IEEE Journal of Biomedical and Health Informatics最新文献

{"title":"Semantic Clinical Knowledge Augmentation Improves Medical Question Answering Across Commercial and Open Large Language Models.","authors":"Peter L Elkin, Aaron N Elkin, Guresh Mehta, Frank LeHouillier, Jonathan R Nebeker, Nazmus Saquib, Steven H Brown","doi":"10.1109/JBHI.2026.3742187","DOIUrl":"10.1109/JBHI.2026.3742187","url":null,"abstract":"<p><strong>Objective: </strong>To evaluate whether semantic clinical knowledge augmentation through Semantic Clinical Artificial Intelligence (SCAI) improves medical question answering across commercial and open large language models, and to examine how a reasoning distilled model performs on the same benchmark.</p><p><strong>Materials and methods: </strong>We evaluated Google Gemini, Microsoft Copilot, Meta Llama 3 70B, and DeepSeek-R1-Distill-Llama-70B on official text only United States Medical Licensing Exam (USMLE) sample questions from Step 1 (n = 87), Step 2 CK (n = 103), and Step 3 (n = 123), with and without SCAI. SCAI comprised HD-NLP parsing, graph and knowledge graph embeddings, a trained SCAI LLM semantic knowledge reasoner, and a semantic knowledge base; the current implementation contained 33,023,902 triples across 246 relation labels. Responses were scored against the answer key with secondary human verification. All models produced a response to every text only item, so incorrect responses were counted as confabulations.</p><p><strong>Results: </strong>Across 313 items, accuracy increased from 90.7% to 97.1% for Gemini, 82.4% to 92.0% for Llama 3 70B, and 55.3% to 81.8% for DeepSeek-R1-Distill; Copilot changed from 93.6% to 94.2%. Within model gains were statistically significant for Gemini, Llama 3 70B, and DeepSeek-R1-Distill on all three steps, but not for Copilot. The best single model result was Llama 3 70B plus SCAI on Step 3 (121/123, 98.4%). Gemini plus SCAI was the numerically strongest commercial system.</p><p><strong>Conclusions: </strong>SCAI was associated with materially better accuracy and lower confabulation (False Positive Results) across several heterogeneous LLMs, supporting a semantically grounded pipeline in which a dedicated SCAI LLM generates clinical context for a host LLM while suggesting that strong general reasoning performance does not automatically translate into healthcare readiness.</p>","PeriodicalId":13073,"journal":{"name":"IEEE Journal of Biomedical and Health Informatics","volume":"PP ","pages":""},"PeriodicalIF":7.7,"publicationDate":"2026-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149148024","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":"Unsupervised CT Metal Artifact Reduction Via Consistent Artifact Modeling.","authors":"Enyu Bao, Yifei Chen, Junhao Ye, Xueyan Song, Kasidit Anmahapong, Ziang Wang, Guanyu Zhou, Feiwei Qin, Yaqi Wang, Changmiao Wang, Huiyu Zhou, Qiyuan Tian","doi":"10.1109/JBHI.2026.3740719","DOIUrl":"https://doi.org/10.1109/JBHI.2026.3740719","url":null,"abstract":"<p><p>Metal artifacts severely corrupt CT images, masking anatomical structures and undermining diagnostic reliability. Although supervised metal artifact reduction (MAR) achieves strong suppression, its dependence on paired clean and corrupted data confines it to simulated domains and hinders clinical translation. We recast unsupervised MAR as an artifact-consistent residual learning problem and propose a physically grounded, attention-guided generative framework that closes the loop between artifact estimation and removal. A single-generator dual-branch architecture estimates metal-induced corruption as a transferable additive residual and reinjects it to synthesize controlled degraded samples during cyclic training, explicitly constraining the removable component. Guided by interpolated pseudo-priors, a difference-aware attention mechanism concentrates correction on corrupted regions while safeguarding intact anatomy, all without paired supervision. Extensive experiments on synthetic benchmarks and real clinical data show that our method restores structural fidelity, suppresses streaks and beam-hardening, and generalizes robustly across diverse implants and anatomical sites. Beyond perceptual quality, it delivers state-of-the-art pelvic bone segmentation under metal corruption at efficient inference cost. This work charts an interpretable, efficient, and clinically scalable route toward reliable CT metal artifact suppression in real-world practice. Our source code is available at https://github.com/wonderfulpoet/CAM-Net.