Informatics

17 pages, 306 KB

Open AccessArticle

Negotiating Human–AI Complementarity in Geriatric and Palliative Care: A Qualitative Study of Healthcare Practitioners’ Perspectives in Northeast China

by Chenyang Guo, Chao Fang, Wenbo Zhang and John Troyer

Informatics 2025, 12(4), 120; https://doi.org/10.3390/informatics12040120 - 1 Nov 2025

Viewed by 132

Abstract

Artificial intelligence (AI) is becoming increasingly significant in healthcare around the world, especially in China, where rapid population ageing coincides with rising expectations for quality of life and a shrinking care workforce. This study explores Chinese health practitioners’ perspectives on using AI assistants [...] Read more.

Artificial intelligence (AI) is becoming increasingly significant in healthcare around the world, especially in China, where rapid population ageing coincides with rising expectations for quality of life and a shrinking care workforce. This study explores Chinese health practitioners’ perspectives on using AI assistants in integrated geriatric and palliative care. Drawing on Actor–Network Theory, care is viewed as a network of interconnected human and non-human actors, including practitioners, technologies, patients and policies. Based in Northeast China, a region with structurally marginalised healthcare infrastructure, this article analyses qualitative interviews with 14 practitioners. Our findings reveal three key themes: (1) tensions between AI’s rule-based logic and practitioners’ human-centred approach; (2) ethical discomfort with AI performing intimate or emotionally sensitive care, especially in end-of-life contexts; (3) structural inequalities, with weak policy and infrastructure limiting effective AI integration. The study highlights that AI offers clearer benefits for routine geriatric care, such as monitoring and basic symptom management, but its utility is far more limited in the complex, relational and ethically sensitive domain of palliative care. Proposing a model of human–AI complementarity, the article argues that technology should support rather than replace the emotional and relational aspects of care and identifies policy considerations for ethically grounded integration in resource-limited contexts. Full article

27 pages, 624 KB

Open AccessArticle

Explainable AI for Clinical Decision Support Systems: Literature Review, Key Gaps, and Research Synthesis

by Mozhgan Salimparsa, Kamran Sedig, Daniel J. Lizotte, Sheikh S. Abdullah, Niaz Chalabianloo and Flory T. Muanda

Informatics 2025, 12(4), 119; https://doi.org/10.3390/informatics12040119 - 28 Oct 2025

Viewed by 586

Abstract

While Artificial Intelligence (AI) promises significant enhancements for Clinical Decision Support Systems (CDSSs), the opacity of many AI models remains a major barrier to clinical adoption, primarily due to interpretability and trust challenges. Explainable AI (XAI) seeks to bridge this gap by making [...] Read more.

While Artificial Intelligence (AI) promises significant enhancements for Clinical Decision Support Systems (CDSSs), the opacity of many AI models remains a major barrier to clinical adoption, primarily due to interpretability and trust challenges. Explainable AI (XAI) seeks to bridge this gap by making model reasoning understandable to clinicians, but technical XAI solutions have too often failed to address real-world clinician needs, workflow integration, and usability concerns. This study synthesizes persistent challenges in applying XAI to CDSS—including mismatched explanation methods, suboptimal interface designs, and insufficient evaluation practices—and proposes a structured, user-centered framework to guide more effective and trustworthy XAI-CDSS development. Drawing on a comprehensive literature review, we detail a three-phase framework encompassing user-centered XAI method selection, interface co-design, and iterative evaluation and refinement. We demonstrate its application through a retrospective case study analysis of a published XAI-CDSS for sepsis care. Our synthesis highlights the importance of aligning XAI with clinical workflows, supporting calibrated trust, and deploying robust evaluation methodologies that capture real-world clinician–AI interaction patterns, such as negotiation. The case analysis shows how the framework can systematically identify and address user-centric gaps, leading to better workflow integration, tailored explanations, and more usable interfaces. We conclude that achieving trustworthy and clinically useful XAI-CDSS requires a fundamentally user-centered approach; our framework offers actionable guidance for creating explainable, usable, and trusted AI systems in healthcare. Full article

(This article belongs to the Section Health Informatics)

► Show Figures

Figure 1

17 pages, 4146 KB

Open AccessArticle

Sentiment Analysis of Meme Images Using Deep Neural Network Based on Keypoint Representation

by Endah Asmawati, Ahmad Saikhu and Daniel O. Siahaan

Informatics 2025, 12(4), 118; https://doi.org/10.3390/informatics12040118 - 28 Oct 2025

Viewed by 283

Abstract

Meme image sentiment analysis is a task of examining public opinion based on meme images posted on social media. In various fields, stakeholders often need to quickly and accurately determine the sentiment of memes from large amounts of available data. Therefore, innovation is [...] Read more.

