LongAgent model for outcome prediction
LongAgent: History-Guided Agentic Search for Longitudinal Outcome Prediction
This research introduces a novel method for using AI to analyze longitudinal medical data, which could improve the accuracy of predicting patient outcomes.
A new AI model called LongAgent is proposed for predicting future outcomes from longitudinal medical data. It uses an agent-based approach to autonomously search for the best combinations of variables and time windows. On synthetic data, it achieved a mean prediction RMSE of 1.7376, outperforming the best non-agent baseline by 0.0151. On a real clinical dataset, it performed comparably to the best baseline.
LongAgent: History-Guided Agentic Search for Longitudinal Outcome Prediction
Extracting informative representations from longitudinal data that can predict future outcomes remains a critical challenge in medicine. Medical datasets are inherently heterogeneous, consisting of a large number of variables collected from different sources, sampled with different temporal spacings, and representing different aspects of human health status. This requires identifying those variables with predictive value, processing longitudinal information, and integrating multiple variables for outcome prediction. Here, we propose a novel agent-based approach, LongAgent, that can autonomously search over combinations of variable sets, temporal windows and longitudinal aggregation functions, and identify candidates with promising predictive performance. LongAgent utilises a history memory of previous searches and numerical evidence to guide subsequent exploration. On synthetic data, LongAgent achieves a mean prediction RMSE of 1.7376 and improves over the strongest non-agent baseline by 0.0151 (95% CI: [0.0045,0.0260]; p=0.0273). On a real clinical dataset, it performs comparably to the best baseline.