A Vital Sign-Based Model to Predict Clinical Deterioration in Hospitalized Children*

Abstract

Objectives: Clinical deterioration in hospitalized children is associated with increased risk of mortality and morbidity. A prediction model capable of accurate and early identification of pediatric patients at risk of deterioration can facilitate timely assessment and intervention, potentially improving survival and long-term outcomes. The objective of this study was to develop a model utilizing vital signs from electronic health record data for predicting clinical deterioration in pediatric ward patients. Design: Observational cohort study. Setting: An urban, tertiary-care medical center. Patients: Patients less than 18 years admitted to the general ward during years 2009–2018. Interventions: None. Measurements and Main Results: The primary outcome of clinical deterioration was defined as a direct ward-to-ICU transfer. A discrete-time logistic regression model utilizing six vital signs along with patient characteristics was developed to predict ICU transfers several hours in advance. Among 31,899 pediatric admissions, 1,375 (3.7%) experienced the outcome. Data were split into independent derivation (yr 2009–2014) and prospective validation (yr 2015–2018) cohorts. In the prospective validation cohort, the vital sign model significantly outperformed a modified version of the Bedside Pediatric Early Warning System score in predicting ICU transfers 12 hours prior to the event (C-statistic 0.78 vs 0.72; p < 0.01). Conclusions: We developed a model utilizing six commonly used vital signs to predict risk of deterioration in hospitalized children. Our model demonstrated greater accuracy in predicting ICU transfers than the modified Bedside Pediatric Early Warning System. Our model may promote opportunities for timelier intervention and risk mitigation, thereby decreasing preventable death and improving long-term health.

Evaluation of the Need for Intensive Care in Children With Pneumonia: Machine Learning Approach

“…Our work is one of the few studies to focus on a large data set for a specific diagnosis, pediatric pneumonia. Our algorithm's performance has better performance than previous studies that had AUCs ranging from approximately 0.7 to 0.9 [22][23][24]29], suggesting the advantage of an ML approach dedicated to children with pneumonia. With satisfactory performance, the application of the ML algorithms we proposed can be applied to support physicians' decisions for ICU care based on individual patient conditions and further improve health care quality during hospitalization.…”

“…Their logistic regression model reached an AUC of 0.91. Mayampurath et al [ 23 ] used 6 common vital signs (eg, temperature, pulse, blood pressure) to predict an ICU transfer event up to 36 hours in advance, reaching AUCs of 0.7-0.8. Rubin et al [ 24 ] applied a boosted trees model to electronic health records to predict pediatric ICU transfer at most 2 hours to 8 hours in advance with an AUC of 0.85.…”

Clinical progress note: Situation awareness for clinical deterioration in hospitalized children

“…The prediction of clinical deterioration in children has historically relied on the intuition of the medical team as to which patients may be at risk for clinical decline 4 . More recently, real‐time clinical prediction modeling leverages advanced algorithms and electronic health record data to predict deterioration risk based on vital signs and patient characteristic trends 5 . Broadly speaking, these models demonstrate limited success as compared to traditional methods and have yet to be widely implemented.…”

“…4 More recently, real-time clinical prediction modeling leverages advanced algorithms and electronic health record data to predict deterioration risk based on vital signs and patient characteristic trends. 5 Broadly speaking, these models demonstrate limited success as compared to traditional methods and have yet to be widely implemented.…”

Machine Learning-Based Systems for the Anticipation of Adverse Events After Pediatric Cardiac Surgery

“…Most of the postoperative adverse events are preceded by changes in patients' vital signs. Therefore, vital signs, such as heart rate (HR), respiration rate (RR), body temperature (BT), systolic (SBP), diastolic (DBP) and mean blood pressure (MBP) and oxygen saturation (SpO 2 ) are the most common patient's variables used by the different authors to build their predictive models (13)(14)(15)(16)(17)(18)(19)(20)(21)(22)(23)(24)(25), with different levels of resolution ranging from few seconds (18,21) to few hours (13). Zhai et al (25) were the first group proposing to use an ML model to predict ward-to-ICU transfer using automatically extracted EHR data.…”