FinFax: Fast Interpretation of Fax with NLP

Faxes are commonly utilized in healthcare organizations to facilitate information exchange among healthcare facilities, despite the existence of electronic health record (EHR) systems. Nevertheless, the manual processing of faxes is both time-consuming and prone to errors. Unfortunately, critical medical information conveyed through faxes often leads to delays and potential harm due to the unavailability of vital clinical data when required. This predicament is further exacerbated by the substantial volume of faxes received by healthcare organizations on a daily basis.

While there exist multiple solutions for extracting information from scanned health records, these solutions typically focus on specific segments of the overall workflow. However, in order to effectively drive real-life applications, the entirety of the workflow assumes crucial significance. Hence, this paper presents an all-encompassing system called "FinFax," meticulously developed and rigorously tested in collaboration with a clinic in the gulf coast region. FinFax possesses the capability to proficiently classify documents contained within faxes, extract pertinent information, and seamlessly integrate with Epic to write final output to OnBase database. To the best of our knowledge, FinFax is one of the first end-to-end system originating from an academic environment specifically designed for fax processing, integrating seamlessly with Epic, and successfully evaluated in a real-life hospital setting. A comprehensive analysis is provided, elucidating how the proposed end-to-end system significantly simplifies the existing workflow.