Table 0; documenting the steps to go from clinical database to research dataset.

OBJECTIVES: Data-driven decision support tools have been increasingly recognized to transform health care. However, such tools are often developed on predefined research datasets without adequate knowledge of the origin of this data and how it was selected. How a dataset is extracted from a clinical database can profoundly impact the validity, interpretability and interoperability of the dataset, and downstream analyses, yet is rarely reported. Therefore, we present a case study illustrating how a definitive patient list was extracted from a clinical source database and how this can be reported. STUDY DESIGN AND SETTING: A single-center observational study was performed at an academic hospital in the Netherlands to illustrate the impact of selecting a definitive patient list for research from a clinical source database, and the importance of documenting this process. All admissions from the critical care database admitted between January 1, 2013, and January 1, 2023, were used. RESULTS: An interdisciplinary team collaborated to identify and address potential sources of data insufficiency and uncertainty. We demonstrate a stepwise data preparation process, reducing the clinical source database of 54,218 admissions to a definitive patient list of 21,553 admissions. Transparent documentation of the data preparation process improves the quality of the definitive patient list before analysis of the corresponding patient data. This study generated seven important recommendations for preparing observational health-care data for research purposes. CONCLUSION: Documenting data preparation is essential for understanding a research dataset originating from a clinical source database before analyzing health-care data. The findings contribute to establishing data standards and offer insights into the complexities of preparing health-care data for scientific investigation. Meticulous data preparation and documentation thereof will improve research validity and advance critical care.

The association between coronary artery calcification and vectorcardiography in mechanically ventilated COVID-19 patients: the Maastricht Intensive Care COVID cohort.

BACKGROUND: Coronary artery calcification (CAC) is associated with poor outcome in critically ill patients. A deterioration in cardiac conduction and loss of myocardial tissue could be an underlying cause. Vectorcardiography (VCG) and cardiac biomarkers provide insight into these underlying causes. The aim of this study was to investigate whether a high degree of CAC is associated with VCG-derived variables and biomarkers, including high-sensitivity troponin-T (hs-cTnT) and N-terminal pro-B-type natriuretic peptide (NT-proBNP). METHODS: Mechanically ventilated coronavirus-19 (COVID-19) patients with an available chest computed tomography (CT) and 12-lead electrocardiogram (ECG) were studied. CAC scores were determined using chest CT scans. Patients were categorized into 3 sex-specific tertiles: low, intermediate, and high CAC. Daily 12 leads-ECGs were converted to VCGs. Daily hs-cTnT and NT-proBNP levels were determined. Linear mixed-effects regression models examined the associations between CAC tertiles and VCG variables, and between CAC tertiles and hs-cTnT or NT-proBNP levels. RESULTS: In this study, 205 patients (73.2% men, median age 65 years [IQR 57.0; 71.0]) were included. Compared to the lowest CAC tertile, the highest CAC tertile had a larger QRS area at baseline (6.65 µVs larger [1.50; 11.81], p = 0.012), which decreased during admission (- 0.27 µVs per day [- 0.43; - 0.11], p = 0.001). Patients with the highest CAC tertile also had a longer QRS duration (12.02 ms longer [4.74; 19.30], p = 0.001), higher levels of log hs-cTnT (0.79 ng/L higher [0.40; 1.19], p < 0.001) and log NT-proBNP (0.83 pmol/L higher [0.30; 1.37], p = 0.002). CONCLUSION: Patients with a high degree of CAC had the largest QRS area and higher QRS amplitude, which decreased more over time when compared to patients with a low degree of CAC. These results suggest that CAC might contribute to loss of myocardial tissue during critical illness. These insights could improve risk stratification and prognostication of patients with critical illness.

Deep embedded clustering generalisability and adaptation for integrating mixed datatypes: two critical care cohorts.

We validated a Deep Embedded Clustering (DEC) model and its adaptation for integrating mixed datatypes (in this study, numerical and categorical variables). Deep Embedded Clustering (DEC) is a promising technique capable of managing extensive sets of variables and non-linear relationships. Nevertheless, DEC cannot adequately handle mixed datatypes. Therefore, we adapted DEC by replacing the autoencoder with an X-shaped variational autoencoder (XVAE) and optimising hyperparameters for cluster stability. We call this model "X-DEC". We compared DEC and X-DEC by reproducing a previous study that used DEC to identify clusters in a population of intensive care patients. We assessed internal validity based on cluster stability on the development dataset. Since generalisability of clustering models has insufficiently been validated on external populations, we assessed external validity by investigating cluster generalisability onto an external validation dataset. We concluded that both DEC and X-DEC resulted in clinically recognisable and generalisable clusters, but X-DEC produced much more stable clusters.

Rotational thromboelastometry as a biomarker for mortality - The Maastricht Intensive Care COVID cohort.

BACKGROUND: Patients with severe coronavirus disease 2019 (COVID-19) present with persisting hypercoagulability, hypofibrinolysis and prolonged clot initiation as measured with viscoelastic assays. The objective of this study was to investigate the trajectories of traditional assays of hemostasis, routine and tissue plasminogen activator (tPA) rotational thromboelastometry (ROTEM) in COVID-19 patients and to study their association with mortality. METHODS: Patients enrolled within the Maastricht Intensive Care COVID (MaastrICCht) cohort were included. Traditional assays of hemostasis (prothrombin time; PT, fibrinogen and D-dimer) were measured daily and ROTEM EXTEM, FIBTEM and tPA assays were performed weekly. Trajectories of these biomarkers were analyzed over time for survivors and non-survivors using linear mixed-effects models. Additional Fine and Gray competing risk survival analysis was performed for the first available measurement after intubation. RESULTS: Of the 138 included patients, 57 (41 %) died in the intensive care unit (ICU). Over 450, 400 and 1900 individual measurements were available for analysis of routine, tPA ROTEM and traditional assays of hemostasis, respectively, with a median [IQR] follow-up of 15 [8-24] days. Non-survivors on average had prolonged CT (clotting time) and increased fibrinogen compared to survivors. MCF (maximum clot firmness), LOT (lysis onset time), LT (lysis time) and PT measurements increased more over time in non-survivors compared to survivors. Associations persisted after adjustment for demographics and disease severity. EXTEM and FIBTEM CT at intubation were associated with increased 45-day ICU mortality. CONCLUSIONS: ROTEM measurements demonstrate a further increase of hypercoagulability and (hypo)fibrinolysis parameters in non-survivors throughout ICU admission. Furthermore, prolonged CT at intubation was associated with higher 45-day ICU mortality.

A guide to sharing open healthcare data under the General Data Protection Regulation.

Sharing healthcare data is increasingly essential for developing data-driven improvements in patient care at the Intensive Care Unit (ICU). However, it is also very challenging under the strict privacy legislation of the European Union (EU). Therefore, we explored four successful open ICU healthcare databases to determine how open healthcare data can be shared appropriately in the EU. A questionnaire was constructed based on the Delphi method. Then, follow-up questions were discussed with experts from the four databases. These experts encountered similar challenges and regarded ethical and legal aspects to be the most challenging. Based on the approaches of the databases, expert opinion, and literature research, we outline four distinct approaches to openly sharing healthcare data, each with varying implications regarding data security, ease of use, sustainability, and implementability. Ultimately, we formulate seven recommendations for sharing open healthcare data to guide future initiatives in sharing open healthcare data to improve patient care and advance healthcare.