Meme image sentiment analysis is a task of examining public opinion based on meme images posted on social media. In various fields, stakeholders often need to quickly and accurately determine the sentiment of memes from large amounts of available data. Therefore, innovation is needed in image pre-processing so that an increase in performance metrics, especially accuracy, can be obtained in improving the classification of meme image sentiment. This is because sentiment classification using human face datasets yields higher accuracy than using meme images. This research aims to develop a sentiment analysis model for meme images based on key points. The analyzed meme images contain human faces. The facial features extracted using key points are the eyebrows, eyes, and mouth. In the proposed method, key points of facial features are represented in the form of graphs, specifically directed graphs, weighted graphs, or weighted directed graphs. These graph representations of key points are then used to build a sentiment analysis model based on a Deep Neural Network (DNN) with three layers (hidden layer: i = 64, j = 64, k = 90). There are several contributions of this study, namely developing a human facial sentiment detection model using key points, representing key points as various graphs, and constructing a meme dataset with Indonesian text. The proposed model is evaluated using several metrics, namely accuracy, precision, recall, and F-1 score. Furthermore, a comparative analysis is conducted to evaluate the performance of the proposed model against existing approaches. The experimental results show that the proposed model, which utilized the directed graph representation of key points, obtained the highest accuracy at 83% and F1 score at 81%, respectively. Full article

(This article belongs to the Special Issue Practical Applications of Sentiment Analysis)

► Show Figures

Figure 1

34 pages, 8515 KB

Open AccessArticle

Hybrid Approach Using Dynamic Mode Decomposition and Wavelet Scattering Transform for EEG-Based Seizure Classification

by Sreevidya C, Neethu Mohan, Sachin Kumar S and Aravind Harikumar

Informatics 2025, 12(4), 117; https://doi.org/10.3390/informatics12040117 - 28 Oct 2025

Viewed by 337

Abstract

Epilepsy is a brain disorder that affects individuals; hence, preemptive diagnosis is required. Accurate classification of seizures is critical to optimize the treatment of epilepsy. Patients with epilepsy are unable to lead normal lives due to the unpredictable nature of seizures. Thus, developing [...] Read more.

Epilepsy is a brain disorder that affects individuals; hence, preemptive diagnosis is required. Accurate classification of seizures is critical to optimize the treatment of epilepsy. Patients with epilepsy are unable to lead normal lives due to the unpredictable nature of seizures. Thus, developing new methods to help these patients can significantly improve their quality of life and result in huge financial savings for the healthcare industry. This paper presents a hybrid method integrating dynamic mode decomposition (DMD) and wavelet scattering transform (WST) for EEG-based seizure analysis. DMD allows for the breakdown of EEG signals into modes that catch the dynamical structures present in the EEG. Then, WST is applied as it is invariant to time-warping and computes robust hierarchical features at different timescales. DMD-WST combination provides an in-depth multi-scale analysis of the temporal structures present within the EEG data. This process improves the representation quality for feature extraction, which can convey dynamic modes and multi-scale frequency information for improved classification performance. The proposed hybrid approach is validated with three datasets, namely the CHB-MIT PhysioNet dataset, the Bern Barcelona dataset, and the Khas dataset, which can accurately distinguish the seizure and non-seizure states. The proposed method performed classification using different machine learning and deep learning methods, including support vector machine, random forest, k-nearest neighbours, booster algorithm, and bagging. These models were compared in terms of accuracy, precision, sensitivity, Cohen’s kappa, and Matthew’s correlation coefficient. The DMD-WST approach achieved a maximum accuracy of 99% and F1 score of 0.99 on the CHB-MIT dataset, and obtained 100% accuracy and F1 score of 1.00 on both the Bern Barcelona and Khas datasets, outperforming existing methods Full article

► Show Figures

Figure 1

18 pages, 5614 KB

Open AccessArticle

Computational Analysis of Zingiber officinale Identifies GABAergic Signaling as a Potential Therapeutic Mechanism in Colorectal Cancer

by Suthipong Chujan, Nutsira Vajeethaveesin and Jutamaad Satayavivad

Informatics 2025, 12(4), 116; https://doi.org/10.3390/informatics12040116 - 24 Oct 2025

Viewed by 374

Abstract

Colorectal cancer cases are on the rise and have become a leading cause of cancer-related deaths. Ginger (Zingiber officinale) is widely used in traditional herbal medicine and has been proposed as a potential treatment for colorectal cancer. This study aimed to [...] Read more.

