Women are more likely than men to die from heart attacks. The causes are age disparities and the burdens of comorbidities, which makes risk assessment in women difficult. Scientists from the University of Zurich have created a new artificial intelligence-based risk score that enhances tailored care for female cardiac event patients.
In women, an acute heart attack often leads to abdominal pain radiating to the back and is therefore often not recognized as such. Image Credit: iStock/Svitlana Hulko
One of the main causes of death worldwide is heart disease, and women are more likely than males to die from a heart attack.
Cardiologists have been concerned about this for many years, and it has sparked debate about the origins and consequences of potential therapy gaps in the medical community.
The issue begins with the symptoms: unlike males, who typically suffer chest pain radiating to the left arm, heart attacks in women frequently present as nausea and vomiting as well as abdomen discomfort traveling to the back.
However, patients and medical staff sometimes mistake these symptoms, which has disastrous results.
Risk Profile and Clinical Picture is Different in Women
The connection between biological sex and heart attacks has now been more thoroughly studied by an international research group under the direction of Thomas F. Lüscher, professor at the Center for Molecular Cardiology at the University of Zurich (UZH).
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.
Thomas F. Lüscher, Professor, Center for Molecular Cardiology, University of Zurich
Female heart attack patients had greater fatality rates than male heart attack patients did when age disparities at admission and preexisting risk factors like hypertension and diabetes are taken into account.
“However, when these differences are taken into account statistically, women and men have similar mortality,” the cardiologist adds.
Current Risk Models Favor the Under-Treatment of Female Patients
Scientists from Switzerland and the United Kingdom examined data from 420,781 patients in Europe who had experienced the most typical type of heart attack for their study, which was published in the prominent journal The Lancet.
The study shows that established risk models which guide current patient management are less accurate in females and favor the under-treatment of female patients.
Florian A. Wenzl, Study First Author, Center for Molecular Medicine, University of Zurich
“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,” Wenzl says.
AI-Based Risk Profiling Improves Individualized Care
Big Data analytics and machine intelligence, in the opinion of many scientists and biotech firms, are the next step toward individualized patient care.
“Our study heralds the era of artificial intelligence in the treatment of heart attacks,” says Wenzl. The secret to individualized treatments is the ability of contemporary computer algorithms to learn from vast data sets and make specific estimates about the prognosis of specific patients.
Artificial intelligence has enormous potential for the treatment of cardiac disease in both male and female patients, according to Thomas F. Lüscher and his team.
“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.
Journal Reference
Wenzl, F. A., 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. doi.org/10.1016/S0140-6736(22)01483-0.
Source: https://www.uzh.ch/en.html