Related Experiment Video
Updated: Dec 28, 2025
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
Development and Validation of a Web-Based Pediatric Readmission Risk Assessment Tool
Thom Taylor1,2,3, Danielle Altares Sarik2, Daria Salyakina4,2
1Nicklaus Children's Research Institute, thomas.taylor@nicklaushealth.org.
Insights
Predicting unplanned pediatric readmissions is now possible using pre-discharge data. Developed algorithms can identify children at risk for readmission within 3, 7, or 30 days, aiding discharge planning.
Area of Science:
- Pediatric Healthcare Informatics
- Clinical Risk Prediction
- Health Services Research
Background:
- Unplanned readmissions (URs) in pediatric care present a significant challenge for healthcare systems.
- Accurate prediction of URs is crucial for effective resource allocation and patient management.
- Existing methods for predicting pediatric URs often lack accuracy or are not readily applicable before discharge.
Purpose of the Study:
- To develop and validate accurate algorithms for predicting pediatric unplanned readmissions within 3, 7, and 30 days of hospital discharge.
- To create a tool that utilizes pre-discharge clinical data for risk stratification.
- To support timely and informed discharge planning decisions in pediatric care.
Main Methods:
- Utilized a large retrospective cohort of over 1.3 million pediatric admissions from the Children's Hospital Association Pediatric Health Information System (2016-2017).
- Employed gradient boosting trees (XGBoost) to model complex interactions among patient predictors.
- Developed prediction models for 3, 7, and 30-day unplanned readmission risk.
Main Results:
- The study identified 1.6% of patients with 3-day URs, 2.4% with 7-day URs, and 4.4% with 30-day URs.
- Prediction models demonstrated strong discrimination, with AUCs of 0.771 (3-day), 0.778 (7-day), and 0.811 (30-day).
- A publicly available pediatric readmission risk score prediction tool was developed.
Conclusions:
- Pediatric unplanned readmission risk can be accurately predicted using information available before patient discharge.
- The developed algorithms and tool can be integrated into electronic medical record systems for practical application.
- This predictive capability can significantly enhance hospital discharge planning and potentially reduce readmission rates.
Objectives:
Accurately predicting and reducing risk of unplanned readmissions (URs) in pediatric care remains difficult. We sought to develop a set of accurate algorithms to predict URs within 3, 7, and 30 days of discharge from inpatient admission that can be used before the patient is discharged from a current hospital stay.
Methods:
We used the Children's Hospital Association Pediatric Health Information System to identify a large retrospective cohort of 1 111 323 children with 1 321 376 admissions admitted to inpatient care at least once between January 1, 2016, and December 31, 2017. We used gradient boosting trees (XGBoost) to accommodate complex interactions between these predictors.
Results:
In the full cohort, 1.6% of patients had at least 1 UR in 3 days, 2.4% had at least 1 UR in 7 days, and 4.4% had at least 1 UR within 30 days. Prediction model discrimination was strongest for URs within 30 days (area under the curve [AUC] = 0.811; 95% confidence interval [CI]: 0.808-0.814) and was nearly identical for UR risk prediction within 3 days (AUC = 0.771; 95% CI: 0.765-0.777) and 7 days (AUC = 0.778; 95% CI: 0.773-0.782), respectively. Using these prediction models, we developed a publicly available pediatric readmission risk scores prediction tool that can be used before or during discharge planning.
Conclusions:
Risk of pediatric UR can be predicted with information known before the patient's discharge and that is easily extracted in many electronic medical record systems. This information can be used to predict risk of readmission to support hospital-discharge-planning resources.
