Electronic Records Useful in Predicting Patients with Low Back Pain

A study in Pain Research & Management suggests that data from electronic health records (EHRs) could be used to develop a predictive model for patients likely to develop low back pain (LBP).

In many cases, the researchers acknowledge, pain episodes and flare-ups naturally remit and recur in an episodic manner, and patients can engage in self-care and activity avoidance during those flare-ups to minimize the impact.

“However, for a substantial minority of patients, the pain episodes become more frequent, more intense, or increase in duration, and eventually progress to a more severe disease stage with consequences for treatment response, mental health, physical functioning, and utilization of health care,” the study authors note. But are there enough pain signals within routinely collected clinical data within EHRs to predict future utilization patterns?

The researchers used a database maintained by Geisinger Health System to develop a series of logistic regression models to predict who will be a high-cost patient (defined as top 30% of the cost distribution) at each of the first 3 LBP visits. High cost was defined as any patient who used care over the subsequent 12 months that was greater than $1,176, the 70^th percentile of the distribution. They found that, with a high degree of variability, they were able to fairly accurately predict with patients would become high utilizers of healthcare services.

Some of the more interesting study findings:

· Men are more likely to become expensive than women

· Patients receiving workers’ compensation as their primary payer type, had higher use of prescription opioids, or were smokers before their first LBP visit were more likely to become expensive.

· Patients whose first encounter was with a primary care physician were less likely to become expensive than those who received their first LBP care elsewhere.

Some of the limitations of the study include that it only measured those who had at least one year of follow-up after the first LBP visit. “This may have biased the sample selection process because patients who did not meet this criterion may have had systematically less severe LBP,” the researchers note. Second, not all of the data used by the researchers is available in all EHRs—including the financial variables.

Still, they argue that their model allows the potential to identify potentially expensive patients in real time before they become truly expensive. That is a tantalizing notion for managed care organizations, certainly, but also has potentially substantial positive benefit for future pain patients. “As the era of electronic medical records move beyond its current infancy, however, EHR-based predictive modelling strategies, such as the one presented herein, are likely to become more feasible and commonplace,” the researchers conclude.