Biodata Mining最新文献

{"title":"A framework for cognitive personality priors in agentic AI: the role of personas in autonomous team science.","authors":"Asma J Nawaz, Jake R Patock, Itzel Valencia, Binglan Li, Jacob S Berkowitz, Stefany Coxe, Itai Danovitch, Nicholas P Tatonetti, Jason H Moore","doi":"10.1186/s13040-026-00598-2","DOIUrl":"10.1186/s13040-026-00598-2","url":null,"abstract":"","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":"19 1","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13555974/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148913767","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"fourSynergy: ensemble-based interaction calling on 4C-seq data using gradient-free optimization.","authors":"Sophie-Marie Wind, Lucas Plagwitz, Jonas Dix, Gero Heidtmann, Dominik Heider, Carolin Walter","doi":"10.1186/s13040-026-00596-4","DOIUrl":"https://doi.org/10.1186/s13040-026-00596-4","url":null,"abstract":"<p><strong>Background: </strong>Chromatin organization plays a crucial role in gene regulation and is associated with various severe diseases like cancer. Since chromatin changes are potentially reversible, a deeper understanding of the alterations could be harnessed for the development of new therapies. Circular Chromosome Conformation Capture Sequencing (4C-seq) is a sequencing technique enabling the identification of chromatin interactions between genes and regulatory elements. This work aims to develop an ensemble algorithm that utilizes synergies among available 4C-seq tools, which in turn allows to achieve improved 4C-seq chromatin interaction calling. We employed existing 4C-seq algorithms using a weighted-voting approach. By optimizing the tool weights according to various predictive performance metrics using gradient-free optimization strategies, we demonstrate the potential of combining multiple 4C-seq analysis tools for interaction calling.</p><p><strong>Results: </strong>Our results demonstrate that a weighted-voting-based ensemble approach significantly improves predictive performance in chromatin interaction detection in a leave-one-group-out cross-validation setting, achieving a mean F1-score of 0.31 and a mean AUPRC of 0.34, compared to 0.13 and 0.16, respectively. To make this approach accessible, we integrated it into fourSynergy, a 4C-seq analysis framework focusing on near-bait 4C-seq interactions that includes a Snakemake pipeline, an R/Bioconductor package, and an interactive Shiny application.</p><p><strong>Conclusions: </strong>This work provides not only a comprehensive curated collection of 4C-seq datasets, but also demonstrates that ensemble approaches can improve predictive performance in chromatin interaction detection compared to individual 4C-seq algorithms.</p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":"19 1","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13474968/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148766540","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrative evidence-knowledge marker selection enhances LLM-based cell type annotation in single-cell RNA-seq analysis.","authors":"Jiyeong Shin, Soyoung Jeong, Hyun Je Kim, Minsik Oh","doi":"10.1186/s13040-026-00593-7","DOIUrl":"10.1186/s13040-026-00593-7","url":null,"abstract":"<p><strong>Background: </strong>Cell type annotation is essential for gaining biological insight from single-cell RNA sequencing data, yet manual labeling remains time-consuming and difficult to reproduce. Various computational approaches have been developed to automate this process, and recent studies suggest that large language models can infer cell types with promising accuracy in single-cell analysis. However, most workflows still rely on cluster-specific markers derived from gene expression alone or manual curation. As a result, marker selection can be sensitive to statistical criteria and dataset-dependent bias, which may lead to the selection of less informative genes or missing important markers, while providing limited biological context.</p><p><strong>Results: </strong>To address this limitation, we introduce CELLIA, an LLM-based workflow for automated and robust cell type annotation. CELLIA employs an integrative evidence-knowledge marker selection strategy that combines statistical differential expression criteria with curated tissue-specific marker resources to identify informative marker genes. In benchmarking analyses of 102 cell types, this approach improved agreement with manual annotations. In addition, CELLIA achieved higher agreement in subtype-level analyses of closely related immune populations and was further evaluated in a non-immune stromal subtype setting, covering 25 cell types in total.</p><p><strong>Conclusion: </strong>By integrating evidence-knowledge from gene expression with curated biological prior knowledge, CELLIA provides a more stable marker selection and improves the reliability of LLM-cell type annotation.