Explore the vast range of titles available.

Real-world data (RWD) are increasingly used in health research and regulatory decision-making to assess the effectiveness, safety, and value of interventions in routine care. However, the heterogeneity of European health care systems, data capture methods, coding standards, and governance structures poses challenges for generating robust and reproducible real-world evidence. The European Health Data & Evidence Network (EHDEN) was established to address these challenges by building a large-scale federated data infrastructure that harmonizes RWD across Europe. This study aims to describe the composition and characteristics of the databases harmonized within EHDEN as of September 2024. We seek to provide transparency regarding the types of RWD available and their potential to support collaborative research and regulatory use. EHDEN recruited data partners through structured open calls. Selected data partners received funding and technical support to harmonize their data to the Observational Medical Outcomes Partnership Common Data Model (OMOP CDM), with assistance from certified small-to-medium enterprises trained through the EHDEN Academy. Each data source underwent an extract-transform-load process and data quality assessment using the data quality dashboard. Metadata-including country, care setting, capture method, and population criteria-were compiled in the publicly accessible EHDEN Portal. As of September 1, 2024, the EHDEN Portal includes 210 harmonized data sources from 30 countries. The highest representation comes from Italy (13%), Great Britain (12.5%), and Spain (11.5%). The mean number of persons per data source is 2,147,161, with a median of 457,664 individuals. Regarding care setting, 46.7% (n=98) of data sources reflect data exclusively from secondary care, 42.4% (n=89) from mixed care settings (both primary and secondary), and 11% (n=23) from primary care only. In terms of population inclusion criteria, 55.7% (n=117) of data sources include individuals based on health care encounters, 32.9% (n=69) through disease-specific data collection, and 11.4% (n=24) via population-based sources. Data capture methods also vary, with electronic health records (EHRs) being the most common. A total of 74.7% (n=157) of data sources use EHRs, and more than half of those (n=85) rely on EHRs as their sole method of data collection. Laboratory data are used in 29.5% (n=62) of data sources, although only one relies exclusively on laboratory data. Most laboratory-based data sources combine this method with other forms of data capture. EHDEN is the largest federated health data network in Europe, enabling standardized, General Data Protection Regulation-compliant analysis of RWD across diverse care settings and populations. This descriptive summary of the network's data sources enhances transparency and supports broader efforts to scale federated research. These findings demonstrate EHDEN's potential to enable collaborative studies and generate trusted evidence for public health and regulatory purposes.

Syndromic surveillance now forms an integral part of the surveillance for a wide range of hazards in many countries. Establishing syndromic surveillance systems can be difficult due to the many different sources of data that can be used, cost pressures, the importance of data security, and the presence of different (and rapidly evolving) technologies. Here we describe major points in the development of the UK Health Security Agency English real-time syndromic surveillance service over its first 2 decades (1998 to 2018). We identify the key wider themes that we believe are important in ensuring a sustainable and useful syndromic surveillance service. We conducted semistructured interviews with current members of the UK Health Security Agency syndromic surveillance team who were involved from the earliest stages and previous senior colleagues who were supportive of the syndromic surveillance work during the early phases. For this viewpoint, we partitioned the development of syndromic surveillance in England into 3 time periods: 1998 to 2005 (“the beginnings”); 2006 to 2011 (“the growth phase”); and 2012 to 2018 (“mainstream”). We asked the interviewees for their views about the development of syndromic surveillance, and in particular the main drivers and events, the team and system, and outputs and uses. The results from the interviews highlighted some key themes including the integration of syndromic surveillance into the public health system, creativity, good collaboration and teamwork, leadership and determination to persevere, and agility and the ability to adapt to new threats. Using the results of the discussions and our personal experience of running the syndromic surveillance service from inception and over decades, we constructed a set of recommendations for establishing and running sustainable syndromic surveillance systems. In this age of increased automation, with the ability to transfer data in real-time and to use machine learning and artificial intelligence, we are approaching a “new age of syndromic surveillance.” We consider that the focus on the public health questions, relationships, collaboration, leadership, and true teamwork should not be underestimated in the success of and usefulness of real-time syndromic surveillance systems.

