Learning Pain from Action Unit Combinations: A Weakly Supervised Approach via Multiple Instance Learning

Diurnal Pain Classification in Critically Ill Patients using Machine Learning on Accelerometry and Analgesic Data

Quantifying pain in patients admitted to intensive care units (ICUs) is challenging due to the increased prevalence of communication barriers in this patient population. Previous research has posited a positive correlation between pain and physical activity in critically ill patients. In this study, we advance this hypothesis by building machine learning classifiers to examine the ability of accelerometer data collected from daily wearables to predict self-reported pain levels experienced by patients in the ICU. We trained multiple Machine Learning (ML) models, including Logistic Regression, CatBoost, and XG-Boost, on statistical features extracted from the accelerometer data combined with previous pain measurements and patient demographics. Following previous studies that showed a change in pain sensitivity in ICU patients at night, we performed the task of pain classification separately for daytime and nighttime pain reports. In the pain versus no-pain classification setting, logistic regression gave the best classifier in daytime (AUC: 0.72, F1-score: 0.72), and CatBoost gave the best classifier at nighttime (AUC: 0.82, F1-score: 0.82). Performance of logistic regression dropped to 0.61 AUC, 0.62 F1-score (mild vs. moderate pain, nighttime), and CatBoost's performance was similarly affected with 0.61 AUC, 0.60 F1-score (moderate vs. severe pain, daytime). The inclusion of analgesic information benefited the classification between moderate and severe pain. SHAP analysis was conducted to find the most significant features in each setting. It assigned the highest importance to accelerometer-related features on all evaluated settings but also showed the contribution of the other features such as age and medications in specific contexts. In conclusion, accelerometer data combined with patient demographics and previous pain measurements can be used to screen painful from painless episodes in the ICU and can be combined with analgesic information to provide moderate classification between painful episodes of different severities.

Analyzing facial action units in children to differentiate genuine and fake pain during inferior alveolar nerve block: a cross-sectional study

This study aimed to investigate the association between facial action units and pain levels in Syrian children, focusing on both genuine and fake pain expressions. A total of 300 Syrian children aged 6-9 years participated in the study. Pain levels were assessed using the validated Face, Legs, Activity, Cry, Consolability scale, and facial expressions were analyzed using the Facial Action Coding System. The children were asked to mimic their feelings after receiving a dental injection to elicit fake pain expressions. Statistical analysis, including multinomial logistic regression and chi-square tests, was conducted to determine the Action Units (AUs) associated with each pain level and to compare the differences between real and fake pain expressions. The results revealed significant associations between specific AUs and pain levels. For real pain expressions, the most activated AUs across different pain levels with positive coefficient values of correlation (P-value < 0.01) were analyzed. In contrast, for fake pain expressions, AU12 and AU38 were consistently observed to be the most activated. These findings suggest that certain AUs are uniquely associated with fake pain expressions, distinct from those observed in real pain expressions. Furthermore, there were no significant differences between boys and girls in terms of their genuine and fake pain expressions, indicating a similar pattern of AU activation (P-value > 0.05). It was concluded that AUs 4, 6, 41, and 46 were associated with mild pain, and AUs 4, 6, 41, 46, and 11 were associated with moderate pain cases. In severe pain, AUs 4, 6, 7, 9, 11, and 43 were associated. In fake pain feelings, AU43, AU38, and AU12 were the most activated with no difference between boys and girls.

Ensemble neural network approach detecting pain intensity from facial expressions

This paper reports on research to design an ensemble deep learning framework that integrates fine-tuned, three-stream hybrid deep neural network (i.e., Ensemble Deep Learning Model, EDLM), employing Convolutional Neural Network (CNN) to extract facial image features, detect and accurately classify the pain. To develop the approach, the VGGFace is fine-tuned and integrated with Principal Component Analysis and employed to extract features in images from the Multimodal Intensity Pain database at the early phase of the model fusion. Subsequently, a late fusion, three layers hybrid CNN and recurrent neural network algorithm is developed with their outputs merged to produce image-classified features to classify pain levels. The EDLM model is then benchmarked by means of a single-stream deep learning model including several competing models based on deep learning methods. The results obtained indicate that the proposed framework is able to outperform the competing methods, applied in a multi-level pain detection database to produce a feature classification accuracy that exceeds 89 %, with a receiver operating characteristic of 93 %. To evaluate the generalization of the proposed EDLM model, the UNBC-McMaster Shoulder Pain dataset is used as a test dataset for all of the modelling experiments, which reveals the efficacy of the proposed method for pain classification from facial images. The study concludes that the proposed EDLM model can accurately classify pain and generate multi-class pain levels for potential applications in the medical informatics area, and should therefore, be explored further in expert systems for detecting and classifying the pain intensity of patients, and automatically evaluating the patients' pain level accurately.