EDEN : An Event DEtection Network for the annotation of Breast Cancer recurrences in administrative claims data

TL;DR

EDEN is a novel deep learning model designed to accurately detect breast cancer recurrences in administrative claims data by handling temporal sequences and right-censoring, enabling large-scale research in this domain.

Contribution

The paper introduces EDEN, a time-aware LSTM network with a custom loss function, specifically addressing challenges in annotating cancer recurrence in claims data.

Findings

EDEN outperforms existing methods on real-world datasets.

The model effectively handles right-censoring and visit temporality.

It enables large-scale breast cancer recurrence annotation in claims data.

Abstract

While the emergence of large administrative claims data provides opportunities for research, their use remains limited by the lack of clinical annotations relevant to disease outcomes, such as recurrence in breast cancer (BC). Several challenges arise from the annotation of such endpoints in administrative claims, including the need to infer both the occurrence and the date of the recurrence, the right-censoring of data, or the importance of time intervals between medical visits. Deep learning approaches have been successfully used to label temporal medical sequences, but no method is currently able to handle simultaneously right-censoring and visit temporality to detect survival events in medical sequences. We propose EDEN (Event DEtection Network), a time-aware Long-Short-Term-Memory network for survival analyses, and its custom loss function. Our method outperforms several state-of-the-art approaches on real-world BC datasets. EDEN constitutes a powerful tool to annotate disease recurrence from administrative claims, thus paving the way for the massive use of such data in BC research.