Agile science: creating useful products for behavior change in the real world

Abstract

Evidence-based practice is important for behavioral interventions but there is debate on how best to support real-world behavior change. The purpose of this paper is to define products and a preliminary process for efficiently and adaptively creating and curating a knowledge base for behavior change for real-world implementation. We look to evidence-based practice suggestions and draw parallels to software development. We argue to target three products: (1) the smallest, meaningful, self-contained, and repurposable behavior change modules of an intervention; (2) "computational models" that define the interaction between modules, individuals, and context; and (3) "personalization" algorithms, which are decision rules for intervention adaptation. The "agile science" process includes a generation phase whereby contender operational definitions and constructs of the three products are created and assessed for feasibility and an evaluation phase, whereby effect size estimates/casual inferences are created. The process emphasizes early-and-often sharing. If correct, agile science could enable a more robust knowledge base for behavior change.

Keywords: Behavior change; Implementation science; Research methods.

Fig 1

Computational model structure of a just in time adaptive intervention. Adapted from Martin, Deshpande, Hekler, and Rivera [38]

Fig 2

Diagram of the model predictive controller that utilizes the computational model in Fig. 2. Adapted from Martin, Hekler, and Rivera [43]

Fig 3

Agile Science Process v0.1