Towards Automated Medical Coding with Knowledge Graph and Explainability

Automated Medical coding (AMC) aims to automatically convert Discharge Summaries into alphanumeric codes such as the International Classification of Diseases (ICD), Current Procedural Terminology (CPT), and the Healthcare Common Procedure Coding System (HCPCS). The absence of domain-specific knowledge in Computer-Assisted Coding (CAC) Applications built with Machine Learning and Deep Learning techniques leads to false-positive results. Knowledge Graph creation requires domain experts and is yet a manual approach which is a highly time- consuming and labor-intensive task.

the challenge:

A trustable Clinical Decision Support Systems (CDSS) for Oncology- related issues.