A multivariate Bayesian classification algorithm for cerebral stage prediction by diffusion tensor imaging in amyotrophic lateral sclerosis

• DOI: 10.1016/j.nicl.2022.103094
• Publication Date: 2022-06-21T12:08:41Z
• Authors: Anna Behler; Hans-Peter Müller; Albert C. Ludolph; Dorothée Lulé; Jan Kassubek
• Keywords: Classification scheme

Diffusion tensor imaging (DTI) can be used to tract-wise map correlates of the sequential disease progression and, therefore, assess stages amyotrophic lateral sclerosis (ALS) in vivo. According a threshold-based scheme, classification ALS patients into is possible, however, several cannot staged for methodological reasons. This study aims implement multivariate Bayesian algorithm stage prediction at an individual patient level based on DTI metrics involved tract systems improve mapping.The analysis fiber tracts each was performed 325 and 130 age- gender-matched healthy controls. Based Bayes' theorem accordance with progression, multistage classifier implemented. Patients were categorized vivo using method algorithm. By margin confidence, reliability categorizations accessible.Based classifier, 88% all could assigned compared 77% staging scheme. Additionally, confidence classifications estimated.By application multi-stage individualized cerebral possible sequentially furthermore, respective determined. The improvement provide framework extending DTI-based ALS.