Related Experiment Video
Updated: May 9, 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 of a Multivariable Risk Prediction Tool to Predict Adverse Outcomes among Children with Type 1 Diabetes:
Fiona Lieu1, Wrivu N Martin2, Stewart Birt1,3
1The Central Coast Clinical School, School of Medicine and Public Health, The University of Newcastle, Callaghan, New South Wales, Australia.
Insights
This study developed a risk model for children with type 1 diabetes mellitus (T1DM) to predict severe hypoglycaemia, hyperglycaemia, and diabetic ketoacidosis (DKA) hospitalisations. The model accurately identifies high-risk pediatric patients needing closer monitoring.
Area of Science:
- Pediatric Endocrinology
- Diabetes Management
- Clinical Risk Prediction
Background:
- Children and adolescents with type 1 diabetes mellitus (T1DM) face frequent hospitalizations for severe hypoglycaemia, hyperglycaemia, and diabetic ketoacidosis (DKA).
- Identifying high-risk pediatric patients for acute decompensation remains a clinical challenge.
Purpose of the Study:
- To develop and validate a risk prediction model for acute healthcare utilization in pediatric T1DM patients.
- Accurately estimate the risk of severe hypoglycaemia, hyperglycaemia, and DKA-related hospitalizations.
Main Methods:
- Retrospective data collection from pediatric patients (<18 years) with T1DM.
- Development of a multivariable risk prediction model using logistic regression.
- Assessment of model discrimination using ROC curves and Kaplan-Meier analysis for time to event.
Main Results:
- A five-predictor model (continuous glucose monitoring, prior acute care, missed appointments, child welfare involvement, socioeconomic status) was developed.
- The model demonstrated good discrimination (AUC = 0.81) and accurately stratified patients into risk groups.
- Significant differences in time to acute healthcare utilization were observed across risk strata.
Conclusions:
- The developed risk prediction model effectively identifies pediatric T1DM patients at increased risk of acute healthcare utilization.
- This tool can aid in proactive management and intervention for high-risk individuals.
- Further research can refine the model for broader clinical application.
Background:
Children and adolescents with type 1 diabetes mellitus (T1DM) are frequently hospitalised for severe hypoglycaemia, hyperglycaemia, and diabetic ketoacidosis (DKA). While several risk factors have been recognised, clinically identifying these children at high risk of acute decompensation remains challenging.
Objective:
To develop a risk prediction model to accurately estimate the risk of acute healthcare utilisation due to severe hypoglycaemia, hyperglycaemia, and DKA in children and adolescents with T1DM.
Materials And Methods:
Using a retrospective dataset, baseline demographic and clinical data were collected from patients (<18 years) seen at a regional paediatric diabetes clinic from 1 January 2018 to 1 January 2020. The outcome was the number of emergency department presentations or hospital admissions for severe hypoglycaemia, hyperglycaemia, and DKA across the study period. Variables that were significant in univariate analysis were entered into a multivariable model. Receiver operator characteristic (ROC) curves assessed the model's discrimination and generated cut-offs for risk group stratification (low, medium, and high). Kaplan-Meier survival analysis measured time to acute healthcare utilisation across the risk groups.
Results:
Our multivariable risk prediction model consisted of five predictors (continuous glucose monitoring device, previous acute healthcare utilisation, missed appointments, and child welfare services involvement and socioeconomic status). The model exhibited good discrimination (area under the ROC = 0.81), accurately stratified children into low-, medium-, and high-risk groups, and demonstrated significant differences between median time to healthcare utilisation.
Conclusion:
Our model identified patients at an increased risk of acute healthcare utilisation due to severe hypoglycaemia, hyperglycaemia, and DKA.
Related Concept Videos
01:22Diabetes Mellitus: Overview and Type I Subtype
Type 1 diabetes is an autoimmune disease in which the immune system mistakenly attacks and destroys the insulin-producing beta cells in the pancreas. As a result, the body is unable to produce sufficient insulin, and individuals with...
01:22Diabetes Mellitus: Type 2 and Gestational
01:15Diabetes: Symptoms, Diagnosis, and Complications
01:20Pathophysiology of Diabetes
Type 1 diabetes is characterized by autoimmune-mediated destruction of pancreatic β cells, with environmental factors potentially triggering this process in genetically susceptible individuals. Despite many not having a family history, certain genes increase susceptibility,...
01:16Insulin: Dosing Regimen and Adverse Effects
The basal dose constitutes about 40%-50% of the total daily dose, with the rest as premeal insulin. The mealtime insulin dose should mirror...
01:23Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast,...