Toward Opioid-Free Ambulatory Surgery: A Prospective Study Using Machine Learning to Predict Postoperative Opioid Use.

BACKGROUND

Postoperative opioid use carries risk of dependence and diversion. We developed an opioid-sparing regimen and identified factors associated with postoperative opioid use.

STUDY DESIGN

The Toward Opioid-Free Ambulatory Surgery (TOFAS) program was developed by establishing a regimen of ibuprofen 600mg and acetaminophen 650mg alternating every 3-hours with a rescue prescription of oxycodone 5mg (10 doses). The study included adults undergoing ambulatory operations. A machine learning (ML) model was then developed to predict post-operative opioid use. Performance was evaluated by area under the receiver operating characteristic curve (AUC) using an 80/20 train-test split and repeated across 10 random seeds to assess stability. Feature selection was performed iteratively using training data while model performance was evaluated on test sets.

RESULTS

223 patients were prospectively enrolled (median age 50 years, 69% male, 91% white). The most common procedure was inguinal hernia repair (49%). 42% of patients filled their opioid prescription with median of 4 doses used. The ML model achieved a mean test AUC of 0.674 (range: 0.634-0.732) across 10 runs. Mean sensitivity was 0.70, and specificity 0.68. Most selected factors included active cancer, age, anesthesia type, race/ethnicity, COPD history, intraoperative complications, preoperative acetaminophen use, and pain intensity. Specifically in seed 3 (AUC: 0.67), the most influential features were age (model gain 17.8%) and pain intensity (model gain 11%).

CONCLUSION

The ML model reliably identified high-risk individuals, supporting the potential for personalized opioid-sparing strategies in outpatient surgery. This model may help identify patients likely to require opioids enabling tailored pain management planning.