% on CIFAR-10, significantly outperforming the SimA baseline (35.9%). Notably, even on the highly resistant PathMNIST dataset, DEB attains a 10.2% TPR @ 1% FPR, establishing a substantial advantage over the PIA baseline (1.1%). This work provides practical insights into the privacy risks inherent in diffusion models and emphasizes that model providers should carefully assess these vulnerabilities when exposing intermediate generation APIs. Full article

22 pages, 1205 KB

Open AccessArticle

Fine-Grained Vision-Language Method with Prompt Tuning for Blind Image Quality Assessment

by Kai Tan, Wang Luo, Yaqing Chen, Xin He, Yumei Zhang, Mengqiang Li and Haoyu Wang

Information 2026, 17(4), 316; https://doi.org/10.3390/info17040316 (registering DOI) - 24 Mar 2026

Abstract

Blind image quality assessment (BIQA) without reference images remains significantly challenging due to the fact that perceptual quality is largely determined by subtle, spatially localized distortions. However, existing Contrastive Language–Image Pre-training (CLIP)-based methods exhibit limited sensitivity to fine-grained degradations such as local blur, noise, compression artifacts, and exposure inconsistencies, since they are optimized for global semantic alignment. To overcome these limitations, we propose a fine-grained vision–language framework that enhances distortion-aware representation by considering both fine-grained visual and detailed textual domains. Specially, our method employs a fine-grained CLIP architecture in conjunction with explicit textual descriptions to enable the effective identification of subtle regional degradations. Furthermore, a parameter-efficient prompt-tuning strategy is utilized to facilitate the learning of task-adaptive prompt representations tailored to image quality assessment (IQA). Extensive experiments on three widely used in-the-wild IQA benchmarks show that the proposed method achieves strong consistency with human subjective judgments: our training-free FGCLIP-IQA reaches a maximum SROCC of 0.732 on KonIQ-10k, outperforming the vanilla CLIP-IQA baseline, while the prompt-tuned FGCLIP-IQA+ further achieves a maximum SROCC of 0.909 on KonIQ-10k with only a small number of learnable parameters and exhibits robust cross-dataset generalization capabilities. These results demonstrate that the fine-grained vision–language alignment shows great potential for future development, and provides an efficient and accurate solution for the BIQA task. Full article

(This article belongs to the Section Information Processes)

27 pages, 9439 KB

Open AccessArticle

Real-Time Digital Twin Architecture for Immersive Industrial Automation Training

by Jessica S. Ortiz, Víctor H. Andaluz and Christian P. Carvajal

Sensors 2026, 26(7), 2023; https://doi.org/10.3390/s26072023 (registering DOI) - 24 Mar 2026

Abstract

Industrial automation laboratories often face limitations related to restricted access to industrial equipment, safety constraints, and limited scalability for hands-on experimentation. To address these challenges, this work proposes a real-time multi-layer Digital Twin architecture integrating a physical Siemens S7-1500 PLC, an immersive Unity-based virtual environment, HMI supervision, and IoT-enabled remote monitoring within a unified communication framework. The architecture is structured into physical, digital, and integration layers, enabling modular scalability and bidirectional synchronization between the physical process and its virtual representation through Ethernet TCP/IP communication. System performance was evaluated using synchronization metrics including communication latency, jitter, deterministic timing deviation, and event synchronization accuracy. Experimental results demonstrated stable PLC–Digital Twin communication with average latencies below 15 ms and jitter below 0.5 ms, ensuring reliable real-time interaction during continuous operation. A comparative evaluation with engineering students also showed improved learning conditions, achieving high perceived usability (SUS = 86/100) and reduced cognitive workload (NASA-TLX = 34/100). These results confirm the effectiveness of the proposed architecture as a scalable platform for Industry 4.0 training environments. Full article

(This article belongs to the Special Issue Integrating Cloud Computing, Sensing Technologies, and Digital Twins in IoT Applications)

