I am interested in working with natural language processing in the context of electronic health records, specifically in the field of psychiatry (and more specifically in the field of schizophrenia). So far, I’ve only found the MIMIC-III database that might fit my needs. I wonder if I might have overseen other (psychiatric) EHR datasets? Any suggestions are greatly appreciated.
P.S.: Is there a good overview about the MIMIC-III? As I said, it might fit my needs, but I am missing something like an overview (e.g. like for the bank signature dataset) to get an intuition about the number of psychiatric patients, demographic data, etc.