Improving Precancerous Case Characterization via Transformer-based Ensemble Learning

TL;DR

This paper presents transformer-based NLP models and ensemble learning techniques to improve the classification and characterization of precancerous and cancerous cases in colorectal cancer, enhancing early detection capabilities.

Contribution

The study introduces a novel transformer-based ensemble approach for NLP-driven CRC phenotyping, specifically targeting precancerous lesion attributes and early cancer detection.

Findings

Achieved 0.914 macro-F1 score for classifying patient cases.

Improved performance to 0.923 with ensemble classifiers.

Demonstrated NLP's potential in early cancer diagnosis using real-world data.

Abstract

The application of natural language processing (NLP) to cancer pathology reports has been focused on detecting cancer cases, largely ignoring precancerous cases. Improving the characterization of precancerous adenomas assists in developing diagnostic tests for early cancer detection and prevention, especially for colorectal cancer (CRC). Here we developed transformer-based deep neural network NLP models to perform the CRC phenotyping, with the goal of extracting precancerous lesion attributes and distinguishing cancer and precancerous cases. We achieved 0.914 macro-F1 scores for classifying patients into negative, non-advanced adenoma, advanced adenoma and CRC. We further improved the performance to 0.923 using an ensemble of classifiers for cancer status classification and lesion size named entity recognition (NER). Our results demonstrated the potential of using NLP to leverage real-world health record data to facilitate the development of diagnostic tests for early cancer prevention.