Big data analysis accurately predicts patient survival from heart failure

April 13, 2018, Yale University
Credit: stock.adobe.com

Heart failure is the leading cause of death and disability in the United States, costing healthcare systems worldwide more than $30 billion annually. Current approaches to treatment are limited by crude clinical assessments of the disease. In a new study, Yale researchers have successfully used big data methods to improve prediction of heart failure patient survival. They also described data-driven categories of patients that are distinct in their response to commonly used therapies.

This innovative approach, detailed in the Journal of the American Heart Association, could lead to better care for this incurable chronic condition, the researchers said.

Led by Drs. Tariq Ahmad and Nihar Desai, both assistant professors in Yale's Section of Cardiovascular Medicine, the research team analyzed health data from a large registry of more than 40,000 . The researchers used a statistical "machine-learning" technique to first predict outcomes for the patients one year after diagnosis. They also applied cluster analysis methods to sort the patients into four clinically recognizable categories with different responses to commonly used medications.

The big-data methods vastly outperformed currently used measures of , and had better prediction of risk than previously published prediction models, Ahmad said. The research team also used entirely data-driven methods to group patients into distinct clusters that responded differently to medical therapies.

As a final step, the researchers used their findings to develop a predictive online tool that could be integrated into electronic health records in healthcare systems. Their long-term goal is to apply these advanced analytic strategies to improve research and to provide personalized care for -failure patients as well as "enhanced intelligence" to clinicians at the bedside, Ahmad said.

The investigators also pointed to this study as a model for future work that could be achieved through collaborations between data scientists and clinicians at Yale. They cited the recently created Center for Biomedical Data Science at Yale School of Medicine as an example of ongoing efforts to drive a paradigm shift toward team-based science across the medical center and the school.

Explore further: Study highlights need for better treatment of heart failure patients

More information: Tariq Ahmad et al. Machine Learning Methods Improve Prognostication, Identify Clinically Distinct Phenotypes, and Detect Heterogeneity in Response to Therapy in a Large Cohort of Heart Failure Patients, Journal of the American Heart Association (2018). DOI: 10.1161/JAHA.117.008081

Related Stories

Study highlights need for better treatment of heart failure patients

March 27, 2018
A new study by researchers from the Universities of Leicester and Keele, has highlighted the need for better treatment of heart disease patients suffering from additional chronic conditions.

Heart's pumping function is not an indicator of heart failure survival rates

November 12, 2017
Contrary to popular practice, a measure of the heart's pumping function known as "left ventricular ejection fraction" is not associated with the long-term outcomes of hospitalized heart failure patients, a UCLA-led study ...

Big data model improves prediction of key hospital outcome

February 18, 2016
More than half of hospital deaths in the United States are related to severe infections, or sepsis. Yale researchers developed a prediction model, drawing on "big data" about local patients and using machine-learning methods, ...

Guideline adherence, not patient volume, may be better hospital heart failure metric

January 29, 2018
In evaluating the quality of care given to those hospitalized with heart failure, adherence to clinical guidelines may be a better measure of quality than the number of heart failure patients a hospital admits, according ...

Following treatment guidelines more important than volume for assessing heart failure care

February 5, 2018
Looking at how well hospitals adhere to treatment guidelines for heart failure is more important than comparing patient volumes at hospitals, new research shows.

Study gets to the heart of heart failure

January 29, 2016
A failing heart is said to be like an "engine out of fuel." To better understand the problem of energy production in heart-failure patients, researchers at Yale University and Duke University studied the underlying metabolic ...

Recommended for you

Research team traces pathway to cardioprotection in post-ischemic heart failure

December 11, 2018
During an ischemic attack, the heart is temporarily robbed of its blood supply. The aftermath is devastating: reduced heart contractility, heart cell death, and heart failure. Contributing to these detrimental changes is ...

Macrophage cells key to helping heart repair—and potentially regenerate, new study finds

December 11, 2018
Scientists at the Peter Munk Cardiac Centre have identified the type of cell key to helping the heart repair and potentially regenerate following a heart attack.

Study reveals new link between atrial fibrillation and mutations in heart disease gene

December 11, 2018
Atrial fibrillation (Afib), a heart condition that causes a rapid, irregular heartbeat that increases a person's risk of stroke and heart failure, is fairly common among older adults. However, its early onset form is relatively ...

Researchers have found that incidence of heart failure was around two-fold higher in people with diabetes

December 11, 2018
Researchers have found that incidence of heart failure was around two-fold higher in people with diabetes.

Workplace exposure to pesticides and metals linked to heightened heart disease risk

December 11, 2018
Workplace exposure to metals and pesticides is linked to a heightened risk of heart disease in Hispanic and Latino workers, reveals research published online in the journal Heart.

Study: Age, race differences determine risk of stroke in women and men

December 11, 2018
A new study found that, between the ages of 45 and 74 years, white women were less likely to have a stroke than white men, but at age 75 and older, there was no difference in stroke risk between white women and men. In contrast, ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.