About 80 percent of adults experience lower back pain in their lifetime; it is the most common cause of job-related disability. Many argue that prescribing opioids for lower back pain contributed to the opioid crisis; thus, determining the quality of lower back pain in clinical practice could provide an effective tool not only to improve the management of lower back pain but also to curb unnecessary opioid prescriptions.
Acute and chronic lower back pain are different conditions with different treatments. However, they are coded in electronic health records with the same code and can be differentiated only by retrospective reviews of the patient’s chart, which includes the review of clinical notes. The single code for two different conditions prevents appropriate billing and therapy recommendations, including different return-to-work scenarios. The artificial intelligence model in this study, the first of its kind, could be used to improve the accuracy of coding, billing, and therapy for patients with lower back pain.
The researchers used 17,409 clinical notes for 16,715 patients to train artificial intelligence models to determine the severity of lower back pain.
“Several studies have documented increases in medication prescriptions and visits to physicians, physical therapists, and chiropractors for lower back pain episodes,” said Ismail Nabeel, MD, MPH, Associate Professor of Environmental Medicine and Public Health at the Icahn School of Medicine at Mount Sinai. “This study is important because artificial intelligence can potentially more accurately distinguish whether the pain is acute or chronic, which would determine whether a patient should return to normal activities quickly or rest and schedule follow-up visits with a physician. This study also has implications for diagnosis, treatment, and billing purposes in other musculoskeletal conditions, such as the knee, elbow, and shoulder pain, where the medical codes also do not differentiate by pain level and acuity.”
This research was funded by Pilot Projects Research Training Program of the NY and NJ Education and Research Center (ERC), National Institute for Occupational Safety and Health grant # T42 OH 008422, Hasso Plattner Foundation and NVIDIA.