Journal of healthcare informatics research最新文献

{"title":"Imputation Free Deep Survival Prediction with Conditional Variational Autoencoders.","authors":"Natalia Hong, Aditya Acharya, Krishna Gokhale, Jenny Cooper, Charles Gadd, Francesca Crowe, Krishnarajah Nirantharakumar, Christopher Yau","doi":"10.1007/s41666-026-00234-y","DOIUrl":"10.1007/s41666-026-00234-y","url":null,"abstract":"<p><p>Electronic Health Records (EHRs) provide rich opportunities for developing risk prediction tools to support clinical decision-making, yet they are inherently incomplete because data are recorded selectively during routine care. Such missingness may be informative, reflecting clinical judgment and patient status, and missing data patterns can shift between model development and real-world deployment. These challenges limit the reliability and transportability of predictive models in healthcare settings. We propose an imputation-free framework that jointly trains Conditional Variational Autoencoders with deep survival models to enable risk prediction directly from incomplete EHR data. We demonstrate the approach using the deep survival model DeSurv and evaluate its performance through simulation studies and two retrospective cohorts from the Clinical Practice Research Datalink primary care database. The proposed framework consistently outperforms conventional missing data methods, achieving superior performance on ground-truth metrics in simulations and improved calibration-based survival metrics in real-world cohorts. It also demonstrates increased robustness to unseen missingness patterns and distributional shifts. By providing a unified strategy for handling missing data across development, validation, and deployment, this work advances methodological robustness in healthcare informatics and supports more reliable clinical risk prediction in practice.</p><p><strong>Supplementary information: </strong>The online version contains supplementary material available at 10.1007/s41666-026-00234-y.</p>","PeriodicalId":101413,"journal":{"name":"Journal of healthcare informatics research","volume":"10 2","pages":"275-298"},"PeriodicalIF":4.6,"publicationDate":"2026-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13156366/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147871160","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Identifying Alzheimer's Disease Progression Subphenotypes Via a Graph-based Framework Using Electronic Health Records.","authors":"Yu Huang, Jie Xu, Zhengkang Fan, Yu Hu, Xing He, Aokun Chen, Yuxi Liu, Rui Yin, Jingchuan Guo, Steven T DeKosky, Michael Jaffee, Manqi Zhou, Chang Su, Fei Wang, Yi Guo, Jiang Bian","doi":"10.1007/s41666-026-00230-2","DOIUrl":"10.1007/s41666-026-00230-2","url":null,"abstract":"<p><p>Understanding the heterogeneity of neurodegeneration in Alzheimer's disease (AD) and identifying distinct progression pathways is critical for improving diagnosis, treatment, prognosis, and prevention. Motivated by this need, this study aimed to identify disease progression subphenotypes among patients with mild cognitive impairment (MCI) and AD using electronic health records (EHRs). We developed a novel approach that combines a graph neural network (GNN)-based framework with time series clustering to characterize progression subphenotypes from MCI to AD. We applied the proposed framework to a real-world cohort of 2,525 patients (61.66% female; mean age 76 years), of whom 64.83% were Non-Hispanic White, 16.48% Non-Hispanic Black, 2.53% were of other races, and 10.85% were Hispanic. Our model identified four distinct progression subphenotypes, each exhibiting characteristic clinical patterns, with average MCI-to-AD progression times ranging from 805 to 1,236 days. These findings indicate that AD does not follow a uniform progression trajectory but instead manifests heterogeneous pathways, and the proposed framework provides an explainable, data-driven approach for delineating AD progression subphenotypes, offering actionable insights for healthcare informatics research and the clinical management of patients at risk for AD.