</p>","PeriodicalId":13073,"journal":{"name":"IEEE Journal of Biomedical and Health Informatics","volume":"PP ","pages":""},"PeriodicalIF":7.7,"publicationDate":"2026-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149136156","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":"KGR-MAS: Knowledge Graph-Enhanced Multi-Agent LLM Framework for Evidence-Based Medical Diagnosis and Clinical Decision Support.","authors":"Li Yin, XueFeng Du, Yanqi Cheng, Ning Tong, Fengqi Li","doi":"10.1109/JBHI.2026.3740738","DOIUrl":"https://doi.org/10.1109/JBHI.2026.3740738","url":null,"abstract":"<p><p>Large Language Models (LLMs) demonstrate significant potential in healthcare applications, yet they exhibit reasoning bias, information bottlenecks, and limited adaptability in complex clinical settings. To address these limitations, we propose KGR-MAS, which introduces an integrated control loop that couples (1) KG-derived diagnostic paths for executable subtask decomposition and dynamic agent allocation, while using these KG reasoning paths to initialize shared short-term memory; (2) a language-level LSTM-inspired gating mechanism with Transformer-XL short-term memory to regulate cross-agent information flow and maintain global coherence; and (3) a KG-guided RAG-STM process that triggers evidence retrieval at diagnostic checkpoints and writes the retrieved evidence back into STM for subsequent reasoning. We constructed a large-scale medical knowledge graph achieving the best embedding performance (Hits@1:32.8%, MRR:0.498). Experimental results on MedQA and MedMCQA show that KGR-MAS achieves 87.2% accuracy on MedQA($uparrow$14.4%), and 77.4% average accuracy across four open-domain datasets ($uparrow$29.0%), outperforming larger models like GPT-o1(72.0%). KGR-MAS provides interpretable, accurate, and clinically grounded diagnostic reasoning, highlighting its potential as a next-generation AI assistant for medical decision-making.</p>","PeriodicalId":13073,"journal":{"name":"IEEE Journal of Biomedical and Health Informatics","volume":"PP ","pages":""},"PeriodicalIF":7.7,"publicationDate":"2026-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149135978","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":"TPF-BP: A Three-Stage Physiology-Guided Self-Supervised Transfer Learning Framework for Personalized Blood Pressure Measurement.","authors":"Yuhui Cen, Renqi Chen, Xing Zhu, Hongbo Wang, Jingjing Luo","doi":"10.1109/JBHI.2026.3740802","DOIUrl":"https://doi.org/10.1109/JBHI.2026.3740802","url":null,"abstract":"<p><p>Personalized and continuous cuffless blood pressure (BP) monitoring using photoplethysmography (PPG) is a critical requirement for next-generation wearable healthcare systems. Despite recent progress, existing PPG-based learning models exhibit limited generalization and personalization across individuals, hindering robust real-world deployment. To overcome these limitations, we propose TPF-BP, a novel self-supervised transfer learning framework that integrates physiological priors into representation learning. Specifically, a physiology-guided masked autoencoder is employed for self-supervised pre-training to enhance latent feature extraction from PPG signals and their derivatives, followed by a homologous triple-branch model for sequential supervised pre-training and personalized fine-tuning. Extensive experiments demonstrate that four base models trained with TPF-BP reduce the mean absolute errors of systolic and diastolic BP estimation by an average of 7.66% and 5.78%, respectively, in few-shot transfer scenarios across three public datasets and one self-collected dataset. Additionally, we publicly release CRHE, our self-collected multi-wavelength, dual-24h PPG-BP dataset, along with its benchmark results. The dataset features circadian rhythm annotations and was collected using wearable devices and ambulatory BP monitors. Together, TPF-BP and CRHE provide essential methodological and data resources to advance intelligent physiological modeling and personalized health monitoring. The dataset is publicly available at https://github.com/FDU-Bio-Monitoring/CRHE-Long-Term-PPG-BP-Dataset.