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.
IntroductionDespite existing work examining the effectiveness of smartphone digital interventions for schizophrenia at the group level, response to digital treatments is highly variable and requires more research to determine which persons are most likely to benefit from a digital intervention.Materials and methodsThe current work utilized data from an open trial of patients with psychosis (N = 38), primarily schizophrenia spectrum disorders, who were treated with a psychosocial intervention using a smartphone app over a one-month period. Using an ensemble of machine learning models, pre-intervention data, app use data, and semi-structured interview data were utilized to predict response to change in symptom scores, engagement patterns, and qualitative impressions of the app.ResultsMachine learning models were capable of moderately (r = 0.32–0.39, R2 = 0.10–0.16, MAEnorm = 0.13–0.29) predicting interaction and experience with the app, as well as changes in psychosis-related psychopathology.ConclusionThe results suggest that individual smartphone digital intervention engagement is heterogeneous, and symptom-specific baseline data may be predictive of increased engagement and positive qualitative impressions of digital intervention in patients with psychosis. Taken together, interrogating individual response to and engagement with digital-based intervention with machine learning provides increased insight to otherwise ignored nuances of treatment response.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.