Abstract
PurposeThe purpose of this study is to investigate relationship of patient age and sex to patterns of degenerative spinal stenosis on lumbar MRI (LMRI), rated as moderate or greater by a spine radiologist, using natural language processing (NLP) tools.MethodsIn this retrospective, IRB-approved study, LMRI reports acquired from 2007 to 2017 at a single institution were parsed with a rules-based natural language processing (NLP) algorithm for free-text descriptors of spinal canal stenosis (SCS) and neural foraminal stenosis (NFS) at each of six spinal levels (T12-S1) and categorized according to a 6-point grading scale. Demographic differences in the anatomic distribution of moderate (grade 3) or greater SCS and NFS were calculated by sex, and age and within-group differences for NFS symmetry (left vs. right) were calculated as odds ratios.ResultsForty-three thousand two hundred fifty-five LMRI reports (34,947 unique patients, mean age = 54.7; sex = 54.9% women) interpreted by 152 radiologists were studied. Prevalence of significant SCS and NFS increased caudally from T12-L1 to L4-5 though less at L5-S1. NFS was asymmetrically more prevalent on the left at L2-L3 and L5-S1 (p < 0.001). SCS and NFS were more prevalent in men and SCS increased with age at all levels, but the effect size of age was largest at T12-L3. Younger patients (< 50 years) had relatively higher NFS prevalence at L5-S1.ConclusionNLP can identify patterns of lumbar spine degeneration through analysis of a large corpus of radiologist interpretations. Demographic differences in stenosis prevalence shed light on the natural history and pathogenesis of LSDD.
Highlights
Materials and methodsLumbar spine degenerative disease (LSDD) resulting in spinal canal stenosis and neural foraminal stenosis (SCS, NFS) is a major cause of disability and drives a significant portion of healthcare costs [1]
The full text of each radiology report was passed through a customized, rules-based natural language processing (NLP) algorithm for automatic extraction of stenosis grading on a per-level basis, building on principles described by Tan et al [13]
This study describes an NLP-driven approach toward understanding the interaction between demographics and distribution of LSDD through large-scale analysis of radiology reports for Lumbar MRI (LMRI) examinations
Summary
Materials and methodsLumbar spine degenerative disease (LSDD) resulting in spinal canal stenosis and neural foraminal stenosis (SCS, NFS) is a major cause of disability and drives a significant portion of healthcare costs [1]. Gold standard normative measurements of SCS and NFS from cadaveric studies have limited generalizability as they do not directly correlate with the selected population undergoing MRI evaluation. How these measurements correlate with in vivo imaging techniques is uncertain [2]. Best-practice reporting standards for LMRI have been described with multidisciplinary consensus, favoring a systematic, level-bylevel approach, using consistent and accurate terminology [8,9,10] These features allow a rich textual description of LSDD to be extracted from the radiology report text. The relative structure of LMRI reporting, reflecting from the level-by-level nature of disease, is relatively more amenable to natural language processing (NLP) analysis compared to that in other organ systems, potentiating analysis of very large datasets
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
