<< Back to the abstract archive
The Spectrum of Severity in Metopic Craniosynostosis: An Updated Analysis of the Largest Cohort to Date Using Craniorate� Machine Learning Algorithm
Angel Dixon, Nicol�s Kass, Annie Glenney, Joseph Morcharnuk, Erin Anstadt, Lucas Dvoracek, Megan Pencek, Wenzheng Tao, Ross Whitaker, Lisa David, Christopher Runyan, Michael Golinko, Michael Alperovich, Jesse Taylor, Jordan Swanson, Jesse Goldstein
UPMC Children's Hospital of Pittsburgh
2024-01-15
Presenter: Angel Dixon
Affidavit:
Yes
Director Name: Jesse Goldstein
Author Category: Medical Student
Presentation Category: Clinical
Abstract Category: Craniomaxillofacial
Purpose: CranioRate� is a machine learning tool designed to assess craniosynostosis severity by analyzing cranial morphology. This study examines the largest metopic craniosynostosis patient group to date, aiming to understand metopic severity and identify affected skull regions.
Methods: CranioRate� provides two objective, holistic metrics for quantifying severity in metopic craniosynostosis: Metopic Severity Score (MSS) and Cranial Morphology Deviation (CMD). De-identified CTs from normal and metopic patients from multiple U.S. institutions were compiled and analyzed using descriptive statistics, demographic associations, and regression analyses.
Results: A total of 656 CT scans (92 normal patients, 564 metopic patients) from the CranioRate� portal, including five U.S. institutions, were analyzed. Average age at CT was 0.75 � 0.51 years, and 74.0% of patients were male. Among normal controls, average MSS was 0.00 � 1.04, and average CMD was 85.23 � 19.32. Among metopic patients, mean MSS was 5.31� 2.59, and mean CMD was 196.66�46.96. Both MSS and CMD were significantly different between control and metopic patients (p<0.0001); no severity differences were noted between centers (p>0.05). There was a positive correlation between severity and earlier age at CT (MSS: r2 = .03, p=0.045). Regression analysis identified the central frontal bone, lateral orbit, and supraorbital rim as regions most associated with severity differences (p<0.05).
Conclusions: Our novel results objectively identify cranial regions associated with metopic craniosynostosis severity and establish a temporal relationship between severity and presentation. Future work with CranioRate� aims to encompass the entire metopic spectrum through additional institutional collaborations.
