The fresh Milliman report found that after testing the impact of various modifications to Together Senior Health’s dementia AlgoRithm, fresh claims-based models showed positive predictive value to support high-quality care.
WHY IT’S IMPORTANT
Together, part of Linus Health, they developed a proprietary cognitive impairment identification and stratification algorithm – validated against electronic health record data – to assist identify patients at increased risk of undiagnosed Alzheimer’s disease, dementia and cognitive decline.
“RADAR offers payers and providers a rapid and highly effective method for identifying patients at highest risk for undiagnosed dementia,” Deborah Barnes, co-founder of Together, said in announcing the report. “Most importantly, according to the results of Milliman’s in-depth analysis, RADAR is highly accurate.”
According to Dr. John Showalter, an internal medicine physician specializing in dementia and chief strategy officer at Linus, with fresh RADAR models using claims data, the overall predictive performance could be twice as high as predictive mammography algorithms and three times greater than predictive colonoscopy algorithms . Health.
“The evidence clearly demonstrates that the gold standard for breast and colorectal cancer screening produces predictive results comparable to the revised RADAR model,” he said in a statement Tuesday.
“However, RADAR is much better because it requires no patient time, discomfort or involvement at all, nor is it as expensive as these common guideline-based procedures.”
Actuarial firm Milliman evaluated RADAR using administrative claims data to test the impact of various modifications, including recalculating model weights and assessing the marginal effectiveness of including fresh predictor variables or predictors. According to the fresh one reportthe process involved creating cohort datasets, running models, calculating summary statistics, and evaluating fresh predictors.
Recent claims-based models can assist drive proactive care and diagnosis. Combined with clinical insights, they could “enable payers and providers to deliver more accurate and appropriate risk adjustment results that support quality of care,” added Mike Butler, an independent board director of Linus Health and former president of Providence Health.
“Based on my decades of experience overseeing value-based care and risk-based contracts, RADAR’s ability to quickly stratify the population for undiagnosed cognitive disorders is of paramount importance.”
“When using claim-based predictors, the accuracy of predicting the risk of undiagnosed dementia is significantly improved by refitting the model to reweight the predictors,” Milliman said in the report.
Together, they are also developing and testing versions of RADAR that include claims, EHRs, and other data sources not included in this report.
A BIGGER TREND
While AI and machine learning in healthcare are often replaced by manual tasks, brain health technology companies like Linus view AI differently, according to David Bates, the company’s CEO and co-founder.
“In brain health, artificial intelligence opens up a whole world of opportunities for earlier detection – and intervention – at a time when the urgency to find different approaches that can change the global view of brain health and aging has never been more urgent,” he previously said
Detecting often unnoticeable signs of cognitive impairment by using artificial intelligence to expand clinical knowledge and analyze signals and patterns of performance during cognitive testing is only part of the picture, he said.
When clinical cognitive testing metrics are combined with other inputs such as health history, life habits, symptoms and social determinants of health, AI can assist providers “with fresh insights into patients’ brain health, so they can in turn empower their patients ” with education and, where appropriate, follow-up steps,” he said.
ON RECORDING
“Health care systems want to do the right thing when caring for their aging patients, but they have difficulty targeting cognitive assessments to the right people,” Butler said in a statement. “The RADAR algorithm is a game changer, especially for Medicare Advantage plans and value-based care providers.”
“Due to the historic care demands facing primary care practices today, providers and payers must carefully select which patients should first undergo more extensive cognitive impairment screening so that those at higher risk can begin preventive treatment as soon as possible” – Barnes in the appendix.