Researchers from the Stern Stroke Center at Montefiore Medical Center published trial results this week showing that stroke survivors were twice as likely to take anticoagulants when using an artificial intelligence platform compared to patients receiving standard therapies.
The AI platform, AiCure, features software algorithms on smartphones that confirm patient identify, medication and drug ingestion. Patients receive automated reminders and precise dosing instructions and healthcare workers can review data in real-time.
The platform allows for healthcare practitioners to detect nonadherence early and ensure patients stay on track with their regimen, according to the researchers.
“In the absence of routine laboratory monitoring, artificial intelligence has the potential to automate a critical component of care — adherence monitoring — and provide continuity of care between visits to ensure patients persist with their therapy and get full therapeutic benefit,” lead author Dr. Daniel Labovitz said in prepared remarks.
The 12-week study enrolled ischemic stroke survivors and randomly assigned them to either use the AI platform or receive treatment as usual. Researchers measured the concentration of anticoagulants in blood samples to evaluate treatment adherence.
Blood tests revealed that all of the patients in the AI branch took medication regularly, versus 50% of their counterparts in the control arm.
“Many patients are unable to self-manage and are at increased risk of stroke and bleeding,” co-author & AiCure’s chief strategy officer Laura Shafner said. “The use of technology and artificial intelligence has the potential to significantly improve health outcomes and reduce costs in clinical care.”
The researchers also noted that the patients, with an average age of 57 years old, were able to easily learn how to use the smartphone-based technology, despite having little prior experience. This AI platform is the only automated technology to be validated in ambulatory settings against drug concentration levels, according to the team.
The study was supported by a grant from the National Center for Advancing Translational Sciences of the National Institutes of Health.
