Error in Wording in Methods Section

In the Original Investigation “Deep Learning for Cross-Diagnostic Prediction of Mental Disorder Diagnosis and Prognosis Using Danish Nationwide Register and Genetic Data,” published in the February 2023 issue of JAMA Psychiatry, the authors incorrectly referred to the removal of individuals with non-European ancestry from th e data set as quality control in the Methods section. Rather, the removal of individuals with diverse genetic ancestry from the analyses of genotype data was done to minimize the risk of false findings by not accounting for population stratification. The Methods section now includes the added clarif ication, “…and included the removal of related individuals as well as individuals of non-European descent. The latter was to ensure that the models would not use ancestry as a proxy for potential imbalances of the disorders in the data set.” The authors have explained this clarification in a L etter to the Editor and the original article was corrected online.
Source: JAMA Psychiatry - Category: Psychiatry Source Type: research