Colorectal cancer cases are on the rise and have become a leading cause of cancer-related deaths. Ginger (Zingiber officinale) is widely used in traditional herbal medicine and has been proposed as a potential treatment for colorectal cancer. This study aimed to explore the network pharmacology and pharmacodynamics of ginger in colorectal cancer treatment. Colorectal cancer patient data from the GEO dataset were analyzed to identify differentially expressed genes (DEGs). Six key components of ginger were selected based on specific criteria, and their target proteins were predicted using the TCMSP database. By overlapping DEGs with predicted targets, 36 candidate drug targets were identified. These targets were analyzed for biological alterations, pathway enrichment, protein–protein interactions, and hub-gene selection, integrating network pharmacology. Molecular docking simulations were conducted to confirm the binding interactions between ginger components and target proteins. The findings showed that GABAergic signaling and apoptosis were the most enriched pathways, suggesting their potential role in colorectal cancer treatment. Docking simulations further revealed that ginger’s active compounds bind to COX2 and ESR1, indicating anti-inflammatory effects and modulation of estrogenic activity. This study provides insight into the systemic mechanisms of ginger in colorectal cancer treatment through an integrated “drug–gene–pathway–disease” network approach. Full article

► Show Figures

Figure 1

24 pages, 5556 KB

Open AccessArticle

Efficient Wearable Sensor-Based Activity Recognition for Human–Robot Collaboration in Agricultural Environments

by Sakorn Mekruksavanich and Anuchit Jitpattanakul

Informatics 2025, 12(4), 115; https://doi.org/10.3390/informatics12040115 - 23 Oct 2025

Viewed by 372

Abstract

This study focuses on human awareness, a critical component in human–robot interaction, particularly within agricultural environments where interactions are enriched by complex contextual information. The main objective is identifying human activities occurring during collaborative harvesting tasks involving humans and robots. To achieve this, [...] Read more.

This study focuses on human awareness, a critical component in human–robot interaction, particularly within agricultural environments where interactions are enriched by complex contextual information. The main objective is identifying human activities occurring during collaborative harvesting tasks involving humans and robots. To achieve this, we propose a novel and lightweight deep learning model, named 1D-ResNeXt, designed explicitly for recognizing activities in agriculture-related human–robot collaboration. The model is built as an end-to-end architecture incorporating feature fusion and a multi-kernel convolutional block strategy. It utilizes residual connections and a split–transform–merge mechanism to mitigate performance degradation and reduce model complexity by limiting the number of trainable parameters. Sensor data were collected from twenty individuals with five wearable devices placed on different body parts. Each sensor was embedded with tri-axial accelerometers, gyroscopes, and magnetometers. Under real field conditions, the participants performed several sub-tasks commonly associated with agricultural labor, such as lifting and carrying loads. Before classification, the raw sensor signals were pre-processed to eliminate noise. The cleaned time-series data were then input into the proposed deep learning network for sequential pattern recognition. Experimental results showed that the chest-mounted sensor achieved the highest F1-score of 99.86%, outperforming other sensor placements and combinations. An analysis of temporal window sizes (0.5, 1.0, 1.5, and 2.0 s) demonstrated that the 0.5 s window provided the best recognition performance, indicating that key activity features in agriculture can be captured over short intervals. Moreover, a comprehensive evaluation of sensor modalities revealed that multimodal fusion of accelerometer, gyroscope, and magnetometer data yielded the best accuracy at 99.92%. The combination of accelerometer and gyroscope data offered an optimal compromise, achieving 99.49% accuracy while maintaining lower system complexity. These findings highlight the importance of strategic sensor placement and data fusion in enhancing activity recognition performance while reducing the need for extensive data and computational resources. This work contributes to developing intelligent, efficient, and adaptive collaborative systems, offering promising applications in agriculture and beyond, with improved safety, cost-efficiency, and real-time operational capability. Full article

► Show Figures

Figure 1

18 pages, 1914 KB

Open AccessArticle

Leveraging Transformer with Self-Attention for Multi-Label Emotion Classification in Crisis Tweets

by Patricia Anthony and Jing Zhou

Informatics 2025, 12(4), 114; https://doi.org/10.3390/informatics12040114 - 22 Oct 2025

Viewed by 482

Abstract

Social media platforms have become a widely used medium for individuals to express complex and multifaceted emotions. Traditional single-label emotion classification methods fall short in accurately capturing the simultaneous presence of multiple emotions within these texts. To address this limitation, we propose a [...] Read more.

