Learning health care systems (LHSs) have the potential to transform health care. However, this transformation process faces significant challenges.
An LHS could be developed in the following ways: by taking away practical impediments that prevent patients and professionals from engaging in scientific research (model 1: optimization LHS); by routinely analyzing observational data from electronic health records and other sources (model 2: comprehensive data LHS); by making clinical decisions based on the outcomes of the aforementioned data analyses and directly evaluating the outcomes in order to continuously improve decision-making (model 3: real-time LHS); or by embedding clinical trials into routine care delivery (model 4: full LHS).
Each model has different ethical implications for consent and oversight. Also, the four-model approach shows that reorganizing a health care center into an LHS is not an all-or-nothing decision. Rather, it is a choice from a menu of possibilities. Instead of discussing the advantages and disadvantages of the LHS menu in its entirety, the medical community should focus on the designs and ethical aspects of each of the separate options.
Based on proposals and early examples of LHSs in the literature and conceptual analysis of the LHS mission, we provide four models with distinct organizational and ethical implications that may facilitate the transformation.