</p>","PeriodicalId":101413,"journal":{"name":"Journal of healthcare informatics research","volume":" ","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13128099/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147825516","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Scoping Review of Synthetic Data Generation by Language Models in Biomedical Research and Application: Data Utility and Quality Perspectives.","authors":"Hanshu Rao, Weisi Liu, Haohan Wang, I-Chan Huang, Zhe He, Xiaolei Huang","doi":"10.1007/s41666-026-00229-9","DOIUrl":"10.1007/s41666-026-00229-9","url":null,"abstract":"<p><p>Synthetic data generation using large language models (LLMs) demonstrates substantial promise in addressing biomedical data challenges and shows increasing adoption in biomedical research. This study systematically reviews recent advances in synthetic data generation for biomedical applications and clinical research, focusing on how LLMs address data scarcity, utility, and quality issues with different modalities. We conducted a scoping review following PRISMA-ScR guidelines and searched literature published between 2020 and 2025 through PubMed, ACM, Web of Science, and Google Scholar. A total of 59 studies were included based on relevance to synthetic data generation in biomedical contexts. Among the reviewed studies, the predominant data modalities were unstructured texts (78.0%), tabular data (13.6%), and multimodal sources (8.4%). Common generation methods included LLM prompting (74.6%), fine-tuning (20.3%), and specialized models (5.1%). Evaluations were heterogeneous: intrinsic metrics (27.1%), human-in-the-loop assessments (44.1%), and LLM-based evaluations (13.6%). However, limitations and key barriers persist in data modalities, domain utility, resource and model accessibility, and standardized evaluation protocols. Future efforts may focus on developing standardized, transparent evaluation frameworks and expanding accessibility to support effective applications in biomedical research.</p><p><strong>Supplementary information: </strong>The online version contains supplementary material available at 10.1007/s41666-026-00229-9.</p>","PeriodicalId":101413,"journal":{"name":"Journal of healthcare informatics research","volume":"10 2","pages":"367-392"},"PeriodicalIF":4.6,"publicationDate":"2026-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13156355/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147871218","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Susceptibility of Large Language Models to User-Driven Factors in Medical Queries.","authors":"Kyung Ho Lim, Ujin Kang, Xiang Li, Jin Sung Kim, Young-Chul Jung, Sangjoon Park, Byung-Hoon Kim","doi":"10.1007/s41666-025-00218-4","DOIUrl":"10.1007/s41666-025-00218-4","url":null,"abstract":"<p><p>Large language models (LLMs) are increasingly used in healthcare; however, their reliability is shaped not only by model design but also by how queries are phrased and how complete the information is. This study assesses how user-driven factors, including misinformation framing, source authority, model personas, and omission of critical clinical details, influence the diagnostic accuracy and reliability of LLM-generated medical responses. Utilizing two public datasets (MedQA and Medbullets), we conducted two tests: (1) perturbation-evaluating LLM persona (assistant vs. expert AI), misinformation source authority (inexperienced vs. expert), and tone (assertive vs. hedged); and (2) ablation-omission of key clinical data. Proprietary LLMs (GPT-4o (OpenAI), Claude-3·5 Sonnet (Anthropic), Claude-3·5 Haiku (Anthropic), Gemini-1·5 Pro (Google), Gemini-1·5 Flash (Google)) and open-source LLMs (LLaMA-3 8B, LLaMA-3 Med42 8B, DeepSeek-R1 8B) were used for evaluation. Results show that in the perturbation test, all LLMs were susceptible to user-driven misinformation, with an assertive tone exerting the strongest overall impact, while proprietary models were more vulnerable to strong or authoritative misinformation. In the ablation test, omitting physical examination findings and laboratory results caused the largest accuracy decline. Proprietary models achieved higher baseline accuracy but demonstrated sharper performance drops under biased or incomplete input. These findings highlight that structured prompts and a complete clinical context are essential for accurate responses. Users should avoid authoritative misinformation framing and provide a complete clinical context, especially for complex and challenging queries. By clarifying the impact of user-driven biases, this study contributes insights to the safe integration of LLMs into healthcare practice.</p><p><strong>Supplementary information: </strong>The online version contains supplementary material available at 10.1007/s41666-025-00218-4.