Social media platforms have become a widely used medium for individuals to express complex and multifaceted emotions. Traditional single-label emotion classification methods fall short in accurately capturing the simultaneous presence of multiple emotions within these texts. To address this limitation, we propose a classification model that enhances the pre-trained Cardiff NLP transformer by integrating additional self-attention layers. Experimental results show our approach achieves a micro-F1 score of 0.7208, a macro-F1 score of 0.6192, and an average Jaccard index of 0.6066, which is an overall improvement of approximately 3.00% compared to the baseline. We apply this model to a real-world dataset of tweets related to the 2011 Christchurch earthquakes as a case study to demonstrate its ability to capture multi-category emotional expressions and detect co-occurring emotions that single-label approaches would miss. Our analysis revealed distinct emotional patterns aligned with key seismic events, including overlapping positive and negative emotions, and temporal dynamics of emotional response. This work contributes a robust method for fine-grained emotion analysis which can aid disaster response, mental health monitoring and social research. Full article

(This article belongs to the Special Issue Practical Applications of Sentiment Analysis)

► Show Figures

Figure 1

22 pages, 956 KB

Open AccessSystematic Review

Tailoring Treatment in the Age of AI: A Systematic Review of Large Language Models in Personalized Healthcare

by Giordano de Pinho Souza, Glaucia Melo and Daniel Schneider

Informatics 2025, 12(4), 113; https://doi.org/10.3390/informatics12040113 - 21 Oct 2025

Viewed by 461

Abstract

Large Language Models (LLMs) are increasingly proposed to personalize healthcare delivery, yet their real-world readiness remains uncertain. We conducted a systematic literature review to assess how LLM-based systems are designed and used to enhance patient engagement and personalization, while identifying open challenges these [...] Read more.

Large Language Models (LLMs) are increasingly proposed to personalize healthcare delivery, yet their real-world readiness remains uncertain. We conducted a systematic literature review to assess how LLM-based systems are designed and used to enhance patient engagement and personalization, while identifying open challenges these tools pose. Four digital libraries (Scopus, IEEE Xplore, ACM, and Nature) were searched, yielding 3787 studies; 16 met the inclusion criteria. Most studies, published in 2024, span different types of motivations, architectures, limitations and privacy-preserving approaches. While LLMs show potential in automating patient data collection, recommendation/therapy generation, and continuous conversational support, their clinical reliability is limited. Most evaluations use synthetic or retrospective data, with only a few employing user studies or scalable simulation environments. This review highlights the tension between innovation and clinical applicability, emphasizing the need for robust evaluation protocols and human-in-the-loop systems to guide the safe and equitable deployment of LLMs in healthcare. Full article

(This article belongs to the Section Health Informatics)

► Show Figures

Figure 1

19 pages, 4399 KB

Open AccessArticle

Privacy-Preserving Synthetic Mammograms: A Generative Model Approach to Privacy-Preserving Breast Imaging Datasets

by Damir Shodiev, Egor Ushakov, Arsenii Litvinov and Yury Markin

Informatics 2025, 12(4), 112; https://doi.org/10.3390/informatics12040112 - 18 Oct 2025

Viewed by 496

Abstract

Background: Significant progress has been made in the field of machine learning, enabling the development of methods for automatic interpretation of medical images that provide high-quality diagnostics. However, most of these methods require access to confidential data, making them difficult to apply under [...] Read more.

Background: Significant progress has been made in the field of machine learning, enabling the development of methods for automatic interpretation of medical images that provide high-quality diagnostics. However, most of these methods require access to confidential data, making them difficult to apply under strict privacy requirements. Existing privacy-preserving approaches, such as federated learning and dataset distillation, have limitations related to data access, visual interpretability, etc. Methods: This study explores the use of generative models to create synthetic medical data that preserves the statistical properties of the original data while ensuring privacy. The research is carried out on the VinDr-Mammo dataset of digital mammography images. A conditional generative method using Latent Diffusion Models (LDMs) is proposed with conditioning on diagnostic labels and lesion information. Diagnostic utility and privacy robustness are assessed via cancer classification tasks and re-identification tasks using Siamese neural networks and membership inference. Results: The generated synthetic data achieved a Fréchet Inception Distance (FID) of 5.8, preserving diagnostic features. A model trained solely on synthetic data achieved comparable performance to one trained on real data (ROC-AUC: 0.77 vs. 0.82). Visual assessments showed that synthetic images are indistinguishable from real ones. Privacy evaluations demonstrated a low re-identification risk (e.g., mAP@R = 0.0051 on the test set), confirming the effectiveness of the privacy-preserving approach. Conclusions: The study demonstrates that privacy-preserving generative models can produce synthetic medical images with sufficient quality for diagnostic task while significantly reducing the risk of patient re-identification. This approach enables secure data sharing and model training in privacy-sensitive domains such as medical imaging. Full article

(This article belongs to the Special Issue Health Data Management in the Age of AI)

► Show Figures

Figure 1

26 pages, 10529 KB

Open AccessSystematic Review

Ethics of the Use of Artificial Intelligence in Academia and Research: The Most Relevant Approaches, Challenges and Topics

by Joe Llerena-Izquierdo and Raquel Ayala-Carabajo

Informatics 2025, 12(4), 111; https://doi.org/10.3390/informatics12040111 - 13 Oct 2025

Viewed by 1270

Abstract

The widespread integration of artificial intelligence into university academic activity requires responsibly addressing the ethical challenges it poses. This study critically analyses these challenges, identifying opportunities and risks in various academic disciplines and practices. A systematic review was conducted using the PRISMA method [...] Read more.

