Related Experiment Video
Updated: Jan 17, 2026
A Rat Graft Rejection Model of Intestinal Transplantation with Exteriorized Ileostomy for Longitudinal Prognosis Assessment
Published on: June 10, 2025
Short-term mortality prediction in children with gastrointestinal congenital anomalies using a random forest
1Carol Davila University of Medicine and Pharmacy, Bucharest, Romania. andreea_serban@drd.umfcd.ro.
Insights
A machine learning model accurately predicts 30-day mortality in children with gastrointestinal congenital malformations. Key factors include complications, post-operative care, and patient health scores, aiding early risk identification.
Area of Science:
- Pediatric Surgery
- Machine Learning in Healthcare
- Global Health Outcomes
Background:
- Gastrointestinal congenital malformations pose significant risks to children.
- Identifying high-risk pediatric patients for mortality is crucial for timely intervention.
Purpose of the Study:
- To develop a predictive model for identifying children with gastrointestinal congenital malformations at high risk of 30-day mortality.
- To leverage machine learning for improved mortality prediction in this vulnerable pediatric population.
Main Methods:
- Utilized data from the Global PaedSurg collaboration, including 3849 patients from 74 countries.
- Employed data preprocessing techniques including imputation and class balancing (oversampling non-survivors, undersampling survivors).
- Trained a random forest classifier for mortality prediction.
Main Results:
- The random forest model achieved 88.84% accuracy in predicting 30-day mortality.
- High precision (84.13%) and sensitivity (89.98%) were observed in identifying non-survivors.
- Key predictors included diagnosis of complications, duration of postoperative antibiotics, need for parenteral nutrition/ventilation, ASA score, admission weight, and surgical safety checklist use.
Conclusions:
- Random forest classification is a viable method for predicting short-term mortality in pediatric gastrointestinal congenital malformations.
- This study is the first global application of machine learning for this specific prediction task.
- The model identifies critical clinical, procedural, and socio-demographic factors associated with mortality risk.
Background:
We aim to develop a predictive model to identify children with gastrointestinal congenital malformations at high risk of 30-day mortality following intervention or hospital admission.
Methods:
The data used for our analysis was collected as part of the Global PaedSurg research collaboration, and includes 3849 patients from 74 countries. Data preprocessing, missing data imputation, oversampling of the non-survivor class, and random undersampling of the survivor class were performed prior to training a random forest classifier for mortality prediction.
Results:
The overall 30-day mortality in our model dataset is 19.5%. The model displays an overall accuracy of 88.84% (CI: 86.79%, 90.66%), with strong precision (84.13%, CI: 78.4%, 88.8%) and sensitivity (89.98%, CI: 87.8%, 91.9%) in identifying non-survivors. The area under the curve (AUC) is 0.941 (CI: 0.924, 0.957) for subjects in the non-survival class. The most important features in the classifier are the diagnosis of a complication, the duration of postoperative antibiotic treatment, the need for parenteral nutrition or ventilation, the American Society of Anesthesiologists (ASA) score, weight upon admission, and the use of a surgical safety checklist.
Conclusions:
Random forest classifier is a viable option for short-term mortality prediction for children with gastrointestinal congenital malformations.
Impact:
To our knowledge, this is the first global study to apply machine learning for mortality prediction in children with gastrointestinal malformations, using data from 3849 patients across 74 countries. The random forest model achieves 88.84% (CI: 86.79%, 90.66%) accuracy, with strong precision (84.13%, CI: 78.4%, 88.8%) and sensitivity (89.98%, CI: 87.8%, 91.9%) in identifying at-risk patients. Key predictors include clinical factors (diagnosis of complications, American Society of Anaesthesiologists score, weight on admission, duration of post-operative antibiotic treatment), procedural elements (surgical checklist), and socio-demographic variables (continent, income level).
More Related Videos
07:13Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
Published on: April 18, 2025
06:46Competing-Risk Nomogram for Predicting Cancer-Specific Survival in Multiple Primary Colorectal Cancer Patients after Surgery
Published on: September 27, 2024
