A recent Mayo Clinic study has made a data-driven discovery for patients with heart failure in the intensive care unit.

Using machine learning, the researchers identified groups of patients with heart failure with higher and lower risk of mortality based on underlying patterns of laboratory values.

"The goal of this study was to explore different groups in the larger population of patients with heart failure admitted to the cardiac ICU," says Jacob Jentzer, M.D., a Kern Health Care Delivery Scholar and lead author of the study. "Recognizing that a critically ill heart failure patient belongs to one of these groups can help clinicians understand their likely underlying disease process and prognosis, allowing individualized therapy with the goal of improving outcomes."

Through the analysis, Dr. Jentzer and his colleagues identified five distinct groups, including patients with evidence of iron deficiency, kidney dysfunction, inflammation and poor blood flow. Each group had unique characteristics and risk profiles. Researchers underscore that by identifying these distinct groups, clinicians can craft treatment plans for each patient's needs and help to enhance outcomes and overall quality of care.

The groups in the study included:

• Uncomplicated: Patients generally had milder disease.
• Iron-deficient: Signs of iron deficiency, which can significantly impact heart function.
• Cardiorenal: Patients showed signs of kidney dysfunction, which is a common complication of severe heart failure.
• Inflamed: Patients revealed signs of significant inflammation.
• Hypoperfused: Patients showed signs of poor blood flow to vital organs, indicating more severe heart failure.

The findings revealed that the patients in the uncomplicated group generally had the best outcomes. In contrast, the patients in the inflamed, cardiorenal and iron-deficient groups all had an intermediate mortality risk.

Researchers note that patients in the hypoperfused group had the highest risk of mortality.

"The phenotypes and subgroups based on patterns of laboratory findings identified in this study have not been described before and could represent different noncardiac organ complications driven by different underlying biologic processes," says Dr. Jentzer. "This may help identify unique targeted therapies in a future study." 

Researchers underscore the influence of the Kern Health Care Delivery Scholars Program on researchers conducting studies such as this that impact the practice and seek to improve healthcare delivery. 

"The Kern Health Care Delivery Scholars program enables practicing clinicians, such as Dr. Jentzer, to dedicate time to learning healthcare delivery methods so they can approach clinical challenges in a novel way," says Shannon Dunlay, M.D., a heart failure cardiologist and senior author of the study. "The findings from this study can be used to identify personalized treatment strategies for patients with heart failure in the cardiac ICU."

Review the study for a complete list of authors, disclosures and funding.

About Mayo Clinic Robert D. and Patricia E. Kern Center for the Science of Health Care Delivery

The Mayo Clinic Robert D. and Patricia E. Kern Center for the Science of Health Care Delivery collaborates with clinical areas across Mayo to create and evaluate data-driven solutions to transform the experience of health and healthcare for patients, staff and communities. It drives continuous improvement of Mayo Clinic as a learning health system, enabling safe, evidence-based, high-quality care.

Related Articles