</p>","PeriodicalId":13073,"journal":{"name":"IEEE Journal of Biomedical and Health Informatics","volume":"PP ","pages":""},"PeriodicalIF":7.7,"publicationDate":"2026-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149136193","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":"FlowPredictor-Corrector: A Hemodynamics-Guided Two-Step Deep Learning Framework for Vascular Flow Prediction.","authors":"Zhuo Li, Yao Zeng, Mengfei Wang, Yulu Yang, Meixiu Pan, Ao Liu, Qiang Sun, Haifeng Zhao, Ruipeng Zhang, Yuehua Li","doi":"10.1109/JBHI.2026.3741575","DOIUrl":"https://doi.org/10.1109/JBHI.2026.3741575","url":null,"abstract":"<p><p>Accurate hemodynamic assessment is of significant clinical value in the diagnosis, prognosis, and treatment planning of cardiovascular and cerebrovascular diseases. However, obtaining noninvasive, rapid, and high-fidelity hemodynamic information remains challenging. Invasive measurements carry risks, numerical simulations rely on complex modeling and high computational power, and while deep learning methods are efficient, they often lack physical constraints, leading to unstable performance in complex and diverse vascular geometries. To address this, we propose an innovative two-step framework called FlowPredictor-Corrector (FPC), which integrates point-cloud learning with physics-based hemodynamic correction to achieve a rapid mapping from vascular geometry to 4D hemodynamics. We constructed a dataset across three carotid artery anatomical regions (normal ICA C1 segment, normal carotid bifurcation, and stenotic carotid bifurcation) and conducted a systematic comparison with mainstream point cloud models (PointNet, PointNet++, Point Transformer). Our results demonstrate that the proposed method achieves high consistency with reference data for hemodynamic predictions ($R^{2} > 0.92$). Furthermore, it shows high agreement with computational fluid dynamics (CFD) and clinical ultrasound reports in stenotic grade classification based on internal carotid artery (ICA)/common carotid artery (CCA) peak systolic velocity (PSV) ($AUC = 0.947$). The model inference time was approximately 1.0 s per case. In summary, FPC not only balances efficiency with accuracy but also exhibits strong physical consistency and clinical interpretability, supporting further investigation toward rapid 4D hemodynamic prediction and potential clinical applications. To facilitate reproducibility and further research, the code and a representative test case are publicly available at https://anonymous.4open.science/r/FPC-B09E.</p>","PeriodicalId":13073,"journal":{"name":"IEEE Journal of Biomedical and Health Informatics","volume":"PP ","pages":""},"PeriodicalIF":7.7,"publicationDate":"2026-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149135971","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":"CoDER: Consistent Drug Efficacy Ranking.","authors":"Mahsa Rezaei, Yilmaz Atay, Omer Kahveci, Pouya Paidar, Pietro Hiram Guzzi, Pierangelo Veltri, Tamer Kahveci","doi":"10.1109/JBHI.2026.3741663","DOIUrl":"https://doi.org/10.1109/JBHI.2026.3741663","url":null,"abstract":"<p><p>Drug ranking plays a pivotal role in drug repurposing and precision medicine by prioritizing candidate therapies under biological and clinical constraints. A major challenge is identifying drugs whose efficacy remains consistent across multiple human tissues, as heterogeneity in gene expression, regulatory mechanisms, and tissue-specific biology can lead to variable or unreliable therapeutic effects. Many existing approaches focus on single tissues or aggregate performance across tissues, obscuring important sources of variability. We present CoDER (Consistent Drug Efficacy Ranking), a graph-based computational framework for identifying drug orderings that remain stable across a minimum number of tissues. CoDER integrates multiple biological data sources-including GTEx, TRRUST, DisGeNET, and DGIdb-to derive tissue-specific drug efficacy profiles and represent pairwise drug dominance relationships as a tissue-labeled directed graph. We formalize this task as a $lambda$-consistent ordering problem and show that it is NP-hard. To address this computational challenge, CoDER employs a scalable divide-and-conquer strategy that limits exhaustive search to tractable subproblems and iteratively refines candidate sets to recover long $lambda$-consistent drug sequences. Applied to 273 drugs across 49 human tissues, CoDER efficiently identifies interpretable tissue-consistent rankings and achieves higher scalability and longer $lambda$-consistent paths than the evaluated tissue-aware ranking baselines. These results suggest that CoDER provides a practical computational framework for tissue-consistent drug prioritization and hypothesis generation.