##################################################################################################### Provided data contains learned vectors for disease and procedures, across different insurances (Medicare, Medicaid, Private insurance or Self pay) patient had. All vectors are obtained as described in the paper: "Modeling Healthcare Uality via Compart Representations of electronic Health Records". The embeddings size is set to 200 (check reference for details). Diseases and procedures are gived by their names, preceded with following prefixes: - 'DB_' for billable diseases - 'DN_' for non-billable diseases - 'PB_' for billable procedures - 'PN_' for non-billable prodecures Billable diseases and procedures are not coded in ICD9, thus we provide an exact mappings from disease/procedure names to their respective ICD9 codes. ##################################################################################################### If the provided data proves usefull, please consider citing our paper: Stojanovic, J., Gligorijevic, Dj., Radosavljavic, V., Djuric, N., Grbovic, M., Obradovic, Z. (2016) " Modeling Healthcare Quality via Compact Representations of Electronic Health Records," IEEE/ACM Transactions on Computational Biology and Bioinformatics, IEEE, 2016, July 14, doi 10.1109/TCBB.2016.2591523. #####################################################################################################