Key result
Replacing CPT codes with RVUs in a machine learning model to predict surgical case length maintained performance while reducing prediction time ninefold.
Why the study?
Using CPT codes to train machine-learned models limits the ability to incorporate new procedures and adds complexity, whereas relative value units could serve as an alternative primary feature.
Does using RVU instead of CPT codes improve machine learning model performance and efficiency in predicting surgical case length?
Observational (n=11,696)
Yes
Does using RVU instead of CPT codes improve machine learning model performance and efficiency in predicting surgical case length?
Replacing CPT codes with RVUs in machine learning models maintains accuracy for predicting surgical case length while significantly reducing model complexity and prediction time.
Answers are grounded in this paper and cite their sources.
RVU-based models may enable faster surgical scheduling predictions without accuracy loss; hypothesis-generating for broader perioperative adoption.
Methods used to predict surgical case time often rely upon the current procedural terminology (CPT) code as a nominal variable to train machine-learned models, however this limits the ability of the model to incorporate new procedures and adds complexity as the number of unique procedures increases. The relative value unit (RVU, a consensus-derived billing indicator) can serve as a proxy for procedure workload and could replace the CPT code as a primary feature for models that predict surgical case length. Using 11,696 surgical cases from Duke University Health System electronic health records data, we compared boosted decision tree models that predict individual case length, changing the method by which the model coded procedure type; CPT, RVU, and CPT-RVU combined. Performance of each model was assessed by inference time, MAE, and RMSE compared to the actual case length on a test set. Models were compared to each other and to the manual scheduler method that currently exists. RMSE for the RVU model (60.8 min) was similar to the CPT model (61.9 min), both of which were lower than scheduler (90.2 min). 65.2% of our RVU model's predictions (compared to 43.2% from the current human scheduler method) fell within 20% of actual case time. Using RVUs reduced model prediction time by ninefold and reduced the number of training features from 485 to 44. Replacing pre-operative CPT codes with RVUs maintains model performance while decreasing overall model complexity in the prediction of surgical case length.
No takes yet. Share an insight, caveat, or question.
Garside et al. (2021) conducted an observational in Non-emergent colorectal and spinal surgeries (n=11,696). RVU-based predictive model vs. CPT-based predictive model and human scheduler was evaluated on Root mean squared error (RMSE) of predicted surgical case length in minutes. Replacing CPT codes with RVUs in a machine learning model to predict surgical case length maintained performance while reducing prediction time ninefold.
Synapse has enriched 10 related papers. Consider them for comparative context: