Postoperative Pain Assessment Model Based on Pulse Contour Characteristics Analysis

Classification of pain expression images in elderly with hip fractures based on improved ResNet50 network

The aim of this study is designed an improved ResNet 50 network to achieve automatic classification model for pain expressions by elderly patients with hip fractures. This study built a dataset by combining the advantages of deep learning in image recognition, using a hybrid of the Multi-Task Cascaded Convolutional Neural Networks (MTCNN). Based on ResNet50 network framework utilized transfer learning to implement model function. This study performed the hyperparameters by Bayesian optimization in the learning process. This study calculated intraclass correlation between visual analog scale scores provided by clinicians independently and those provided by pain expression evaluation assistant(PEEA). The automatic pain expression recognition model in elderly patients with hip fractures, which constructed using the algorithm. The accuracy achieved 99.6% on the training set, 98.7% on the validation set, and 98.2% on the test set. The substantial kappa coefficient of 0.683 confirmed the efficacy of PEEA in clinic. This study demonstrates that the improved ResNet50 network can be used to construct an automatic pain expression recognition model for elderly patients with hip fractures, which has higher accuracy.

Preliminary study: quantification of chronic pain from physiological data

Supplemental Digital Content is Available in the Text.

Preliminary evidence suggests that physiological variables collected with our low-cost pain meter are correlated with chronic pain, both for individuals and populations.

Introduction:

It is unknown if physiological changes associated with chronic pain could be measured with inexpensive physiological sensors. Recently, acute pain and laboratory-induced pain have been quantified with physiological sensors.

Objectives:

To investigate the extent to which chronic pain can be quantified with physiological sensors.

Methods:

Data were collected from chronic pain sufferers who subjectively rated their pain on a 0 to 10 visual analogue scale, using our recently developed pain meter. Physiological variables, including pulse, temperature, and motion signals, were measured at head, neck, wrist, and finger with multiple sensors. To quantify pain, features were first extracted from 10-second windows. Linear models with recursive feature elimination were fit for each subject. A random forest regression model was used for pain score prediction for the population-level model.

Results:

Predictive performance was assessed using leave-one-recording-out cross-validation and nonparametric permutation testing. For individual-level models, 5 of 12 subjects yielded intraclass correlation coefficients between actual and predicted pain scores of 0.46 to 0.75. For the population-level model, the random forest method yielded an intraclass correlation coefficient of 0.58. Bland–Altman analysis shows that our model tends to overestimate the lower end of the pain scores and underestimate the higher end.

Conclusion:

This is the first demonstration that physiological data can be correlated with chronic pain, both for individuals and populations. Further research and more extensive data will be required to assess whether this approach could be used as a “chronic pain meter” to assess the level of chronic pain in patients.

Photoplethysmogram Analysis and Applications: An Integrative Review

Beyond its use in a clinical environment, photoplethysmogram (PPG) is increasingly used for measuring the physiological state of an individual in daily life. This review aims to examine existing research on photoplethysmogram concerning its generation mechanisms, measurement principles, clinical applications, noise definition, pre-processing techniques, feature detection techniques, and post-processing techniques for photoplethysmogram processing, especially from an engineering point of view. We performed an extensive search with the PubMed, Google Scholar, Institute of Electrical and Electronics Engineers (IEEE), ScienceDirect, and Web of Science databases. Exclusion conditions did not include the year of publication, but articles not published in English were excluded. Based on 118 articles, we identified four main topics of enabling PPG: (A) PPG waveform, (B) PPG features and clinical applications including basic features based on the original PPG waveform, combined features of PPG, and derivative features of PPG, (C) PPG noise including motion artifact baseline wandering and hypoperfusion, and (D) PPG signal processing including PPG preprocessing, PPG peak detection, and signal quality index. The application field of photoplethysmogram has been extending from the clinical to the mobile environment. Although there is no standardized pre-processing pipeline for PPG signal processing, as PPG data are acquired and accumulated in various ways, the recently proposed machine learning-based method is expected to offer a promising solution.

