A Longitudinal Attribute-Conditioned Neural Network for Modeling Health-State Transition Probabilities in Temporally Irregular Data: The LANTERN Framework
Researchers have developed a new framework called LANTERN for modeling health-state transition probabilities in irregularly timed longitudinal data. This framework uses an attribute-conditioned neural network to learn from individual health histories and time elapsed between observations. When tested on data from the Health and Retirement Study, LANTERN demonstrated improved discrimination for severe disability and maintained strong calibration, outperforming logistic regression, Gradient Boosted Trees, and a recurrent neural network in terms of transition matrix error. AI
IMPACT This framework offers a more accurate method for predicting health state transitions, potentially improving actuarial models and long-term care planning.