Interpretable Machine Learning for Predicting Risk Factors for Chronic Postsurgical Pain After Cesarean Delivery: A Prospective Cohort Study
Year: 2026
Type: article
Study design: Observational Study
Abstract: Chronic postsurgical pain (CPSP) after cesarean delivery can severely impair the mother's quality of life and her ability to care for the infant. The aim of this study was to develop and validate a high‐performance, interpretable, machine learning–based prediction model to identify high‐risk factors for chronic incisional pain at 3, 6, and 12 months postoperatively and chronic non‐incisional pain at 12 months postoperatively. A total of 678 patients who underwent elective cesarean delivery at our hospital were included in the prospective study. A total of 38 preoperative, intraoperative, and postoperative variables, including demographic characteristics, psychological scale scores, and anesthesia/analgesia regimens, were collected. We combined the Boruta algorithm, recursive feature elimination, and the Mantel test for feature selection and constructed a high‐performance machine learning–based prediction model (MLPM‐CPSP‐CD). The incidence of chronic incisional pain at 3, 6, and 12 months postoperatively was 12.39%, 9.73%, and 7.96%, respectively, whereas the incidence of chronic non‐incisional pain was 24.04%. The MLPM‐CPSP‐CD model demonstrated excellent predictive performance. The core high‐risk factors for postoperative chronic incisional pain were SQ‐6 (history of dysmenorrhea), SH‐5 (patient‐controlled analgesia [PCA] pump pressing frequency), and SH‐6 (PCA opioid consumption). This study provides an important foundation for developing and optimizing perioperative pain management strategies.
Source: MedComm
DOI: 10.1002/mco2.71131
Authors: Jiaoli Sun, Kaiwen Zhang, Wei Mei, Xianwei Zhang
Language: English
Subfield: Anesthesiology and Pain Medicine
Field: Medicine
Domain: Health Sciences
Open Access status: gold
Estimated APC paid: $3,500
Award: G4781525651
OpenAlex ID: W7148933422
