EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Predicting acute and long-term mortality in a cohort of pulmonary embolism patients using machine learning

Wahbi K El-Bouri, Alexander Sanders, Gregory Y H Lip, BBC-VTE investigators

European Journal of Internal Medicine · 2023-12 · 118 · 42-48

DOI: 10.1016/j.ejim.2023.07.012 ↗

Kurz gefasst

Fachartikel in der Zeitschrift European Journal of Internal Medicine, 2023-12. Verfasst von Wahbi K El-Bouri und 3 weiteren Autor:innen. Beteiligte Einrichtung: Liverpool Centre for Cardiovascular Science, University of Liverpool and Liverpool Heart & Chest Hospital, Liverpool, UK; Department of Cardiovascula…. Hauptthemen laut MEDLINE: Venous Thromboembolism, Pulmonary Embolism. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Pulmonary embolism (PE) is a severe condition that causes significant mortality and morbidity. Due to its acute nature, scores have been developed to stratify patients at high risk of 30-day mortality. Here we develop a machine-learning based score to predict 30-day, 90-day, and 365-day mortality in PE patients. METHODS: The Birmingham and Black Country Venous Thromboembolism registry (BBC-VTE) of 2183 venous thromboembolism patients is used. Random forests were trained on a 70% training cohort and tested against 30% held-out set. The outcomes of interest were 30-day, 90-day, and 365-day mortality. These were compared to the pulmonary embolism severity index (PESI) and simplified pulmonary embolism severity index (sPESI). Shapley values were used to determine important predictors. Oral anticoagulation at discharge was also investigated as a predictor of mortality. RESULTS: The machine learning risk score predicted 30-day mortality with AUC 0.71 [95% CI: 0.63 - 0.78] compared to the sPESI AUC of 0.65 [95% CI: 0.57 - 0.73] and PESI AUC of 0.64 [95% CI: 0.56 - 0.72]. 90-day mortality and 365-day mortality were predicted with an AUC of 0.74 and 0.73 respectively. High counts of neutrophils, white blood cell counts, and c-reactive protein and low counts of haemoglobin were important for 30-day mortality prediction but progressively lost importance with time. Older age was an important predictor of high risk throughout. CONCLUSION: Machine learning algorithms have improved on standard clinical risk stratification for PE patients. External cohort validation is required before incorporation into clinical workflows.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Venous ThromboembolismPulmonary EmbolismHumansRisk AssessmentPrognosisSeverity of Illness Index

Stichwörter der Autor:innen

Deep vein thrombosisRandom forestsRisk stratificationSimplified pulmonary embolism severity indexVenous thromboembolism

Autor:innen und Institutionen

  • Liverpool Centre for Cardiovascular Science, University of Liverpool and Liverpool Heart & Chest Hospital, Liverpool, UK; Department of Cardiovascular and Metabolic Medicine, Institute of Life Course and Medical Science…
  • Liverpool Centre for Cardiovascular Science, University of Liverpool and Liverpool Heart & Chest Hospital, Liverpool, UK.

Zitieren

APA

El-Bouri, W. K., Sanders, A., Lip, G. Y. H., & BBC-VTE investigators (2023). Predicting acute and long-term mortality in a cohort of pulmonary embolism patients using machine learning. European Journal of Internal Medicine, 118, 42-48. https://doi.org/10.1016/j.ejim.2023.07.012

Vancouver

El-Bouri WK, Sanders A, Lip GYH, BBC-VTE investigators. Predicting acute and long-term mortality in a cohort of pulmonary embolism patients using machine learning. European Journal of Internal Medicine. 2023;118:42-48. doi:10.1016/j.ejim.2023.07.012

BibTeX
@article{ElBouri2023,
  author = {El-Bouri, Wahbi K and Sanders, Alexander and Lip, Gregory Y H and BBC-VTE investigators, BBC-VTE investigators},
  title = {Predicting acute and long-term mortality in a cohort of pulmonary embolism patients using machine learning},
  journal = {European Journal of Internal Medicine},
  year = {2023},
  volume = {118},
  pages = {42--48},
  doi = {10.1016/j.ejim.2023.07.012}
}
Kostenlos starten →