loading page

Multi-parameter-based Radiological Diagnosis of Chiari Malformation using Machine Learning Technology
  • +5
  • Bora Tetik,
  • Güleç Mert Doğan,
  • Ramazan Paşahan,
  • Mehmet Akif Durak,
  • Emek Güldoğan,
  • Kaya Saraç,
  • Çağatay Önal,
  • Ismail Okan Yıldırım
Bora Tetik
İnönü Üniversitesi
Author Profile
Güleç Mert Doğan
Malatya Eğitim ve Araştırma Hastanesi
Author Profile
Ramazan Paşahan
İnönü Üniversitesi
Author Profile
Mehmet Akif Durak
İnönü Üniversitesi
Author Profile
Emek Güldoğan
İnönü Üniversitesi
Author Profile
Kaya Saraç
İnönü Üniversitesi
Author Profile
Çağatay Önal
İnönü Üniversitesi
Author Profile
Ismail Okan Yıldırım
İnönü Üniversitesi
Author Profile

Abstract

Background: The known primary radiological diagnosis of Chiari Malformation-I (CM-I) is based on the degree of tonsillar herniation ( TH) below the Foramen Magnum (FM). However, recent data also shows the association of such malformation with smaller posterior cranial fossa (PCF) volume and the anatomical issues regarding the Odontoid. This study presents the achieved result regarding some detected potential radiological findings that may aid CM-I diagnosis using several machine learning (ML) algorithms. Materials and Methods: Between 2011 and 2020, radiological examinations of 100 clinically/radiologically proved symptomatic CM-I cases and 100 control were evaluated by matching age and gender. A team of Neuroradiologists had reviewed the MR images of the study population. A total of 11 different radiological parameters were assessed for CM-I diagnosis. The parameters were defined and examined in 5 designed different ML algorithms. Statistical analysis was conducted for data analysis. Results: The mean age of patients was 29.92 ± 15.03 years. The primary presenting symptoms were headaches (62%). Syringomyelia and retrocurved-odontoid were detected in 34% and 8% of patients, respectively. All of the morphometric measures were significantly different between the groups, except for the distance from the dens axis to the posterior margin of FM. The Radom Forest model is found to have the best 1.0 (14 of 14) ratio of accuracy in regard to 14 different combinations of morphometric features. Conclusion: This study indicates the potential usefulness of ML-guided PCF measurements, other than TH, that may be used to predict and diagnose CM-I accurately. Our results support the view of TH as a single radiological parameter may fail during the diagnosis of CM-I. Combining two or three preferable osseous structure-based parameters may increase the accuracy of radiological diagnosis of CM-I.

Peer review status:IN REVISION

06 Apr 2021Submitted to International Journal of Clinical Practice
19 Apr 2021Submission Checks Completed
19 Apr 2021Assigned to Editor
19 Apr 2021Reviewer(s) Assigned
22 Apr 2021Review(s) Completed, Editorial Evaluation Pending
07 Jun 20211st Revision Received
12 Jun 2021Review(s) Completed, Editorial Evaluation Pending
12 Jun 2021Submission Checks Completed
12 Jun 2021Assigned to Editor