</p>","PeriodicalId":101413,"journal":{"name":"Journal of healthcare informatics research","volume":"10 2","pages":"498-522"},"PeriodicalIF":4.6,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13156382/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147871165","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Towards Accurate and Reliable ICU Outcome Prediction: A Multimodal Learning Framework Based on Belief Function Theory using Structured EHRs and Free-Text Notes.","authors":"Yucheng Ruan, Daniel J Tan, See-Kiong Ng, Ling Huang, Mengling Feng","doi":"10.1007/s41666-025-00219-3","DOIUrl":"10.1007/s41666-025-00219-3","url":null,"abstract":"<p><p>Accurate Intensive Care Unit (ICU) outcome prediction is critical for improving patient treatment quality and ICU resource allocation. Existing research mainly focuses on structured data, e.g. demographics and vital signs, and lacks effective frameworks to integrate clinical notes from heterogeneous electronic health records (EHRs). This study aims to explore a multimodal framework based on belief function theory that can effectively fuse heterogeneous structured EHRs and free-text notes for accurate and reliable ICU outcome prediction. The fusion strategy accounts for prediction uncertainty within each modality and conflicts between multimodal data. Experiments on two large ICU datasets demonstrate that our method achieves superior predictive performance compared to existing approaches. For example, it improving F1 score and AUPRC by 6.51% and 3.72%, respectively, and increases predictive reliability with an 18.08% decrease in Brier score for mortality prediction in MIMIC-III dataset. Comparable improvements are consistently observed on the ZICIP dataset, underscoring the predictability and reliability of the approach. These improvements translate into fewer false positives, supporting more precise triage decisions and more efficient allocation of critical care resources. Beyond ICU outcome prediction, the proposed framework offers a versatile tool for multimodal EHR analysis, with potential applications across diverse clinical tasks.</p>","PeriodicalId":101413,"journal":{"name":"Journal of healthcare informatics research","volume":"10 2","pages":"523-564"},"PeriodicalIF":4.6,"publicationDate":"2025-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13156398/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147871157","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MiniGPT-Pancreas: Multimodal Large Language Model for Pancreas Cancer Observation and Localization in CT Images.","authors":"Andrea Moglia, Elia Clement Nastasio, Luca Mainardi, Pietro Cerveri","doi":"10.1007/s41666-025-00224-6","DOIUrl":"10.1007/s41666-025-00224-6","url":null,"abstract":"<p><p>Pancreatic cancer remains one of the deadliest malignancies, primarily because of its subtle CT appearance and frequent late-stage diagnosis. We introduce MiniGPT-Pancreas, a lightweight multimodal large language model (MLLM) that interprets natural-language queries within an interactive ChatGPT-style interface, as well as computed tomography images, and returns precise bounding-box predictions for the pancreas and associated tumors. A cascaded fine-tuning strategy was applied to MiniGPTv2, a multi-task general-purpose MLLM, with a focus on pancreas and tumor detection, using the National Institute of Health (NIH) and Medical Segmentation Decathlon (MSD) pancreas datasets. Pancreas detection achieved an average intersection over Union (IoU) of 0.57 on NIH and MSD datasets, outperforming the base MiniGPT-Pancreas model and more recent MLLMs like GLM-4.1V-9B-Base (general-purpose) and UMIT (specific to the biomedical domain). Tumor observation on MSD yielded an accuracy, precision, recall, and F1 score of all about 0.87, surpassing MiniGPT-v2, GLM-4.1V-9B-Base, and UMIT. For tumor localization, the IoU was 0.28, higher than UMIT (IoU=0.07), but lower than GLM-4.1V-9B-Base (IoU=0.48). On multi-organ detection on the AbdomenCT-1k dataset, MiniGPT-Pancreas outperformed GLM-4.1V-9B-Base and UMIT in all organs, with an IoU of 0.50 on pancreas vs. 0.43 and 0.03, respectively. MiniGPT-Pancreas was rated highly by an international group of 10 expert general surgeons (Italy, Singapore, and the UK) as a potential training tool, especially for verification (4.5/5.0), and training of young specialists (4.5/5.0) on a 5-point Likert scale. While operating on 2D slices limits volumetric context, MiniGPT-Pancreas demonstrates that compact MLLMs can rival specialized vision networks in pancreas imaging, offering an intuitive, language-driven tool for AI-assisted radiology. The code is publicly available at https://github.com/elianastasio/MiniGPTPancreas.