28 pages, 1313 KB

Open AccessArticle

WCGAN-GA-RF: Healthcare Fraud Detection via Generative Adversarial Networks and Evolutionary Feature Selection

by Junze Cai, Shuhui Wu, Yawen Zhang, Jiale Shao and Yuanhong Tao

Information 2026, 17(4), 315; https://doi.org/10.3390/info17040315 (registering DOI) - 24 Mar 2026

Abstract

Healthcare fraud poses significant risks to insurance systems, undermining both financial sustainability and equitable access to care. Accurate detection of fraudulent claims is therefore critical to ensuring the integrity of healthcare insurance operations. However, the increasing sophistication of fraud techniques and limited data availability have undermined the performance of traditional detection approaches. To address these challenges, this paper proposes WCGAN-GA-RF, an integrated fraud detection framework that synergistically combines Wasserstein Conditional Generative Adversarial Network with gradient penalty (WCGAN-GP) for synthetic data generation, genetic algorithm-based feature selection (GA-RF) for dimensionality reduction, and Random Forest (RF) for classification. The proposed framework was empirically validated on a real-world dataset of 16,000 healthcare insurance claims from a Chinese healthcare technology firm, characterized by a 16:1 class imbalance ratio (

5.9 %

fraudulent samples) and 118 original features. Using a stratified

80 / 20

train–test split with results averaged over five independent runs, the WCGAN-GA-RF framework achieved a precision of

96.47 \pm 0.5 %

, a recall of

97.05 \pm 0.4 %

, and an F1-score of

96.26 \pm 0.4 %

. Notably, the GA-RF component achieved a

65 %

feature reduction (from 80 to 28 features) while maintaining competitive detection accuracy. Comparative experiments demonstrate that the proposed approach outperforms conventional oversampling methods, including Random Oversampling (ROS), Synthetic Minority Oversampling Technique (SMOTE), and Adaptive Synthetic Sampling (ADASYN), particularly in handling high-dimensional, severely imbalanced healthcare fraud data. Full article

(This article belongs to the Special Issue Advancements in Healthcare Data Science: Innovations, Challenges and Applications)

26 pages, 16958 KB

Open AccessFeature PaperArticle

On-Device Motion Activity Intensity Recognition Using Smartwatch Accelerator

by Seungyeon Kim and Jaehyun Yoo

Electronics 2026, 15(7), 1351; https://doi.org/10.3390/electronics15071351 (registering DOI) - 24 Mar 2026

Abstract

Wearable device-based Human Activity Recognition (HAR) is widely used in health management, rehabilitation, and personal safety. While contemporary HAR research effectively classifies a wide range of discrete activities, there remains a significant gap in organizing these heterogeneous motions into a structured intensity framework suitable for continuous risk assessment. Furthermore, many high-performing models rely on computationally intensive architectures that hinder real-time deployment on resource-constrained wearables. We propose an on-device method for estimating five-level activity intensity in real time using only accelerometer signals from a commercial smartwatch. To bridge the gap between simple identification and intensity modeling, 13 dynamic and emergency-like wrist motions were integrated with 11 daily activities from the PAMAP2 dataset, yielding 21 activities mapped onto an ordinal five-level intensity scale. A finetuned Multi-Layer Perceptron (MLP) classifier trained on this integrated dataset achieved 0.939 accuracy and a quadratic weighted kappa (QWK) of 0.971. The model was deployed on a Galaxy Watch 7, achieving

< 1

ms inference latency and a size

< 0.1

MB, confirming real-time feasibility. This approach demonstrates that organizing diverse activities into a lightweight, intensity-aware framework provides a robust foundation for safety-aware monitoring systems under real-world, on-device constraints. Full article

(This article belongs to the Special Issue Wearable Sensors for Human Position, Attitude and Motion Tracking)