The European Health Data Space (EHDS) aspires to enable secure, interoperable, and decentralized health data usage across Europe. This paper explores legal and technical challenges in implementing EHDS goals, particularly for secondary data use. It highlights federated and swarm learning as promising yet complex solutions, requiring robust infrastructure, standardization, and regulatory clarity. We emphasize the need for coordinated legislative and technological advances to realize EHDS ambitions.

Mental health (MH) issues are the leading cause of mortality for young people, highlighting the importance of timely, high-quality, and affordable care. However, recent trends show a deceleration in the growth of youth mental health (YMH) services capacity in Australia. Meanwhile, digital interventions hold significant potential to sustain and enhance YMH outcomes. This study aimed to evaluate (1) the comparative impact of different services capacity growth trajectories on YMH outcomes and (2) whether digital interventions can offset rising demand and declining workforce capacity, to offer insights into strategic resource allocation for sustained improvements. Participatory system dynamics modeling was used to investigate the impact of MH services capacity growth trajectories and digital interventions on YMH outcomes, with simulation results projected for 2025-2035. The study focused on individuals aged 15-24 years from a culturally diverse, rapidly expanding urban population in Australia. Outcomes assessed included years lived with psychological distress and disorders, MH-related emergency department presentations, and self-harm hospitalizations. Among the services modeled, doubling the growth rates for specialized MH services had the greatest impact (8.4% reduction in cumulative years lived with symptomatic mental disorder). Doubling the growth rates for specialized MH service, headspace (headspace National Youth Mental Health Foundation Ltd), and referrals to online services, together, could significantly enhance YMH outcomes. Compared to baseline, this strategic investment approach is projected to reduce cumulative years spent with symptomatic mental disorders, cumulative MH-related emergency department presentations, and cumulative self-harm hospitalizations by 14%, 6.4%, and 4.1%, respectively, from 2025 to 2035. Digital interventions alone produced comparable impacts to specialized services, but critically, could not prevent worsening outcomes when specialized services experienced degrowth. Combining digital interventions with expansion of specialized services yielded best outcomes with reductions of 15%, 5.1%, and 4.4% in these indicators, respectively. The findings emphasize digital technologies as an effective interim and long-term solution to mitigate the slow and uncertain growth in the specialized MH workforce. However, simulation results showed that achieving sustained long-term improvements necessitates concurrent investment in expanding the specialized MH workforce, as digital interventions alone cannot compensate for degradation in specialized services capacity. A strategic combined approach offers the most effective pathway to improving YMH outcomes.

Electrocardiogram (ECG) data constitutes one of the most widely available biosignal data in clinical and research settings, providing critical insights into cardiovascular diseases as well as broader health conditions. Advancements in deep learning demonstrate high performance in diverse ECG classification tasks, ranging from arrhythmia detection to risk prediction for various diseases. However, the widespread adoption of deep learning for ECG analysis faces significant barriers, including the heterogeneity of file formats, restricted access to pretrained model weights, and complex technical workflows for out-of-domain users. This study aims to address major bottlenecks in ECG-based deep learning by introducing ExChanGeAI, an open-source, web-based platform designed to offer an integrated, user-friendly platform for ECG data analysis. Our objective is to streamline the entire workflow-from initial data ingestion (regardless of device or format) and intuitive visualization to privacy-preserving model training and task-specific fine-tuning-making advanced ECG deep learning accessible for both clinical researchers and practitioners without machine learning (ML) expertise. ExChanGeAI incorporates robust preprocessing modules for various ECG file types, a set of interactive visualization tools for exploratory data analysis, and multiple state-of-the-art deep learning architectures for ECGs. Users can choose to train models from scratch or fine-tune pretrained models using their own datasets, while all computations are performed locally to ensure data privacy. The platform is adaptable for deployment on personal computers as well as scalable to high-performance computing infrastructures. We demonstrate the platform's performance on several clinically relevant classification tasks across 3 external and heterogeneous validation datasets, including a newly curated test set from routine care, evaluating both model generalizability and resource efficiency. Our experiments show that de novo training with user-provided, task-specific data can outperform a leading foundation model, while requiring substantially fewer parameters and computational resources. The platform enables users to empirically determine the most suitable model for their specific tasks, based on systematic validations, while lowering technical barriers for out-of-domain experts and promoting open research. ExChanGeAI provides a comprehensive, privacy-aware platform that democratizes access to ECG analysis and model training. By simplifying complex workflows, ExChanGeAI empowers out-of-domain researchers to use state-of-the-art ML on diverse datasets, democratizing the access to ML in the field of ECG data. The platform is available as open-source code under the Massachusetts Institute of Technology (MIT) license.

