Summary Background The Global Registry of Acute Coronary Events (GRACE) 2.0 was developed and validated in predominantly male patient populations. We aimed to evaluate its sex-specific performance in non-ST-segment elevation acute coronary syndromes (NSTEACS) and develop an improved score (GRACE 3.0) that takes into account sex differences in disease characteristics. Methods We evaluated the GRACE 2.0 score in 420?781 consecutive patients with NSTE-ACS in contemporary national cohorts from the United Kingdom and Switzerland. Machine learning models to predict in-hospital mortality were based on GRACE variables and developed on sex-disaggregated data from 386,591 patients from England, Wales and Northern Ireland (divided into a training cohort of 309,083 [80.0%] patients and a validation cohort of 77?508 [20.0%] patients). External validation of the GRACE 3.0 score was performed on 20,727 patients in Switzerland. Results Between January 1, 2005 and August 27, 2020, 400,054 NSTEACS patients in the United Kingdom and 20,727 NSTEACS patients in Switzerland were included in the study. Discrimination of in-hospital death by the GRACE 2.0 score was good in male patients (area under the receiver operating characteristic curve [AUC] 0.86, 95% CI 0.86–0.86) and notably lower in male patients. female (0·82, 95% CI 0.81-0.82, p<0.0001). The GRACE 2.0 score underestimated the risk of in-hospital mortality in female patients, favoring their incorrect stratification to the low to intermediate risk group, for which the score does not indicate early invasive treatment. Taking into account sex differences, GRACE 3.0 showed superior discrimination and good calibration with an AUC of 0.91 (95% CI 0.89–0.92) in male patients and 0.87 (95% CI 0.89–0.92) in male patients. % 0.84–0.89 ) in female patients in an external cohort validation. GRACE 3·0 led to a clinically relevant reclassification of female patients to the high-risk group. Interpretation The GRACE 2.0 score has limited discriminatory performance and underestimates in-hospital mortality in female patients with NSTEACS. The GRACE 3.0 score performs better in men and women and reduces sex inequalities in risk stratification. Money Swiss National Science Foundation, Swiss Heart Foundation, Lindenhof Foundation, Foundation for Cardiovascular Research and Theodor-Ida-Herzog-Egli Foundation. |
Comments
Heart attacks are a leading cause of death worldwide, and women who suffer a heart attack have a higher mortality rate than men. This has been a cause of concern for cardiologists for decades and has generated controversy in the medical field over the causes and effects of potential gaps in treatment. The problem begins with the symptoms: unlike men, who often experience chest pain with radiation to the left arm, a heart attack in women usually manifests itself as abdominal pain that radiates to the back or as nausea and vomiting. Unfortunately, these symptoms are often misinterpreted by patients and healthcare personnel, with disastrous consequences.
The risk profile and clinical picture is 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 investigated the role of biological sex in heart attacks in more detail. “In fact, there are notable differences in the disease phenotype observed in women and men. Our study shows that women and men differ significantly in their risk factor profile upon hospital admission,” says Lüscher. When differences in age at admission and existing risk factors such as hypertension and diabetes are not taken into account, female patients with myocardial infarction have a higher mortality than male patients. “However, when these differences are statistically taken into account, women and men have similar mortality,” adds the cardiologist.
Current risk models favor undertreatment of female patients
In their study, published in the prestigious journal The Lancet , researchers from Switzerland and the United Kingdom analyzed data from 420,781 patients across Europe who had suffered the most common type of myocardial infarction. "The study shows that established risk models that guide current patient management are less accurate in women and favor undertreatment of patients," says first author Florian A. Wenzl from the Center for Molecular Medicine at UZH. . “Using a machine learning algorithm and the largest data sets in Europe, we were able to develop a novel AI-based risk score that 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
Many researchers and biotech companies agree that artificial intelligence and big data analytics are the next step on the path to personalized patient care. “Our study heralds the era 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 enormous potential in the application of artificial intelligence for the treatment of heart diseases in both male and female patients. “I hope that the implementation of this new score in treatment algorithms will refine current treatment strategies, reduce sex inequalities and ultimately improve the survival of heart attack patients, both men and women,” says Lüscher.