The widespread integration of artificial intelligence into university academic activity requires responsibly addressing the ethical challenges it poses. This study critically analyses these challenges, identifying opportunities and risks in various academic disciplines and practices. A systematic review was conducted using the PRISMA method of publications from January 2024 to January 2025. Based on the selected works (n = 60), through a systematic and rigorous examination, this study identifies ethical challenges in teaching and research; opportunities and risks of its integration into academic practice; specific artificial intelligence tools categorised according to study approach; and a contribution to the current debate, providing criteria and practical guidelines for academics. In conclusion, it can be stated that the integration of AI offers significant opportunities, such as the optimisation of research and personalised learning, as well as notable human and ethical risks, including the loss of critical thinking, technological dependence, and the homogenisation of ideas. It is essential to adopt a conscious approach, with clear guidelines that promote human supervision, ensuring that AI acts as a tool for improvement rather than for the replacement of intelligent human performance, and that it supports human action and discernment in the creation of knowledge. Full article

► Show Figures

Figure 1

24 pages, 1212 KB

Open AccessArticle

Heart Attack Risk Prediction via Stacked Ensemble Metamodeling: A Machine Learning Framework for Real-Time Clinical Decision Support

by Brandon N. Nava-Martinez, Sahid S. Hernandez-Hernandez, Denzel A. Rodriguez-Ramirez, Jose L. Martinez-Rodriguez, Ana B. Rios-Alvarado, Alan Diaz-Manriquez, Jose R. Martinez-Angulo and Tania Y. Guerrero-Melendez

Informatics 2025, 12(4), 110; https://doi.org/10.3390/informatics12040110 - 11 Oct 2025

Viewed by 602

Abstract

Cardiovascular diseases claim millions of lives each year, yet timely diagnosis remains a significant challenge due to the high number of patients and associated costs. Although various machine learning solutions have been proposed for this problem, most approaches rely on careful data preprocessing [...] Read more.

Cardiovascular diseases claim millions of lives each year, yet timely diagnosis remains a significant challenge due to the high number of patients and associated costs. Although various machine learning solutions have been proposed for this problem, most approaches rely on careful data preprocessing and feature engineering workflows that could benefit from more comprehensive documentation in research publications. To address this issue, this paper presents a machine learning framework for predicting heart attack risk online. Our systematic methodology integrates a unified pipeline featuring advanced data preprocessing, optimized feature selection, and an exhaustive hyperparameter search using cross-validated grid evaluation. We employ a metamodel ensemble strategy, testing and combining six traditional supervised models along with six stacking and voting ensemble models. The proposed system achieves accuracies ranging from 90.2% to 98.9% on three independent clinical datasets, outperforming current state-of-the-art methods. Additionally, it powers a deployable, lightweight web application for real-time decision support. By merging cutting-edge AI with clinical usability, this work offers a scalable solution for early intervention in cardiovascular care. Full article

(This article belongs to the Special Issue Health Data Management in the Age of AI)

► Show Figures

Figure 1

22 pages, 618 KB

Open AccessArticle

Comparison of Ensemble and Meta-Ensemble Models for Early Risk Prediction of Acute Myocardial Infarction

by Daniel Cristóbal Andrade-Girón, Juana Sandivar-Rosas, William Joel Marin-Rodriguez, Marcelo Gumercindo Zúñiga-Rojas, Abrahán Cesar Neri-Ayala and Ernesto Díaz-Ronceros

Informatics 2025, 12(4), 109; https://doi.org/10.3390/informatics12040109 - 11 Oct 2025

Viewed by 480

Abstract

Cardiovascular disease (CVD) is a major cause of mortality around the world. This underscores the critical need to implement effective predictive tools to inform clinical decision-making. This study aimed to compare the predictive performance of ensemble learning algorithms, including Bagging, Random Forest, Extra [...] Read more.

Cardiovascular disease (CVD) is a major cause of mortality around the world. This underscores the critical need to implement effective predictive tools to inform clinical decision-making. This study aimed to compare the predictive performance of ensemble learning algorithms, including Bagging, Random Forest, Extra Trees, Gradient Boosting, and AdaBoost, when applied to a clinical dataset comprising patients with CVD. The methodology entailed data preprocessing and cross-validation to regulate generalization. The performance of the model was evaluated using a variety of metrics, including accuracy, F1 score, precision, recall, Cohen’s Kappa, and area under the curve (AUC). Among the models evaluated, Bagging demonstrated the best overall performance (accuracy ± SD: 93.36% ± 0.22; F1 score: 0.936; AUC: 0.9686). It also reached the lowest average rank (1.0) in Friedman test and was placed, together with Extra Trees (accuracy ± SD: 90.76% ± 0.18; F1 score: 0.916; AUC: 0.9689), in the superior statistical group (group A) according to Nemenyi post hoc test. The two models demonstrated a high degree of agreement with the actual labels (Kappa: 0.87 and 0.83, respectively), thereby substantiating their reliability in authentic clinical contexts. The findings substantiated the preeminence of aggregation-based ensemble methods in terms of accuracy, stability, and concordance. This underscored the prominence of Bagging and Extra Trees as optimal candidates for cardiovascular diagnostic support systems, where reliability and generalization were paramount. Full article