</p>","PeriodicalId":13073,"journal":{"name":"IEEE Journal of Biomedical and Health Informatics","volume":"PP ","pages":""},"PeriodicalIF":7.7,"publicationDate":"2026-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149136545","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":"DINOSAM+: Structure-Guided Prompt Learning for Semi-Supervised 3D Medical Image Segmentation.","authors":"Sibo Qiao, Chaoying Yang, Zhiyuan Zhao, Min Wang, Cong Liu, Sunil Prajapat, Mohammad Shabaz, Hemant Ghayvat","doi":"10.1109/JBHI.2026.3740676","DOIUrl":"10.1109/JBHI.2026.3740676","url":null,"abstract":"<p><p>Semi-supervised 3D medical image segmentation under low-label settings often suffers from noisy pseudo labels and anatomically inconsistent predictions, which limit segmentation reliability. Existing methods primarily emphasize training strategies or loss engineering, but they still fail to sufficiently exploit structural priors to guide pseudo-label generation and unlabeled supervision. Hence, we propose DINOSAM+, a structure-guided semi-supervised framework for reliable 3D medical image segmentation. Specifically, a frozen self-supervised representation model, DINOv2, is employed to extract coarse structural attention from volumetric slices, which is further refined by a lightweight structure-aware network into foreground, boundary, and background probability maps, thereby providing more discriminative structural cues for pseudo-label generation. Based on these refined structural maps, structure-aware prompts are automatically generated for SAM-Med3D to produce pseudo labels with improved spatial consistency and structural completeness. The resulting pseudo labels are then incorporated into a Mean Teacher framework with confidence filtering, improving the reliability of unlabeled supervision and reducing error accumulation during training. Experiments on the LA and Synapse datasets show improved Dice, HD95, and worst-case performance under limited annotations.</p>","PeriodicalId":13073,"journal":{"name":"IEEE Journal of Biomedical and Health Informatics","volume":"PP ","pages":""},"PeriodicalIF":7.7,"publicationDate":"2026-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149127260","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":"ST-DAI: Single-shot 2.5D Spatial Transcriptomics with Intra-Sample Domain Adaptive Imputation for Cost-efficient 3D Reconstruction.","authors":"Jiahe Qian, Yaoyu Fang, Xinkun Wang, Lee A Cooper, Bo Zhou","doi":"10.1109/JBHI.2026.3740681","DOIUrl":"10.1109/JBHI.2026.3740681","url":null,"abstract":"<p><p>Three-dimensional spatial transcriptomics (ST) is constrained by the high cost of fully profiling every serial tissue section. Existing histology-to-expression approaches can reduce within-sample measurement, but they generally require large external training cohorts and may be affected by cross-specimen domain shift. We introduce ST-DAI, a sample-specific framework that couples a cost-efficient 2.5D acquisition protocol with intra-sample domain-adaptive imputation. One reference section is fully measured, while adjacent target sections are sparsely measured to provide specimen-specific molecular anchors. ST-DAI first aligns the reference and target sections, pretrains a sparse-to-dense Pseudo Map Network on the reference section, and then performs Fast Multi-Domain Refinement using Parameter-Efficient Domain-Alignment Layers and confidence-weighted pseudo-supervision. A Data Consistency Operation preserves all experimentally observed target values in the final reconstruction. Across six Xenium breast-cancer and six Human DLPFC 10x Visium section settings, ST-DAI achieves the best reconstruction metrics among the evaluated methods under their respective acquisition protocols. Additional analyses further show improved preservation of morphology-derived five-class nuclear composition, differential-expression contrasts, marker localization, and spatial-domain organization. These results support sample-specific 2.5D acquisition as a practical strategy for reducing the measurement burden of volumetric ST while retaining quantitative and biologically interpretable spatial expression structure.