Reply to: machine learning in renal cell carcinoma research: promise and pitfalls of ‘renal‐izing’ the potential of artificial intelligence

Abstract

Reply to: machine learning in renal cell carcinoma research: promise and pitfalls of 'renal-izing' the potential of artificial intelligenceWe wish to thank Khene et al. [1] for their comments on our article [2], thus offering us the opportunity to clarify important methodological points.First, Khene et al. discussed the design of the study, it appears to us that we rigorously followed the Standardized Reporting of Machine Learning Applications in Urology (STREAM-URO) guidelines with the use of an external validation (training: n = 2636 patients from 17 centres, testing: n = 1759 patients from another eight centres).The training and testing datasets were similar according to both patients' characteristics and upstaging rate (15.2% in each of them; see Table S2).Khene et al. [1] challenged the choice of the training and testing datasets, by mentioning that the database had a high rate of missing observations, notably for R.E.N.A.L. (Radius, Exophytic/Endophytic, Nearness, Anterior/Posterior, Location) nephrometry score.This predictor had 24.7% and 18.1% of missing values in the training and testing datasets, respectively, which is clearly acceptable (Table S2).

Ähnliche Arbeiten