Prediction of recovery from multiple organ dysfunction syndrome in pediatric sepsis patients

Abstract

Motivation Sepsis is a leading cause of death and disability in children globally, accounting for ∼3 million childhood deaths per year. In pediatric sepsis patients, the multiple organ dysfunction syndrome (MODS) is considered a significant risk factor for adverse clinical outcomes characterized by high mortality and morbidity in the pediatric intensive care unit. The recent rapidly growing availability of electronic health records (EHRs) has allowed researchers to vastly develop data-driven approaches like machine learning in healthcare and achieved great successes. However, effective machine learning models which could make the accurate early prediction of the recovery in pediatric sepsis patients from MODS to a mild state and thus assist the clinicians in the decision-making process is still lacking. Results This study develops a machine learning-based approach to predict the recovery from MODS to zero or single organ dysfunction by 1 week in advance in the Swiss Pediatric Sepsis Study cohort of children with blood-culture confirmed bacteremia. Our model achieves internal validation performance on the SPSS cohort with an area under the receiver operating characteristic (AUROC) of 79.1% and area under the precision-recall curve (AUPRC) of 73.6%, and it was also externally validated on another pediatric sepsis patients cohort collected in the USA, yielding an AUROC of 76.4% and AUPRC of 72.4%. These results indicate that our model has the potential to be included into the EHRs system and contribute to patient assessment and triage in pediatric sepsis patient care. Availability and implementation Code available at https://github.com/BorgwardtLab/MODS-recovery. The data underlying this article is not publicly available for the privacy of individuals that participated in the study. Supplementary information Supplementary data are available at Bioinformatics online.

Epidemiology and Antimicrobial Susceptibility of Invasive Bacterial Infections in Children—A Population-Based Study From Norway

“…The estimated annual incidence of invasive bacterial infections in Norway (age 0-18, 26.2/100,000) was very similar to data on blood culture proven sepsis in Switzerland (age 0-16, 25.1/100,000). 1 However, the annual incidence for infants was somewhat higher in our study (274.4/100,000) compared with the Swiss study (231.3/100,000). This could mirror that the latter only included isolates associated with clinical proven sepsis (by SIRS criteria).…”

“…25 Age stratified distribution of pathogens from children were in the same range as in a large Swiss study. 1 The E. faecalis/faecium ratio was high (7.1) in our study compared with a European point-prevalence survey (1.9). 8 Given that E. faecium mostly causes nosocomial infections, 26 16,27 In our study, the incidence of invasive bacterial infections was lower in children (except infants) than in adults.…”

“…B acterial infections are one of the most frequently causes of death in children, 1,2 and increasing antimicrobial resistance is a major health concern worldwide. 3 Surveillance of epidemiology and antimicrobial susceptibility testing (AST) data for bacteria causing serious infections is of high importance, 4 but data specific for children are often lacking, also in Norway.…”

“…7,8 The distribution of the most frequent bacteria recovered in pediatric bloodstream infections varies in different countries and settings [8][9][10][11] and with age. 1,9 Studies comparing AST data in bacterial isolates from children versus adults are limited. 8,12,13 A Canadian study reported lower rates of resistance to commonly used antibiotics in Escherichia coli and Staphylococcus aureus isolates from children than adults.…”

Swiss Sepsis National Action Plan: A coordinated national action plan to stop sepsis-related preventable deaths and to improve the support of people affected by sepsis in Switzerland

“…Switzerland, with its high density of academic hospitals, universities, as well as biotech, pharma, and information technology companies, is ideally positioned to drive Sepsis-related research should include diagnostic areas of key relevance such as biomarker and biosensor discovery and implementation to improve sepsis recognition. In particular, assisted decision-support systems using artificial intelligence (40,41) have considerable potential to improve sepsis recognition and early treatment. In addition, the pathophysiology, and the molecular and genetic mechanisms triggering dysregulated host response to infection remain poorly elucidated, providing ample opportunities for basic research.…”