A team from the University of Zurich, Germany, developed an AI system to better predict heart attacks in men and women, according to a study published in The Lancet. The aim is to offer the correct treatment as soon as possible.
Heart attacks are one of the leading causes of death worldwide, but women show a much higher mortality rate than men. Cardiologists have been concerned about this for many years because it often leads to gaps in treatment between men and women.
The issue starts because men tend to have much more evident symptoms, including chest pain with discomfort radiating to the left arm. In contrast, women usually experience abdominal pain, nausea, and vomiting, which are often misinterpreted by healthcare professionals delaying vital treatment.
To address this issue, a team from the Center for Molecular Cardiology at the University of Zurich (UZH) decided to investigate how biological sex affects heart attacks. “Indeed, there are notable differences in the disease phenotype observed in females and males. Our study shows that women and men differ significantly in their risk factor profile at hospital admission,” says Thomas F. Lüscher, from the University of Zurich.
When the authors disregarded age and pre-existing risk factors, such as hypertension or diabetes, females have a higher mortality rate than males after a heart attack. “However, when these differences are taken into account statistically, women and men have similar mortality,” added Lüscher.
The researchers analysed data from over 420,000 patients across Europe who suffered the most common type of heart attack and discovered that current patient treatment plans are biased towards men. “The study shows that established risk models which guide current patient management are less accurate in females and favor the undertreatment of female patients,” says first author Florian A. Wenzl of the Center for Molecular Medicine at UZH.
To cover this gap, the team developed a new risk score that takes into account the differences between men and women. The idea is to find women who are having a heart attack earlier and provide life-saving treatment. “Using a machine learning algorithm and the largest datasets in Europe, we were able to develop a novel artificial- intelligence-based risk score which accounts for sex-related differences in the baseline risk profile and improves the prediction of mortality in both sexes,” said Wenzl.
This is another example of using AI and big data to offer personalised care for patients. “Our study heralds the era of artificial intelligence in the treatment of heart attacks,” said Wenzl. Modern computer algorithms can use large data sets to offer accurate predictions about the prognosis of individual patients. This is the key to a personalised treatment.
Not surprisingly, the authors see tremendous potential in the application of artificial intelligence for the management of heart disease in male and female patients. “I hope the implementation of this novel score in treatment algorithms will refine current treatment strategies, reduce sex inequalities, and eventually improve the survival of patients with heart attacks – both male and female,” says Lüscher.
Wenzl F, Kraler S, Ambler G et al. (2022) Sex-specific evaluation and redevelopment of the GRACE score in non-ST-segment elevation acute coronary syndromes in populations from the UK and Switzerland: a multinational analysis with external cohort validation. The Lancet, https://doi.org/10.1016/S0140-6736(22)01483-0