Psychological factors contribute more to chronic low back pain than spine pathology: An LLM-based analysis of radiology reports
- 1Rush University Medical Center
Abstract
BackgroundChronic low back pain (cLBP) is the leading global cause of disability, yet anatomical, psychological, and socioeconomic determinants are typically studied in isolation, with limited large-scale integration of imaging and biopsychosocial data. We linked imaging findings with demographic, anthropometric, and biopsychosocial characteristics to determine their relative contributions to cLBP.
MethodsWe retrospectively analyzed 1,480 Chicago-based patients with lumbar spine MRI between 3/2014 and 3/2024. cLBP was as two or more LBP diagnoses recorded six months apart. Spinal pathologies (stenosis, disc disease, facet arthropathy and spondylolisthesis) were extracted from radiology reports using a large language model (GPT-4) and benchmarked against a regex (rule-based text search) pipeline. Multivariable logistic regression evaluated associations between cLBP diagnosis and demographic, anthropometric, socioeconomic, psychological, and anatomical determinants. A parallel linear regression modeled overall anatomical pathology burden.
ResultsThe LLM pipeline achieved an F1-score of 0.98 versus 0.92 for regex. cLBP diagnosis was most strongly associated with depression (OR=2.69, p<0.001) and anxiety (OR=2.31, p<0.001), with smaller contributions from spinal stenosis (OR=1.07, p=0.006) and spondylolisthesis (OR=1.15, p=0.039). Leave-one-domain-out analysis showed psychological factors were most impactful ({Delta}AIC=120.1), followed by anatomical ({Delta}AIC=37.0), demographic/anthropometric ({Delta}AIC=21.8), and socioeconomic ({Delta}AIC=3.0). Overall anatomical burden was associated with age, male sex, higher BMI, and Non-Hispanic White race, with no associations with socioeconomic or psychological variables.
ConclusionsFactors associated with diagnosed cLBP and those associated with structural spinal pathology are largely dissociated. Psychological comorbidities show the strongest associations with cLBP, while anatomical burden is mostly driven by demographics, reinforcing the psychosocial nature of cLBP.
Related
- Endovascular management of acute and chronic arterial mesenteric ischaemia: A narrative review of evidence informing interventional radiology treatment
- Factors associated with choosing diagnostic radiology as a future specialty among Palestinian medical students: a multicenter cross-sectional study
- 5.0T multi-parametric diffusion MRI histogram analysis for prostate cancer pathology grading and adverse pathological factors
- Self-perceived cognition and psychological well-being in patients with chronic kidney disease undergoing maintenance haemodialysis
- Beyond Physical Recovery: Psychological Factors and Assessment Tools in Return to Sport Decision-making after Anterior Cruciate Ligament Reconstruction – A Scoping Review
BibTeX
@misc{perrone2026psychological,
title = {{Psychological factors contribute more to chronic low back pain than spine pathology: An LLM-based analysis of radiology reports}},
author = {M. Perrone and H. Tachi and H. Albadi and D. Moore and A. Alavilli and N. Lee and T. Johnson and J. Martin},
howpublished = {medRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.16.26363055},
url = {https://www.medrxiv.org/content/10.64898/2026.09.16.26363055v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Psychological factors contribute more to chronic low back pain than spine pathology: An LLM-based analysis of radiology reports
AU - M. Perrone
AU - H. Tachi
AU - H. Albadi
AU - D. Moore
AU - A. Alavilli
AU - N. Lee
AU - T. Johnson
AU - J. Martin
PY - 2026
DA - 2026/09/16
PB - medRxiv
DO - 10.64898/2026.09.16.26363055
UR - https://www.medrxiv.org/content/10.64898/2026.09.16.26363055v1
AB - BackgroundChronic low back pain (cLBP) is the leading global cause of disability, yet anatomical, psychological, and socioeconomic determinants are typically studied in isolation, with limited large-scale integration of imaging and biopsychosocial data. We linked imaging findings with demographic, anthropometric, and biopsychosocial characteristics to determine their relative contributions to cLBP. MethodsWe retrospectively analyzed 1,480 Chicago-based patients with lumbar spine MRI between 3/2014 and 3/2024. cLBP was as two or more LBP diagnoses recorded six months apart. Spinal pathologies (stenosis, disc disease, facet arthropathy and spondylolisthesis) were extracted from radiology reports using a large language model (GPT-4) and benchmarked against a regex (rule-based text search) pipeline. Multivariable logistic regression evaluated associations between cLBP diagnosis and demographic, anthropometric, socioeconomic, psychological, and anatomical determinants. A parallel linear regression modeled overall anatomical pathology burden. ResultsThe LLM pipeline achieved an F1-score of 0.98 versus 0.92 for regex. cLBP diagnosis was most strongly associated with depression (OR=2.69, p<0.001) and anxiety (OR=2.31, p<0.001), with smaller contributions from spinal stenosis (OR=1.07, p=0.006) and spondylolisthesis (OR=1.15, p=0.039). Leave-one-domain-out analysis showed psychological factors were most impactful ({Delta}AIC=120.1), followed by anatomical ({Delta}AIC=37.0), demographic/anthropometric ({Delta}AIC=21.8), and socioeconomic ({Delta}AIC=3.0). Overall anatomical burden was associated with age, male sex, higher BMI, and Non-Hispanic White race, with no associations with socioeconomic or psychological variables. ConclusionsFactors associated with diagnosed cLBP and those associated with structural spinal pathology are largely dissociated. Psychological comorbidities show the strongest associations with cLBP, while anatomical burden is mostly driven by demographics, reinforcing the psychosocial nature of cLBP.
ER -