A new report from Milliman, Inc. concluded that after testing the impact of several modifications to Together Senior Health’s Dementia AlgoRithm, new claims-based models demonstrate positive predictive value that can support quality care.
WHY IT’S IMPORTANT
Together, Linus Health, part of Linus Health, developed its patented cognitive impairment identification and stratification algorithm – validated using electronic health record data – to help find patients at increased risk for undiagnosed Alzheimer’s disease, dementia and cognitive decline.
“RADAR provides payers and providers with a rapid, highly efficient method for identifying their patients at highest risk for undiagnosed dementia,” said Deborah Barnes, co-founder of Together, in the report announcement. “Most importantly, RADAR is highly accurate, according to the results of this thorough analysis from Milliman.”
With new RADAR models using claims data, overall predictive performance can now be twice that of predictive mammography algorithms and three times that of predictive colonoscopy algorithms, according to Dr. John Showalter, an internist specializing in dementia and chief strategy officer at Linus Health.
“The evidence clearly shows that the gold standard for breast and colorectal cancer screenings produces predictive results comparable to the refit RADAR model,” he said in a statement on Tuesday.
“However, RADAR is much better because it requires no time, discomfort or patient involvement at all, and it is also not nearly as expensive as these common guideline-oriented procedures.”
The actuarial company Milliman, Inc. evaluated RADAR using administrative claims data to test the impact of various changes, including recalculating the model weights and evaluating the marginal effectiveness of including new predictor variables or predictors. According to the new reportthe process required creating cohort datasets, running the models, calculating summary statistics, and evaluating the new predictors.
The new claims-based models could help drive proactive care and diagnoses, and when combined with clinical insights, could “enable payers and providers to obtain more accurate and appropriate risk adjustment results that support quality care,” Mike Butler, an independent board member of Linus Health and former president of Providence Health, added.
“Based on my decades of experience overseeing value-based care and risk-based contracting, RADAR’s ability to quickly stratify populations for undiagnosed cognitive disorders is transformative.”
“When using claims-based predictors, the accuracy for predicting the risk of undiagnosed dementia is significantly improved by refitting the model to reweight the predictors,” Milliman said in the report.
Together is also developing and testing versions of RADAR that include claims, EHR and other data sources not included in this report.
THE BIG TREND
While artificial intelligence and machine learning models in healthcare are often pursued to replace manual tasks, this is not how brain health tech companies like Linus view AI, according to David Bates, CEO and co-founder of the company.
“In brain health, AI opens up a whole world of possibilities for earlier detection – and intervention – at a time when the urgency has never been greater to find diverse approaches that change the global view of human health. brain and aging can change,” he previously said. Healthcare IT news.
Uncovering often unnoticeable signs of cognitive impairment by using AI to enhance clinical expertise and analyze signals and performance patterns during cognitive tests is only part of the picture, he said.
When clinical cognitive test metrics are combined with other inputs such as health history, lifestyle habits, symptoms and social determinants of health, AI can help healthcare providers “gain new insights into their patients’ brain health so that they can, in turn, provide their patients with new insights.” education and next steps where necessary,” he said.
ON THE RECORD
“Health systems want to do the right thing to care for their aging patients, but struggle with targeting cognitive assessments to the right people,” Butler said in a statement. “The RADAR algorithm is a gamechanger, especially for Medicare Advantage plans and value-based healthcare providers.”
“Because of the historic healthcare demands facing primary care practices today, providers and payers must carefully assess which patients should first undergo more in-depth screenings for cognitive impairment so that those at higher risk can receive preventative interventions as quickly as possible,” says Barnes. added.
Andrea Fox is editor-in-chief of Healthcare IT News.
Email: afox@himss.org
Healthcare IT News is a HIMSS Media publication.