Classification of cancer pathology reports: a large-scale comparative study

TL;DR

This study applies advanced deep learning models to automatically classify cancer pathology reports into ICD-O3 codes, demonstrating high accuracy and interpretability on a large Italian dataset.

Contribution

It provides a comprehensive comparison of deep learning architectures for cancer report classification, highlighting the effectiveness of flat models and maximum aggregation for interpretability.

Findings

Achieved 90.3% accuracy on topography classification

Achieved 84.8% accuracy on morphology classification

Hierarchical models did not outperform flat models

Abstract

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.