Related Experiment Video
Updated: Jan 18, 2026
A Modified Sonographic Algorithm for Image Acquisition in Life-Threatening Emergencies in the Critically Ill Newborn
Published on: April 7, 2023
Performance of an Automated Screening Algorithm for Early Detection of Pediatric Severe Sepsis
Matthew Eisenberg1,2, Kate Madden3,4, Jeffrey R Christianson5
1Division of Emergency Medicine, Department of Medicine, Boston Children's Hospital, Boston, MA.
Insights
A new electronic health record system effectively detects severe sepsis in children. This automated pediatric sepsis screening tool aids early detection in emergency departments and inpatient settings.
Area of Science:
- Pediatric critical care medicine
- Health informatics
- Clinical decision support systems
Background:
- Severe sepsis is a life-threatening condition in children requiring timely diagnosis and treatment.
- Existing sepsis detection methods may lack efficiency and timeliness in busy clinical environments.
- Electronic health records (EHRs) offer a platform for developing automated clinical alert systems.
Purpose of the Study:
- To develop and evaluate a continuous, automated EHR-based alert system for severe sepsis detection in pediatric patients.
- To improve the timely identification of severe sepsis in emergency department (ED) and inpatient settings.
- To enhance the positive predictive value (PPV) of sepsis detection algorithms through iterative refinement.
Main Methods:
- A retrospective cohort study was conducted at a quaternary care children's hospital.
- A pediatric sepsis screening algorithm was created and embedded within the EHR.
- Algorithm performance was evaluated based on sensitivity, specificity, PPV, and negative predictive value (NPV) compared to chart review diagnoses.
Main Results:
- The final algorithm achieved a sensitivity of 72% and specificity of 91.8% for severe sepsis detection.
- The overall positive predictive value (PPV) was 8.1%, with higher PPVs in ICUs (10.4%) and EDs (9.6%).
- The negative predictive value (NPV) was high at 99.7%, indicating effective ruling out of sepsis.
Conclusions:
- A continuous, automated EHR-based sepsis screening algorithm can identify severe sepsis in pediatric patients.
- The system has the potential to support early sepsis detection in inpatient and ED settings.
- Algorithm performance varied by hospital location, necessitating further optimization for diverse clinical environments.
Objectives:
To create and evaluate a continuous automated alert system embedded in the electronic health record for the detection of severe sepsis among pediatric inpatient and emergency department patients.
Design:
Retrospective cohort study. The main outcome was the algorithm's appropriate detection of severe sepsis. Episodes of severe sepsis were identified by chart review of encounters with clinical interventions consistent with sepsis treatment, use of a diagnosis code for sepsis, or deaths. The algorithm was initially tested based upon criteria of the International Pediatric Sepsis Consensus Conference; we present iterative changes which were made to increase the positive predictive value and generate an improved algorithm for clinical use.
Setting:
A quaternary care, freestanding children's hospital with 404 inpatient beds, 70 ICU beds, and approximately 60,000 emergency department visits per year PATIENTS:: All patients less than 18 years presenting to the emergency department or admitted to an inpatient floor or ICU (excluding neonatal intensive care) between August 1, 2016, and December 28, 2016.
Intervention:
Creation of a pediatric sepsis screening algorithm.
Measurements And Main Results:
There were 288 (1.0%) episodes of severe sepsis among 29,010 encounters. The final version of the algorithm alerted in 9.0% (CI, 8.7-9.3%) of the encounters with sensitivity 72% (CI, 67-77%) for an episode of severe sepsis; specificity 91.8% (CI, 91.5-92.1%); positive predictive value 8.1% (CI, 7.0-9.2%); negative predictive value 99.7% (CI, 99.6-99.8%). Positive predictive value was highest in the ICUs (10.4%) and emergency department (9.6%).
Conclusions:
A continuous, automated electronic health record-based sepsis screening algorithm identified severe sepsis among children in the inpatient and emergency department settings and can be deployed to support early detection, although performance varied significantly by hospital location.
