Using Artificial Intelligence to Measure and Optimize Adherence in Patients on Anticoagulation Therapy
In this poster you will learn:
- Treatment adherence is a critical component of anticoagulation therapy. When anticoagulation is indicated for stroke prevention, strict adherence to warfarin has been shown to be highly effective. The recent introduction of direct oral anticoagulants (DOACs), while reducing the need for regular monitoring in an elderly and sick patient population, has also placed pressure on patients to self-manage and be fully adherent.
- Non-adherence accounts for approximately 30-50% of treatment failures in patients on anticoagulation therapy. Elderly patients who are discharged home after a stroke are at high risk of medication non-adherence and discontinuation of therapy. Regular monitoring of INR levels in patients prescribed warfarin allow for suboptimal adherence rates to be detected in a timely manner. Currently, there is no readily available, reliable test to indicate medication adherence for patients on DOACs. Suboptimal rates of adherence to DOACs go undetected, placing high-risk patients at increased risk of stroke.
- The majority of monitoring solutions (pill counts, patient self-reports, pharmacy refill data, electronic packaging) do not confirm medication ingestion. And while some solutions have demonstrated a moderate effect on adherence, a lack of randomized controlled trials and variability in study designs have precluded any definitive assessment on their effect on adherence or health outcomes. Accurate and continuous monitoring of medication adherence to all oral anticoagulants (warfarin and DOACs) allows for immediate intervention with patients who miss doses.
- Because of its ability to ensure treatment adherence, directly observed therapy (DOT) has been used for decades to measure and maximize adherence for treatment of tuberculosis, HIV and in some early phase clinical trials. However, the cost and logistical complexity of DOT makes it unavailable in routine clinical practice; healthcare professionals must rely on less effective monitoring or no monitoring at all. The artificial intelligence (AI) Platform (AiCure, New York, NY) uses artificial intelligence to visually confirm medication ingestion using software that can be downloaded as an application onto any mobile device. Software algorithms identify the patient, the drug, and confirm ingestion. Encrypted data are sent to cloud-based dashboards for real-time monitoring and intervention; missed doses, late doses, or incorrect usage immediately trigger alerts.