</p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":"19 1","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13560450/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148921481","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Clifti-GPT: privacy-preserving federated fine-tuning and transferable inference of foundation models on clinical single-cell data.","authors":"Mohammad Bakhtiari, Maria Louise Elkjaer, Ali Oğuz Can, Fabian Theis, Mhaned Oubounyt, Jan Baumbach","doi":"10.1186/s13040-026-00582-w","DOIUrl":"10.1186/s13040-026-00582-w","url":null,"abstract":"<p><p>Foundation models have demonstrated immense value for scRNA-seq analysis, but their fine-tuning or inference on heterogeneous, privacy-sensitive clinical cohorts is governed by strict data protection policies, which often prohibit centralization. We introduce Clifti-GPT, a privacy-preserving federated framework based on secure multi-party computation (SMPC) that enables collaborative model training and transferable inference, where zero-shot predictions are performed across decentralized clinical repositories by securely aggregating local statistics rather than transferring data embeddings, without sharing patient data, clinical-level statistics, or models. Built upon the scGPT foundation model, Clifti-GPT achieves performance within 4% of centralized scGPT baselines in accuracy, precision, recall, and macro-F1 for cell type classification and reference mapping across six datasets. Furthermore, it demonstrates rapid convergence in terms of communication rounds, reaching 99% of centralized performance on cell type classification in at most two federated rounds on two evaluated datasets, and scales robustly to 30 clients with less than 2% accuracy loss on a large-scale federated cell type classification setting. Our analysis shows that batch effects impact both Clifti-GPT and centralized baseline, while correction leads to similar results across evaluation metrics in heterogeneous settings for both models. Together, these results indicate that Clifti-GPT enables effective fine-tuning and application of single-cell foundation models across distributed clinical datasets in a manner that is GDPR-compatible by design and addresses real-world privacy and institutional data-governance requirements.</p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":"19 1","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13445909/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148680813","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Chest-X-ray based deep feature-driven framework for anemia detection insights from a large hospital cohort.","authors":"Hao-Chun Liao, Dung-Jang Tsai, Shan-Yueh Chang, Chin Lin, Shih-Hua Lin, Wen-Hui Fang","doi":"10.1186/s13040-026-00588-4","DOIUrl":"10.1186/s13040-026-00588-4","url":null,"abstract":"<p><strong>Background: </strong>Anemia is a common global health problem traditionally diagnosed through laboratory hemoglobin testing, which requires invasive blood sampling. This study evaluated the feasibility of using a chest X-ray (CXR)-based deep feature-driven framework for noninvasive anemia prediction.</p><p><strong>Patients and methods: </strong>We conducted a retrospective cohort study using data from Tri-Service General Hospital, Taipei, Taiwan, collected between June 2016 and February 2022. A total of 305,793 adults aged ≥ 20 years who had at least one CXR were included. The dataset was divided into development, tuning, internal validation, and external validation sets. A two-stage framework leveraging a pretrained Vision Transformer (ViT-B/32) encoder for feature extraction, followed by a downstream logistic regression classifier, was developed to predict anemia (Hb ≤ 10 g/dL) from CXR images without model fine-tuning.</p><p><strong>Results: </strong>The framework for predicting anemia showed strong performance, with an AUC of 0.845 in the internal validation set (sensitivity 68.5%, specificity 84.7%) and 0.852 in the external set (sensitivity 71.5%, specificity 83.2%). Subgroup analysis revealed better diagnostic accuracy with computed radiography, posteroanterior view, and in males aged 55 to 64, while younger females had lower accuracy. The framework, especially when combined with clinical variables, outperformed other clinical models.</p><p><strong>Conclusion: </strong>This study presents a deep feature extraction approach for opportunistic moderate-to-severe anemia anemia screening using chest X-rays. With further validation, this model may facilitate early identification of anemia in routine clinical practice.</p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":"19 1","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13555854/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148913729","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"EMMA-STRAT: a multi-omics based machine learning framework for stratification of endometrial carcinoma molecular subtypes and MSI status.","authors":"Naisarg Patel, Andres Salumets, Vijayachitra Modhukur","doi":"10.1186/s13040-026-00587-5","DOIUrl":"https://doi.org/10.1186/s13040-026-00587-5","url":null,"abstract":"<p><strong>Background: </strong>Uterine Corpus Endometrial Carcinoma (UCEC) is the most common gynecologic malignancy, with molecular heterogeneity influencing prognosis and treatment response. Although TCGA-defined molecular subtypes and multi-omics datasets have improved biological understanding of UCEC, externally evaluated computational frameworks for molecular stratification remain limited. To address this, we developed EMMA-STRAT, a supervised multi-omics machine learning framework integrating mRNA expression, miRNA expression, and DNA methylation data to classify UCEC genomic subtypes and microsatellite instability (MSI) status.</p><p><strong>Results: </strong>Using the TCGA cohort (N = 433) for model development and internal validation, we benchmarked six classifiers and evaluated final model performance on two independent Clinical Proteomic Tumor Analysis Consortium (CPTAC) cohorts (N = 95 and N = 108). Multi-omics integration consistently outperformed single-omics models, with RNA expression as the strongest standalone modality. For MSI-H versus MSS classification, a LightGBM model trained on 20 SVM-selected features per omics layer achieved an internal balanced accuracy of 98.1% and external balanced accuracies of 93.1-94.9%. For four-class genomic subtyping, a Multi-Layer Perceptron trained on 50 LASSO-selected features per omics layer achieved an internal balanced accuracy of 89.1% and external balanced accuracies of 84.7-86.2%. Both models showed favorable discrimination and probability calibration relative to reference baselines, although calibration estimates for low-prevalence classes including POLE should be interpreted cautiously. SHapley Additive exPlanations (SHAP)-based interpretability analysis identified model-selected features including MLH1, CDKN2A, PPP4R4, and hsa-miR-378a, with downstream analyses supporting their biological plausibility. All results are openly accessible via an interactive browser at https://naisarg14.github.io/EMMA-STRAT-web-viewer/index.html .