Hierarchical Deep Learning Ensemble to Automate the Classification of Breast Cancer Pathology Reports by ICD-O Topography
This work addresses the significant 4-year lag in cancer statistics reporting in South Africa by automating a manual process for cancer registries, though it is incremental as it builds on existing deep learning methods for a specific domain.
The paper tackled the problem of automating the classification of breast cancer pathology reports using ICD-O topography codes to reduce manual annotation delays, achieving improvements of over 14% in F1 micro and 55% in F1 macro scores compared to state-of-the-art CNN models.
Like most global cancer registries, the National Cancer Registry in South Africa employs expert human coders to label pathology reports using appropriate International Classification of Disease for Oncology (ICD-O) codes spanning 42 different cancer types. The annotation is extensive for the large volume of cancer pathology reports the registry receives annually from public and private sector institutions. This manual process, coupled with other challenges results in a significant 4-year lag in reporting of annual cancer statistics in South Africa. We present a hierarchical deep learning ensemble method incorporating state of the art convolutional neural network models for the automatic labelling of 2201 de-identified, free text pathology reports, with appropriate ICD-O breast cancer topography codes across 8 classes. Our results show an improvement in primary site classification over the state of the art CNN model by greater than 14% for F1 micro and 55% for F1 macro scores. We demonstrate that the hierarchical deep learning ensemble improves on state-of-the-art models for ICD-O topography classification in comparison to a flat multiclass model for predicting ICD-O topography codes for pathology reports.