Application of Basic Epidemiologic Principles and Electronic Health Records in a Deep Learning Prediction Model

To the Editor We read with great interest the article by Wang et al. In their study, the authors applied deep learning techniques to predict 1-year risk of nonmelanoma skin cancer from clinical diagnostic information and medical records, including medication received. Their model showed an area under the receiver operating characteristic curve of 0.89 (95% CI, 0.87-0.91), which is impressive accuracy. However, the study may have important flaws in its design that are likely to have biased upward the estimation of the model ’s accuracy.
Source: JAMA Dermatology - Category: Dermatology Source Type: research