Risk Factors and Prediction of Chronic Postsurgical Pain Among Patients With Distal Lower Extremity Fracture: Cohort...

Area of Science:

• Orthopedic surgery
• Pain medicine
• Data science in healthcare

Background:

• Chronic postsurgical pain (CPSP) is a significant issue after fracture repair, impacting quality of life.
• Young patients with distal lower extremity fractures are understudied regarding CPSP.
• Predictive models are needed for early detection and personalized pain management.

Purpose of the Study:

• To develop and validate a predictive model for early identification of patients at risk of CPSP.
• To create a web-based risk calculator for clinical use.

Main Methods:

• Collected in-hospital records and 1-year follow-up data from 818 patients.
• Employed a 3-stage modeling approach: LASSO regression, information gain, and logistic regression.
• Validated the model and developed a web-based predictive nomogram using Shinyapps.io.

Main Results:

• 38.4% of patients experienced CPSP; 18.2% of those developed neuropathic pain.
• Identified 6 independent predictors of CPSP, including analgesic technique and NRS scores.
• Achieved high predictive accuracy (AUC 0.872 development, 0.838 validation) with good calibration.

Conclusions:

• Pain management, surgical techniques, and psychological factors influence CPSP development.
• A machine learning-integrated predictive nomogram can identify early CPSP risk at discharge.
• The tool enhances accessibility to transitional pain care interventions.