The Assessment of Autonomic Nervous System Activity Based on Photoplethysmography in Healthy Young Men

Noninvasive assessment of autonomic nervous system (ANS) activity is of great importance, but the accuracy of the method used, which is primarily based on electrocardiogram-derived heart rate variability (HRV), has long been suspected. We investigated the feasibility of photoplethysmography (PPG) in ANS evaluation. Data of 32 healthy young men under four different ANS activation patterns were recorded: baseline, slow deep breathing (parasympathetic activation), cold pressor test (peripheral sympathetic activation), and mental arithmetic test (cardiac sympathetic activation). We extracted 110 PPG-based features to construct classification models for the four ANS activation patterns. Using interpretable models based on random forest, the main PPG features related to ANS activation were obtained. Results showed that pulse rate variability (PRV) exhibited similar changes to HRV across the different experiments. The four ANS patterns could be better classified using more PPG-based features compared with using HRV or PRV features, for which the classification accuracies were 0.80, 0.56, and 0.57, respectively. Sensitive features of parasympathetic activation included features of nonlinear (sample entropy), frequency, and time domains of PRV. Sensitive features of sympathetic activation were features of the amplitude and frequency domain of PRV of the PPG derivatives. Subsequently, these sensitive PPG-based features were used to fit the improved HRV parameters. The fitting results were acceptable (p < 0.01), which might provide a better method of evaluating ANS activity using PPG.

Pain Monitoring Using Heart Rate Variability and Photoplethysmograph-Derived Parameters by Binary Logistic Regression

Purpose

To construct a pain classification model using binary logistic regression to calculate pain probability and monitor pain based on heart rate variability (HRV) and photoplethysmography (PPG) parameters.

Methods

Heat stimulation was used to simulate pain for modeling the pain generation process, and electrocardiography and PPG signals were recorded simultaneously. After signal analysis, statistical analysis was performed using SPSS to determine the parameters that were significant for pain. Thereafter, a pain classification model with HRV and PPG parameters was established using binary logistic regression.

Results

The sensitivity and specificity of the pain classification model were 60.0% and 72.0%, respectively. When pain occurred, the probability calculated using the pain classification model increased from < 50% to > 50%. When the pain was relieved, the probability decreased to < 50%. The probability of pain was consistent with the numeric rating scale value, which indicated that the model can correctly determine the presence of pain.

Conclusion

This pain classification model has sufficient robustness and adaptability to be applied to different healthy people for classification and monitoring. This model is helpful in establishing a real-time pain monitoring system to improve pain management for patients in the postoperative intensive care unit and patient-controlled analgesia and provide a reference for doctors regarding medication.

Recurrence Plot and Machine Learning for Signal Quality Assessment of Photoplethysmogram in Mobile Environment

The purpose of this study was to develop a machine learning model that could accurately evaluate the quality of a photoplethysmogram based on the shape of the photoplethysmogram and the phase relevance in a pulsatile waveform without requiring complicated pre-processing. Photoplethysmograms were recorded for 76 participants (5 min for each participant). All recorded photoplethysmograms were segmented for each beat to obtain a total of 49,561 pulsatile segments. These pulsatile segments were manually labeled as ‘good’ and ‘poor’ classes and converted to a two-dimensional phase space trajectory image using a recurrence plot. The classification model was implemented using a convolutional neural network with a two-layer structure. As a result, the proposed model correctly classified 48,827 segments out of 49,561 segments and misclassified 734 segments, showing a balanced accuracy of 0.975. Sensitivity, specificity, and positive predictive values of the developed model for the test dataset with a ‘poor’ class classification were 0.964, 0.987, and 0.848, respectively. The area under the curve was 0.994. The convolutional neural network model with recurrence plot as input proposed in this study can be used for signal quality assessment as a generalized model with high accuracy through data expansion. It has an advantage in that it does not require complicated pre-processing or a feature detection process.

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

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

Multimodal spatio-temporal deep learning approach for neonatal postoperative pain assessment

The current practice for assessing neonatal postoperative pain relies on bedside caregivers. This practice is subjective, inconsistent, slow, and discontinuous. To develop a reliable medical interpretation, several automated approaches have been proposed to enhance the current practice. These approaches are unimodal and focus mainly on assessing neonatal procedural (acute) pain. As pain is a multimodal emotion that is often expressed through multiple modalities, the multimodal assessment of pain is necessary especially in case of postoperative (acute prolonged) pain. Additionally, spatio-temporal analysis is more stable over time and has been proven to be highly effective at minimizing misclassification errors. In this paper, we present a novel multimodal spatio-temporal approach that integrates visual and vocal signals and uses them for assessing neonatal postoperative pain. We conduct comprehensive experiments to investigate the effectiveness of the proposed approach. We compare the performance of the multimodal and unimodal postoperative pain assessment, and measure the impact of temporal information integration. The experimental results, on a real-world dataset, show that the proposed multimodal spatio-temporal approach achieves the highest AUC (0.87) and accuracy (79%), which are on average 6.67% and 6.33% higher than unimodal approaches. The results also show that the integration of temporal information markedly improves the performance as compared to the non-temporal approach as it captures changes in the pain dynamic. These results demonstrate that the proposed approach can be used as a viable alternative to manual assessment, which would tread a path toward fully automated pain monitoring in clinical settings, point-of-care testing, and homes.