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

Abstract

Background Although 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. Objective This 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. Methods PPGs 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. Results PPGs 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%. Conclusions Although 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 Registration Clinical Research Information Service KCT0002080; https://cris.nih.go.kr/cris/search/search_result_st01.jsp?seq=6638

A systematic review of neurophysiological sensing for the assessment of acute pain

“…However, a key challenge in the success of DL models is the need for large amounts of training data, as the data increases, a well-behaved performance model can be obtained 115 . This in part may explain why most ML models outperformed DL models using the same dataset 35 , 39 or with the use of the same sensor modality 117 , 118 . In many cases, large datasets (in particular, labelled datasets) may be too difficult or costly to be collected for many learning problems.…”

“…In automated pain assessment, these differences have shown an adverse effect in the modelling of both neural and physiological signals for the assessment of pain. In the reviewed literature, several studies using neural (EEG, fNIRS) or physiological (PPG, EDA, EMG) signals reported notable inter-subject variability in pain perception and responses; these reported differences in neural and physiological responses affected the capacity of machine learning models to generalise across people 28 , 34 , 70 , 71 , 103 , 117 . Inter-individual differences often lead to model overfitting, which can be interpreted as the lack of model’s generalisability to give accurate predictions with new data 117 .…”

“…In the reviewed literature, several studies using neural (EEG, fNIRS) or physiological (PPG, EDA, EMG) signals reported notable inter-subject variability in pain perception and responses; these reported differences in neural and physiological responses affected the capacity of machine learning models to generalise across people 28 , 34 , 70 , 71 , 103 , 117 . Inter-individual differences often lead to model overfitting, which can be interpreted as the lack of model’s generalisability to give accurate predictions with new data 117 . In addition, intra-individual variability is usually superimposed on top of inter-individual variability, which represents an added confounder to model neural and physiological signals 150 .…”

Photoplethysmography temporal marker-based machine learning classifier for anesthesia drug detection

“…In the future study, an extensive dataset including demographic and clinical data will be created using hospital databases along with the anesthesia depth reference (BIS) to develop a better machine learning model that could estimate the correct depth of anesthesia and provide a reliable and cost-effective monitoring solution to the staff. Additionally, deep learning has been proposed as a promising tool to achieve reliable detection of anesthesia, which deserves exploration based on multi-center, large-scale datasets [34].…”

Multimodal physiological sensing for the assessment of acute pain

“…For example, EDA can capture sympathetic changes related to pain, as it measures the sweat glad activity as response to pain ( 9 ). PPG can be used to measure the autonomic response through analysis of heart rate variability (HRV) ( 10 ). The respiratory system is also affected by a sympathetic nerves, which have a stimulating effect by increasing oxygen intake in the event of acute pain ( 11 ).…”