Heart failure is a condition where the heart struggles to pump blood effectively throughout the body.
Current methods of classifying heart failure don’t accurately predict how the disease will progress.
However, a recent study led by UCL researchers has identified five subtypes of heart failure that could potentially help predict the future risk for individual patients.
The findings of this study could improve patient care and treatment strategies.
Identifying Five Subtypes
The researchers analyzed detailed data from over 300,000 patients aged 30 or older who were diagnosed with heart failure in the UK over a span of 20 years.
Using machine learning methods, they identified five subtypes of heart failure: early onset, late onset, atrial fibrillation related, metabolic, and cardiometabolic.
Distinct Characteristics and Risks
Each subtype had distinct characteristics and differed in the risk of mortality within a year after diagnosis.
The one-year all-cause mortality risks for each subtype were as follows: early onset (20%), late onset (46%), atrial fibrillation related (61%), metabolic (11%), and cardiometabolic (37%).
Potential Clinical Application
The research team also developed an app that clinicians could potentially use to determine the subtype of heart failure in individual patients.
This could improve predictions of future risks and facilitate informed discussions between doctors and patients.
Lead author Professor Amitava Banerjee explained that the goal was to better understand how heart failure progresses in individual patients.
The ability to distinguish between subtypes could lead to more targeted treatments and a fresh perspective on potential therapies.
Validation and Clinical Evaluation
To avoid bias, the researchers used four different machine-learning methods to group cases of heart failure.
They applied these methods to data from two large UK primary care datasets, which represented the entire UK population and were linked to hospital admissions and death records.
The findings were validated using a separate dataset.
The Factors Considered
The subtypes were established based on 87 factors, including age, symptoms, the presence of other conditions, medications, and the results of various tests and assessments.
In addition to clinical data, the researchers also examined genetic data from individuals with heart failure.
They discovered a connection between specific subtypes of heart failure and higher polygenic risk scores for conditions like hypertension and atrial fibrillation. Polygenic risk scores indicate the overall genetic risk for a particular condition.
The researchers acknowledge that further research and clinical trials are needed to evaluate the practical implications of this classification method.
The app designed by the team requires validation and assessment in routine patient care.
Conclusion: The study’s identification of five subtypes of heart failure has the potential to significantly improve the prediction of future risks for individual patients.
By employing machine learning methods and analyzing comprehensive datasets, researchers can better understand the progression of heart failure and provide targeted treatments.
This research opens new avenues for personalized patient care and treatment strategies in the field of heart failure.
If you care about heart health, please read studies that yogurt may help lower the death risks in heart disease, and coconut sugar could help reduce artery stiffness.
For more information about health, please see recent studies about antioxidants that could help reduce dementia risk, and epilepsy drug may help treat Alzheimer’s disease.
The study was published in The Lancet Digital Health.
Copyright © 2023 Knowridge Science Report. All rights reserved.