AI tools found five forms of heart failure – ET HealthWorld


Washington: A new study by UCL researchers has discovered five types of heart failure which could possibly be used to predict future risk for individual patients.

Heart failure is a general term for when the heart cannot pump blood throughout the body properly. Current ways of classifying heart failure do not accurately predict how the disease is likely to progress.

For the study, published in Lancet Digital Health, researchers analyzed detailed anonymous patient data from more than 300,000 people aged 30 and over who were diagnosed with heart failure in the UK over a 20-year span. Using various machine learning methods, they identified five subtypes: early-onset, late-onset, atrial fibrillation-related (atrial fibrillation is a condition that causes an irregular heart rhythm), metabolic (linked to obesity but with a low rate of cardiovascular disease) and cardiometabolic (linked to obesity and cardiovascular disease).

The researchers found differences between the subtypes in the patients’ risk of death in the year after diagnosis. The risks of all-cause mortality at one year were: early-onset (20%), late-onset (46%), atrial fibrillation-related (61%), metabolic (11%), and cardiometabolic (37%). .

He investigation The team also developed an app that doctors could use to determine which subtype a person has with heart failure, which could improve future risk predictions and inform conversations with patients.

Lead author Professor Amitava Banerjee (UCL Institute of Health Informatics) said: “We are seeking to improve the way we classify heart failure, with the aim of better understanding the likely course of the disease and communicating this to patients. patients. Currently, it is difficult to know how the disease progresses. to predict for individual patients Some people will remain stable for many years, while others will rapidly deteriorate.

  Black men were likely underdiagnosed with lung problems because of bias in software, study suggests - ET HealthWorld

“Better distinction between types of heart failure may also lead to more specific treatments and may help us think differently about potential therapies.

“In this new study, we identified five robust subtypes using multiple machine learning methods and multiple data sets.

“The next step is to see if this way of classifying heart failure can make a practical difference for patients, if it improves risk predictions and the quality of information doctors provide, and if it changes the treatment of patients. It also we need to know if it would be cost-effective. The app we’ve designed needs to be tested in a clinical trial or further research, but it could help in routine care.”

To avoid bias from a single machine learning method, the researchers used four separate methods to group heart failure cases. They applied these methods to data from two large UK primary care datasets, which were representative of the UK population as a whole and were also linked to hospital admissions and death records. (Data sets were Clinical Practice Research Datalink (CPRD) and The Health Improvement Network (THIN), covering the years 1998 to 2018.)

The research team trained the machine learning tools on slices of the data, and once they selected the strongest subtypes, they validated these clusters using a separate dataset.

Subtypes were established based on 87 (of a possible 635) factors including age, symptoms, presence of other conditions, medications the patient was taking, and test results (eg, of blood pressure) and evaluations (eg, of renal function).

The team also analyzed genetic data from 9,573 people with heart failure from the UK Biobank study. They found a link between particular subtypes of heart failure and higher polygenic risk scores (overall risk scores due to genes as a whole) for conditions such as high blood pressure and atrial fibrillation.

    <!–

  • Updated On May 27, 2023 at 07:15 AM IST
  • –>

  • Posted on May 27, 2023 at 07:09 am IST
  • <!–

  • 3 min read
  • –>

Join the community of over 2 million industry professionals

Sign up to our newsletter for the latest insights and analysis.

Download the ETHealthworld app

  • Get real-time updates
  • Save your favorite items


Scan to download app




Source link

  Peloton launches its new Guide fitness workout

Leave a Comment