Classification of cancer pathology reports: a large-scale comparative study
This work addresses the challenge of automating medical coding for cancer reports, which is incremental as it applies existing deep learning methods to a new domain-specific dataset.
The study tackled the problem of automatically assigning ICD-O3 codes to free-text cancer pathology reports using deep learning, achieving a multiclass accuracy of 90.3% for topography and 84.8% for morphology on a large Italian dataset.
We report about the application of state-of-the-art deep learning techniques to the automatic and interpretable assignment of ICD-O3 topography and morphology codes to free-text cancer reports. We present results on a large dataset (more than 80 000 labeled and 1 500 000 unlabeled anonymized reports written in Italian and collected from hospitals in Tuscany over more than a decade) and with a large number of classes (134 morphological classes and 61 topographical classes). We compare alternative architectures in terms of prediction accuracy and interpretability and show that our best model achieves a multiclass accuracy of 90.3% on topography site assignment and 84.8% on morphology type assignment. We found that in this context hierarchical models are not better than flat models and that an element-wise maximum aggregator is slightly better than attentive models on site classification. Moreover, the maximum aggregator offers a way to interpret the classification process.