Adaptive and Just-in-Time Adaptive Interventions

Behavioral interventions for prevention and treatment are an important part of the fight against drug abuse and conditions such as HIV/AIDS and mental illness. Among the challenges faced by scientists is how and when to alter the course of treatment for participants in the intervention. Adaptive interventions (also known as "adaptive treatment strategies" or "dynamic treatment regimens") change based on what is best for the patient at that time.

Just-in-time adaptive interventions (JITAIs) are a special type of adaptive intervention where—thanks to mobile technology like activity sensors and smartphones—an intervention can be delivered when and where it is needed.

Technically speaking, an adaptive intervention is a sequence of decision rules that specify how the intensity or type of treatment should change depending on the patient's needs. Methodology Center researchers are developing data-analytic methods for constructing decision rules that allow researchers to build better adaptive interventions and JITAIs.

Just-in-Time Adaptive Intervention (JITAI)

cell phones and FitBit on a tableRealistically, a clinician can only check in with patients at appointments, but people nearly always carry their smartphones. These phones contain a lot of information about when a person is and is not at risk for engaging in harmful behavior. In JITAIs, continuously collected data via a mobile device (like a smartphone or FitBit) are combined with each participant’s preferences and current context to select an appropriate intervention whenever and wherever it is needed. The JITAI is then delivered through the mobile device. 

Example JITAI: Being there for quitting smokers on the verge of lapse

cigarette and nicotine gumSusan Murphy and Inbal "Billie" Nahum-Shani are collaborating with Bonnie Spring of Northwestern University and Santosh Kumar of Memphis University to create an intervention to reduce relapse among abstinent daily smokers. Ninety-three percent of smokers fail during the first week of their quit attempt. We know that stress is an excellent predictor of relapse to smoking. This study seeks to determine whether stress a useful indicator of when to trigger an intervention to prevent a smoking lapse. Read more.

Micro-Randomized Trials (MRTs)

blank MRT diagram

In micro-randomized trials, individuals are randomized hundreds or thousands of times over the course of the study. The goal of these trials is to assess the proximal, in-the-moment, impact of interventions (e.g. interventions that are intended to impact behavior over small time intervals). Through MRTs we can gather data to build optimized JITAIs. In the Heart Steps program, MRTs are being used to build a JITAI that encourages physical activity among people with a heart condition. Read more.

MRTs in Intervention and Prevention Research

Multiple MRTs have been funded and are being conducted. They are being used to build JITAIs that address health problems including smoking and cardiovascular health.

Open the list.

Sequential, Multiple Assignment, Randomized Trial (SMART)

generic SMART flow chartInterventions that adapt at the right times can improve participant outcomes (for example by intensifying treatment a person’s disorder does not respond to the initial treatment) while decreasing the cost and burden of the intervention (for example bystepping down treatment when a person is doing well). The sequential, multiple assignment, randomized trial (SMART) can provide the data needed to construct high-quality adaptive interventions.

Rationale for SMART

In a SMART there is a separate stage for each of the critical decisions involved in the adaptive intervention. At each stage, all participants are randomly assigned to a treatment option. By randomizing participants multiple times, scientists can assess the effectiveness of each option and develop the best set of decision rules. Read more.

glasses of alcoholExample: Using Medication to Prevent Alcoholism Relapse

In one of the first SMARTs ever conducted, researchers designed a trial to test how best to use the drug Naltrexone in the treatment of alcoholism relapse. The trial tested how to define relapse and what treatments best compliment Naltrexone. Read more.

SMART Designs in Action

Many SMART designs have been funded and conducted. We have compiled a partial list of SMARTs addressing a broad range of health problems,from substance use to obesity. We stopped adding to the list in 2017 when it reached a length that we feel effectively illustrates the breadth of adaptive interventions that can be constructed using a SMART. Open the list.