Studying the characteristics of postoperative pain at such an early stage allows for improved management. It helps to predict, according to the type of surgery and the anaesthesia used, those patients in which higher VAS values may be seen and to better adapt analgesic therapy 1).
Despite advances in surgical and anesthesiology techniques, many patients continue to experience postoperative pain after lumbar disc operations
The administration of tramadol with paracetamol was more effective than tramadol alone for early acute postoperative pain therapy following lumbar discectomy. Therefore while adding paracetamol in early pain management is recommended, continuing paracetamol for the late postoperative period is not advised 2).
Epidural fibrosis and epidural adhesion after laminectomy are developed from adjacent dense scar tissue, which is a natural wound healing process 3) 4) 5) 6) , and ranked as the major contributor for postoperative pain recurrence after laminectomy or discectomy.
see Failed back surgery syndrome
Pain intensity evaluation by self-report is difficult and biased in non-communicating people, which may contribute to inappropriate pain treatment. The use of artificial intelligence (AI) to evaluate pain intensity based on automated facial expression analysis has not been evaluated in clinical conditions.
Fontaine et al. trained and externally validated a deep-learning system (ResNet-18 convolutional neural network) to identify and classify 2810 facial expressions of 1189 patients, captured before and after surgery, according to their self-reported pain intensity using a numeric rating scale (NRS, 0-10). AI performances were evaluated by accuracy (concordance between AI prediction and patient-reported pain intensity), sensitivity, and specificity to diagnose pain ≥4/10 and ≥7/10. We then confronted AI performances with those of 33 nurses to evaluate pain intensity from facial expressions in the same situation.
Results: In the external testing set (120 face images), the deep learning system was able to predict exactly the pain intensity among the 11 possible scores (0-10) in 53% of the cases with a mean error of 2.4 points. Its sensitivities to detect pain ≥4/10 and ≥7/10 were 89.7% and 77.5%, respectively. Nurses estimated the right NRS pain intensity with a mean accuracy of 14.9% and identified pain ≥4/10 and ≥7/10 with sensitivities of 44.9% and 17.0%.
Subject to further improvement of AI performances through further training, these results suggest that AI using facial expression analysis could be used to assist physicians to evaluate pain and detecting severe pain, especially in people not able to report appropriately their pain by themselves.
Significance: These original findings represent a major step in the development of a fully automated, rapid, standardized, and objective method based on facial expression analysis to measure pain and detect severe pain 7).
Intradiscal surgical procedures are among the most controversial procedures for lumbar spine surgery. The theoretical advantage is that an epidural scarring is avoided and that a smaller incision or even just a puncture site is used. This is also purported to reduce postoperative pain and hospital stay (often performed as an outpatient procedure).