ICD 10 Cleaning Code Removing Valid Codes about cv19index HOT 5 CLOSED

Glad it is working well for you. Yes you are safe to use the old model with the current features, provided you are running that model on a Medicare population or a close proxy of it (generally 65 and older). You should use the “xgboost_all_ages” model if you are running on healthy adults under 65. Yes, the XGBoost model was trained including the 3 character ICD codes. The error related to that was only in the code we had to run the model, not in the training process, which was done on the ClosedLoop platform and handles all of these transformations correctly. Dave From: Xin Chen <[email protected]> Sent: Friday, April 17, 2020 7:06 PM To: closedloop-ai/cv19index <[email protected]> Cc: David DeCaprio <[email protected]>; Mention <[email protected]> Subject: Re: [closedloop-ai/cv19index] ICD 10 Cleaning Code Removing Valid Codes (#17) @DaveDeCaprio <https://github.com/DaveDeCaprio> Thanks for your great work on cv19index! About the old model (the one trained only on medicare data), are we saft to use the old model by feeding it the corrent features as intended, i.e., with 3 character ICD-10 codes mapping to CCSR? How did the old model get trained? Did the training data map the 3 character ICD-10 codes to CCSR or not? Thanks in advance! — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#17 (comment)> , or unsubscribe <https://github.com/notifications/unsubscribe-auth/AAGNLOXANJCVAJLXHEXODPLRNDVFZANCNFSM4L24A4HA> . <https://github.com/notifications/beacon/AAGNLOXYL2JD5BWFGSWAAWLRNDVFZA5CNFSM4L24A4HKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOESYAWBI.gif>