Risk Factors for Chronic Post-Surgical Pain in the Elderly: A Single-Center Retrospective Study

Area of Science:

• Geriatric Surgery
• Pain Medicine
• Machine Learning in Healthcare

Background:

• Chronic post-surgical pain (CPSP) is a common complication in elderly patients.
• Predicting CPSP based on perioperative factors and patient mental status requires further investigation.

Purpose of the Study:

• To identify perioperative risk factors for 3-month CPSP in elderly patients undergoing non-cardiac surgery.
• To define CPSP as pain intensity ≥3 on the Numerical Rating Scale at 3-month follow-up.

Main Methods:

• Retrospective study of 367 elderly patients across three surgical subgroups.
• Analysis of variables using descriptive statistics and machine learning algorithms (10 models).
• Model performance assessed via 5-fold cross-validation; SHAP used for factor interpretation.

Main Results:

• Overall 3-month CPSP prevalence was 25.07%, varying by surgery: orthopedic (48.05%), urinary tumor (10.34%), abdominal tumor (7.14%).
• Random Forest model demonstrated strong predictive ability across subgroups.
• Frailty identified as a universal risk factor; surgery-specific factors also noted.

Conclusions:

• Data-driven models can reliably predict CPSP in elderly patients.
• Frailty is a key risk factor across all surgical types.
• Surgery-specific risk profiles support tailored perioperative assessment and prevention.