Hornstein S, Zantvoort K, Lueken U, Funk B, Hilbert K. (2023). Personalization strategies in digital mental health interventions: a systematic review and conceptual framework for depressive symptoms. Front. Digit. Health 5:1170002. doi: 10.3389/fdgth.2023.1170002

The aim of this systematic literature review was to explore how personalization is utilized and what benefits it has for digital mental health interventions (DMHIs). The search included empirical studies on DMHIs targeting depression in adults from 2015 to 2022, which resulted in 138 articles and 94 distinct DMHIs. Personalization was operationalized as purposefully designed variation between individuals in an intervention’s therapeutic elements or its structure. Furthermore, personalization strategies were differentiated by what is personalized (i.e., content, level of guidance, content order) and the mechanism (i.e., user choice, provider choice, machine learning). Applying this definition, researchers identified personalization in 66% of the interventions included, with personalized intervention content (32%) and communication with the end user (30%) as most prevalent. Personalization via automated if-then-decision rules (48%) and user choice (36%) were the most commonly used mechanisms, while application of machine learning was rare (3%). Overall, this review demonstrated that the majority of DMHIs for depression use personalization approaches; however, future interventions could provide tailoring on more dimensions of the intervention experience and may benefit from using machine learning models. Additionally, empirical evidence for the benefits of personalization was scarce and further evidence is needed.