Artificial intelligence for LVO stroke detection could save $11M annually, model estimates
Utilizing artificial intelligence to aid in the detection of intracranial large vessel occlusion strokes could potentially save the healthcare system millions, according to a new analysis.
Dutch imaging experts performed a health technology assessment—a method of assessing new innovations at early stages—for their analysis. They used assumptions including a 6% rate of missed diagnoses of LVO strokes, $40 per AI analysis, and a 50% reduction in missed cases via the technology.
Applying their assumptions across a cohort of nearly 72,000 patients, gleaned from United Kingdom stroke registry data, produced yearly cost savings of $11 million (USD), experts wrote in Insights into Imaging.
“The most important next step is to validate the outcomes of the early health technology assessment in clinical practice,” Kicky van Leeuwen, with the Department of Medical Imaging at Radboud University Medical Center, Nijmegen, Netherlands, and colleagues wrote Sept. 25. “With increasing number of AI tools implemented in the clinic, it is important to assess the impact of AI tools on our healthcare system. Real-life outcome measures should be used to gain insights into how to apply AI tools in a sensible and safe way. This is a prerequisite to prove the claim that AI is making healthcare better and more affordable.”
Researchers modeled two scenarios—current standard of care, with patients receiving a head CT angiography (with or without CT perfusion) read by physicians or using AI as a diagnostic aid. They used a conservative estimate of 6% missed LVO strokes, with some figures ranging as high as 20%. Other variables including the cost of care were gathered from previous large stroke studies. Van Leeuwen et al. noted that about 86% of the patient cohort used were “early presenters,” and that cost savings could be curbed with a greater percentage of patients later in their stroke episode.
“Early [health technology assessment] analyses are not meant to provide a firm ‘go’ or ‘no-go’ recommendation for the development or purchasing of an innovation but provide insights in the direction to head regarding development, implementation and reimbursement,” the authors advised. “In this study, the analyses show that cost benefits are obtained in the long term, while the costs for the software are short term and are usually covered by the radiology department or hospital. This observation could contribute to the debate on the investments, financial accountability and reimbursement for the clinical use of AI technology.”
Marty Stempniak has covered healthcare since 2012, with his byline appearing in the American Hospital Association's member magazine, Modern Healthcare and McKnight's. Prior to that, he wrote about village government and local business for his hometown newspaper in Oak Park, Illinois. He won a Peter Lisagor and Gold EXCEL awards in 2017 for his coverage of the opioid epidemic.