Back to all papers

[Clinical Advances and Artificial Intelligence Applications in Bone Health Management in Children and Adolescents].

September 20, 2026pubmed logopapers

Authors

Wu T,Mao M,Li P

Affiliations (1)

  • ( 610041)Department of Child Health Care, Women and Children's Nutrition Center, Key Laboratory of Birth Defects and Related Diseases of Women and Children of the Ministry of Education, West China Second University Hospital, Sichuan University, Chengdu 610041, China.

Abstract

Childhood and adolescence are critical windows for peak bone mass accrual, skeletal modeling, and the establishment of musculoskeletal function. During this period, unrecognized and untreated modifiable skeletal risk factors can progress to permanent structural skeletal disorders. Pediatric bone health management cannot rely on adult-derived diagnostic paradigms, nor should it be reduced to isolated metrics such as calcium intake, vitamin D status, and bone mineral density (BMD). Instead, all assessments must be interpreted in the context of each child's individual growth trajectory, integrating skeletal maturation, pubertal stage, weight status, motor function, comorbidities, and preexisting structural skeletal deformities. Contemporary clinical guidelines and consensus statements consistently emphasize that BMD testing, nutritional and exercise-related functional assessments, and skeletal deformity screening in pediatric populations must be guided by well-defined clinical indications and risk stratification. They explicitly caution against adult-centric result interpretation, indiscriminate testing, and one-off screening disconnected from longitudinal care. Despite these recommendations, notable gaps persist in routine clinical practice, including under-recognition of high-risk pediatric patients, fragmentation of the care continuum across screening, reassessment, and referral, suboptimal follow-up adherence, and marked variability in manual measurement reliability and imaging quality control. Artificial intelligence (AI) has demonstrated promising performance across multiple pediatric skeletal care domains, including bone age assessment, Cobb angle quantification, scoliosis population screening, hip ultrasound quality assurance, disease progression risk stratification, and longitudinal follow-up management. Nonetheless, its real-world clinical utility remains to be fully validated through large-scale multicenter trials and real-world evidence studies. This review synthesizes current evidence on standardized assessment protocols, AI-enabled clinical applications, and early identification strategies for common skeletal deformities in pediatric bone health. We further discuss actionable care pathways for risk stratification, cross-setting referral coordination, and continuous longitudinal care tailored to children and adolescents.

Topics

Artificial IntelligenceBone DiseasesJournal ArticleReviewEnglish Abstract

Ready to Sharpen Your Edge?

Subscribe to join 11k+ peers who rely on RadAISlice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.