Send us Fan Mail

The Surfers analyze outputs from NASHmap, the first Machine Learning model that can identify patients likely to have NASH, to learn what we can about the disease and how to think about its value for racial and ethnic minorities.

Prof. Schattenberg and colleagues built the NASHmap model from a NIDDK database and validated it using the Optum de-identified EHR dataset. The model includes 14 variables, some obvious, others less so, that produce an AUC of 0.82 in the NIDDK database and 0.79 in the Optum database. This conversation explores some model elements and statistical outputs to glean knowledge about what the model says about NASH itself.