</p>","PeriodicalId":13073,"journal":{"name":"IEEE Journal of Biomedical and Health Informatics","volume":"PP ","pages":""},"PeriodicalIF":7.7,"publicationDate":"2026-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149127355","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":"DermL2V: Unifying Heterogeneous Dermatology Texts Via LLM-Driven Encoding.","authors":"Bowen Guo, Jie Xu, Chen Ma, Zeju Li, Yuanyuan Wang, Yi Guo","doi":"10.1109/JBHI.2026.3740718","DOIUrl":"10.1109/JBHI.2026.3740718","url":null,"abstract":"<p><p>Dermatology diagnosis requires text encoding models that map unstructured descriptions to clinical semantic representations. Using public dermatology corpora to train such models remains highly challenging due to the lack of a specialized dataset offering unified semantic triplets as well as the difficulty of adaptively weighting clinically informative tokens and enhancing discrimination between clinically different but lexically similar descriptions. In this paper, we first construct DermSCL, a dermatology-specific dataset that organizes heterogeneous dermatology texts into 140,278 structured anchor-positive-negative semantic triplets and provides a unified supervision signal for text representation learning. Pretrained on DermSCL, we propose DermL2V, an LLM-based dermatology text encoder that improves representations by adaptively aggregating clinically relevant token information within a text and distinguishing semantic differences across different texts. First, we introduce a novel Clinical-Aware Relevance Aggregation module, where multiple relevance heads learn complementary token-level relevance patterns under dermatology-specific contrastive supervision to strengthen the representation. Second, we design a Boundary-Aware Semantic Mixup Strategy, which constructs intra- and inter-triplet near-boundary supervisory signals to enhance discrimination between clinically distinct yet lexically similar descriptions. Together, these two components synergistically improve the semantic robustness and discriminative capacity of the learned representations for dermatology. Furthermore, we evaluate DermL2V on important clinical tasks, including dermatology knowledge retrieval, embedding space analysis, concept classification and cross-modal retrieval. Across four out-of-domain dermatology retrieval datasets, DermL2V achieves the best average NDCG@10 and Recall@10 scores while delivering the best performance on the other downstream tasks. These results show DermL2V's potential as a dermatology-specific semantic encoder, providing reliable representations for retrieval-centered clinical applications. The project source code is publicly available here.</p>","PeriodicalId":13073,"journal":{"name":"IEEE Journal of Biomedical and Health Informatics","volume":"PP ","pages":""},"PeriodicalIF":7.7,"publicationDate":"2026-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149127315","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":"The HUA BioResource: A National Infrastructure for Genetic and Phenotypic Insights into BMI and Obesity in Greece.","authors":"Panagiotis G Symianakis, Ioanna Panagiota Kalafati, Charalampia Amerikanou, Despoina Brekou, Maria Dimitriou, Aliki-Eleni Farmaki, Olga Giannakopoulou, Panagiota Giardoglou, Effimia Grigoriou, Maria Kafyra, Stavroula Kanoni, Vassiliki-Eirini Kariakli, Efthymia A Katsareli, Eirini Marouli, Ioanna Ntalla, Natia A Pogosova, Eirini V Theodoraki, Maria Tsota, Andreas Alexandrou, Anastasia Amfilochiou, Erifili Hatziagelaki, Andriana C Kaliora, Alexander Kokkinos, Genovefa Kolovou, Loukianos S Rallidis, Kimon Stamatelopoulos, Nikolaos Tentolouris, Anastasia Thanopoulou, Konstantinos Triantafyllou, George Trovas, Antigone S Dimas, Vasiliki Mamakou, Konstantinos Rouskas, Panos Deloukas, Eleftheria Zeggini, George V Dedoussis","doi":"10.1109/JBHI.2026.3741223","DOIUrl":"10.1109/JBHI.2026.3741223","url":null,"abstract":"<p><p>The HUA BioResource (HUABR) is one of the first large-scale multicohort resources in Greece, integrating genetic and phenotypic data across 16 national studies. This paper presents the first comprehensive description of the HUA BioResource (HUABR), outlining its structure, data collection methodology, and research potential. The repository serves as a critical resource for investigating the interplay between genetics, lifestyle, and body mass index (BMI), enabling advanced analyses of obesity and obesity-related cardiometabolic disorders. Initial findings highlight significant associations between BMI and genetic predisposition as well as lifestyle, contextual and clinical factors, with polygenic risk scores (PRSs) enhancing obesity prediction models. By creating one of the first databases with unified, multidisciplinary data for Greek citizens, the HUA Bioresource fosters international collaborations and advances precision medicine, public health, and targeted prevention strategies.</p>","PeriodicalId":13073,"journal":{"name":"IEEE Journal of Biomedical and Health Informatics","volume":"PP ","pages":""},"PeriodicalIF":7.7,"publicationDate":"2026-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149127420","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}