Predicting the evolution of low back pain patients in routine clinical practice: results from a registry within the Spanish National Health Service

Abstract

Background context: The Spanish National Health Service (SNHS) is a tax-funded public organization that provides free health care to every resident in Spain.

Purpose: To develop models for predicting the evolution of low back pain (LBP) in routine clinical practice within SNHS.

Study design: Analysis of a prospective registry in routine clinical practice, in 17 centers across SNHS.

Patient sample: Patient sample includes 4,477 acute and chronic LBP patients treated in primary and hospital care.

Outcome measures: Pain and disability, measured through validated instruments.

Methods: Patients treated for LBP were assessed at baseline and 3 months later. Data gathered were the following: sex, age, employment status, duration of pain, severity of LBP, pain down to the leg (LP) and disability, history of lumbar surgery, diagnostic procedures undertaken, imaging findings, and treatments used throughout the study period. Three separate multivariate logistic regression models were developed for predicting a clinically relevant improvement in LBP, LP, and disability at 3 months.

Results: In total, 4,261 patients (95.2%) attended follow-up. For all the models, calibration was reasonable and the area under the receiver operating characteristic curve was ≥0.640. For LBP, LP, and disability, factors associated with a higher probability of improvement at 3 months were the following: not having undergone lumbar surgery, higher baseline scores for the corresponding variable, lower ones for the rest, and being treated with neuroreflexotherapy. Additional factors were the following: for LBP, shorter pain duration; for LP, not undergoing electromyography; and for disability, shorter pain duration, not being diagnosed with disc degeneration, and being treated with muscle relaxants and not opioids.

Conclusions: A prospective registry can be used for developing predictive models to quantify the odds that a given LBP patient will experience a clinically relevant improvement. This may empower patients for an informed shared decision making.