Computer Vision

Solving the problem of scanning patient records.

While the healthcare industry has been trying to fix the claims denial problem for the past 20 years with various revenue cycle management solutions, the problem has persisted and the numbers continue to climb, presenting significant fiscal challenges to providers.

The problem

Patient records are often illegible after having been faxed, scanned, and covered in doctor’s handwriting. These issues make it almost impossible to scan a record without the result being garbage characters. The inability for OCR scanning to be able to accurately scan records is causing delays in the consolidation of EMR databases. It is also throwing up roadblocks in the consumerization of healthcare or the ability of patients to easily control their medical records by co-locating them in a secure, electronic environment.

AI solution.

The computer vision system allows a hospital to upload a PDF of a patient record, then converting the free text and identifying procedures and diagnosis using the AI Computer Vision system (Link: Healthcare AI Computer Vision case study). The computer vision system was created with the following features and functions in mind:

Speed of upload. The ability to lift and interpret only the free text on the page. This means that any doctor handwriting, or imperfections as a result of scan or faxing needed to be addressed so that the free text could be read. Accuracy of reading free text. Interpretation of free text to interface with data dictionary.

MVP-1 was delivered with a 92% reading accuracy of patient records that had been faxed and scanned resulting in a less than 150dpi document. It is expected that the computer vision system will excel at 99% reading accuracy, processing 200 pages in under 45 seconds.