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

2026-03-18

AI Summary

This study addresses the challenge of early prediction of post-acute sequelae of SARS-CoV-2 (PASC) severity in adult women, which is often confounded by factors such as menopause. To mitigate this, the authors propose a temporal modeling approach that integrates static clinical data with four-week longitudinal physiological signals—specifically heart rate and sleep patterns—collected via wearable devices, leveraging a large language model enhanced with a causal disentanglement mechanism. This framework effectively isolates pathological signals from non-causal confounders like menopause and diabetes, substantially improving prediction specificity. Evaluated on a cohort of 1,155 women, the model achieved 86.7% accuracy in predicting clinical PASC severity, with key symptoms such as dyspnea and fatigue exhibiting significance scores of 1.00, while all confounding factors remained below 0.27, demonstrating strong causal discriminability and clinical utility.

Technology Category

• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Reasoning under Uncertainty: Causality
• Machine Learning: Causal Learning

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search
• Web Mining and Content Analysis: Large pretrained models with web data

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.

Problem

• Long COVID
• PASC
• confounding factors
• menopause
• trajectory prediction

Innovation

• causal disentanglement
• long COVID
• wearable data
• large language model
• trajectory prediction