► Show Figures

Figure 1

30 pages, 706 KB

Open AccessReview

A Review on Scholarly Publication Recommender Systems: Features, Approaches, Evaluation, and Open Research Directions

by Anita Khadka and Saurav Sthapit

Informatics 2025, 12(4), 108; https://doi.org/10.3390/informatics12040108 - 10 Oct 2025

Viewed by 551

Abstract

The exponential growth of scientific literature has made it increasingly difficult for researchers to identify relevant and timely publications within vast academic digital libraries. Although academic search engines, reference management tools, and recommender systems have evolved, many still rely heavily on metadata and [...] Read more.

The exponential growth of scientific literature has made it increasingly difficult for researchers to identify relevant and timely publications within vast academic digital libraries. Although academic search engines, reference management tools, and recommender systems have evolved, many still rely heavily on metadata and lack mechanisms to incorporate full-text content or time-awareness. This review systematically examines the landscape of scholarly publication recommender systems, employing the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) methodology for a comprehensive and transparent selection of relevant studies. We highlight the limitations of current systems and explore the potential of integrating fine-grained citation knowledge—such as citation proximity, context, section, graph, and intention—extracted from full-text documents. These elements have shown promise in enhancing both the contextual relevance and recency of recommendations. Our findings highlight the importance of moving beyond accuracy-focused metrics toward user-centric evaluations that emphasise novelty, diversity, and serendipity. This paper advocates for the development of more holistic and adaptive recommender systems that better align with the evolving needs of researchers. Full article

► Show Figures

Figure 1

46 pages, 7346 KB

Open AccessReview

Integrating Speech Recognition into Intelligent Information Systems: From Statistical Models to Deep Learning

by Chaoji Wu, Yi Pan, Haipan Wu and Lei Ning

Informatics 2025, 12(4), 107; https://doi.org/10.3390/informatics12040107 - 4 Oct 2025

Viewed by 1163

Abstract

Automatic speech recognition (ASR) has advanced rapidly, evolving from early template-matching systems to modern deep learning frameworks. This review systematically traces ASR’s technological evolution across four phases: the template-based era, statistical modeling approaches, the deep learning revolution, and the emergence of large-scale models [...] Read more.

Automatic speech recognition (ASR) has advanced rapidly, evolving from early template-matching systems to modern deep learning frameworks. This review systematically traces ASR’s technological evolution across four phases: the template-based era, statistical modeling approaches, the deep learning revolution, and the emergence of large-scale models under diverse learning paradigms. We analyze core technologies such as hidden Markov models (HMMs), Gaussian mixture models (GMMs), recurrent neural networks (RNNs), and recent architectures including Transformer-based models and Wav2Vec 2.0. Beyond algorithmic development, we examine how ASR integrates into intelligent information systems, analyzing real-world applications in healthcare, education, smart homes, enterprise systems, and automotive domains with attention to deployment considerations and system design. We also address persistent challenges—noise robustness, low-resource adaptation, and deployment efficiency—while exploring emerging solutions such as multimodal fusion, privacy-preserving modeling, and lightweight architectures. Finally, we outline future research directions to guide the development of robust, scalable, and intelligent ASR systems for complex, evolving environments. Full article

(This article belongs to the Section Machine Learning)

► Show Figures

Figure 1

31 pages, 2508 KB

Open AccessSystematic Review

From Mammogram Analysis to Clinical Integration with Deep Learning in Breast Cancer Diagnosis

by Beibit Abdikenov, Tomiris Zhaksylyk, Aruzhan Imasheva and Dimash Rakishev

Informatics 2025, 12(4), 106; https://doi.org/10.3390/informatics12040106 - 2 Oct 2025

Viewed by 799

Abstract

Breast cancer is one of the main causes of cancer-related death for women worldwide, and enhancing patient outcomes still depends on early detection. The most common imaging technique for diagnosing and screening for breast cancer is mammography, which has a high potential for [...] Read more.

