Crash Course: Flexibility in Adaptive Interventions

This expanded Crash Course highlights a series of frequently asked questions that investigate the protocolized but flexible nature of adaptive interventions.

Q: Must an adaptive intervention recommend a single intervention option at each decision point? For example, must an adaptive intervention recommend a single intervention option for non-responders?

A: No—an adaptive intervention may recommend that a practitioner choose between multiple intervention options at any given decision point. For example, the hypothetical two-stage adaptive intervention below recommends the addition of a behavioral intervention or an increase in medication dosage as a second-stage treatment for children who did not respond to the first-stage intervention.

Discussion: This type of adaptive intervention might result from clinical expertise, prior data, or a randomized trial that suggests there is no evidence of a difference between intensifying behavioral intervention and adding low-dose medication among non-responders to first-stage behavioral intervention.

Q: Is it the case that Adaptive Interventions seek to replace clinical judgment?

A: No. The goal is to provide protocolized but flexible guidance on when and how to make critical decisions about treatment while leaving room for clinical judgment.

Discussion: The adaptive intervention above recommends two second stage treatments for non-responders, calling upon clinicians to use their judgment to decide whether to intensify behavioral intervention or augment with low-dose medication for children who do not respond to behavioral intervention.

Q: You state that adaptive interventions are protocolized, but then you state that clinical judgment can be part of an adaptive intervention. How can this be?

A: Yes, we agree with both statements. It is a common misconception that clinical judgment is at odds with a protocolized/manualized intervention.

Discussion: Most real-world biobehavioral or educational adaptive interventions utilize some form of clinical judgment. An adaptive intervention is designed to guide the most critical decisions practitioners make, not replace clinical judgment. In cases where there is no evidence to suggest that one intervention is better or worse than another, clinical judgment (or other approaches to intervention such as shared decision making between the clinician and the patient) is necessary to decide which treatment to offer. In some cases, adaptive interventions are explicitly designed to identify junctures in treatment when clinical judgment is most necessary.

Q: Are adaptive interventions compatible with other approaches to decision-making?

A: Yes. As in the case of clinical judgment, adaptive interventions leave room for other decision-making modalities and may be explicitly designed to support the use of those modalities.

Discussion: Consider that in shared decision-making (SDM), both the patient and the practitioner contribute to the medical decision-making process and agree on treatment decisions. An adaptive intervention that supports SDM may include decision rules that hinge on input from both the patient and the practitioner. An adaptive intervention for high blood pressure may recommend health coaching as an initial intervention for most patients but recommend medication as an initial intervention for those who express low confidence in their ability to make lifestyle changes.

For more answers, visit our FAQ resource.