Machine learning based quantitative pain assessment for the perioperative period.

This study developed and evaluated a model for assessing pain during the surgical period using photoplethysmogram data from 242 patients. Pain levels were measured at 2 min intervals using a numerical rating scale or clinical criteria: preoperative, before and after intubation, before and after skin incision, and postoperative. Key features from the photoplethysmography waveform were extracted to build XGBoost-based models for intraoperative and postoperative pain assessment. The combined perioperative model was compared with a commercial surgical pain index, yielding area under the receiver operating characteristics curve scores of 0.819 and 0.927 for intraoperative and postoperative periods, respectively, compared to the commercial index's scores of 0.829 and 0.577. These results highlight the models' effectiveness in pain assessment throughout the surgical process, identifying waveform skewness and diastolic phase rate decrease as critical for intraoperative pain assessment and systolic phase area or baseline fluctuation as significant for postoperative pain assessment.Clinical trial registration: Registration name: Clinical Research Information Service (CRIS). Registration site: http://cris.nih.go.kr . Number: KCT0005840. Principal Investigator: Dr. Byung-Moon Choi. Date of registration: January 28, 2021.