Development and Validation of a Web-Based Pediatric Readmission Risk Assessment Tool

Abstract

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] 5 0.811; 95% confidence interval [CI]: 0.808-0.814) and was nearly identical for UR risk prediction within 3 days (AUC 5 0.771; 95% CI: 0.765-0.777) and 7 days (AUC 5 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.

A Self-Care Prediction Model for Children with Disability Based on Genetic Algorithm and Extreme Gradient Boosting

“…Previous studies have shown the effectiveness and usefulness of web-based risk assessments in identifying risks and assisting the decision-making for pediatric readmission prediction [34], preventive medicine [35], violent behavior prediction [36], and trauma therapy [37]. Thus, in this section, we aim to design and develop web-based self-care prediction application (web-app) to provide decision tools for therapist in diagnosing children with disabilities.…”

“…As suggested by Demšar [33], a statistical significance test can be utilized to prove the significance of the proposed model as compared to other classification models. Furthermore, previous studies have also reported the effectiveness and usefulness of the practical application of prediction model to identify risks and assist the decision-making for pediatric readmission prediction [34], preventive medicine [35], violent behavior prediction [36], and trauma therapy [37].…”

Identifying Children at Readmission Risk: At-Admission versus Traditional At-Discharge Readmission Prediction Model

“…Prior pediatric readmission studies are thus far limited to the development of a prediction model after patient hospital discharges [23,24]. Most of these after-discharge readmission prediction studies reported predictive models for a 30-day readmission and, recently one study showed promise for 7-day pediatric readmission prediction [25][26][27]. However, these after-discharge predictive models might provide a limited amount of time for hospitals and providers to identify high-risk children and devise any appropriate general or patient intervention plans, mainly due to characteristics and timing of pediatric readmission.…”

Comparing Machine Learning to Regression Methods for Mortality Prediction Using Veterans Affairs Electronic Health Record Clinical Data

“…Despite the theoretical advantages of machine learning models for clinical prediction, studies comparing machine learning to traditional regression models have been mixed. While some studies have concluded that machine learning methods outperformed logistic regression,9–15 a systematic review and other studies suggest that machine learning algorithms may perform similarly to logistic regression for clinical outcome prediction 16–18…”

“…The term “statistical learning”6 explicitly recognizes that regression and machine learning methods are elements of a spectrum of statistical prediction methods. In this paper, we have made the somewhat artificial dichotomy of traditional regression versus machine learning both for simplicity and to mirror the terminology in other recent work in this area 9–17. We sought to compare these models across both binary outcomes (ie, 10-y mortality) as well as survival outcomes (time to mortality) by comparing prediction performance at 1, 2, and 5 years of follow-up.…”