摘要：Monitoring the pain intensity in critically ill patients is crucial because intense pain can cause adverse events, including poor survival rates; however, continuous pain evaluation is difficult. Vital signs have traditionally been considered ineffective in pain assessment; nevertheless, the use of machine learning may automate pain assessment using vital signs. This retrospective observational study was performed at a university hospital in Sendai, Japan. Objective pain assessments were performed in eligible patients using the Critical-Care Pain Observation Tool (CPOT). Three machine-learning methods-random forest (RF), support vector machine (SVM), and logistic regression (LR)-were employed to predict pain using parameters, such as vital signs, age group, and sedation levels. Prediction accuracy was calculated as the harmonic mean of sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC). Furthermore, 117,190 CPOT assessments were performed in 11,507 eligible patients (median age: 65 years; 58.0% males). We found that pain prediction was possible with all three machine-learning methods. RF demonstrated the highest AUROC for the test data (RF: 0.853, SVM: 0.823, and LR: 0.787). With this method, pain can be objectively, continuously, and semi-automatically evaluated in critically ill patients.
其他摘要：Abstract Monitoring the pain intensity in critically ill patients is crucial because intense pain can cause adverse events, including poor survival rates; however, continuous pain evaluation is difficult. Vital signs have traditionally been considered ineffective in pain assessment; nevertheless, the use of machine learning may automate pain assessment using vital signs. This retrospective observational study was performed at a university hospital in Sendai, Japan. Objective pain assessments were performed in eligible patients using the Critical-Care Pain Observation Tool (CPOT). Three machine-learning methods—random forest (RF), support vector machine (SVM), and logistic regression (LR)—were employed to predict pain using parameters, such as vital signs, age group, and sedation levels. Prediction accuracy was calculated as the harmonic mean of sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC). Furthermore, 117,190 CPOT assessments were performed in 11,507 eligible patients (median age: 65 years; 58.0% males). We found that pain prediction was possible with all three machine-learning methods. RF demonstrated the highest AUROC for the test data (RF: 0.853, SVM: 0.823, and LR: 0.787). With this method, pain can be objectively, continuously, and semi-automatically evaluated in critically ill patients.
