Acutelines: a Dutch emergency department-based data-biobank for multimodal, longitudinal acute care research
van Wijk, R. J.; Lopez Alcaraz, J. M.; Schoonhoven, A. D.; Li, J.; Ter Horst, S.; ter Voert, M. A.; Eerens, A. M.; la Bastide, A. J.; Postema, J.; ter Maaten, J. C.; ter Avest, E.; Strodthoff, N.; Bouma, H. R.
Show abstract
Background: High-quality, longitudinal data from the Emergency Department (ED) are essential for understanding acute illness trajectories and for developing clinically deployable prediction models. However, most existing ED datasets are static, limited in modality or disconnected from long-term outcomes or biomaterials. Methods: We describe a two-year sample of Acutelines, a continuously operating ED-based data-biobank infrastructure at the University Medical Center Groningen. Acutelines is embedded in routine care and captures the full acute care trajectory and uses a stepped consent procedure. It integrates demographics, vital signs, laboratory results, diagnoses, treatments, waveforms, patient-reported outcomes, and prospectively collected biomaterials. Data are linked to in-hospital outcomes and post-discharge mortality. Results: The presented dataset comprises 29,314 ED visits from 18,850 adult patients. Clinical variables are available for nearly all visits, with additional data and questionnaires (n=4,963) and biomaterials (n=2,723) collected in predefined subgroups. Associations between early triage features (National Early Warning Score, vital signs, diagnostic categories) and outcomes, illustrate the clinical depth and longitudinal value of the infrastructure. Conclusion: Acutelines is a living, continuously expanding research infrastructure. Its combination of ED-first inclusion, multimodal data, linkage to long-term outcomes, and availability of biomaterials distinguishes it from existing datasets. Acutelines provides a robust foundation for hypothesis generation, translational research, and the development, validation, and benchmarking of data-driven clinical decision support tools and biomarker tests in acute medicine, while its ongoing expansion enables prospective studies and interventional research. Trial registration: Acutelines is registered at ClinicalTrials.gov under trial registration number NCT04615065.
Matching journals
The top 2 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Trans-sectoral patient pathways in urgent and emergency care: a Study Protocol for a prospective mixed-methods study in Germany (TRANSPARENT Study) 93%
- COVID Outcome Prediction in the Emergency Department (COPE): Development and validation of a model for predicting death and need for intensive care in COVID-19 patients 92%
- Development and validation of automated computer aided-risk score for predicting the risk of in-hospital mortality using first electronically recorded blood test results and vital signs for COVID-19 hospital admissions: a retrospective development and validation study 91%
Similar papers in this journal
- Prognostic accuracy of emergency department triage tools for adults with suspected COVID-19: The PRIEST observational cohort study 92%
- Accuracy of the National Early Warning Score version 2 (NEWS2) in predicting need for time-critical treatment: Retrospective observational cohort study 92%
- Hospitalizations for emergency-sensitive conditions in Germany during the Covid-19 pandemic Insights from the German-wide Helios hospital network 91%
Similar papers in this journal
- Derivation and validation of a triage tool for acutely ill adults with suspected COVID-19: The PRIEST observational cohort study 92%
- Triaging and Referring In Adjacent General and Emergency Departments (the TRIAGE trial): a cluster randomised controlled trial 91%
- LMIC-PRIEST: Derivation and validation of a clinical severity score for acutely ill adults with suspected COVID-19 in a middle-income setting 91%
Similar papers in this journal
- The impact of atypical intrahospital transfers on patient outcomes: a mixed methods study 91%
- Systematic identification of rare disease patients in electronic health records enables evaluation of clinical outcomes 91%
- Using explainable machine learning to identify patients at risk of reattendance at discharge from emergency departments 91%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.