HiCu: Leveraging Hierarchy for Curriculum Learning in Automated ICD Coding
This work addresses the challenge of designing effective curricula for curriculum learning in multi-label classification, specifically for automating ICD coding to assist clinicians, though it is incremental as it builds on existing curriculum learning methods.
The paper tackles the problem of automating medical code prediction from clinical notes by proposing HiCu, a hierarchical curriculum learning algorithm that leverages the structure of ICD codes to design training curricula, resulting in improved generalization across multiple neural network architectures.
There are several opportunities for automation in healthcare that can improve clinician throughput. One such example is assistive tools to document diagnosis codes when clinicians write notes. We study the automation of medical code prediction using curriculum learning, which is a training strategy for machine learning models that gradually increases the hardness of the learning tasks from easy to difficult. One of the challenges in curriculum learning is the design of curricula -- i.e., in the sequential design of tasks that gradually increase in difficulty. We propose Hierarchical Curriculum Learning (HiCu), an algorithm that uses graph structure in the space of outputs to design curricula for multi-label classification. We create curricula for multi-label classification models that predict ICD diagnosis and procedure codes from natural language descriptions of patients. By leveraging the hierarchy of ICD codes, which groups diagnosis codes based on various organ systems in the human body, we find that our proposed curricula improve the generalization of neural network-based predictive models across recurrent, convolutional, and transformer-based architectures. Our code is available at https://github.com/wren93/HiCu-ICD.