Affiliation:
1. Department of Orthopaedic Surgery, West China Hospital, West China Medical School SiChuan University ChengDu SiChuan Province People's Republic of China
2. Department of Orthopaedic Surgery, School of Medicine Duke University Durham North Carolina USA
3. Department of Immuno‐Oncology City of Hope Comprehensive Cancer Center Duarte California USA
4. Department of Orthopedic Surgery Rush University Medical Center Chicago Illinois USA
Abstract
AbstractBackgroundLow back pain (LBP) is a heterogeneous disease with biological, physical, and psychosocial etiologies. Models for predicting LBP severity and chronicity have not made a clinical impact, perhaps due to difficulty deciphering multidimensional phenotypes. In this study, our objective was to develop a computational framework to comprehensively screen metrics related to LBP severity and chronicity and identify the most influential.MethodsWe identified individuals from the observational, longitudinal Osteoarthritis Initiative cohort (N = 4796) who reported LBP at enrollment (N = 215). OAI descriptor variables (N = 1190) were used to cluster individuals via unsupervised learning and uncover latent LBP phenotypes. We also developed a dimensionality reduction algorithm to visualize clusters/phenotypes using Uniform Manifold Approximation and Projection (UMAP). Next, to predict chronicity, we identified those with acute LBP (N = 40) and persistent LBP over 8 years of follow‐up (N = 66) and built logistic regression and supervised machine learning models.ResultsWe identified three LBP phenotypes: a “high socioeconomic status, low pain severity group”, a “low socioeconomic status, high pain severity group”, and an intermediate group. Mental health and nutrition were also key clustering variables, while traditional biomedical factors (e.g., age, sex, BMI) were not. Those who developed chronic LBP were differentiated by higher pain interference and lower alcohol consumption (a correlate to poor physical fitness and lower soceioeconomic status). All models for predicting chronicity had satisfactory performance (accuracy 76%–78%).ConclusionsWe developed a computational pipeline capable of screening hundreds of variables and visualizing LBP cohorts. We found that socioeconomic status, mental health, nutrition, and pain interference were more influential in LBP than traditional biomedical descriptors like age, sex, and BMI.
Funder
Department of Science and Technology of Sichuan Province
National Institute of Arthritis and Musculoskeletal and Skin Diseases
National Natural Science Foundation of China
Subject
Orthopedics and Sports Medicine
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献