Building Health Application Recommender System Using Partially Penalized Regression

Behavioral intervention technologies through mobile applications have a great potential to enhance patient care by improving efficacy. One approach to optimize the utility of mobile health applications is through an individualized health application recommender system. We formalize such a recommender system as a policy that maps individual subject information to a recommended app. We propose to estimate the optimal policy which maximizes the expected utility by partial regularization via orthogonality using the adaptive Lasso (PRO-aLasso). We also derive the convergence rate of the expected outcome of the estimated policy to that of the true optimal policy. The PRO-aLasso estimators are shown to enjoy the same oracle properties as the adaptive Lasso. Simulations studies show that the PRO-aLasso yields simple, more stable policies with better results as compared to the adaptive Lasso and other competing methods. The performance of our method is demonstrated through an illustrative example using IntelliCare mobile health applications.