Automated triage system for intensive care admissions during the covid‐19 pandemic using hybrid xgboost‐ahp approach

Creative Commons License

Deif M. A., Solyman A. A. A., Alsharif M. H., Uthansakul P.

Sensors, vol.21, no.19, 2021 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 21 Issue: 19
  • Publication Date: 2021
  • Doi Number: 10.3390/s21196379
  • Journal Name: Sensors
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, Aerospace Database, Aqualine, Aquatic Science & Fisheries Abstracts (ASFA), Biotechnology Research Abstracts, CAB Abstracts, Communication Abstracts, Compendex, EMBASE, INSPEC, MEDLINE, Metadex, Veterinary Science Database, Directory of Open Access Journals, Civil Engineering Abstracts
  • Keywords: Automated triage, COVID‐19 pan-demic, Emergency department, Hybrid XGBoost‐AHP approach, Intensive care admissions
  • Istanbul Gelisim University Affiliated: Yes


© 2021 by the authors. Licensee MDPI, Basel, Switzerland.The sudden increase in patients with severe COVID‐19 has obliged doctors to make admissions to intensive care units (ICUs) in health care practices where capacity is exceeded by the demand. To help with difficult triage decisions, we proposed an integration system Xtreme Gradient Boosting (XGBoost) classifier and Analytic Hierarchy Process (AHP) to assist health authorities in identifying patients’ priorities to be admitted into ICUs according to the findings of the biological laboratory investigation for patients with COVID‐19. The Xtreme Gradient Boosting (XGBoost) clas-sifier was used to decide whether or not they should admit patients into ICUs, before applying them to an AHP for admissions’ priority ranking for ICUs. The 38 commonly used clinical variables were considered and their contributions were determined by the Shapley’s Additive explanations (SHAP) approach. In this research, five types of classifier algorithms were compared: Support Vec-tor Machine (SVM), Decision Tree (DT), K‐Nearest Neighborhood (KNN), Random Forest (RF), and Artificial Neural Network (ANN), to evaluate the XGBoost performance, while the AHP system compared its results with a committee formed from experienced clinicians. The proposed (XGBoost) classifier achieved a high prediction accuracy as it could discriminate between patients with COVID‐19 who need ICU admission and those who do not with accuracy, sensitivity, and specificity rates of 97%, 96%, and 96% respectively, while the AHP system results were close to experienced clinicians’ decisions for determining the priority of patients that need to be admitted to the ICU. Eventually, medical sectors can use the suggested framework to classify patients with COVID‐19 who require ICU admission and prioritize them based on integrated AHP methodologies.