Good morning: We index and summarize medical records using a proprietary algorithm. Being medical records they repeat the same information almost on every single page, like facility name, medical record number, date of birth, name, facility address, phone, fax etc. We have a large volume of records we process so manually identifying these is not possible. We need to be able to identify certain words or groups of words that are found on a majority of the pages and remove them, without human intervention. One thought we had was to pull demographic information from the order which often times has facility information and patient information that we can use to match against and delete, but often times we will get outside requests to simply index and summarize and have no way to get that information short of having a human open each file, identify the facility, etc. enter it in and use that as a screening agent for what to delete. Any suggestions or anyone come across a similar problem?



Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.

Browse other questions tagged or ask your own question.