Postoperative Pain at Discharge From the Post-anesthesia Care Unit: A Case-Control Study

Area of Science:

• Anesthesiology
• Pain Management
• Machine Learning in Healthcare

Background:

• Severe postoperative pain affects approximately 20% of patients within 24 hours despite advancements.
• Machine learning has shown potential in predicting postoperative pain using various models.
• This study focuses on identifying postoperative pain predictors in a Mexican cohort using physiological and demographic data.

Purpose of the Study:

• To investigate predictors of postoperative pain using a machine learning approach.
• To develop a predictive model for postoperative pain based on physiological indicators and demographic factors.
• To assess pain determinants at Post-anesthesia Care Unit (PACU) discharge in a Mexican population.

Main Methods:

• Retrospective case-control study involving 550 patients (292 cases, 258 controls) discharged from the PACU.
• Data collection included physiological responses (blood pressure, heart rate, respiratory rate), anesthesia type, and demographic factors.
• Machine learning techniques, including logistic regression, were employed to develop a predictive model for postoperative pain.

Main Results:

• Significant differences in postoperative pain were observed between cases and controls.
• Key influencing factors identified include sex, anesthesia type, and physiological responses.
• Visual Analog Scale (VAS) scores at PACU admission were predictive of pain at discharge.

Conclusions:

• Findings confirm sex-based disparities and the influence of anesthesia type on postoperative pain.
• A logistic regression model incorporating physiological responses and sex shows potential for improving pain management.
• Future research should focus on comprehensive predictive models and prospective validation to enhance postoperative pain strategies.