Application of the VIRGO taxonomy to differentiate acute myocardial infarction in young women

Characteristics of Young Women Presenting With Acute Myocardial Infarction: The Prospective, Multicenter, Observational Young Women Presenting Acute Myocardial Infarction in France Study

BACKGROUND

The percentage of women <50 years of age hospitalized with myocardial infarction is increasing. We describe the clinical, morphological, and biological characteristics, as well as the clinical outcomes of this population.

METHODS AND RESULTS

This prospective, observational study included consecutive women <50 years of age admitted for myocardial infarction at 30 centers in France (May 2017-June 2019). The primary outcome was the composite of net adverse clinical events: all-cause death, cardiovascular death, recurrent myocardial infarction, stent thrombosis, any stroke, or major bleeding occurring during hospitalization with a 12-month follow up. Three hundred fourteen women were included. The mean age was 43.0 (±5.7) years, 60.8% presented with ST-segment-elevation myocardial infarction, 75.5% were current smokers, 31.2% had a history of complicated pregnancy, and 55.1% reported recent emotional stress. Most (91.6%) women presented with typical chest pain. Of patients on an estrogen-containing contraceptive, 86.0% had at least 1 contraindication. Of patients with ST-segment-elevation myocardial infarction, 17.8% had myocardial infarction with nonobstructive coronary arteries and 14.6% had spontaneous coronary artery dissection, whereas 29.3% presented with multivessel vessel disease. During hospitalization, 11 net adverse clinical events occurred in 9 (2.8%) women, but no deaths or stent thromboses occurred. By 12 months, 14 net adverse clinical events occurred in 10 (3.2%) women; 2 (0.6%) died (from progressive cancer) and 25 (7.9%) had an ischemia-driven repeat percutaneous coronary intervention.

CONCLUSIONS

Most young women with myocardial infarction reported typical chest pain and had modifiable cardiovascular risk factors. History of adverse pregnancy outcomes and prescription of combined oral contraceptive despite a contraindication were prevalent, emphasizing the need for comprehensive cardiological and gynecological evaluation and follow-up.

REGISTRATION

URL: https://www.clinicaltrials.gov; Unique identifier: NCT03073447.

Imaging of heart disease in women: review and case presentation

Cardiovascular diseases (CVD) remain the leading cause of mortality worldwide. Although major diagnostic and therapeutic advances have significantly improved the prognosis of patients with CVD in the past decades, these advances have less benefited women than age-matched men. Noninvasive cardiac imaging plays a key role in the diagnosis of CVD. Despite shared imaging features and strategies between both sexes, there are critical sex disparities that warrant careful consideration, related to the selection of the most suited imaging techniques, to technical limitations, and to specific diseases that are overrepresented in the female population. Taking these sex disparities into consideration holds promise to improve management and alleviate the burden of CVD in women. In this review, we summarize the specific features of cardiac imaging in four of the most common presentations of CVD in the female population including coronary artery disease, heart failure, pregnancy complications, and heart disease in oncology, thereby highlighting contemporary strengths and limitations. We further propose diagnostic algorithms tailored to women that might help in selecting the most appropriate imaging modality.

Taxonomy-based data representation for data mining: an example of the magnitude of risk associated with H. pylori infection

BACKGROUND

The amount of available and potentially significant data describing study subjects is ever growing with the introduction and integration of different registries and data banks. The single specific attribute of these data are not always necessary; more often, membership to a specific group (e.g. diet, social 'bubble', living area) is enough to build a successful machine learning or data mining model without overfitting it. Therefore, in this article we propose an approach to building taxonomies using clustering to replace detailed data from large heterogenous data sets from different sources, while improving interpretability. We used the GISTAR study data base that holds exhaustive self-assessment questionnaire data to demonstrate this approach in the task of differentiating between H. pylori positive and negative study participants, and assessing their potential risk factors. We have compared the results of taxonomy-based classification to the results of classification using raw data.

RESULTS

Evaluation of our approach was carried out using 6 classification algorithms that induce rule-based or tree-based classifiers. The taxonomy-based classification results show no significant loss in information, with similar and up to 2.5% better classification accuracy. Information held by 10 and more attributes can be replaced by one attribute demonstrating membership to a cluster in a hierarchy at a specific cut. The clusters created this way can be easily interpreted by researchers (doctors, epidemiologists) and describe the co-occurring features in the group, which is significant for the specific task.

CONCLUSIONS

While there are always features and measurements that must be used in data analysis as they are, the use of taxonomies for the description of study subjects in parallel allows using membership to specific naturally occurring groups and their impact on an outcome. This can decrease the risk of overfitting (picking attributes and values specific to the training set without explaining the underlying conditions), improve the accuracy of the models, and improve privacy protection of study participants by decreasing the amount of specific information used to identify the individual.