Artificial intelligence improves the treatment of women with heart attacks

Heart attacks are more fatal in women than in men. Reasons are differences in age and in the comorbidity burden, which make risk assessment in women a challenge. Researchers at the University of Zurich have now developed a novel risk score based on artificial intelligence that improves the personalized care of heart attack patients.

Heart attacks are one of the leading causes of death worldwide, and women who suffer a heart attack have a higher mortality rate than men. This has occupied cardiologists for decades and has led to controversy in medicine about the causes and effects of possible treatment gaps. The problem begins with the symptoms: Unlike men, who usually experience chest pain radiating to the left arm, a heart attack in women often manifests itself as abdominal pain radiating to the back or through nausea and vomiting. Unfortunately, these symptoms are often misinterpreted by patients and caregivers – with devastating consequences.

The risk profile and clinical picture are different in women

An international research team led by Thomas F. Lüscher, Professor at the Center for Molecular Cardiology at the University of Zurich (UZH), has now examined the role of biological sex in heart attacks in more detail. “Indeed, there are striking differences in the disease phenotype observed in women and men. Our study shows that women and men differ significantly in their risk factor profile when they are admitted to hospital,” says Lüscher.

Adjusting for age differences at admission and existing risk factors such as high blood pressure and diabetes, female heart attack patients have a higher mortality rate than male patients. “However, if you take these differences into account statistically, women and men have a similar mortality rate,” adds the cardiologist.

Current risk models advocate undertreatment of female patients

In their study published in The lancetresearchers from Switzerland and the UK analyzed data from 420,781 patients across Europe who had suffered the most common type of heart attack. “The study shows that established risk models that guide current patient management are less accurate in women and encourage undertreatment of female patients,” says lead author Florian A. Wenzl from the UZH Center for Molecular Medicine.

“Using a machine learning algorithm and the largest data sets in Europe, we were able to develop a novel artificial intelligence-based risk score that accounts for gender differences in the baseline risk profile and improves the prediction of mortality in both genders,” Wenzl says.

AI-based risk profiling improves individual care

Many researchers and biotech companies agree that artificial intelligence and big data analytics are the next step towards personalized patient care. “Our study heralds the age of artificial intelligence in the treatment of heart attacks,” says Wenzl. Modern computer algorithms can learn from large data sets to make accurate predictions about the prognosis of individual patients – the key to individualized treatments.

Thomas F. Lüscher and his team see great potential in the application of artificial intelligence for the management of heart disease in both male and female patients. “I hope that the implementation of this novel score in treatment algorithms will refine current treatment strategies, reduce gender inequalities and ultimately improve the survival of heart attack patients – both males and females,” says Lüscher.