Do modern neural network architectures improve forecasting of analgesic response and POUR risk compared to conventional machine learning methods in patients with acute postoperative pain?
Simpler machine learning methods may outperform complex neural networks in forecasting postoperative pain and analgesic response.
Response to prescribed analgesic drugs varies between individuals, and choosing the right drug/dose often involves a lengthy, iterative process of trial and error. Furthermore, a significant portion of patients experience adverse events such as post-operative urinary retention (POUR) during inpatient management of acute postoperative pain. To better forecast analgesic responses, we compared conventional machine learning methods with modern neural network architectures to gauge their effectiveness at forecasting temporal patterns of postoperative pain and analgesic use, as well as predicting the risk of POUR. Our results indicate that simpler machine learning approaches might offer superior results; however, all of these techniques may play a promising role for developing smarter post-operative pain management strategies.
Nickerson et al. (Mon,) studied this question.