20 pages, 733 KB

Open AccessArticle

A Small-Sample Graph Neural Network Approach for Predicting Sortie Mission Reliability of Shipborne Vehicle Layouts

by Han Shi, Nengjian Wang and Qinhui Liu

J. Mar. Sci. Eng. 2026, 14(7), 599; https://doi.org/10.3390/jmse14070599 (registering DOI) - 24 Mar 2026

Abstract

Conventional methods for calculating sortie mission reliability of shipborne vehicle layouts suffer from excessive computational overhead, long runtimes, and large labeled data requirements. To address these limitations, this work proposes a specialized graph neural network architecture tailored for limited-data small-sample scenarios, denoted as the Small-Sample Graph Neural Network (SS-GNN). The proposed SS-GNN integrates multi-relational graph convolutional layers, an adaptive attention weighting mechanism, small-sample regularization techniques, and an uncertainty quantification module to accurately capture the heterogeneous multidimensional dependencies between vehicles. To further improve learning performance under data-scarce conditions, we employ a hybrid training strategy combining meta-learning-based pretraining, contrastive learning for representation enhancement, knowledge distillation, and transfer learning. Experimental results demonstrate that SS-GNN substantially outperforms traditional reliability calculation methods, classical machine learning models, and state-of-the-art GNN baselines across three key dimensions: predictive accuracy, computational efficiency, and generalization robustness, while also providing theoretically grounded uncertainty estimates for all predictions. This work provides both a theoretical foundation and a practical technical framework for shipborne vehicle reliability prediction and offers a generalizable solution for small-sample graph regression tasks in industrial domains. Future work will focus on extending the approach to extremely low-data regimes via specialized few-shot learning algorithms, incorporating dynamic relation modeling for time-varying sortie processes, and integrating domain knowledge graphs to broaden its operational applicability. Full article

(This article belongs to the Section Ocean Engineering)

►▼ Show Figures

Figure 1

27 pages, 8179 KB

Open AccessArticle

DINOv3-PEFT: A Dual-Branch Collaborative Network with Parameter-Efficient Fine-Tuning for Precise Road Segmentation in SAR Imagery

by Debao Chen, Wanlin Yang, Ye Yuan and Juntao Gu

Remote Sens. 2026, 18(7), 973; https://doi.org/10.3390/rs18070973 (registering DOI) - 24 Mar 2026

Abstract

Extracting road networks from Synthetic Aperture Radar (SAR) data represents a core challenge in remote sensing scene analysis, particularly for applications in traffic monitoring and emergency management. The task is complicated by several inherent limitations: speckle noise degrades image quality, geometric distortions arise from the side-looking acquisition geometry, and roads often exhibit weak radiometric separation from surrounding terrain. Traditional processing pipelines and recent single-branch deep learning frameworks have shown insufficient performance when global contextual reasoning and fine-scale spatial detail must both be addressed. This work presents DINOv3-PEFT, a parameter-efficient dual-encoder network designed specifically for SAR road segmentation. The architecture employs two complementary processing streams tailored to SAR characteristics: one stream utilizes adapter-based fine-tuning applied to pre-trained DINOv3 weights (kept frozen), which captures long-distance spatial relationships crucial for maintaining network connectivity despite speckle corruption. The second stream, based on convolutional operations, focuses on extracting localized geometric features that preserve the narrow, elongated structure and sharp boundaries typical of road infrastructure. Feature fusion occurs through the Topological-Geometric Feature Integration (TGFI) Module, which synthesizes multi-scale representations hierarchically. This mechanism proves effective at bridging fragmented road segments and recovering geometric accuracy in scenarios with heavy shadow casting or signal interference. Performance evaluation on the GF-3 satellite dataset across four spatial resolutions (1 m, 3 m, 5 m, and 10 m) demonstrates the proposed method achieves an 82.61% F1-score, a 76.51% IoU, and a 98.08% overall accuracy, all averaged across the four resolutions. When benchmarked against six state-of-the-art methods, DINOv3-PEFT demonstrates substantial improvements in road class segmentation quality and topological connectivity preservation, supporting its robustness for operational SAR road mapping tasks. Full article

(This article belongs to the Special Issue Road Extraction and Distress Assessment by Spaceborne, Airborne and Terrestrial Platforms (Second Edition))