Recent natural language processing breakthroughs, particularly with the emergence of large language models (LLMs), have demonstrated remarkable capabilities on general knowledge benchmarks. However, there is limited data on the performance and understanding of these models in relation to the Fast Healthcare Interoperability Resources (FHIR) standard. The complexity and specialized nature of FHIR present challenges for LLMs, which are typically trained on broad datasets and may have a limited understanding of the nuances required for domain-specific tasks. Improving health data interoperability can greatly benefit the use of clinical data and interaction with electronic health records. This study presents the Fast Healthcare Interoperability Resources (FHIR) Workbench, a comprehensive suite of datasets designed to evaluate the ability of LLMs to understand and apply the FHIR standard. In total, 4 evaluation datasets were created to assess the FHIR knowledge and capabilities of LLMs. These tasks include multiple-choice questions on general FHIR concepts and the FHIR Representational State Transfer (REST) application programming interface, as well as correctly identifying the resource type and generating FHIR resources from unstructured clinical patient notes. In addition, we evaluate open-source LLMs, such as Qwen 2.5 Coder and DeepSeek-V3, and commercial LLMs, including GPT-4o and Gemini 2, on these tasks in a zero-shot setting. To provide context for interpreting LLM performance, a subset of the datasets was human-evaluated by recruiting 6 participants with varying levels of FHIR expertise. Our evaluation across multiple FHIR tasks revealed nuanced performance metrics. Commercial models demonstrated exceptional capabilities, with GPT-4o achieving a 0.9990 F1-score on the FHIR-ResourceID task, 0.9400 on the FHIR-QA task, and 0.9267 on the FHIR-RESTQA task. Open-source models also demonstrated strong performance, with DeepSeek-v3 achieving 0.9400 on FHIR-QA, 0.9400 on FHIR-RESTQA, and 0.9142 on FHIR-ResourceID. Qwen 2.5 Coder-7B-Instruct demonstrated high accuracy, scoring 0.9533 on FHIR-QA and 0.8920 on FHIR-ResourceID. However, all models struggled with the Note2FHIR task, with performance ranging from 0.0382 (OLMo) to a maximum of 0.3633 (GPT-4.5-preview), highlighting the significant challenge of converting unstructured clinical text into FHIR-compliant resources. Human participants achieved accuracy scores ranging from 0.50 to 1.0 across the first 3 tasks. This study highlights the competitive performance of both open-source models, such as Qwen and DeepSeek, and commercial models, such as GPT-4o and Gemini, in FHIR-related tasks. While open-source models are advancing rapidly, commercial models still have an advantage for specific, complex tasks. The FHIR Workbench offers a valuable platform for evaluating the capabilities of these models and promoting improvements in health data interoperability.

Ovarian follicles and endometrial thickness are monitored repeatedly for assisted reproduction, burdening patients and clinics. Self-scans with a home ultrasound device can relieve this. We aimed to evaluate the reliability of self-scans using the smartphone-based Pulsenmore follicle count vaginal self-scan device (FC) versus in-clinic (IC) sonographies, in ovarian stimulation for in-vitro fertilization or fertility preservation. This study is a single-center, interventional, controlled, prospective study including 44 patients without pelvic pathologies undergoing stimulation for in-vitro fertilization (2022-2024). Following training, patients used a vaginal home ultrasound device to scan their uterus and ovaries with remote guidance by a sonographer in each cycle check-point. Clinical decisions were based on standard IC sonographies. FC and IC results were compared for image quality, endometrial thickness, and follicle count or size. Aspirated oocyte numbers were compared to the follicles recorded at the last visit by home and IC scans. Absolute differences in follicular count and endometrial thickness between IC and FC scans were compared using means, SDs, and 95% CIs. The Spearman correlation (r) analyzed the relations between IC and FC outcomes. All tests applied were 2-tailed, with a P value of ≤5% considered statistically significant. Patient and sonographer satisfaction were assessed via surveys. Of 44 patients, 34 completed this study. The mean age was 34.7 (SD 4.0) years, and BMI was 25.8 (SD 5.0) kg/m². A total of 65% (22/34) pursued fertility preservation and 35% (12/34) aimed to conceive. The image quality scores of all home scans were at a minimum suitable level, with most of better quality. FC measurements closely matched IC findings for key clinical parameters: antral follicle count (mean FC 11.94, SD 6.62 vs mean IC 15.23, SD 10.2, ρ=0.86, P<.001); number of stimulated follicles ≥10 mm (FC 12.19, SD 6.27 vs IC 13.5, SD 8.87, ρ=0.84, P<.001); identification of the leading follicle >14 mm (achieved in 87% of FC scans); and follicular number or size pretriggering. The aspirated oocyte or last-visit stimulated follicles (>10 mm; FC 1.12, SD 0.6 vs IC 1.06, SD 0.56, ρ=0.82, P<.001), mature oocytes or follicles >13 mm ratios (FC 1.28, SD 1.11 vs IC 1.04, SD 0.77, ρ=0.88, P<.001), and endometrial thickness pretriggering (FC 9.87, SD 2.2 mm vs IC 9.63, SD 2.7 mm, ρ=0.54, P=.002) were well-correlated between the home and standard scans, with 87.1% concordance in identifying endometrial adequacy (≥7 mm). In the patient survey, 82% (28/34) expressed interest in future use of the FC device. In the sonographer survey, 91% (31/34) demonstrated patient improvement. The home ultrasound device was feasible, comparable, and well-correlated with standard IC scans, laying the basis for remote home-based monitoring of follicular development during ovarian stimulation. We believe this also applies to monitoring milder stimulations and even natural cycles.

The cerebrospinal fluid drainage test is crucial for evaluating patients with idiopathic normal pressure hydrocephalus (iNPH) before shunt surgery, while traditional methods have low sensitivity. This study aimed to evaluate the improvement of cognitive and gait parameters after external lumbar drainage (ELD) through the application of digital tests and to investigate the predictive value of digital cognitive and gait assessments for shunt outcomes. A total of 70 patients with probable iNPH were enrolled from the West China Hospital of Sichuan University. All patients underwent traditional and digital cognitive and gait assessments at baseline and 3 days after ELD. Thirty-nine patients received lumboperitoneal shunt and were followed up at 3, 6, and 12 months postoperatively using the modified Rankin scale and the Japanese iNPH grading scales. Firth logistic regression models and receiver operating characteristic analysis were used to assess the predictive value of digital tests for shunt response. The performance of the digital tests, including one-back test (P=.01), the Stroop color-word test (P=.009), and gait parameters, exhibited significant improvement 3 days post-ELD. Of the 39 shunted patients, 34 exhibited at least 1-point improvement in modified Rankin scale or iNPH grading scales postshunt at their last follow-up. Greater improvement rates in combined digital neuropsychological and gait tests after ELD were associated with a lower risk of unfavorable shunt outcome (adjusted odds ratio=0.98; P=.03). Combined digital neuropsychological and gait tests outperformed traditional tests in distinguishing shunt responders (area under receiver operating characteristic curves=0.92 vs 0.55, P=.015). Our study shows that digital neuropsychological and gait tests enhance predictive efficacy when compared to traditional testing methods. It could serve as objective evaluation tools for assessing patients with iNPH.

