In clinical trials, recently introduced respiratory syncytial virus (RSV) immunisation products have shown high efficacy in preventing severe RSV outcomes. Implementing successful immunisation programmes is however key to realising these benefits in real-world settings. We aimed to investigate uptake of the long-acting monoclonal antibody nirsevimab, the RSV maternal vaccine, and RSV vaccines for older adults in countries where immunisation programmes have been introduced, and to explore how uptake varies between countries and population subgroups. In this systematic review and meta-analysis, we carried out four monthly searches in Medline, Embase, and Global Health databases for studies reporting uptake of nirsevimab, the RSV maternal vaccine, and RSV vaccines for older adults. We included population-based studies published between December 1, 2022 and February 5, 2025. Two independent reviewers screened studies, extracted data, and completed a risk of bias assessment using the Joanna Briggs Institute (JBI) Critical Appraisal Tools. We assessed uptake stratified by country and socio-demographic and clinical subgroups. Meta-analyses were conducted using random-effects modelling. PROSPERO registration number: CRD42025643585. We screened a total of 1267 studies, 43 of which met the inclusion criteria reporting data on over 1.38 million individuals from six countries. Nirsevimab uptake data were reported in 34 studies: 16 from Spain, eight from the United States, seven from France, one with combined data from Andorra and Spain, and one from each of Italy and Luxembourg. Our pooled estimates showed that nirsevimab uptake on population level was 90.1% (95% confidence interval (CI): 86.4–92.9) in Spain and 51.2% (95% CI: 29.3–72.7) in the United States during the 2023/24 RSV season. Uptake data for the RSV maternal vaccine and RSV vaccines for older adults were reported in five and eight studies, respectively, all from the United States. Meta-analysis showed population-level uptake of 30.5% (95% CI: 20.6–42.6) and 18.2% (95% CI: 10.8–28.9), respectively. Uptake varied across subgroups. Uptake of nirsevimab varied substantially between the countries that have implemented infant RSV immunisation programmes. Despite the limited number of studies and the lack of more accurate data at national level the low uptake estimates for RSV maternal vaccine and RSV vaccines for older adults are concerning. National, clinical, and public health initiatives are needed to increase uptake of RSV immunisation products and ensure maximum benefit to people currently at risk of severe RSV outcomes. 10.13039/501100023699 Health Data Research UK , Inflammation and Immunity Driver Programme.

Secure and privacy-preserving health status representation learning has become a critical challenge in clinical prediction systems. While deep learning models require substantial high-quality data for training, electronic health records are often restricted by strict privacy regulations and institutional policies, particularly during emerging health crises. Traditional approaches to data integration across medical institutions face significant privacy and security challenges, as healthcare providers cannot directly share patient data. This work presents MultiProg, a secure federated learning framework for clinical representation learning. Our approach enables multiple medical institutions to collaborate without exchanging raw patient data, maintaining data locality while improving model performance. The framework employs a multi-channel architecture where institutions share only the low-level feature extraction layers, protecting sensitive patient information. We introduce a feature calibration mechanism that ensures robust performance even with heterogeneous feature sets across different institutions. Through extensive experiments, we demonstrate that the framework successfully enables secure knowledge sharing across institutions without compromising sensitive patient data, achieving enhanced predictive capabilities compared to isolated institutional models. Compared to state-of-the-art methods, our approach achieves the best performance across multiple datasets with statistically significant improvements.

The integration of multimodal Electronic Health Records (EHR) data has significantly advanced clinical predictive capabilities. Existing models, which utilize clinical notes and multivariate time-series EHR data, often fall short of incorporating the necessary medical context for accurate clinical tasks, while previous approaches with knowledge graphs (KGs) primarily focus on structured knowledge extraction. In response, we propose EMERGE, a Retrieval-Augmented Generation (RAG) driven framework to enhance multimodal EHR predictive modeling. We extract entities from both time-series data and clinical notes by prompting Large Language Models (LLMs) and align them with professional PrimeKG, ensuring consistency. In addition to triplet relationships, we incorporate entities' definitions and descriptions for richer semantics. The extracted knowledge is then used to generate task-relevant summaries of patients' health statuses. Finally, we fuse the summary with other modalities using an adaptive multimodal fusion network with cross-attention. Extensive experiments on the MIMIC-III and MIMIC-IV datasets' in-hospital mortality and 30-day readmission tasks demonstrate the superior performance of the EMERGE framework over baseline models. Comprehensive ablation studies and analysis highlight the efficacy of each designed module and robustness to data sparsity. EMERGE contributes to refining the utilization of multimodal EHR data in healthcare, bridging the gap with nuanced medical contexts essential for informed clinical predictions. We have publicly released the code at https://github.com/yhzhu99/EMERGE.

The COVID-19 pandemic highlighted the need for predictive deep-learning models in health care. However, practical prediction task design, fair comparison, and model selection for clinical applications remain a challenge. To address this, we introduce and evaluate two new prediction tasks—outcome-specific length-of-stay and early-mortality prediction for COVID-19 patients in intensive care—which better reflect clinical realities. We developed evaluation metrics, model adaptation designs, and open-source data preprocessing pipelines for these tasks while also evaluating 18 predictive models, including clinical scoring methods and traditional machine-learning, basic deep-learning, and advanced deep-learning models, tailored for electronic health record (EHR) data. Benchmarking results from two real-world COVID-19 EHR datasets are provided, and all results and trained models have been released on an online platform for use by clinicians and researchers. Our efforts contribute to the advancement of deep-learning and machine-learning research in pandemic predictive modeling.