Breast cancer is one of the main causes of cancer-related death for women worldwide, and enhancing patient outcomes still depends on early detection. The most common imaging technique for diagnosing and screening for breast cancer is mammography, which has a high potential for early lesion detection. With an emphasis on the incorporation of deep learning (DL) techniques, this review examines the changing role of mammography in early breast cancer detection. We examine recent advancements in DL-based approaches for mammogram analysis, including tasks such as classification, segmentation, and lesion detection. Additionally, we assess the limitations of traditional mammographic methods and highlight how DL can enhance diagnostic accuracy, reduce false positives and negatives, and support clinical decision-making. The review emphasizes the potential of DL to assist radiologists in clinical decision-making, as well as increases in diagnostic accuracy and decreases in false positives and negatives. We also discuss issues like interpretability, generalization across populations, and data scarcity. This review summarizes the available data to highlight the revolutionary potential of DL-enhanced mammography in breast cancer screening and to suggest future research avenues for more reliable, transparent, and clinically useful AI-driven solutions. Full article

(This article belongs to the Section Medical and Clinical Informatics)

► Show Figures

Figure 1

15 pages, 1072 KB

Open AccessArticle

Balancing Layout Space and Risk Comprehension in Health Communication: A Comparison of Separated and Integrated Icon Arrays

by Li-Jen Wang and Meng-Cong Zheng

Informatics 2025, 12(4), 105; https://doi.org/10.3390/informatics12040105 - 30 Sep 2025

Viewed by 728

Abstract

This study investigated how icon array layouts influence comprehension of medical risk information, particularly in relation to users’ cognitive abilities. In a within-subjects experiment (N = 121), participants reviewed clinical scenarios with treatment-related risks and side effect risks displayed in either separated or [...] Read more.

This study investigated how icon array layouts influence comprehension of medical risk information, particularly in relation to users’ cognitive abilities. In a within-subjects experiment (N = 121), participants reviewed clinical scenarios with treatment-related risks and side effect risks displayed in either separated or integrated icon arrays. Comprehension was significantly higher for separated treatment-related risk layouts (p < 0.001), while side effect layout showed no effect. Numeracy and graph literacy significantly predicted comprehension. Crucially, individuals with lower numeracy showed marked gains when viewing separated formats, whereas those with higher numeracy performed well regardless of layout. Despite this, participants preferred hybrid formats—separated treatment-related risk with integrated side effect risks—revealing a critical preference–performance gap. By demonstrating how visual layout interacts with user abilities, this study provides actionable guidance for patient decision aid design. The findings show that comprehension accuracy must take precedence over layout compactness and user preference, with separated layouts recommended for treatment-related risks—especially for individuals with lower numeracy—and greater flexibility allowed for side effect risks when space is limited. Full article

► Show Figures

Figure 1

26 pages, 6045 KB

Open AccessArticle

Democratization of Virtual Production: Usability Analysis of Three Solutions with Different Levels of Complexity: Professional, Educational and Cloud-Based

by Roi Méndez-Fernández, Rocío del Pilar Sosa-Fernández, Fátima Fernández-Ledo and Enrique Castelló-Mayo

Informatics 2025, 12(4), 104; https://doi.org/10.3390/informatics12040104 - 30 Sep 2025

Viewed by 632

Abstract

The technical and technological advances of recent years in the field of real-time photorealistic rendering have enabled enormous development in virtual production. However, the democratization of this technology faces two main obstacles: the high economic cost of implementation and the high complexity of [...] Read more.

The technical and technological advances of recent years in the field of real-time photorealistic rendering have enabled enormous development in virtual production. However, the democratization of this technology faces two main obstacles: the high economic cost of implementation and the high complexity of the necessary software. This paper studies three virtual production software solutions that represent different stages in the democratization process of the technology, ranging from the professional software InfinitySet, to the more generalist and educational environment Edison, and to the cloud version of this same software, Edison OnCloud. To this end, an analysis of their functionalities and interfaces is conducted, the SUS questionnaire is applied, and the three systems are evaluated from the perspective of Nielsen’s usability principles. These tests demonstrate the complexity of the professional software InfinitySet, making it unapproachable for non-expert users without extensive previous training. On the other hand, both Edison and Edison OnCloud show significant usability improvements through limiting and reducing functionalities, which also results in a reduction in implementation costs, making the use of the technology feasible in non-professional environments, such as in education or for streamers. Full article

(This article belongs to the Section Human-Computer Interaction)

► Show Figures

Figure 1

30 pages, 2218 KB

Open AccessArticle

OntoCaimer: An Ontology Designed to Support Alzheimer’s Patient Care Systems

by Laura Daniela Lasso-Arcinegas, César Jesús Pardo-Calvache and Mauro Callejas-Cuervo

Informatics 2025, 12(4), 103; https://doi.org/10.3390/informatics12040103 - 25 Sep 2025

Viewed by 585

Abstract

Caring for Alzheimer’s patients presents significant global challenges due to complex symptoms and the constant demand for care, which are further complicated by fragmented information and a lack of explicit integration between physical and computational worlds in existing support systems. This article details [...] Read more.

