Cedar Gate’s Heart Disease & Heart Failure Predictive AI Models Could Save $1.4 Billion with Early Intervention

Machine learning models within Cedar Gate’s platform can identify, with a high level of accuracy, patients who are at risk of coronary artery disease (CAD) and congestive heart failure (CHF), allowing for early intervention and, as a result, the potential to reduce acute events.

Metadata
Provider: 
Business Wire, Inc.Business Wire, Inc.
Retrieved on: 
火曜日, 4月 23, 2024
Information
Tags: 
Health Technology, Health Insurance, Manufacturing, Technology, Professional Services, Hospitals, Artificial Intelligence, Cardiology, Science, Biotechnology, Machinery, Data Analytics, Other Science, Health, Research, Conditional sentence, Bangladesh Technical Education Board, NIH, Risk, Coronary artery disease, Cardiovascular disease, Woman, Death, Machine learning, Data science, Algorithm, Patient, CAD, CHF, Diagnosis, MCC, Hospital, American Heart Association, Heart
Geotags: 
UNITED STATES, NORTH AMERICA, CONNECTICUT, BENCHMARK, EUROPE
概要
Key Points: 
  • Machine learning models within Cedar Gate’s platform can identify, with a high level of accuracy, patients who are at risk of coronary artery disease (CAD) and congestive heart failure (CHF), allowing for early intervention and, as a result, the potential to reduce acute events.
  • “Our AI-powered predictive models enable interventions, diagnoses, and treatments that can reduce risk and slow chronic disease progression on a large scale,” said David B.
  • “Cedar Gate’s AI-powered algorithms can translate to significant cost savings through early, focused diagnostic testing in these high-risk patients.
  • The annual direct and indirect cost of cardiovascular disease was $407.3 billion from 2018 to 2019, according to the American Heart Association.


Cedar Gate Technologies (Cedar Gate) announced that an analysis of their national Healthcare Benchmark Database, encompassing nearly 13 million member lives, revealed a potential savings opportunity of approximately $1.4 billion. Machine learning models within Cedar Gate’s platform can identify, with a high level of accuracy, patients who are at risk of coronary artery disease (CAD) and congestive heart failure (CHF), allowing for early intervention and, as a result, the potential to reduce acute events.

In a study published by the National Institutes of Health (NIH), patients with CAD who experience a major adverse cardiac event face an additional $44,495 in healthcare expenses within one year. Cedar Gate’s predictive model identified 24,628 people in its National Healthcare Benchmark Database who were not already diagnosed with CAD, but at above-average risk of developing the condition, presenting an opportunity for nearly $1.1 billion in savings.

CHF accounts for over one million hospitalizations per year in the U.S. and Europe and as much as $18 billion in direct medical costs at an average of up to $17,830 per hospitalization. The predictive model identified 17,244 undiagnosed members at risk of CHF in Cedar Gate’s database, representing the potential to save $307.4 million or more by helping high-risk members avoid one or multiple hospitalizations in a year.

“Our AI-powered predictive models enable interventions, diagnoses, and treatments that can reduce risk and slow chronic disease progression on a large scale,” said David B. Snow Jr., Chairman and CEO of Cedar Gate. “Preventive care and early intervention are at the center of effective value-based care. By leveraging our team of analytics experts and vast anonymized member data, we’re advancing technology that helps providers and payers optimize outcomes, lower costs, and close gaps in care.”

Cedar Gate’s machine learning algorithms are based on a proprietary accumulated risk scoring system that identifies high-risk individuals for chronic diseases. Unlike conventional rule-based models, it analyzes various metrics from claims history to flag potential cases, even if they don’t meet traditional thresholds. The data science team works closely with a clinical team to validate and improve these models over time.

To evaluate the effectiveness of its model, Cedar Gate used the Matthews Correlation Coefficient (MCC). On its scale of -1 to 1, values closer to 1 indicate the strongest positive correlation. The model scored 0.80, indicating an ability to predict the risk of CAD and CHF very accurately within the identified population.

“Early identification empowers cardiologists and other providers to intervene with high-risk patients and mitigate or slow disease progression,” said Dr. Eduardo Hernandez, a Houston-area cardiologist who serves as president of The Texas Heart Institute Center for Cardiovascular Care and president of Cardiovascular Care Providers. “Cedar Gate’s AI-powered algorithms can translate to significant cost savings through early, focused diagnostic testing in these high-risk patients. That could lead to less-invasive and lower-cost treatments and avoidance of acute intervention in a hospital or ER from chronic disease complications.”

The potential for savings and improved outcomes as a result of early diagnosis and intervention are substantial. Heart disease is the leading cause of death for men and women in the United States. The annual direct and indirect cost of cardiovascular disease was $407.3 billion from 2018 to 2019, according to the American Heart Association.

About Cedar Gate Technologies:

Cedar Gate enables payers, providers, employers, and service administrators to excel at value-based care with a unified technology and services platform delivering analytics, population health, and payment technology on a single data management foundation. From primary care attribution, to bundled payments, to capitation, Cedar Gate is improving clinical, financial, and operational outcomes for every payment model in all lines of business.

Copyright: 
Copyright Business Wire 2024