31 pages, 2968 KB

Open AccessArticle

Progressive Multi-View Graph Projection for Robust Unsupervised Domain Adaptation

by Yuze Ding, Yuheng Liang, Ziyun Zhou and Jiefei Cai

Appl. Sci. 2026, 16(7), 3125; https://doi.org/10.3390/app16073125 (registering DOI) - 24 Mar 2026

Abstract

Unsupervised domain adaptation (UDA) remains challenged by an unstable target structure, pseudo-label noise, and heterogeneous transfer difficulty across domains. To address these issues, we propose Progressive Multi-View Graph Projection (PMGP), a two-stage framework that first learns transferable representations via source supervision, domain-adversarial training, and teacher–student consistency and then performs latent-space refinement through multi-view graph construction and projection learning. Specifically, three perturbation-induced views are considered for each sample: the original view, an input-space patch-masked view, and a representation-space feature-dimension masked view. After joint preprocessing with PCA and L2 normalization, PMGP constructs per-view affinity graphs by combining geometric neighborhood relations with pseudo-supervised semantic relations, and applies locality-preserving projection to learn a structure-aware shared subspace. In this subspace, target pseudo-labels are iteratively refined using source prototypes, target class centers, and progressive confidence filtering. Experiments on Office-Home, ImageCLEF-DA, and VisDA-2017 show that PMGP achieves competitive performance and stable behavior across different benchmark settings and backbone architectures. These results indicate that multi-view graph refinement provides an effective and interpretable way to improve target structure estimation and reduce pseudo-label error accumulation in UDA. Full article

►▼ Show Figures

Figure 1

16 pages, 3132 KB

Open AccessArticle

An Integrated Mathematical Model for Ensuring Train Traffic Safety in a Centralised Dispatching System Based on Control Theory, Based on Finite-State Automata

by Sunnatillo T. Boltayev, Bobomurod B. Rakhmonov, Obidjon O. Muhiddinov, Sohibjamol I. Valiyev, Muxammadaziz Y. Xokimjonov, Eldorbek G. Khujamkulov, Sherzod F. Kholboev and Egamberdi Sh Joniqulov

Automation 2026, 7(2), 54; https://doi.org/10.3390/automation7020054 (registering DOI) - 24 Mar 2026

Abstract

This paper presents an integrated mathematical model to improve the safety and operational efficiency of train traffic in centralised railway dispatching systems. The proposed approach combines the alternative graph model with a Mealy automaton to synchronously address route planning, delay minimisation, and strict compliance with safety requirements. Formal control theory based on finite-state automata is employed to describe routing logic and signal control through state transitions, while the alternative graph model represents scheduling constraints and resource conflicts. To enhance real-time adaptability, a tabu search algorithm is implemented for train schedule optimisation, enabling dynamic rescheduling under changing operational conditions. The mathematical formulation incorporates blocking time parameters, a system of discrete constraints, and automaton-based safety conditions governing train movements and route authorisation. The integrated model explicitly formalises the processes of block section occupation and release, ensuring consistency between control logic and scheduling decisions. Practical testing and computational experiments demonstrate that the proposed approach effectively reduces train delays, improves the reliability of dispatch control, and increases system resilience to dynamic disturbances. The results confirm that the developed model can be implemented within existing centralised dispatching infrastructures without requiring a complete system overhaul. Overall, the proposed framework expands the functional capabilities of centralised dispatch systems by enabling efficient schedule generation, minimising the propagation of delays, and ensuring reliable command exchange between central control posts and field-level railway infrastructure. Full article

(This article belongs to the Section Smart Transportation and Autonomous Vehicles)

►▼ Show Figures

Figure 1

23 pages, 11145 KB

Open AccessArticle

DiffLiGS: Diffusion-Guided LiDAR-Enhanced 3D Gaussian Splatting

by Shucheng Gong, Hong Xie, Jiang Song, Longze Zhu and Hongping Zhang

ISPRS Int. J. Geo-Inf. 2026, 15(4), 140; https://doi.org/10.3390/ijgi15040140 - 24 Mar 2026