</p>","PeriodicalId":101413,"journal":{"name":"Journal of healthcare informatics research","volume":"10 1","pages":"40-69"},"PeriodicalIF":4.6,"publicationDate":"2025-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12873017/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146145462","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-Cohort Federated Learning Shows Synergy in Mortality Prediction for MRI-Based and Metabolomics-Based Age Scores.","authors":"Pedro Mateus, Swier Garst, Jing Yu, Davy Cats, Alexander G J Harms, Mahlet Birhanu, Marian Beekman, P Eline Slagboom, Marcel Reinders, Jeroen van der Grond, Andre Dekker, Jacobus F A Jansen, Magdalena Beran, Miranda T Schram, Pieter Jelle Visser, Justine Moonen, Mohsen Ghanbari, Gennady Roshchupkin, Dina Vojinovic, Inigo Bermejo, Hailiang Mei, Esther E Bron","doi":"10.1007/s41666-025-00208-6","DOIUrl":"10.1007/s41666-025-00208-6","url":null,"abstract":"<p><p>While biological age scores have been shown to characterize aging by estimating chronological age based on physiological biomarkers, interactions between different age scores are largely unknown. To study this, large-scale multi-modal data are crucial. However, such data are scarce as population-based cohorts are generally restricted in sharing their data. Here, we employ federated learning to study the relationship between the two types of biological age scores: BrainAge based on brain MRI and MetaboAge based on metabolites. Using three large population-based cohorts, we trained a federated deep learning model to estimate BrainAge and compared its performance to models trained in a single cohort. The federated BrainAge model yielded significantly lower error for age prediction across the cohorts than locally trained models. Harmonizing the age interval between cohorts further improved BrainAge accuracy. Subsequently, we compared BrainAge and MetaboAge by performing association analysis and survival analysis for dementia and mortality prediction to further characterize both scores. The association analysis showed a weak association between BrainAge and MetaboAge, while the survival analysis indicated complementary predictive values for the mortality risk of the two scores. Federated learning has been shown to be a valuable technique for enabling the use of research cohorts that are restricted in data sharing. We conclude that BrainAge and MetaboAge act synergetically for the prediction of time to all-cause mortality, and both aging scores capture different aspects of the aging process.</p><p><strong>Supplementary information: </strong>The online version contains supplementary material available at 10.1007/s41666-025-00208-6.</p>","PeriodicalId":101413,"journal":{"name":"Journal of healthcare informatics research","volume":"9 4","pages":"606-628"},"PeriodicalIF":4.6,"publicationDate":"2025-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12602841/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145508576","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Smarter Together: Combining Large Language Models and Small Models for Physiological Signals Visual Inspection.","authors":"Huayu Li, Zhengxiao He, Xiwen Chen, Ci Zhang, Stuart F Quan, William D S Killgore, Shu-Fen Wung, Chen X Chen, Geng Yuan, Jin Lu, Ao Li","doi":"10.1007/s41666-025-00207-7","DOIUrl":"10.1007/s41666-025-00207-7","url":null,"abstract":"<p><p>Large language models (LLMs) have shown promising capabilities in visually interpreting medical time-series data. However, their general-purpose design can limit domain-specific precision, and the proprietary nature of many models poses challenges for fine-tuning on specialized clinical datasets. Conversely, small specialized models (SSMs) offer strong performance on focused tasks but lack the broader reasoning needed for complex medical decision-making. To address these complementary limitations, we introduce ConMIL (Conformalized Multiple Instance Learning), a novel decision-support framework distinctively synergizes three key components: (1) a new Multiple Instance Learning (MIL) mechanism, QTrans-Pooling, designed for per-class interpretability in identifying clinically relevant physiological signal segments; (2) conformal prediction, integrated with MIL to generate calibrated, set-valued outputs with statistical reliability guarantees; and (3) a structured approach for these interpretable and uncertainty-quantified SSM outputs to enhance the visual inspection capabilities of LLMs. Our experiments on arrhythmia detection and sleep stage classification demonstrate that ConMIL can enhance the accuracy of LLMs such as ChatGPT4.0, Qwen2-VL-7B, and MiMo-VL-7B-RL. For example, ConMIL -supported Qwen2-VL-7B and MiMo-VL-7B-RL both achieve 94.92% and 96.82% precision on confident samples and (70.61% and 78.02%)/(78.10% and 71.98%) on uncertain samples for the two tasks, compared to 46.13% and 13.16% using the LLM alone. These results suggest that integrating task-specific models with LLMs may offer a promising pathway toward more interpretable and trustworthy AI-driven clinical decision support.</p><p><strong>Supplementary information: </strong>The online version contains supplementary material available at 10.1007/s41666-025-00207-7.</p>","PeriodicalId":101413,"journal":{"name":"Journal of healthcare informatics research","volume":"9 4","pages":"656-685"},"PeriodicalIF":3.7,"publicationDate":"2025-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12602810/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145508589","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Joint Imbalance Adaptation for Radiology Report Generation.","authors":"Wang Li, Guangzeng Han, Yuexin Wu, I-Chan Huang, Xiaolei Huang","doi":"10.1007/s41666-025-00205-9","DOIUrl":"10.1007/s41666-025-00205-9","url":null,"abstract":"<p><p>Radiology report generation, translating radiological images into precise and clinically relevant description, may face the data imbalance challenge - medical tokens appear less frequently than regular tokens, and normal entries are significantly more than abnormal ones. However, very few studies consider the imbalance issues, not even with conjugate imbalance factors. In this study, we propose a <b>J</b>oint <b>Im</b>balance <b>A</b>daptation (<i>JIMA</i>) model to promote task robustness by leveraging token and label imbalance. We employ a hard-to-easy learning strategy that mitigates overfitting to frequent labels and tokens, thereby encouraging the model to focus more on infrequent labels and clinical tokens. JIMA presents notable improvements (16.75-50.50% on average) across evaluation metrics on IU X-ray and MIMIC-CXR datasets. Our ablation analysis and human evaluations show the improvements mainly come from enhancing performance on infrequent tokens and abnormal radiological entries, which can also lead to more clinically accurate reports. While data imbalance (e.g., infrequent tokens and abnormal labels) can lead to the underperformance of radiology report generation, our imbalance learning strategy opens promising directions on how to encounter data imbalance by reducing overfitting on frequent patterns and underfitting on infrequent patterns.</p>","PeriodicalId":101413,"journal":{"name":"Journal of healthcare informatics research","volume":"9 4","pages":"720-742"},"PeriodicalIF":3.7,"publicationDate":"2025-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12602799/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145508599","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Stress and Emotion Open Access Data: A Review on Datasets, Modalities, Methods, Challenges, and Future Research Perspectives.","authors":"Aleksandr Ometov, Anzhelika Mezina, Hsiao-Chun Lin, Otso Arponen, Radim Burget, Jari Nurmi","doi":"10.1007/s41666-025-00200-0","DOIUrl":"10.1007/s41666-025-00200-0","url":null,"abstract":"<p><p>Remote continuous patient monitoring is an essential feature of eHealth systems, offering opportunities for personalized care. Among its emerging applications, emotion and stress recognition hold significant promise, but face major challenges due to the subjective nature of emotions and the complexity of collecting and interpreting related data. This paper presents a review of open access multimodal datasets used in emotion and stress detection. It focuses on dataset characteristics, acquisition methods, and classification challenges, with attention to physiological signals captured by wearable devices, as well as advanced processing methods of these data. The findings show notable advances in data collection and algorithm development, but limitations remain, e.g., variability in real-world conditions, individual differences in emotional responses, and difficulties in objectively validating emotional states. The inclusion of self-reported and contextual data can enhance model performance, yet lacks consistency and reliability. Further barriers include privacy concerns, annotation of long-term data, and ensuring robustness in uncontrolled environments. By analyzing the current landscape and highlighting key gaps, this study contributes a foundation for future work in emotion recognition. Progress in the field will require privacy-preserving data strategies and interdisciplinary collaboration to develop reliable, scalable systems. These advances can enable broader adoption of emotion-aware technologies in eHealth and beyond.</p>","PeriodicalId":101413,"journal":{"name":"Journal of healthcare informatics research","volume":"9 3","pages":"247-279"},"PeriodicalIF":3.7,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12290141/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144736502","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}