</p><p><strong>Conclusions: </strong>EMMA-STRAT provides an externally evaluated, research-grade computational framework for multi-omics molecular stratification of endometrial carcinoma. Integration of mRNA, miRNA, and DNA methylation data supported prediction of MSI-H versus MSS status and TCGA-defined genomic subtypes across independent cohorts. However, since EMMA-STRAT requires multi-omics data and was not directly compared with established clinical classifiers, it should currently be interpreted as a research-oriented molecular stratification framework rather than a clinically deployable decision-making model. The developed framework provides a basis for future prospective validation, incorporation of clinicopathological variables, and direct comparison with ProMisE-based or integrated clinical risk models.</p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":"19 1","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13474893/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148763488","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Exploring the use of machine and deep learning in genome-wide association studies: a comprehensive review.","authors":"Salvatore D'Antona, Mawada Elmagboul Abdalla Abakar, Daniele Ramazzotti, Marco Antoniotti, Alex Graudenzi","doi":"10.1186/s13040-026-00584-8","DOIUrl":"10.1186/s13040-026-00584-8","url":null,"abstract":"<p><p>The advent of high-throughput sequencing technologies has generated increasingly large and complex genomic datasets, necessitating analytical approaches capable of capturing high-dimensional and potentially nonlinear genetic interactions. This situation has significantly impacted the entire field of Genome-Wide Association Study (GWAS), whose primary goal is the identification of genomic traits and variants that are statistically associated with the risk of a disease. However, traditional GWAS methods may show reduced performance when applied to highly polygenic and nonlinear genetic architectures. Computational strategies from Artificial Intelligence (AI) and, in particular, from machine- and deep-learning may provide a powerful tool to overcome such limitations, especially by capturing nonlinear interactions and complex hidden regularities in large-scale data, which traditional GWAS approaches might overlook. To date, only a few approaches have been introduced and systematically assessed. In this review, we describe the main characteristics and limitations of standard statistical approaches for GWAS, the main uses of AI methods in computational genomics, and recent attempts to leverage AI strategies in GWAS. Particular attention will be devoted to key issues, such as the interpretability of methods and results, and the curse of dimensionality. More specifically, the review presents 30 methods designed to leverage AI in GWAS, as well as presenting a comprehensive set of evaluation metrics for their performance, also providing references to the most frequently used databases, and biobanks. Overall, this work may serve as a starting point for both dry- and wet-lab researchers, aiming to extract deeper insights from genomic data by moving beyond traditional linear additive assumptions, and leveraging large-scale datasets through AI-driven approaches.</p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":" ","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13540885/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148537505","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"From unlabeled to labeled: self-supervised deep learning in computational pathology.","authors":"Taymaz Akan, Richa Aishwarya, Md Shenuarin Bhuiyan, Steven A Conrad, John A Vanchiere, Mohammad Alfrad Nobel Bhuiyan","doi":"10.1186/s13040-026-00586-6","DOIUrl":"10.1186/s13040-026-00586-6","url":null,"abstract":"<p><strong>Purpose: </strong>The advancement of decision support systems for pathology and their implementation in clinical practice have been limited by the necessity for extensive, manually annotated datasets. Self-supervised learning (SSL) automates the extraction and interpretation of histopathological features from unannotated images, facilitating efficient model development without dependence on expert labeling. In this study, we introduce the SSL-HistoNet model that learns disease-relevant morphological representations from histopathological images through self-supervised learning.</p><p><strong>Materials and methods: </strong>We applied it to WGA-stained skeletal muscle tissues from mouse models of amyotrophic lateral sclerosis (ALS) and Type I diabetes to explore its ability to capture pathological muscle phenotypes in an annotation-free setting. Following pretraining on unlabeled data, the SSL encoder was further integrated with an attention-guided classifier to evaluate its capacity to identify pathological muscle alterations.</p><p><strong>Results: </strong>SSL-HistoNet achieved a precision of 0.98, a recall of 0.98, and an AUC of 0.98, demonstrating performance comparable to or outperforming state-of-the-art supervised models. Alongside high discriminative performance, exploratory feature analyses demonstrated consistent class-level changes in morphology-related patterns identified through representation learning.