Abstract

Multi-view 3D reconstruction is essential for smart city, supporting applications such as smart city planning and autonomous navigation. While traditional reconstruction pipelines and recent neural implicit methods, such as NeRF, achieve high visual fidelity, they often struggle with geometric accuracy and sparse-view scenarios. To address this challenge, we present DiffLiGS, a novel multi-modal 3D reconstruction framework that integrates LiDAR point clouds and LiDAR-guided diffusion-based priors into the 3D Gaussian Splatting (3DGS) pipeline, enabling high-fidelity and geometrically accurate models. Our method first densifies sparse LiDAR depths using a diffusion model and refines them through multi-view geometric constraints, producing dense LiDAR depth maps that provide robust supervision for 3DGS optimization. Leveraging these dense depth maps, we guide a Stable Video Diffusion model to synthesize novel view images, which are incorporated into training to enhance reconstruction completeness and visual realism. By jointly fusing rich appearance cues from multi-view images with precise LiDAR-derived geometry and diffusion priors, DiffLiGS achieves unified, geometry-aware 3D scene representations. Our extensive experiments demonstrate that our approach significantly improves both geometric accuracy and rendering quality compared to existing 3D reconstruction methods, enabling real-time, high-precision modeling of complex urban environments. Full article

(This article belongs to the Topic 3D Computer Vision and Smart Building and City, 3rd Edition)

►▼ Show Figures

Figure 1

19 pages, 635 KB

Open AccessArticle

Conformal Prediction for Counterfactual Detection in Concept Learning from Synthetic Visual Patterns

by Ulf Norinder, Stephanie Lowry, Heimo Müller and Andreas Holzinger

Electronics 2026, 15(7), 1346; https://doi.org/10.3390/electronics15071346 - 24 Mar 2026

Abstract

Reliable detection of previously unseen classes under distributional shift remains a central challenge in concept learning and explainable artificial intelligence. In particular, high-performance deep learning models often lack statistically grounded mechanisms to signal when an instance deviates from learned concepts. This paper addresses this limitation by investigating whether conformal prediction can be effectively combined with a YOLOv5 deep learning classifier to enable principled counterfactual detection without prior exposure to the counterfactual class. As a controlled testbed, we employ Kandinsky patterns, a structured benchmark widely used in explainable AI research due to its rule-based generative transparency and suitability for concept learning studies. The proposed framework first classifies valid and invalid patterns and subsequently applies inductive conformal prediction to obtain calibrated prediction sets at a user-defined significance level. Counterfactual instances are, at start, identified based solely on information from known true and false patterns, without explicit training examples of the counterfactual class. Experimental results demonstrate that the conformalized detector reliably identifies a substantial proportion of previously unseen counterfactual patterns while maintaining statistical validity. In addition, the method flags unlabeled (“empty”) instances, thereby providing a principled signal for the emergence of new concepts. By conformalizing YOLOv5 outputs, the approach establishes a statistically sound mechanism for uncertainty-aware detection of divergent classes, contributing to robust and explainable concept learning in structured visual pattern recognition. Full article

(This article belongs to the Special Issue Artificial Intelligence for Smart Image Perception, Recognition and Understanding)

►▼ Show Figures

Figure 1

23 pages, 1010 KB

Open AccessSystematic Review

Racial Disparities in Respiratory Syncytial Virus Vaccination in Pregnant Black Women: A Rapid Literature Review

by Gustavo Gonçalves dos Santos, Débora de Souza Santos, Reginaldo Roque Mafetoni, Clara Fróes de Oliveira Sanfelice, Janize Silva Maia, Karina Franco Zihlmann, Ricardo José Oliveira Mouta, Cindy Ferreira Lima, Patrícia Wottrich Parenti, Joaquim Guerra de Oliveira Neto, Wágnar Silva Morais Nascimento, Telma Maria Evangelista de Araújo, Cesar Henrique Rodrigues Reis, Carolliny Rossi de Faria Ichikawa, Júlia Maria das Neves Carvalho, Ana Cristina Ribeiro da Fonseca Dias, Maria Luísa Santos Bettencourt and Maria João Jacinto Guerra

Women 2026, 6(2), 23; https://doi.org/10.3390/women6020023 - 24 Mar 2026

Abstract

Respiratory Syncytial Virus infection is a significant cause of morbidity and mortality in infants. Maternal vaccination with the bivalent vaccine Abrysvo^® in the third trimester (24–36 weeks) is an effective strategy to prevent severe respiratory illnesses in newborns. However, the introduction of this new technology faces structural obstacles that amplify inequalities. This rapid literature review sought to map and synthesize evidence on inequalities and inequities in adherence and accessibility to maternal vaccination among Black pregnant women. A rapid literature review was conducted using a mixed-methods approach (narrative synthesis and thematic analysis), following guidelines adapted from the Preferred Reporting Items for Systematic Reviews and Meta-Analyses and the Cochrane Handbook. The research question was structured using the acronym Population/Problem, Exposure, Comparison, and Outcome, focusing on Black pregnant women, maternal vaccination, comparison with other groups, and barriers/determinants. The search was conducted in databases such as PubMed (via Medical Literature Analysis and Retrieval System Online), Scopus and Literatura Latino-Americana e do Caribe em Ciências da Saúde, covering studies published between 2022 and 2025 that presented disaggregated analysis by race. The analysis and interpretation of the findings were guided by Critical Race Theory. The analysis of the twelve included studies (mainly from the United States, the United Kingdom, and Brazil) revealed systematic and robust disparities. Black pregnant women had lower vaccination coverage and were less likely to receive timely recommendations compared to White pregnant women. The barriers identified include: institutional distrust (resulting from structural racism), poor access to prenatal care, inadequate communication, and socioeconomic factors. Inequities are structural and multifactorial phenomena. To ensure that the benefits of the vaccine are distributed equitably, strategies such as anti-racist training for healthcare teams, active vaccination outreach, and continuous monitoring of data disaggregated by race are essential. Full article

►▼ Show Figures

Figure 1

24 pages, 9125 KB

Open AccessArticle

Decoupled Dual-Stage Generation to Balance Factuality and Empathy in Customer-Support Dialogue Systems

by Serynn Kim, Hongseok Choi and Jin-Xia Huang

Appl. Sci. 2026, 16(7), 3123; https://doi.org/10.3390/app16073123 - 24 Mar 2026

Abstract

In practical customer-support dialogue systems, responses must simultaneously deliver factually grounded information and context-appropriate empathy, yet existing single-stage generation models often exhibit specialization bias, favoring one objective at the expense of the other. To address this limitation, we propose a dual-stage generation framework that explicitly decouples factual grounding from empathetic modulation. Our primary configuration follows a fact-to-empathy order, in which the system first generates a fact-centric draft via structured query interpretation and optional retrieval-augmented generation, then applies empathy-aware tuning conditioned on inferred emotion type, intensity, and empathy necessity. To enable deployment in resource-constrained environments, only the query interpretation module is explicitly trained using knowledge distillation, allowing the overall system to operate with compact 4B–8B backbone language models. Furthermore, we construct a customer-support dialogue dataset designed to reflect realistic interactions involving both informational and emotional demands. Extensive experiments with compact models show that the proposed approach generally improves key dimensions of empathetic response quality while maintaining overall factual performance, thereby helping mitigate the representational entanglement empirically observed in single-stage baselines. Both quantitative metrics and scenario-based analyses confirm that decoupled generation enables a more balanced integration of factuality and empathy than single-stage generation. These results suggest that dual-stage generation provides a practical and extensible foundation for deployable, real-world customer-support dialogue systems. Full article

(This article belongs to the Section Computing and Artificial Intelligence)

►▼ Show Figures

Figure 1

Show export options Show export options

Select all

Export citation of selected articles as:

Error

Oops... you haven't selected anything for export.

Displaying article 1-50 on page 1 of 1711.

Go to page 1 2 3 4 5

Search Results (85,536)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI