IEEE Journal of Biomedical and Health Informatics最新文献

{"title":"Confident and Trustworthy Model for Fidgety Movement Classification.","authors":"Romero Morais, Thao Minh Le, Truyen Tran, Caroline Alexander, Natasha Amery, Catherine Morgan, Alicia Spittle, Vuong Le, Nadia Badawi, Alison Salt, Jane Valentine, Catherine Elliott, Elizabeth M Hurrion, Paul A Dawson, Svetha Venkatesh","doi":"10.1109/JBHI.2025.3624341","DOIUrl":"10.1109/JBHI.2025.3624341","url":null,"abstract":"<p><p>General movements (GMs) are part of the spontaneous movement repertoire and are present from early fetal life onwards up to age five months. GMs are connected to infants' neurological development and can be qualitatively assessed via the General Movement Assessment (GMA). In particular, between the age of three to five months, typically developing infants produce Fidgety Movements (FM) and their absence provides strong evidence for the presence of cerebral palsy (CP). To improve accessibility to the GMA, automated GMA solutions have been a key research area with proposed models becoming increasingly more accurate and interpretable. However, current models cannot gauge their ability to make decisions, which may lead to overconfident mistakes. To address this issue, we propose a Deep learning-based approach that not only classifies movements as fidgety or non-fidgety but also selectively abstains from classification when uncertain. Through two novel regularization losses, our model maintains a balanced coverage across the two movement types, which prevents bias toward an easy-to-classify subset of movements. We show that our proposed model learns to gauge its own confidence on movement classification, and our proposed regularization losses effectively ensure that the model maintains a similar confidence across movement types. We also show that the local movement abstentions have little impact on the video-level coverage and that relying on the most confident predictions improves the video-level performance.</p>","PeriodicalId":13073,"journal":{"name":"IEEE Journal of Biomedical and Health Informatics","volume":"PP ","pages":"3798-3809"},"PeriodicalIF":6.8,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145354574","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ESIP: Explicit Surgical Instrument Prompting for Surgical Workflow Recognition.","authors":"Yixuan Qiu, Mengxing Liu, Siyuan He, Guangquan Zhou, Fei Lyu, Yang Chen, Ping Zhou","doi":"10.1109/JBHI.2025.3625420","DOIUrl":"10.1109/JBHI.2025.3625420","url":null,"abstract":"<p><p>Surgical workflow recognition (SWR) stands as a pivotal component in computer-assisted surgery and is dedicated to identifying phases from surgical videos. Many deep learning-based methods have been proposed for this task and achieved acceptable SWR results. However, these methods usually implicitly extract and aggregate spatio-temporal features, so that it is challenging for these methods to adequately use some spatial information that is strongly relevant to surgical phase in SWR task, such as the information from the surgical instruments. To address this issue, an Explicit Surgical Instrument Prompting (ESIP) approach is proposed for SWR task. ESIP leverages surgical instrument segmentation to generate instrument-specific visual prompts, which explicitly guide the extraction of crucial intra-frame spatial features through a frozen pre-trained backbone, then enable effective inter-frame spatio-temporal feature extraction and aggregation. Unlike multi-task approaches that jointly perform SWR with auxiliary tasks within a shared network framework, ESIP is a single-task SWR approach dedicated to optimize framework itself for more adequate feature extraction. Furthermore, to accomplish the segmentation prompting efficiently, this paper presents SAM-based segmentation with prompt tuning strategy to explicitly integrate segmentation features into spatial features. Experimental results on Cholec80, M2CAI and AutoLaparo datasets demonstrate that our ESIP method achieves the best performance in comparison with 16 SOTA methods, with a Precision of 91.8%, 89.5% and 89.6%, Recall of 92.2%, 89.5% and 76.9%, Jaccard of 83.3%, 77.0% and 67.3%, respectively.</p>","PeriodicalId":13073,"journal":{"name":"IEEE Journal of Biomedical and Health Informatics","volume":"PP ","pages":"3912-3922"},"PeriodicalIF":6.8,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145377228","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Ultrasound-Enhanced Data-Driven Modeling for Characterizing Natural Wrist Tremor Dynamics.","authors":"Xiangming Xue, Vidisha Ganesh, Ashwin Iyer, Daniel Roque, Xiaoning Jiang, Nitin Sharma","doi":"10.1109/JBHI.2025.3622539","DOIUrl":"10.1109/JBHI.2025.3622539","url":null,"abstract":"<p><p>The complex interplay of neural and muscular activity underlying involuntary rhythmic wrist tremors poses significant challenges for effective symptom management, particularly with identifying key tremor characteristics such as dominant frequency and amplitude. This study introduces an ultrasound (US)-enhanced data-driven modeling framework that uses wrist angle kinematics as state variables, which are augmented with muscle-specific ultrasound data inputs. We explore three modeling configurations: a wrist kinematics-only baseline model, a fixed-parameter US-augmented model, and a real-time adaptive US-enhanced model updated using a recursive least squares (RLS) algorithm. Comprehensive validation using time- and frequency-domain analyses was conducted using experimental data from six patients with tremor. Results show that integrating US input improves modeling specificity and accuracy by capturing internal muscle dynamics and temporal evolution patterns that are not accessible through IMU alone. Specifically, the time-domain modeling error (nRMSE) decreased substantially from 49.36% in the baseline model to 24.53% in the US-augmented model. The adaptive model further reduced the error to 0.48%, demonstrating its ability to account for the variability of tremor behaviors dynamically. Moreover, this work introduces, for the first time in tremor research, a comprehensive eigenvalue analysis of the data-driven model to extract clinically relevant tremor characteristics. The method enables accurate estimation of dominant tremor frequencies (average across patients nRMSE = 12.7%), quantification of dominant state contributions (mean $Delta _{text{dominance}}$ = 18.73%), and reliable tremor event detection (F1-score = 0.796). These findings highlight the framework's ability to not only reproduce tremor trajectories but also uncover how tremor behavior evolves over time in response to underlying neuromuscular activity. This work establishes a foundation for real-time tremor tracking and model-based control strategies, such as closed-loop afferent stimulation. By leveraging the unique sensing capabilities of ultrasound, the proposed framework offers a promising path toward personalized tremor modeling and intervention.</p>","PeriodicalId":13073,"journal":{"name":"IEEE Journal of Biomedical and Health Informatics","volume":"PP ","pages":"4162-4174"},"PeriodicalIF":6.8,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145336796","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Physiology-Inspired EEG Transformer for Predicting Movement Transitions in Bimanual Tasks.","authors":"Tianyu Jia, Haiyang Long, Ciaran McGeady, Xingchen Yang, Francesca Colacrai, Jiarong Wang, Linhong Ji, Chong Li, Dario Farina","doi":"10.1109/JBHI.2025.3622729","DOIUrl":"10.1109/JBHI.2025.3622729","url":null,"abstract":"<p><p>Human-machine interfaces (HMIs) have been widely integrated with motor rehabilitation and augmentation systems. Forecasting movement transitions during human-robot interaction is crucial to ensure system safety, intuitiveness, and reactivity, particularly in anticipating human motor intentions under sudden perturbations or emergency scenarios. In this study, we investigated pre-movement neural signatures preceding sudden movement transitions during ongoing bimanual tasks. Informed by these findings, we propose a physiology-informed EEG Transformer (PI-EEGformer) for EEG-based motor intention recognition. An EEG dataset collected from a bimanual movement task, where one hand was required to switch motor states in response to unexpected cues, was used to evaluate the performance of the PI-EEGformer in comparison with seven state-of-the-art models. Results showed that, prior to the movement transition, EEG power spectrum decreased, and movement-related cortical potentials (MRCPs) could be accurately extracted from the contralateral motor cortex. PI-EEGformer reached an average accuracy of 0.912 in inter-subject tests and 0.829 in cross-subject tests in detecting movement transitions using EEG from 500 ms to 100 ms prior to the actual movement. This performance was superior to all the state-of-the-art models tested. These results demonstrate that EEG neural signatures can predict sudden movement transitions during ongoing bimanual tasks. The PI-EEGformer, designed with these physiological signatures, can enable accurate prediction of sudden movement transitions. This study will help improve the response of HMI systems to sudden disturbances, contributing to a more realistic HMI system.</p>","PeriodicalId":13073,"journal":{"name":"IEEE Journal of Biomedical and Health Informatics","volume":"PP ","pages":"4108-4119"},"PeriodicalIF":6.8,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145368064","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CFSCNet: A Coarse-Fine Stream Conformer Neural Network for Swallow Segmentation.","authors":"Yanxia Liu, Chujian Lin, Lian Wang, Xiaozhen Li, Nannan Cui, Zulin Dou","doi":"10.1109/JBHI.2025.3650133","DOIUrl":"10.1109/JBHI.2025.3650133","url":null,"abstract":"<p><p>This study develops an efficient and accurate method for segmenting complex swallowing events in patients with dysphagia. We propose CFSCNet, a novel model that integrates multimodal signals-audio, nasal airflow, and triaxial accelerometry-to enhance swallowing event segmentation. The model employs a dual-stream architecture to capture swallowing information across varying durations and utilizes an exponential moving average-based cost-sensitive weighting method to address data imbalance. To further improve the stability of predictions for clinical applications, a Swallowing State Machine-Driven Post-Processing Method is introduced to smooth the segmentation sequences. CFSCNet achieves state-of-the-art performance on two benchmark datasets, reaching an AUC of 89.83 on the HRCA dataset and 94.10 on the SMSD dataset, significantly outperforming existing methods. Built on a series of tailored methodological innovations, the proposed framework offers a comprehensive and novel solution for swallowing event segmentation. It demonstrates strong accuracy and reliability, as well as great potential for future extension and clinical translation. This work is expected to advance high-precision detection and diagnosis of dysphagia, thereby supporting more effective swallowing rehabilitation and medical interventions.</p>","PeriodicalId":13073,"journal":{"name":"IEEE Journal of Biomedical and Health Informatics","volume":"PP ","pages":"3923-3933"},"PeriodicalIF":6.8,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145889079","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"TrajGPT: Irregular Time-Series Representation Learning of Health Trajectory.","authors":"Ziyang Song, Qincheng Lu, He Zhu, David Buckeridge, Yue Li","doi":"10.1109/JBHI.2025.3620205","DOIUrl":"10.1109/JBHI.2025.3620205","url":null,"abstract":"<p><p>In the healthcare domain, time-series data are often irregularly sampled with varying intervals through outpatient visits, posing challenges for existing models designed for equally spaced sequential data. To address this, we propose Trajectory Generative Pre-trained Transformer (TrajGPT) for representation learning on irregularly-sampled healthcare time series. TrajGPT introduces a novel Selective Recurrent Attention (SRA) module that leverages a data-dependent decay to adaptively filter irrelevant past information. As a discretized ordinary differential equation (ODE) framework, TrajGPT captures underlying continuous dynamics and enables a time-specific inference for forecasting arbitrary target timesteps without auto-regressive prediction. Experimental results based on the longitudinal EHR data PopHR from Montreal health system and eICU from PhysioNet showcase TrajGPT's superior zero-shot performance in disease forecasting, drug usage prediction, and sepsis detection. The inferred trajectories of diabetic and cardiac patients reveal meaningful comorbidity conditions, underscoring TrajGPT as a useful tool for forecasting patient health evolution.</p>","PeriodicalId":13073,"journal":{"name":"IEEE Journal of Biomedical and Health Informatics","volume":"PP ","pages":"3888-3899"},"PeriodicalIF":6.8,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145286040","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"TransGRN: A Transfer Learning-Based Framework for Inferring Gene Regulatory Networks Across Cell Lines.","authors":"Ge Xu, Ziwei Wang, Jiahao Zhou, Weiming Yu, Le Ou-Yang","doi":"10.1109/JBHI.2025.3628564","DOIUrl":"10.1109/JBHI.2025.3628564","url":null,"abstract":"<p><p>Inferring gene regulatory networks (GRNs) is critical for understanding the mechanisms that govern cellular behavior. Advances in single-cell RNA sequencing (scRNA-seq) have enabled GRN analysis at single-cell resolution and stimulated the development of many computational methods. However, most existing approaches depend heavily on extensive prior regulatory information, which limits their effectiveness in few-shot settings where such data for the target cell line are scarce or unavailable. To address this challenge, we propose TransGRN, a transfer learning-based method for inferring gene regulatory networks (GRNs) across cell lines. TransGRN adopts a cross-cell-line pre-training strategy that combines scRNA-seq data from multiple source cell lines with biological knowledge obtained from large language models. In addition, it includes a regulatory interaction extraction module that integrates gene expression profiles with semantic information. By transferring generalizable gene-gene regulatory patterns from source to target cell lines, TransGRN achieves state-of-the-art performance in both benchmark tests and few-shot GRN inference tasks.</p>","PeriodicalId":13073,"journal":{"name":"IEEE Journal of Biomedical and Health Informatics","volume":"PP ","pages":"4013-4022"},"PeriodicalIF":6.8,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145451803","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing Chronic Heart Failure Monitoring, Prevention, and Management With IoT and AI: A Systematic Literature Review.","authors":"Andrea Rucco, Angela Tafadzwa Shumba, Teodoro Montanaro, Ilaria Sergi, Luigi Patrono","doi":"10.1109/JBHI.2025.3628501","DOIUrl":"10.1109/JBHI.2025.3628501","url":null,"abstract":"<p><p>Chronic Heart Failure (CHF) represents a significant global health concern due to its high morbidity and mortality rates. Effectively addressing this challenge requires scalable technology solutions to shift Heart Failure (HF) care from episodic reactive treatment to continuous personalized management. As digital health technologies advance, integrating Artificial Intelligence (AI) and the Internet of Things (IoT) into CHF care enables the development of scalable monitoring, prevention, and management strategies and real-time Clinical Decision Support Systems (CDSSs). This Systematic Literature Review (SLR) analyzes 67 peer-reviewed studies published between January 2021 and May 2024, selected using Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) guidelines to evaluate the technological and clinical impacts of AI-enabled systems in CHF and broader HF care. The review identifies emerging trends, discusses dataset characteristics and clinical relevance, identifies IoT integration patterns, gaps, and deployment barriers, and highlights opportunities for improving the integration of AI/IoT systems into HF care workflows. The studies are organized into four clinical application domains: HF detection, phenotyping and classification, risk stratification, and other miscellaneous applications. Our findings highlight the progress in AI/IoT synergy; however, challenges remain in dataset heterogeneity and coverage, reproducibility, benchmarking practices, and clinical workflow integration, particularly as IoT integration is often limited or insufficiently explored. Our primary recommendations emphasize the use of multimodal datasets, the adoption of interpretable modeling approaches, and stronger interdisciplinary collaboration to improve clinical applicability and support integration into real-world settings.</p>","PeriodicalId":13073,"journal":{"name":"IEEE Journal of Biomedical and Health Informatics","volume":"PP ","pages":"3768-3783"},"PeriodicalIF":6.8,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145437909","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Artifact Suppression in OPM-MEG for Parkinson's Disease Patients With DBS Implants Using Oblique Projection-Based Extended Homogeneous Field Correction.","authors":"Fulong Wang, Fuzhi Cao, Nan An, Jianzhi Yang, Yaxiang Wang, Min Xiang, Qianqian Wu, Weiguo Li","doi":"10.1109/JBHI.2025.3626123","DOIUrl":"10.1109/JBHI.2025.3626123","url":null,"abstract":"<p><p>Deep brain stimulation (DBS) is a critical neuromodulation technique that has been widely applied in the treatment of neurological disorders such as Parkinson's disease (PD) and epilepsy. As an important functional neuroimaging modality, magnetoencephalography (MEG) has played a key role in DBS research. In particular, the next-generation MEG based on optically pumped magnetometers (OPM-MEG), offers greater potential for clinical applications. However, the strong electromagnetic interference generated by DBS systems makes data acquisition and analysis challenging in OPM-MEG recordings from patients with implanted devices. To the best of our knowledge, there have been no studies that systematically investigate the characteristics or suppression of DBS-induced artifacts in OPM-MEG recordings from human subjects. In this paper, we describe a novel OPM-MEG interference suppression algorithm called extended homogeneous field correction based on oblique projection (opHFC), developed for suppressing environmental noise in OPM-MEG. To illustrate the practical application of opHFC in clinical settings, particularly for patients with DBS implants. We evaluate the performance of opHFC in denoising OPM-MEG data from PD patients with DBS implants. By applying opHFC to real-world clinical data, we assess its ability to reduce DBS-induced artifacts while preserving neural activity patterns and conduct a comprehensive comparison between opHFC and several commonly used artifact suppression techniques in OPM-MEG. Our results show that opHFC significantly enhances signal quality and achieves the most effective suppression performance, demonstrating its potential as a reliable tool for advancing OPM-MEG applications in challenging clinical environments. This study highlights the practical value of opHFC in improving OPM-MEG data quality for PD patients with DBS, paving the way for more accurate neuroscientific research and clinical diagnostics.</p>","PeriodicalId":13073,"journal":{"name":"IEEE Journal of Biomedical and Health Informatics","volume":"PP ","pages":"4148-4161"},"PeriodicalIF":6.8,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145388969","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Constrained Multi-Objective Optimization-Based Temporal Network Observability for Biomarker Identification of Individual Patients.","authors":"Kangjia Qiao, Jing Liang, Wei-Feng Guo, Yunpeng Wei, Kunjie Yu, Zhuo Hu","doi":"10.1109/JBHI.2024.3435418","DOIUrl":"10.1109/JBHI.2024.3435418","url":null,"abstract":"<p><p>Identifying the biomarkers from the personalized gene interaction network of individual patients is important for disease diagnosis. However, existing methods not only ignore the prior biomarkers for practical use but also ignore the observability of the entire system. Therefore, this paper proposes a new constrained multi-objective optimization-based temporal network observability model (CMTNO) to identify biomarkers, which not only requires minimizing the number of selected nodes including ordinary nodes and prior nodes (the first optimization objective) but also maximizing the number of selected prior nodes (the second optimization objective) on the premise of ensuring network observability (the constraint condition). Considering the temporal feature of cancer (patients belong to different stages and each patient contains one task), an experience learning-based constrained multi-objective evolutionary algorithm is designed to solve the CMTNO problems. The selected probabilities of ordinary nodes and prior nodes are treated as experience, stored in two separate archives and updated by the optimal solutions on each task. Experience utilization refers to using two archives to generate new initial populations for new patients, in order to improve the optimization efficiency of the algorithm. Besides, a two-step neighbor-based connectivity method is proposed to distinguish different nodes with similar connectivity to further improve the effectiveness of archives. The proposed model and algorithm are evaluated on three kinds of cancer patients' data under two kinds of network models, and results show their effectiveness in identifying effective biomarkers.</p>","PeriodicalId":13073,"journal":{"name":"IEEE Journal of Biomedical and Health Informatics","volume":"PP ","pages":"3630-3642"},"PeriodicalIF":6.8,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141855383","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}