Caring for Alzheimer’s patients presents significant global challenges due to complex symptoms and the constant demand for care, which are further complicated by fragmented information and a lack of explicit integration between physical and computational worlds in existing support systems. This article details the construction and validation of OntoCaimer, an ontology designed to support Alzheimer’s patient care systems by acting as a comprehensive knowledge base that integrates disease recommendations with concepts from the physical world (sensors and actuators). Utilizing METHONTOLOGY and REFSENO formalisms, OntoCaimer was built as a modular ontology. Its validation through the FOCA method demonstrated a high quality score

(\hat{μ} = 0.99)

, confirming its robustness and suitability. Case studies showcased its functionality in automating recommendations, such as managing patient locations or environmental conditions, to provide proactive support. The main contribution of this work is OntoCaimer, a novel ontology that formally integrates clinical recommendations for Alzheimer’s care with concepts from cyber-physical systems (sensors and actuators). Its scientific novelty lies in bridging the gap between virtual knowledge and physical action, enabling direct and automated interventions in the patient’s environment. This approach significantly advances patient care systems beyond traditional monitoring and alerts, offering a tangible path to reducing caregiver burden. Full article

► Show Figures

Figure 1

14 pages, 2125 KB

Open AccessArticle

A Self-Configurable IoT-Based Monitoring Approach for Environmental Variables in Rotational Grazing Systems

by Rodrigo Garcia, Mario Macea, Samir Castaño and Pedro Guevara

Informatics 2025, 12(4), 102; https://doi.org/10.3390/informatics12040102 - 24 Sep 2025

Viewed by 648

Abstract

Shaded resting zones in rotational grazing systems are prone to thermal stress due to limited ventilation and the congregation of animals during peak heat periods. Addressing these challenges requires sensing solutions that are not only accurate but also capable of adapting to dynamic [...] Read more.

Shaded resting zones in rotational grazing systems are prone to thermal stress due to limited ventilation and the congregation of animals during peak heat periods. Addressing these challenges requires sensing solutions that are not only accurate but also capable of adapting to dynamic environmental conditions and energy constraints. In this context, we present the development and simulation-based validation of a self-configurable IoT protocol for adaptive environmental monitoring. The approach integrates embedded machine learning, specifically a Random Forest classifier, to detect critical conditions using synthetic data of temperature, humidity, and CO₂. The model achieved an accuracy of 98%, with a precision of 98%, recall of 85%, and F1-score of 91% in identifying critical states. These results demonstrate the feasibility of embedding adaptive intelligence into IoT-based monitoring solutions. The protocol is conceived as a foundation for integration into physical devices and subsequent evaluation in farm environments such as rotational grazing systems. Full article

► Show Figures

Figure 1

24 pages, 5836 KB

Open AccessArticle

Methodology for Digitalizing Railway Vehicle Maintenance Training Using Augmented Reality

by Hwi-Jin Kwon, Ji-Hun Song, Kyung-Suk Kim and Chul-Su Kim

Informatics 2025, 12(4), 101; https://doi.org/10.3390/informatics12040101 - 23 Sep 2025

Viewed by 696

Abstract

The axle box of a railway vehicle is a critical component, and its maintenance involves complex procedures that are difficult to convey with traditional, document-based manuals. To address these challenges, augmented reality (AR)-based educational content was developed to digitize maintenance training and enhance [...] Read more.

The axle box of a railway vehicle is a critical component, and its maintenance involves complex procedures that are difficult to convey with traditional, document-based manuals. To address these challenges, augmented reality (AR)-based educational content was developed to digitize maintenance training and enhance its effectiveness. The content’s implementation was guided by a systematic storyboard, which was based on interviews with skilled staff. It also utilized specialized algorithms to improve the accuracy of mechanical measurement work and the efficiency of User Interface (UI) generation. The user experience of the developed content was comprehensively evaluated using a combination of two methods: a formative evaluation through direct observation of work performance and a post-survey administered to 40 participants. As a result of the evaluation, the mean work success rate was 62.5%, demonstrating the content’s high efficiency as a training tool. The overall mean score from the post-survey was 4.11, indicating high user satisfaction and perceived usefulness. A one-way ANOVA was performed and revealed a statistically significant difference in post-survey scores among the four age groups. The developed content was found to be more effective for younger participants. The results confirm the high potential of AR as a digital educational method for complex maintenance work. Full article

(This article belongs to the Special Issue Real-World Applications and Prototyping of Information Systems for Extended Reality (VR, AR, and MR))

► Show Figures

Figure 1

Journal Menu

Journal Browser

Informatics, Volume 12, Issue 4 (December 2025) – 20 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI