[muraiki]

From the paper:

"...the novelty of the approach does not lie simply in incremental model performance improvements. Rather, this predictive performance was achieved without hand-selection of variables deemed important by an expert, similar to other applications of deep learning to EHR data. Instead, our model had access to tens of thousands of predictors for each patient, including free-text notes, and identified which data were important for a particular prediction."

So it sounds like the advance here is actually in the following: "a generic data processing pipeline that can take raw EHR data as input, and produce FHIR outputs without manual feature harmonization".

The article doesn't explain this very clearly. Yay!