Novel Analgesic Index for Postoperative Pain Assessment Based on a Photoplethysmographic Spectrogram and Convolutional Neural Network: Observational Study.

Byung-Moon Choi,Hangsik Shin,Ji Yeon Yim,Gyujeong Noh

doi:10.2196/23920

Abstract

BackgroundAlthough commercially available analgesic indices based on biosignal processing have been used to quantify nociception during general anesthesia, their performance is low in conscious patients. Therefore, there is a need to develop a new analgesic index with improved performance to quantify postoperative pain in conscious patients.ObjectiveThis study aimed to develop a new analgesic index using photoplethysmogram (PPG) spectrograms and a convolutional neural network (CNN) to objectively assess pain in conscious patients.MethodsPPGs were obtained from a group of surgical patients for 6 minutes both in the absence (preoperatively) and in the presence (postoperatively) of pain. Then, the PPG data of the latter 5 minutes were used for analysis. Based on the PPGs and a CNN, we developed a spectrogram–CNN index for pain assessment. The area under the curve (AUC) of the receiver-operating characteristic curve was measured to evaluate the performance of the 2 indices.ResultsPPGs from 100 patients were used to develop the spectrogram–CNN index. When there was pain, the mean (95% CI) spectrogram–CNN index value increased significantly—baseline: 28.5 (24.2-30.7) versus recovery area: 65.7 (60.5-68.3); P<.01. The AUC and balanced accuracy were 0.76 and 71.4%, respectively. The spectrogram–CNN index cutoff value for detecting pain was 48, with a sensitivity of 68.3% and specificity of 73.8%.ConclusionsAlthough there were limitations to the study design, we confirmed that the spectrogram–CNN index can efficiently detect postoperative pain in conscious patients. Further studies are required to assess the spectrogram–CNN index’s feasibility and prevent overfitting to various populations, including patients under general anesthesia.Trial RegistrationClinical Research Information Service KCT0002080; https://cris.nih.go.kr/cris/search/search_result_st01.jsp?seq=6638

Highlights

Efficient management of postoperative pain affecting the prognosis of patients is becoming increasingly important [1].To properly administer analgesics, it is necessary to first objectively assess the patient’s degree of pain
Conclusions: there were limitations to the study design, we confirmed that the spectrogram–convolutional neural network (CNN) index can efficiently detect postoperative pain in conscious patients
Current commercial analgesic indices were developed for the purpose of evaluating nociception in patients under general anesthesia [2,3]; there is no standard for the quantification of postoperative pain in conscious patients [4]

Summary

Introduction

Efficient management of postoperative pain affecting the prognosis of patients is becoming increasingly important [1].To properly administer analgesics, it is necessary to first objectively assess the patient’s degree of pain. Current commercial analgesic indices were developed for the purpose of evaluating nociception in patients under general anesthesia [2,3]; there is no standard for the quantification of postoperative pain in conscious patients [4]. The surgical pleth index (SPI; GE Healthcare), developed for quantifying nociception during general anesthesia, only considers the amplitude and heartbeat interval of a PPG [3]. In addition to these 2 parameters, other pain-related features are present in PPG signals [6,7]. There is a need to develop a new analgesic index with improved performance to quantify postoperative pain in conscious patients

Methods

Results

Conclusion