</p><p><strong>Conclusion: </strong>These findings highlight the capability of SSL-HistoNet as an annotation-free framework for outlining disease-specific tissue structures, reducing manual labeling demands and mitigating inter- and intra-observer variability in histological processes.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":" ","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13656617/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148457314","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A three-level risk stratification algorithm for arrhythmia based on CNN-LSTM palindromic structure.","authors":"Hua Zhang, Jing Li, Mingjie Wang, Xuexi Xuan, Kai Xia, Yuanyuan Tan, Li Li, Jianfeng Chen, Haiyan Wang","doi":"10.1186/s13040-026-00585-7","DOIUrl":"10.1186/s13040-026-00585-7","url":null,"abstract":"<p><p>Cardiovascular diseases are characterized by sudden onset, high mortality rates, and high recurrence rates, making early screening and timely intervention essential. However, due to insufficient medical resources, real-time and refined electrocardiogram monitoring of patients is difficult to implement. Meanwhile, the complex spatiotemporal features of electrocardiogram (ECG) signals bring challenges to multidimensional feature mining and accurate recognition. Therefore, in this study, we propose a three-level risk stratification algorithm for arrhythmia, which not only ensures precise intervention for different types of arrhythmias to achieve optimized allocation of medical resources but also comprehensively captures the spatiotemporal features of ECG signals for high-accuracy risk stratification detection. The algorithm first proposes a three-level arrhythmia risk stratification scheme, classifying cases as Normal, Not Life-threatening, and Life-threatening, with corresponding intervention measures of no need for monitoring, close attention, and immediate intervention, respectively. The core model of this algorithm is a deep learning fusion network based on the palindromic structure of Convolutional Neural Network (CNN) and Long Short-Term Memory network (LSTM), which enables precise three-level risk detection for all types of arrhythmias. Experimental results demonstrate that the algorithm exhibits favorable generalization performance across multiple datasets. It not only outperforms standalone CNN and LSTM models but also surpasses classical classifiers. Notably, on the 2-second ECG segments from the gold-standard dataset, it achieves an accuracy of 99.68% and a Specificity of 99.65%.The 10-fold cross-validation yields an accuracy of 99.62% ± 0.09% for 3-second segments, and patient-level validation on 10-second segments achieves an accuracy of 96.5%. The satisfactory results across varied segment lengths verify the reliability and practicality of the proposed method. In both arrhythmia risk stratification and detection tasks, the algorithm presents moderate competitive advantages.</p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":" ","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13640309/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148425454","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cardio-respiratory deep learning model to predict hospital admission from emergency department electrocardiogram images and respiration videos: a prospective study.","authors":"Guang-Yuan Chen, Shao-Chi Lu, Wen-Hsiang Cheng, Jun-Wan Gao, Jen-Tang Sun, Chien-Hua Huang, Chu-Lin Tsai, Li-Chen Fu","doi":"10.1186/s13040-026-00583-9","DOIUrl":"10.1186/s13040-026-00583-9","url":null,"abstract":"<p><strong>Background: </strong>Early prediction of hospital admission at the emergency department (ED) triage can improve patient flow and resource allocation. Most existing models rely solely on structured data. Incorporating multimodal physiologic information, such as cardiac and respiratory signals, may better capture subtle clinical signs. This study aimed to develop a deep learning fusion model that integrates electrocardiogram (ECG) images and respiration videos to predict hospital admission at ED triage.</p><p><strong>Methods: </strong>We prospectively collected ECG images and respiration videos from adult ED patients in a tertiary medical center. The proposed model consisted of modality-specific branches: an ECG branch using transfer learning, a respiration-signal-estimation pipeline, and a spatial attention module to enhance cardiopulmonary feature extraction. Class-balanced loss was applied to address dataset imbalance. Model performance was compared with the baseline Taiwan Triage Acuity Score (TTAS) and single-modality variants. Attention heatmaps using score-class activation mapping (score-CAM) were analyzed for interpretability.</p><p><strong>Results: </strong>The study included 118 patients, with a 27% admission rate. The ECG-respiration fusion model achieved an accuracy of 0.814, a recall of 0.749, a precision of 0.635, an F1-score of 0.680, an area under the receiver operating characteristic curve (AUROC) of 0.863, and an area under the precision-recall curve (AUPRC) of 0.675, outperforming both TTAS and single-modality models. Ablation analyses confirmed the additive value of spatial attention and class-balanced loss. Score-CAM visualizations indicated the model focused on physiologically relevant features, such as respiratory waveform inflection points.</p><p><strong>Conclusions: </strong>A multimodal deep learning approach combining ECG and respiration video signals can predict hospital admission at ED triage. Integrating such models into triage systems may enhance earlier risk identification and resource prioritization.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":" ","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13563894/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148413420","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}