Related Experiment Video
Updated: Aug 24, 2025
Multi-Modal Signals for Analyzing Pain Responses to Thermal and Electrical Stimuli
Published on: April 5, 2019
Diagnosing growing pains in children by using machine learning: a cross-sectional multicenter study
Fuat Akal1, Ezgi D Batu2,3, Hafize Emine Sonmez4
1Department of Computer Engineering, Hacettepe University, Ankara, Turkey.
Insights
Growing pains (GP) are common in children. Machine learning models accurately diagnosed GP by analyzing patient characteristics, potentially aiding clinical diagnosis.
Area of Science:
- Pediatric Rheumatology
- Medical Informatics
- Artificial Intelligence in Medicine
Background:
- Growing pains (GP) represent the most frequent cause of recurrent musculoskeletal pain in children.
- Currently, there are no established diagnostic criteria for GP, leading to diagnostic challenges.
Purpose of the Study:
- To analyze characteristics associated with GP.
- To develop and validate machine learning (ML) models for assisting GP diagnosis.
Main Methods:
- A cohort study enrolled 398 children with GP and 254 controls with other limb pain conditions.
- Tenfold cross-validation was employed to train and test ML models for GP classification.
- The Random Forest algorithm was evaluated for its diagnostic performance.
Main Results:
- GP commonly presents as bilateral, nocturnal lower extremity pain, often causing nighttime awakenings.
- Symptoms like arthritis, trauma history, morning stiffness, limping, activity limitation, and school absence were more frequent in controls.
- The Random Forest ML model achieved high accuracy (0.98), sensitivity (0.99), and specificity (0.97) for diagnosing GP.
Conclusions:
- This study represents the largest cohort investigating GP and the first to utilize ML for diagnosis.
- The developed ML model demonstrates significant potential to aid in the clinical diagnosis of growing pains in children.
Abstract:
Growing pains (GP) are the most common cause of recurrent musculoskeletal pain in children. There are no diagnostic criteria for GP. We aimed at analyzing GP-related characteristics and assisting GP diagnosis by using machine learning (ML). Children with GP and diseased controls were enrolled between February and August 2019. ML models were developed by using tenfold cross-validation to classify GP patients. A total of 398 patients with GP (F/M:1.3; median age 102 months) and 254 patients with other diseases causing limb pain were enrolled. The pain was bilateral (86.2%), localized in the lower extremities (89.7%), nocturnal (74%), and led to awakening at night (60.8%) in most GP patients. History of arthritis, trauma, morning stiffness, limping, limitation of activities, and school abstinence were more prevalent among controls than in GP patients (p = 0.016 for trauma; p < 0.001 for others). The experiments with different ML models revealed that the Random Forest algorithm had the best performance with 0.98 accuracy, 0.99 sensitivity, and 0.97 specificity for GP diagnosis. This is the largest cohort study of children with GP and the first study that attempts to diagnose GP by using ML techniques. Our ML model may be used to facilitate diagnosing GP.
