AI helps head off shock in pediatric sepsis patients

Comparing four methods for predicting septic shock in children hospitalized with sepsis, Johns Hopkins researchers have found a newer machine-learning approach superior to an older one as well as to two conventional methods.

The top performer, the open-source XGBoost (for eXtreme Gradient Boosting), supplied accurate early predictions that, in clinical practice, would have given critical-care teams nearly nine hours to intervene preventively.

The researchers used data from more than 6,100 past patients of Johns Hopkins’s pediatric ICU to train and test the model retrospectively.

XGBoost also had early prediction performance of 0.90 area under the receiver operating curve, 43% overall positive predictive value and patient-specific positive predictive value as high as 62%, the authors report.

The other AI contender was a generalized linear model, while the field was rounded out by Cox proportional hazards modeling and sequential organ-failure assessment scoring.

Senior author Raimond Winslow, PhD, and colleagues describe the work in the June edition of Critical Care Explorations, a journal of the Society of Critical Care Medicine.

Sepsis and septic shock are leading causes of in-hospital mortality,” Winslow and co-authors point out. “Timely treatment is crucial in improving patient outcome, yet treatment delays remain common. Early prediction of those patients with sepsis who will progress to its most severe form, septic shock, can increase the actionable window for interventions.”

The team’s secondary goal was to see if the best tool could help assess the risk of septic shock in real time, as it changed patient by patient.

If so, they surmised, it could help split the cohort into two subgroups—low risk and high risk—which would facilitate triaging by likely sepsis trajectory and probability of septic shock.

XGBoost proved helpful here as well. The authors note the software library can learn nonlinear associations between features and risk. This capability “likely yields its improved performance compared with GLM, a finding also consistent with our previous results.”

Winslow et al. conclude:

We [have] demonstrate[ed] the applicability of our methodology for early prediction and stratification for risk of septic shock in pediatric sepsis patients. Through analyses of risk score evolution over time, we corroborate our past finding of an abrupt transition preceding onset of septic shock in children and are able to stratify pediatric sepsis patients using their risk score trajectories into low and high-risk categories.”

The study is available in full for free.

Dave Pearson

Dave P. has worked in journalism, marketing and public relations for more than 30 years, frequently concentrating on hospitals, healthcare technology and Catholic communications. He has also specialized in fundraising communications, ghostwriting for CEOs of local, national and global charities, nonprofits and foundations.

Trimed Popup
Trimed Popup