A prediction model of low back pain risk: a population based cohort study in Korea

Abstract

Background: Well-validated risk prediction models help to identify individuals at high risk of diseases and suggest preventive measures. A recent systematic review reported lack of validated prediction models for low back pain (LBP). We aimed to develop prediction models to estimate the 8-year risk of developing LBP and its recurrence. Methods: A population based prospective cohort study using data from 435,968 participants in the National Health Insurance Service-National Sample Cohort enrolled from 2002 to 2010. We used Cox proportional hazards models. Results: During median follow-up period of 8.4 years, there were 143,396 (32.9%) first onset LBP cases. The prediction model of first onset consisted of age, sex, income grade, alcohol consumption, physical exercise, body mass index (BMI), total cholesterol, blood pressure, and medical history of diseases. The model of 5-year recurrence risk was comprised of age, sex, income grade, BMI, length of prescription, and medical history of diseases. The Harrell's C-statistic was 0.812 (95% confidence interval [CI], 0.804-0.820) and 0.916 (95% CI, 0.907-0.924) in validation cohorts of LBP onset and recurrence models, respectively. Age, disc degeneration, and sex conferred the highest risk points for onset, whereas age, spondylolisthesis, and disc degeneration conferred the highest risk for recurrence. Conclusions: LBP risk prediction models and simplified risk scores have been developed and validated using data from general medical practice. This study also offers an opportunity for external validation and updating of the models by incorporating other risk predictors in other settings, especially in this era of precision medicine.

Predicting Physician Consultations for Low Back Pain Using Claims Data and Population-Based Cohort Data—An Interpretable Machine Learning Approach

“…Except for participants' sex and a slightly higher back pain intensity, these participants were almost similar compared to those not seeking care for LBP (Supplement Table S7). Recently, a similar difficulty was found in the correct prediction of incident LBP in a large claims data-based study for the new onset and recurrence of LBP with over 400,000 participants [49].…”

Machine Learning Approaches to Predict Chronic Lower Back Pain in People Aged over 50 Years

“…In our study, analysis and modeling with RFE facilitated the identification of patients at a high risk of LBP and the determination of clinical factors associated with chronic LBP. A previous study employed the Cox proportional-hazards model to identify patients at a high risk of LBP [14,24]. However, only one model's performance was obtained, and it was impossible to compare the various models.…”

“…Machine learning has shown excellent performance in improving the predictive value of statistics in medical imaging and postoperative clinical outcomes [9][10][11][12][13]. Although there have been studies in the past attempting to predict LBP risk, previous research had limitations, such as only applying the Cox proportional-hazards model or not incorporating psychosocial factors and ergonomics-related variables [14].…”

Automated Smart Home Assessment to Support Pain Management: Multiple Methods Analysis

“…However, evidence exists that techniques accounting for small samples and low levels of consistent reporting can produce robust models [ 35 , 36 ]. While it may be difficult to predict pain experience trajectories, well-validated risk prediction models have identified individuals at risk for long-term pain [ 37 ]. Predictive models have been tested for low back pain [ 37 ], post-surgical cancer pain [ 38 ], and pain with dementia [ 39 ].…”

“…While it may be difficult to predict pain experience trajectories, well-validated risk prediction models have identified individuals at risk for long-term pain [ 37 ]. Predictive models have been tested for low back pain [ 37 ], post-surgical cancer pain [ 38 ], and pain with dementia [ 39 ]. Statistical modeling has also been used to predict physical and psychological factors for long-term pain [ 40 ]; however, models have not yet been developed to identify pain-reducing behaviors.…”