A Hierarchical Approach for Automated ICD-10 Coding Using Phrase-level Attention
Clinical coding is the task of assigning a set of alphanumeric codes, referred to as ICD, to a medical event based on the context captured in a clinical narrative. The latest version of ICD, ICD-10, includes more than 70,000 codes.
This talk will discuss a novel approach for automatic ICD coding by reformulating the extreme multi-label problem into a simpler multi-class problem using a hierarchical solution. We made this approach viable through extensive data collection to acquire phrase-level human coder annotations to supervise our models on learning the specific relations between the input text and predicted ICD code set.
![Cansu Sen Cansu Sen](https://www.nlpsummit.org/wp-content/uploads/2022/01/Cansu.jpg)
Cansu Sen
Senior Machine Learning Scientist at CodaMetrix
Cansu Sen is a Senior Machine Learning Scientist at CodaMetrix, where she develops NLP models for healthcare data. She holds a Ph.D. degree in Computer Science from WPI. She has authored many research articles published in top machine learning venues such as ACL, KDD, CIKM, and IEEE Big Data.
When
Sessions: April 5th – 6th 2022
Trainings: April 12th – 15th 2022