Medication adherence remains one of healthcare's biggest challenges. It accounts for up to 50% of treatment failures, 25% of hospitalizations, and 125,000 deaths annually. Adherence interventions can change this, but only when you target the right patients in the right way to have the greatest impact.

Adherence Interventions and AI: An Overview

Adherence Interventions Through the Pharmacy

Pharmacy-based adherence interventions offer some of the most effective, cost-efficient strategies for improving medication adherence. 

The Asheville Project remains a shining example of success. It covered 12 community and hospital pharmacy clinics in Asheville, North Carolina, from 2000 through 2005. Through targeted interventions, patients saw significant drops in blood pressure, cholesterol, and cardiovascular events. The share of healthcare expenses shouldered by cardiovascular events declined from 30.6 percent to 19 percent. There was also a 53 percent decrease in the risk of a cardiovascular event and a 50 percent decrease in the risk of a cardiovascular-related hospital visit. 

More recently, a 2019 study assessed the potential of a pharmacist-led adherence intervention to reduce the nonadherence burden on the Australian healthcare system. The retrospective study examined dispensing data from 20,335 patients (11,257 on rosuvastatin, 6,797 on irbesartan, and 2,281 on desvenlafaxine). Each patient received a pharmacist-led medication intervention. Then, researchers compared data from six months before and six months after the intervention. 

Across the three disease states, medication nonadherence costs were estimated to be $517 per adult, or $10.4 billion. After the intervention, costs were estimated to decrease by $95 per adult, saving the Australian healthcare system $1.9 billion annually.

RELATED: Are you struggling to find the right medication adherence technology  to improve your Star Ratings? Download our ebook to learn how to find a  solution that’s right for you. >>

Electronic vs. In-Person Adherence Interventions

The specific mechanism of intervention matters less than how well it is designed. One study of randomized controlled trials evaluated adherence intervention models for patients with diabetes and cardiovascular disease. 

Overall, the study found that in-person interventions had similar efficacy to indirect ones, with success rates of 56 percent and 42 percent respectively. In-person tactics included face-to-face interviews, hospital discharge instructions, clinic-based interventions, and phone calls. Indirect tactics included paper-based mailed and faxed information, automated phone calls, electronic pill boxes, and computer-generated interventions. Electronic indirect interventions were more effective than paper-based ones, with respective efficacies of 67 percent and 33 percent. 

Optimizing Adherence Interventions

One area of electronic intervention with great potential is text messaging. However, according to the Agency for Healthcare Research and Quality (AHRQ), many mobile health services are not agile enough to meet patients’ complex and changing needs, with one-size-fits-all messages sent on a rigid schedule. The fact is, better patient engagement requires more targeted, personalized solutions. 

It’s difficult for a standard text messaging strategy to overcome the complex challenges to adherence, including patient beliefs about a disease, organizational barriers, and costs. Patients may also perceive excessive messages as annoying and begin to ignore them. 

During a substudy in the Phase II clinical trial for Abbott and Gilead’s ABT-126—an α7 nicotinic receptor agonist used in the treatment of schizophrenia—researchers used an artificial intelligence (AI) platform, AiCure, to measure medication adherence. The AiCure app watches patients take their medication and aggregates data for clinical insights. The study found that mean cumulative adherence over 24 weeks was 89.7 percent for subjects monitored using the AI platform, compared with 71.9 percent for subjects monitored by directly observed therapy.

Artificial Intelligence Takes on Adherence

Take Blue Cross Blue Shield of North Carolina for example: Blue Cross Blue Shield of North Carolina used AllazoHealth’s AI Engine to improve medication adherence rates for their Medicare Advantage Part D population of 104,392 patients. The authors believe this study is the first randomized controlled trial to isolate the effect of machine learning technology on enhancing medication adherence interventions.

The study examined adherence rates across the three medication classes directly tied to end-of-year Star Ratings and bonus payments: renin-angiotensin system antagonists (RASAs), oral anti-diabetics (OADs), and statins. It compared the impact of live calls delivered with Allazo targeting, live calls delivered with traditional targeting, and control group without any interventions. Ultimately, all patients in the AllazoHealth group showed a 5.5 times greater uplift in adherence, with 23 percent less money spent on interventions for the AllazoHealth-targeted group versus the traditionally targeted group.

There is no doubt about it: AI plays an essential role in healthcare and medication adherence. By taking a proactive—rather than reactive—approach, healthcare organizations can deploy more effective, efficient interventions at a lower cost, improving adherence and individual health outcomes in the process.

How to Find an Adherence Solution That Improves Your Star Ratings  Ebook