iMedA: Improving MEDication Adherence Through Person-Centered Care and Adaptive Interventions

The design of the digital intervention module is considered to follow the just-in-time adaptive intervention framework (JITAI). JITAI is an intervention design aiming to provide the right type/amount of support, at the right time, by adapting to an individual's circumstances. It has enormous potential for promoting health behavior change, which in this study is supposed to be medication compliance. Based on the JITAI's conceptual model, there are the following components:

1. Decision points (DP) DP is a time when an intervention decision is made. Considering the nature of JITAIs which are delivered through mobiles, DPs are much more rapidly than is standard interventions. In iMedA, DP is considered to be daily and accompanied by the time of medication intake question, i.e. "Did the participant take the anti-hypertensive medication today?".
2. Intervention options (IO) IOs are a set of possible interventions that are going to be delivered at DPs. In JITAI, IOs can be various types of support (information, advice, feedback, etc), source of support (mobile, nurse, physician, etc), amounts of support (intensity, dose, etc), type of media/channel (phone call, SMS, etc). From the conducted literature review, the investigators summarised all types of digital interventions to hypertensive patients as:

• Reminders for medication intake (daily), BP measurement (monthly), PA (biweekly)
• Informational contents regarding hypertension and all its facts, consequences, treatments, risks, medications and side-effects, lifestyle, and so on (text, videos, etc)
• Trends on medication intake/PA/BP/etc
• Motivational messages

1. Distal outcomes (DO) DO is the ultimate goal that the intervention is trying to achieve. In iMedA, the investigators considered primary and secondary DOs. Primarily the investigators aim at improving medication adherence. Then in the long term, blood pressure control is considered as secondary DOs besides the increased quality of life, assessment of the lifestyle behavior (smoking, alcohol consumption, physical activity, and food intake), and communicative and critical health literacy. In order to measure MA, the investigators consider (1) self-reported medication intake through a mobile app; (2) MUAH-16 which is a medication adherence questionnaire for hypertension; and (3) pickups from pharmacies. The self-reported values are supposed to be collected every day. MUAH-16 is measured pre- and post- intervention. BP is considered to be measured every month. There are automatic devices in every primary care center that people can go and measure their BP free of charge. QoL and HL are measured through EQ5D and HL respectively and pre- and post- intervention. Lifestyle assessments are measured (bi)weekly through self-report values.
2. Proximal outcomes (PO) POs are the short-term goals of the interventions. They can be mediators and/or intermediate measures of the DOs. Medication intake rate is considered to be the main PO, which is measured daily. Physical activity rate which is measured (bi)weekly is another PO. Since most of the contents are educational and they try to increase the hypertension knowledge of the participants, the investigators will add a PO to measure how much their knowledge has increased. The investigators consider two methods to measure it. First, after showing the content, the investigators will ask "Did the participant know …?". Second, a simple gamification test will be designed to be delivered biweekly. To prevent poor adherence to the interventions, it is recommended to define a few POs related to intervention engagement and fatigue. Therefore, the investigators consider the number of clicked interventions, number of watched videos, like/dislike feedbacks per each intervention as POs related to intervention adherence and retention.
3. Tailoring variables (TV) TVs are information about the participant that are used to decide when to provide which intervention. In other words, they are used to personalise the interventions and make them adaptive to the individual's circumstances. They can be measured actively or passively or both. Active assessments require an individual's engagement in measuring, for example through self-reports, while passive assessments require minimal/no individual engagement, for example through mobile phone's sensors. POs are often used as TVs. From baseline information, a few TVs can be selected including alcohol consumption, smoking, specific diet (vegetarian, vegan, etc), age, and gender, in order to personalise the interventions. All of the POs are also considered as TVs. From the MUAH-16 questionnaire, the investigators start to know more about individual's beliefs, barriers and behaviour about medication adherence. It has four subscales regarding (1)positive attitude towards healthcare and medication; (2) lack of discipline; (3) aversion towards medication; and (4) active coping with health problems. Each subscale contains four questions. At the beginning of the intervention, MUAH-16 questions are used as TVs. Then during the intervention period, and based on the previously delivered informational contents to the individual, the answers to "Did the participant know …?" questions will be used as TVs.
4. Decision rules (DR) DRs are the adaptation engine of JITAIs. They are used to determine which IO to deliver to whom and when. They are the links between IOs and TVs.

DRs in iMedA will be probabilistic rules from experts modified by "suggestions" from reinforcement learning.