Predicting sepsis onset using a machine learned causal probabilistic network algorithm based on electronic health records data

Abstract

Sepsis is a leading cause of mortality and early identification improves survival. With increasing digitalization of health care data automated sepsis prediction models hold promise to aid in prompt recognition. Most previous studies have focused on the intensive care unit (ICU) setting. Yet only a small proportion of sepsis develops in the ICU and there is an apparent clinical benefit to identify patients earlier in the disease trajectory. In this cohort of 82,852 hospital admissions and 8038 sepsis episodes classified according to the Sepsis-3 criteria, we demonstrate that a machine learned score can predict sepsis onset within 48 h using sparse routine electronic health record data outside the ICU. Our score was based on a causal probabilistic network model—SepsisFinder—which has similarities with clinical reasoning. A prediction was generated hourly on all admissions, providing a new variable was registered. Compared to the National Early Warning Score (NEWS2), which is an established method to identify sepsis, the SepsisFinder triggered earlier and had a higher area under receiver operating characteristic curve (AUROC) (0.950 vs. 0.872), as well as area under precision-recall curve (APR) (0.189 vs. 0.149). A machine learning comparator based on a gradient-boosting decision tree model had similar AUROC (0.949) and higher APR (0.239) than SepsisFinder but triggered later than both NEWS2 and SepsisFinder. The precision of SepsisFinder increased if screening was restricted to the earlier admission period and in episodes with bloodstream infection. Furthermore, the SepsisFinder signaled median 5.5 h prior to antibiotic administration. Identifying a high-risk population with this method could be used to tailor clinical interventions and improve patient care.

AI integration in sepsis care: a step towards improved health and quality of life outcomes

“…Recently, SepsisFinder 9 , another ML-based model was developed to predict the sepsis onset. SepsisFinder was validated using electronic health record (EHR) data consisting of 8038 sepsis cases classified as per Sepsis-3 criteria.…”

“…Although, TREWS 7 and SepsisFinder 9 holds promises for improving critical care in hospitals. However, notable limitations of the validation studies include single-centered and observational nature lacking randomization.…”

Predicting sepsis in-hospital mortality with machine learning: a multi-center study using clinical and inflammatory biomarkers

“…Similarly, the XGBoost model was touted as a reliable tool for predicting acute kidney injury (AKI) in septic patients, demonstrating superior performance over six other machine learning models [ 21 ]. In addition, John and Aron have developed a machine learning scoring method to predict the onset of sepsis within 48 h, a novel approach aimed at identifying at-risk populations, tailoring clinical interventions, and improving patient care [ 22 ]. Considering these findings, our study seeks to extend this emerging field by introducing features associated with immune-inflammation biomarkers.…”