Simply Adjusting for Schedulers’ Bias in Estimated Case Durations Can Accomplish the Same Objectives of Improving Predictions as Use of Machine Learning—Reply

Abstract

researchers and practitioners reserve CT as a secondary test following only indeterminate results of other diagnostic tests. 2,3 Such strategies should be carefully attempted while maintaining excellent overall diagnostic accuracy. 3 As Hu et al pointed out, magnetic resonance imaging is promising; however, it is yet to be determined if the study results can be generalized to average hospitals and to different health care systems.The diagnosis of appendicitis is one of few indications of low-dose CT techniques established with high-level evidence. 4 However, the adoption of low-dose CT is disappointingly slow, and the variation in CT radiation dose used for the diagnosis of appendicitis is surprisingly wide across regions and hospitals. 5,6 The variation is partly attributable to the use of multiphase scanning, which has no rationale for the diagnosis of appendicitis.As Schaps et al pointed out, our observation is perhaps just one piece of a complex puzzle on the carcinogenic risk of CT radiation. Unless there are conclusive experimental data, it would be prudent not to ignore the carcinogenic risk but to adhere to the As Low As Reasonably Achievable (ALARA) principle: first, use CT only when clinically necessary and second, keep the radiation dose as low as possible.