Low back pain (LBP) is a common musculoskeletal problem that is frequently encountered in
the population and can occur at any age. Responsible for the loss of a full healthy year
in both the 10-24 and 50-74 age groups, LBP causes significant personal and social losses
and increases healthcare costs.
In the classification of low back pain, pain that persists for up to 6 weeks is defined
as acute, pain that lasts between 6-12 weeks is subacute, and pain that persists for more
than 12 weeks is considered chronic low back pain (CLBP).
Chronic LBP (CLBP) leads to fear of movement, causing patients to limit their daily
activities and social participation to avoid pain. A sedentary lifestyle in LBP patients
is a factor that contributes to the chronicity of the disease. While most acute LBP
patients recover well within a few weeks or months, the prognosis for patients with
chronic low back pain is generally poor. Approximately one-quarter of patients visiting
primary care facilities develop chronic LBP.
Therefore, identifying the risk factors for chronic LBP, understanding the population at
risk of developing chronic LBP, identifying high-risk individuals, and implementing
appropriate preventive and therapeutic measures are important.
Several musculoskeletal problems have played a role as risk factors in the development of
LBP, and identifying and validating these risk factors can provide a potential mechanism
through which LBP can be effectively treated. Accurately identifying musculoskeletal
problems and risk factors can provide a mechanism to prevent the development of LBP and
reduce the socioeconomic burden associated with the condition.
Machine learning (ML) is a scientific discipline that uses computer algorithms to
identify patterns in large amounts of data and make predictions on new datasets based on
these patterns. ML creates models to predict unknown data from historical data and allows
us to select the most appropriate algorithm. Additionally, ML algorithms can extract
variables that contribute to the prediction of the target variable, and differ from
traditional statistical methods in enhancing the accuracy of future data predictions. ML
has shown excellent performance in increasing the predictive value of medical imaging and
postoperative clinical outcomes.
The aim of this study is to compare the joint range of motion in patients with low back
pain and healthy individuals, and to detect differences in these ranges using artificial
intelligence-supported analysis methods.