JMIR Publications

ABSTRACT

Background:

Digital health programs provide individualized support to patients with chronic diseases and their effectiveness is measured by the extent to which patients achieve target individual clinical outcomes and the program’s ability to sustain patient engagement. However, patient dropout and inequitable intervention delivery strategies, which may unintentionally penalize certain patient subgroups, represent challenges to maximizing effectiveness. Therefore, methodologies that optimize the balance between success factors (achievement of target clinical outcomes and sustained engagement) in an equitable fashion would be desirable, particularly when there are resource constraints.

Objective:

Our objectives were to propose a model for digital health program resource management that accounts jointly for the interaction between individual clinical outcomes and patient engagement, ensures equitable allocation as well as allows for capacity planning, and to conduct extensive simulations using publicly available data on type 2 diabetes, a chronic disease.

Methods:

We propose a restless multiarmed bandit (RMAB) model to plan interventions which jointly optimize long-term engagement and individual clinical outcomes (in this case measured as achievement of target healthy glucose levels). To mitigate the tendency of RMAB to achieve good aggregate performance by exacerbating disparities between groups, we propose new equitable objectives for RMAB and apply bilevel optimization algorithms for solving them. We formulated a model for the joint evolution of patient engagement and individual clinical outcome trajectory to capture the key dynamics of interest in digital chronic disease management programs.

Results:

In simulation exercises, our optimized intervention policies lead to up to 10% more patients reaching healthy glucose levels after 12 months, with 10% reduction in dropout compared to standard-of-care baselines. Further, our new equitable policies reduce the mean absolute difference of engagement and health outcomes across six demographic groups by up to 85% compared to state-of-the art.

Conclusions:

It is feasible and effective to plan digital health interventions accounting for individual clinical outcome objectives and for long-term engagement dynamics, using an RMAB sequential decision-making framework that can also provide capabilities in capacity planning. By applying our new algorithmic contribution, equitable RMAB, this approach can also reach equitable solutions. Overall we present an approach that allows program designers to toggle between different priorities and modulate trade-offs across their desired objectives. Clinical Trial: NA