Predicting Trajectories of Long COVID in Adult Women: The Critical Role of Causal Disentanglement

TL;DR

This study presents a causal modeling approach combining clinical and wearable data to predict long COVID trajectories in women, effectively distinguishing true symptoms from confounding factors like menopause.

Contribution

It introduces a novel causal network framework utilizing a Large Language Model to improve long COVID prediction accuracy and interpretability in women.

Findings

Achieved 86.7% precision in severity prediction.

Effectively differentiated active symptoms from confounders.

Demonstrated model's ability to suppress confounding influences.

Abstract

Early prediction of Post-Acute Sequelae of SARS-CoV-2 severity is a critical challenge for women's health, particularly given the diagnostic overlap between PASC and common hormonal transitions such as menopause. Identifying and accounting for these confounding factors is essential for accurate long-term trajectory prediction. We conducted a retrospective study of 1,155 women (mean age 61) from the NIH RECOVER dataset. By integrating static clinical profiles with four weeks of longitudinal wearable data (monitoring cardiac activity and sleep), we developed a causal network based on a Large Language Model to predict future PASC scores. Our framework achieved a precision of 86.7\% in clinical severity prediction. Our causal attribution analysis demonstrate the model's ability to differentiate between active pathology and baseline noise: direct indicators such as breathlessness and malaise reached maximum saliency (1.00), while confounding factors like menopause and diabetes were successfully suppressed with saliency scores below 0.27.