Some primary and secondary care have large quantities of scanned historical documents that are difficult for humans to find information in quickly or search electronically. We have shown it is cheap and simple for organisations to convert images to text, categorise on image and/or text qualities with a low cost, low tech solution. Accessing this historical information quickly and easily will help clinicians find the information they want and could be used to integrate historical documents with EMRs.
Code and Licence
Source code: https://github.com/nhspapernotes