Tracing the Progression of Sepsis in Critically Ill Children: Clinical Decision Support for Detection of Hematologic Dysfunction

• Published in: Applied clinical informatics 2022-10, Vol.13 (5), p.1002-1014
• Main Authors: Bode, Louisa, Schamer, Sven, Böhnke, Julia, Bott, Oliver Johannes, Marschollek, Michael, Jack, Thomas, Wulff, Antje
• Format: Article
• Language: English
• Subjects: Child; Critical Illness; Decision Support Systems, Clinical; Humans; Prospective Studies; Research Article; Sepsis - diagnosis
• ISSN: 1869-0327; 1869-0327
• DOI: 10.1055/a-1950-9637

Abstract Background  One of the major challenges in pediatric intensive care is the detection of life-threatening health conditions under acute time constraints and performance pressure. This includes the assessment of pediatric organ dysfunction (OD) that demands extraordinary clinical expertise and the clinician's ability to derive a decision based on multiple information and data sources. Clinical decision support systems (CDSS) offer a solution to support medical staff in stressful routine work. Simultaneously, detection of OD by using computerized decision support approaches has been scarcely investigated, especially not in pediatrics. Objectives  The aim of the study is to enhance an existing, interoperable, and rule-based CDSS prototype for tracing the progression of sepsis in critically ill children by augmenting it with the capability to detect SIRS/sepsis-associated hematologic OD, and to determine its diagnostic accuracy. Methods  We reproduced an interoperable CDSS approach previously introduced by our working group: (1) a knowledge model was designed by following the commonKADS methodology, (2) routine care data was semantically standardized and harmonized using openEHR as clinical information standard, (3) rules were formulated and implemented in a business rule management system. Data from a prospective diagnostic study, including 168 patients, was used to estimate the diagnostic accuracy of the rule-based CDSS using the clinicians' diagnoses as reference. Results  We successfully enhanced an existing interoperable CDSS concept with the new task of detecting SIRS/sepsis-associated hematologic OD. We modeled openEHR templates, integrated and standardized routine data, developed a rule-based, interoperable model, and demonstrated its accuracy. The CDSS detected hematologic OD with a sensitivity of 0.821 (95% CI: 0.708–0.904) and a specificity of 0.970 (95% CI: 0.942–0.987). Conclusion  We could confirm our approach for designing an interoperable CDSS as reproducible and transferable to other critical diseases. Our findings are of direct practical relevance, as they present one of the first interoperable CDSS modules that detect pediatric SIRS/sepsis-associated hematologic OD.