Prediction of low back pain using artificial intelligence modeling

Abstract

Background: Back pain has profound effect on daily life with impairment in activities and decrease in quality of life. This paper explores the risk factors for low back pain in terms of radiologic data and applies artificial intelligence modeling to decipher the associations. Methods: Ten different artificial intelligence machine learning and deep learning classification systems were implemented in order to predict the presence or absence of back pain. The dataset used for the analysis is available in public domain and is identified as PONE-D-14-50818. Results: In our analysis, the disk heights of L1 and L2 and ligamentum flavum hypertrophy of the L3 and L4 were statistically significant in terms of predicting symptoms of low back pain. Based upon the data, the logistic regression classification model was effectively able to use quantitative measures from lumbar imaging in order to predict the presence or absence of lower back pain. Conclusions: These models could be instrumental in clinical practice in deciphering lower back pain due to skeletal abnormalities. The artificial intelligence models can not only be used to predict back pain in new patients, but also each new patient's data can be inputted into the model, leading to even higher accuracy of the model for future patients. The model output can help the pain specialist in quantitatively assessing the predominant risk areas and guide intervention thereof. Artificial intelligence and machine learning algorithms can decipher various associations to assess low back pain using magnetic resonance imaging and computed tomography of the lumbar spine.