Predicting Surgery Duration with Neural Heteroscedastic Regression
By Nathan Ng, Rodney A. Gabriel, Julian McAuley, Charles Peter Elkan, Zachary Chase Lipton. 2017
29 citations recorded by the source corpus.
Scheduling surgeries is a challenging task due to the fundamental uncertainty of the clinical environment, as well as the risks and costs associated with under- and over-booking. We investigate neural regression algorithms to estimate the parameters of surgery case durations, focusing on the issue of heteroscedasticity. We seek to simultaneously estimate the duration of each surgery, as well as a surgery-specific notion of our uncertainty about its duration. Estimating this uncertainty can lead to more nuanced and effective scheduling strategies, as we are able to schedule surgeries more efficiently while allowing an informed and case-specific margin of error. Using surgery records %from the UC San Diego Health System, from a large United States health system we demonstrate potential improvements on the order of 20% (in terms of minutes overbooked) compared to current scheduling techniques. Moreover, we demonstrate that surgery durations are indeed heteroscedastic. We show that models that estimate case-specific uncertainty better fit the data (log likelihood). Additionally, we show that the heteroscedastic predictions can more optimally trade off between over and under-booking minutes, especially when idle minutes and scheduling collisions confer disparate costs.
Subfields: Cardiology and Cardiovascular Medicine, Emergency Medical Services, Surgery
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Cardiology and Cardiovascular Medicine
In Emergency Medical Services
In Surgery
Citations in the corpus
- A Multi-Horizon Quantile Recurrent Forecaster (2017, methodology): “This is similar to Ng et al, 2017 where an MLP predicts Gaussian parameters, and such a strategy dates back to Bishop, 1994.”
- Sample Path Generation for Probabilistic Demand Forecasting (2018, methodology): “[14] propose the Seq2Seq model DeepAR, which directly outputs the parameters of a negative binomial, making it a parametric approach (a similar approach is also advocated by [31]).”