Predictive Modeling Approach to Evaluate Individual Response to a Physical Activity Digital Intervention for Subjects with Major Depressive Disorder

Worldwide, there is roughly one mental health care provider for every 400 people with major depressive disorder (MDD). Without including other disorders, it would be impossible for everyone suffering from MDD to get clinical assistance. One step towards closing this gap may be the development of digital interventions. These can be delivered via smartphone, personal computer or tablet and require a significantly decreased time commitment from a provider. Given these benefits, there has been an increasing number of new digital interventions being studied with varying results. This presents a need for evidence-based processes that select the right treatment for a given person. One digital intervention that has been widely studied is a physical activity intervention where subjects are encouraged, via the internet, to become more active as a method of reducing depressive symptoms. The goal of the present study was to evaluate whether baseline characteristics could be leveraged to determine whether individuals would be likely to respond to this form of digital intervention. Machine learning models were trained to predict all individuals’ changes in Beck Depression Inventory-II (BDI-II) score and whether or not an individual had clinically significant change in depression. The correlation between predicted values and true values for change in BDI-II was r = 0.399 and the AUC for predicting clinically significant change was 0.75. Important predictors included marital status, gender, and pre-intervention anxiety and depression severity. These models may facilitate precision medicine in the digital era by enabling personalized treatment planning of digital interventions.