PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
May 28, 2026Pediatrics International0 citations

Validity of Diagnostic and Procedure Codes in Administrative Data to Identify Pediatric Physical Abuse

View Full Paper
EOErika ObikaneTNTomoko NishinoHSHarumi Sonehara

Key Points

  • This research aims to evaluate how well ICD-10 codes identify pediatric physical abuse and develop algorithms for improved detection.
  • Analyzed administrative data of children under 10 years hospitalized for injuries from April 2013 to March 2023 at a children's hospital in Japan.
  • Used child protection team records as the reference standard to assess diagnostic, procedure, and medication codes.
  • Applied machine learning approaches including Lasso regression, random forest, and bootstrap classification-and-regression-tree models.
  • Of 1375 injury cases, only 1 used an abuse-specific ICD-10 code, demonstrating limited reliability for identification.
  • Combining X-ray and fundus examinations revealed 73.6% sensitivity and 85.7% specificity in children aged < 10 years.
  • Sensitivity of 80.9% and specificity of 79.1% were found among children aged < 6 years.

Abstract

BACKGROUND: Many countries lack comprehensive systems or standardized use of diagnostic codes to track child abuse. This study evaluated the validity of the International Classification of Diseases, 10th Revision (ICD-10) diagnostic codes and developed algorithms to identify physical abuse using administrative data. METHODS: We analyzed children under 10 years hospitalized for injuries between April 2013 and March 2023 at a children's hospital in Japan. Child protection team records notifying local services were used as the reference standard. We assessed diagnostic, procedure, and medication codes using machine learning. RESULTS: Among 1375 injury cases, 53 involved physical abuse, but only one used an abuse-specific ICD-10 code, indicating limited reliability. Combining X-ray and fundus examinations achieved 73.6% sensitivity (95% CI, 59.7-84.7) and 85.7% specificity (95% CI, 83.7-87.5) among children aged < 10 years and 80.9% sensitivity (95% CI, 66.7-90.9) and 79.1% specificity (95% CI, 76.2-81.7) among children aged < 6 years. Several machine learning approaches, including Lasso regression, random forest, and bootstrap classification-and-regression-tree models, yielded broadly consistent findings. CONCLUSIONS: ICD-10 codes alone are insufficient for identifying physical abuse combining specific procedures may improve case identification for future epidemiological surveillance.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Obikane et al. (2026) studied this question.

synapsesocial.com/papers/6a17dbbe3fad632b0f9d871ehttps://doi.org/10.1111/ped.70430
Ask AI
Helpful
Bookmark
Share
View Full Paper