On classifying sepsis heterogeneity in the ICU: insight using machine learning. (17th January 2020)

• Record Type: Journal Article
• Authors: Ibrahim, Zina M; Wu, Honghan; Hamoud, Ahmed; Stappen, Lukas; Dobson, Richard J B; Agarossi, Andrea
• Is Part Of: Journal of the American Medical Informatics Association. Volume 27:Number 3(2020)
• Page Start: 437
• Page End: 443
• Publication Date: 2020-01-17
• Subjects: sepsis -- sepsis subtypes -- sepsis prediction -- machine learning -- artificial intelligence in medicine; Medical informatics -- Periodicals; Information Services -- Periodicals; Medical Informatics -- Periodicals; Médecine -- Informatique -- Périodiques; Informatica; Geneeskunde; Informatique médicale; Computer network resources; Electronic journals; 610.285
• DOI: 10.1093/jamia/ocz211
• Languages: English
• ISSNs: 1067-5027

Abstract

Abstract: Objectives: Current machine learning models aiming to predict sepsis from electronic health records (EHR) do not account 20 for the heterogeneity of the condition despite its emerging importance in prognosis and treatment. This work demonstrates the added value of stratifying the types of organ dysfunction observed in patients who develop sepsis in the intensive care unit (ICU) in improving the ability to recognize patients at risk of sepsis from their EHR data. Materials and Methods: Using an ICU dataset of 13 728 records, we identify clinically significant sepsis subpopulations with distinct organ dysfunction patterns. We perform classification experiments with random forest, gradient boost trees, and support vector machines, using the identified subpopulations to distinguish patients who develop sepsis in the ICU from those who do not. Results: The classification results show that features selected using sepsis subpopulations as background knowledge yield a superior performance in distinguishing septic from non-septic patients regardless of the classification model used. The improved performance is especially pronounced in specificity, which is a current bottleneck in sepsis prediction machine learning models. Conclusion: Our findings can steer machine learning efforts toward more personalized models for complex conditions including sepsis.