A study of 1,099 patients was conducted to test decision tree-based learning algorithms to predict analgesic consumption and patient-controlled anesthesia control readjustment, according to 7thSpace.
The results of the study showed the prediction accuracies of total analgesic consumption and PCA requirement by an ensemble of decision trees were 80.9 percent and 73.1 percent, respectively.
Decision tree-based learning outperformed several other classifiers in analgesic consumption prediction. Results also demonstrated the feasibility of the proposed ensemble approach to postoperative pain management to assist anesthesiologists with PCA administration.
More Articles on Anesthesia:
Data Supports Using EXPAREL Infiltration To Control Postsurgical Pain
Dr. Terence Robertson Joins Anesthesia Staff at Bothwell Regional Health Center
Should CRNAs Treat Chronic Pain? Q&A With ASIPP Chairman Dr. Laxmaiah Manchikanti
The results of the study showed the prediction accuracies of total analgesic consumption and PCA requirement by an ensemble of decision trees were 80.9 percent and 73.1 percent, respectively.
Decision tree-based learning outperformed several other classifiers in analgesic consumption prediction. Results also demonstrated the feasibility of the proposed ensemble approach to postoperative pain management to assist anesthesiologists with PCA administration.
More Articles on Anesthesia:
Data Supports Using EXPAREL Infiltration To Control Postsurgical Pain
Dr. Terence Robertson Joins Anesthesia Staff at Bothwell Regional Health Center
Should CRNAs Treat Chronic Pain? Q&A With ASIPP Chairman Dr. Laxmaiah Manchikanti