Predicting Worry Mental States Using Long Short-Term Memory (LSTM) Recurrent Deep Neural Networks

Severe worry is a transdiagnostic syndrome associated with significant morbidity in older adults. In this study, we aim to infer worry-related mental states though brain activity timeseries. We acquired fMRI on two cohorts (N=116 and N=88), using an in-scanner worry induction and reappraisal task. We trained a recurrent long short-term memory (LSTM) neural network, using the first cohort as the train/validation and the second cohort as an independent test set. We predicted worry induction, reappraisal, and neutral states (area under the curve 0.89, 0.77, 0.91 for the test set and 0.78, 0.63, 0.81 for the independent set). The model was most accurate when participants reported high worry during the induction state. Dorsal attention network, and networks seeded on the anterior hippocampus, and supplementary motor area were most important for predicting worry states. The LSTM approach may have critical translational implications for identifying and treating severe worry in older adults.