New AI Analysis Pinpoints COVID-19 Mortality Risk in Medicare Population

Findings from Study of 28 Million People Identifies 61 Percent Increase in Deaths Due to COVID-19, Reinforcing the Importance of Reducing Exposure and Expanded Vaccination for this Population.

BOSTON, April 14, 2021 /PRNewswire/ — Health Data Analytics Institute (HDAI) – an innovator in healthcare AI solutions – and the Department of Outcomes Research at Cleveland Clinic’s Anesthesiology Institute today published findings from one of the world’s largest analyses of COVID-19 mortality risk. The study, titled “Covid-19 and Excess Mortality in Medicare Beneficiaries,” is posted as a pre-print on (Medrxiv), and concludes that overall mortality among Medicare patients increased from 4% to 7.5% for those in the community who had a diagnosis of COVID-19 during 2020, while mortality increased from 20.3% to 24.6% among seniors residing in long-term care facilities.

The study demonstrates first that individual mortality risk due to COVID-19 can be accurately predicted based on age and a Risk Stratification Index (RSI) score developed by HDAI. The RSI is a composite measure of mortality risk associated with underlying medical conditions. Using these mortality predictions, the investigators then showed that mortality from COVID-19 in the Medicare population between March 1, 2020 and November 30, 2020 increased 61% percent from 215,358 expected deaths to 346,062 actual deaths in beneficiaries with probable or confirmed COVID-19 diagnoses. The term “excess deaths” refers to deaths above what would be expected from all causes other than COVID-19.

As described above, actual mortality following a probable or confirmed diagnosis in both the community and in long-term care facilities increased similarly at 3-4%. But the percentage increase was far greater in the community (89%) than among patients in chronic care facilities (21%) who had high baseline risk. The long-term care population without probable or confirmed COVID-19 diagnoses experienced 38,932 excess deaths (35%) compared to historical estimates over the 9-month study period. Remarkably, there were 31,360 fewer deaths than expected in community dwellers without probable or confirmed COVID-19 diagnoses, representing about a 6% reduction. Disruptions to the healthcare system and avoided medical care were thus apparently offset by other factors, representing overall benefit with respect to mortality in the community.

“COVID-19 has had a profound effect on the elderly during the past year. Our research quantifies the pandemic’s effect on the Medicare population, and helps identifying who is most at risk in the community and in nursing facilities,” said Prof. Daniel I. Sessler, one of the study’s co-authors and chair of the Department of Outcomes Research at Cleveland Clinic. “The COVID-19 pandemic has had marked effects on mortality, but the effects were highly context-dependent. Specifically, the virus markedly increased mortality in the community and in nursing facilities, while simultaneously reducing mortality in un-infected community dwellers.”

“An unchecked 60% increase in mortality across the Medicare population would be catastrophic. We therefore hope that successful distribution of vaccines, coupled with vigilant and safe behaviors, will further reduce exposure to COVID-19 and consequent mortality,” said Nassib Chamoun, HDAI’s CEO and founder. “Furthermore, the long-term effects of this disease are only just beginning to be understood. Our ongoing tracking of mortality and other health effects will improve understanding of post-acute sequelae of COVID-19, thereby better characterizing the full effect of COVID-19 on health and healthcare.”

The RSI mortality predictor is based on a claims analysis of approximately 28 million people. The HDAI suite of predictive models are based on research involving more than 20 years of claims data, hundreds of millions of claims records, and collaboration with academic and industry research partners.

Non-commercial access to the RSI mortality risk predictor is available to researchers, health providers, government agencies, and individuals for use as an assessment tool to identify the most vulnerable individuals (Risk Stratification Index | Cleveland Clinic). Individuals can sign up to see their personalized insights on Health Picture (https://healthpicture.com/) and organizations can request access to the model at https://hdaistaging.wpengine.com/api/.

Dr. Sessler is a paid consultant of and holds equity interest in Health Data Analytics Institute.

About HDAI:
Health Data Analytics Institute (HDAI) is an analytics company with a validated, predictive platform for measuring short- and long-term health risks. The HDAI platform provides accurate healthcare predictors built on extensive underlying data assets unlocked by a sophisticated risk modeling methodology refined over 20 years. Progressive health systems, physician groups, and life sciences companies apply HDAI’s solutions to support the development of effective and targeted care plans, the delivery of higher-quality patient care, and the provision of appropriate services for populations. For more information, please visit: hdaistaging.wpengine.com

Your privacy matters

We believe that an individual’s meaningful control over their own data is as valuable as the data itself. That’s why we are committed to protecting privacy at every turn.
We always:
  • Provide transparency about the information we collect and why we collect it
  • Comply with all applicable privacy rules and regulations
  • Delete personal data from our servers if an individual opts out
We never:
  • Sell data to third parties
  • Share data with third parties besides the primary, explicitly authorized institution
  • Collect data besides what is disclosed
  • Keep personal data for individuals who have opted out

We speak legalese only when we have to, but we do our best to keep it human. Provided below are the full versions of our Privacy Policy and Terms of Service. If you have any questions, don’t hesitate to contact us for clarification.