Early Diagnosis of Atrial Fibrillation Recurrence: A Large Tabular Model Approach with Structured and Unstructured Clinical Data

TL;DR

This study develops a large tabular model combining structured and unstructured clinical data to improve early prediction of atrial fibrillation recurrence, outperforming traditional scores and ML models.

Contribution

The paper introduces a novel large tabular model that integrates structured data with free-text reports, enhancing prediction accuracy for AF recurrence.

Findings

LTM outperforms traditional scores and ML models in prediction accuracy.

Integration of unstructured data improves dataset quality and model performance.

Gender and age biases were identified in the predictive models.

Abstract

BACKGROUND: Atrial fibrillation (AF), the most common arrhythmia, is linked to high morbidity and mortality. In a fast-evolving AF rhythm control treatment era, predicting AF recurrence after its onset may be crucial to achieve the optimal therapeutic approach, yet traditional scores like CHADS2-VASc, HATCH, and APPLE show limited predictive accuracy. Moreover, early diagnosis studies often rely on codified electronic health record (EHR) data, which may contain errors and missing information. OBJECTIVE: This study aims to predict AF recurrence between one month and two years after onset by evaluating traditional clinical scores, ML models, and our LTM approach. Moreover, another objective is to develop a methodology for integrating structured and unstructured data to enhance tabular dataset quality. METHODS: A tabular dataset was generated by combining structured clinical data with free-text discharge reports processed through natural language processing techniques, reducing errors and annotation effort. A total of 1,508 patients with documented AF onset were identified, and models were evaluated on a manually annotated test set. The proposed approach includes a LTM compared against traditional clinical scores and ML models. RESULTS: The proposed LTM approach achieved the highest predictive performance, surpassing both traditional clinical scores and ML models. Additionally, the gender and age bias analyses revealed demographic disparities. CONCLUSION: The integration of structured data and free-text sources resulted in a high-quality dataset. The findings emphasize the limitations of traditional clinical scores in predicting AF recurrence and highlight the potential of ML-based approaches, particularly our LTM model.