Metabolic dysfunction-associated steatohepatitis (MASH) cirrhosis is a leading indication for liver transplantation (LT). Patients with MASH cirrhosis are complex and often have extensive comorbidities. The current model for end-stage liver disease (MELD)-based liver allocation system has suboptimal concordance in predicting waitlist mortality for patients with MASH cirrhosis. Furthermore, it does not capture the competing outcomes of death and LT on the liver transplant waitlist. A competing risk analysis using deep learning was conducted to forecast waitlist trajectories of patients with MASH cirrhosis using data available at the time of waitlisting. A deep learning competing risk model was constructed using data from 17,551 waitlisted patients with MASH cirrhosis in the Scientific Registry of Transplant Recipients (SRTR) based on the DeepHit model framework with five-fold cross-validation. Model performance was evaluated and compared to single-risk Cox proportional hazards and random survival forests (RSF) models in predicting death or transplant using the concordance index and Brier score. Additionally, a novel performance metric, the competing event coherence (CEC) score, was developed to evaluate model performance in the setting of competing risks. Features associated with death and transplant in the DeepHit model were identified using permutation importance. Models were externally validated on data from the University Health Network. A total of 17,551 patients were included. The mean MELD at listing was 19.4 (SD 8.1). At 120 months of follow-up on the waitlist, 54.6% (9599/17551) of patients underwent LT, 25.6% (4510/17551) of patients died or were removed due to deterioration, and 19.8% (3442/17551) of patients were removed for improvement or were censored. In a competing risk scenario, DeepHit achieved the best CEC scores at 1 (0.813), 3 (0.811), 6 (0.794), and 12 months (0.772) on the waitlist. The cause-specific RSF model had the highest concordance indices for death or transplant at all time points (death: 0.874 at 1 month, 0.840 at 6 months, and 0.814 at 12 months) except for death at 3 months, where DeepHit (0.883) outperformed RSF. RSF also had lower Brier scores overall, except for transplant at 12 months, where DeepHit outperformed RSF (0.206 vs 0.228). These results were similar on external validation. On feature importance assessment, MELD at listing and its components, as well as functional status, age, and blood type, were associated with death and transplant on the waitlist. A deep learning competing risk analysis can forecast the risks of both death and transplant in patients with MASH on the waitlist, helping to inform clinical decisions by identifying the most impactful covariates for each outcome.

Global digitalization continues to advance, extending its influence into medicine and health care systems worldwide. In recent years, substantial advancements have been made in the research and development of artificial intelligence (AI), raising questions about its potential in medicine. The integration and application of AI in intensive care medicine, particularly in sepsis treatment, presents significant potential for advancing patient outcomes and enhancing patient-relevant benefits. However, a comprehensive and systematic overview of the full spectrum of patient-relevant benefits associated with AI-based clinical decision support systems (CDSS) remains lacking. This scoping review aimed to identify and categorize evidence on patient-relevant benefits of AI-based CDSS in sepsis care. Systematic research was conducted in 4 electronic databases: MEDLINE via PubMed, Embase, the ACM Digital Library, and IEEE Xplore. In addition, a comprehensive search on the websites of relevant international organizations, along with a citation search of the included articles, was conducted. Articles were included if they (1) focused on sepsis and (2) described patient-relevant benefits of AI-based CDSS. Articles published between January 1, 2008, and March 2, 2023, were considered for inclusion. Study selection was performed independently by 2 reviewers. The manuscript was drafted in accordance with the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) checklist. The analysis of the included articles was conducted using the program MAXQDA (VERBI Software GmbH), with systemization finalized in a consensus workshop. A total of 3368 records were identified across the 4 databases, of which 24 met the inclusion criteria and were included in the scoping review. The additional search on international websites and in reference lists identified 6 more relevant articles, resulting in 30 included studies. Of these, 20 were quantitative, comprising 7 prospective and 13 retrospective designs. In addition, 1 qualitative study, 1 mixed methods study, 6 review articles, and 2 articles from institutional websites were included. Patient-relevant benefits were systematized in six main categories: (1) prediction, (2) earlier treatment and prioritization of high-risk patients, (3) individualized therapy, (4) improved patient outcomes (including improved Sequential Organ Failure Assessment score, reduced length of stay, and reduced mortality), (5) general improvements in care, and (6) reduced readmission rate. This scoping review underscores the potential of AI-based CDSS to positively impact patient-relevant benefits, particularly in sepsis care, where they demonstrate considerable promise for improving intensive care. However, the majority of the identified studies rely on retrospective database analyses. Future research should focus on validating these findings through prospective studies.