CARAMEL: Retrospective Study for Personalized Risk Assessment of Cardiovascular Disease in Menopausal and Perimenopausal Women Using Real World Data

Launched by HOSPITAL UNIVERSITARIO VIRGEN MACARENA · May 22, 2025

Keywords

ClinConnect Summary

The CARAMEL trial is studying how to better predict the risk of heart disease in women who are going through menopause or are in the years leading up to it, between the ages of 40 and 60. The researchers want to create personalized risk assessments by analyzing real-world data, which includes electronic health records and various medical imaging results. This study will focus on understanding specific risk factors that affect women differently and using advanced technology, like artificial intelligence, to improve predictions about heart health issues, such as high blood pressure and cholesterol problems.

To be eligible for this study, participants need to identify as female and be aged between 40 and 60 at the time their health data was collected. They must also have at least five to six years of health records available, which show that they have had medical visits or tests during that time. The goal of the trial is to develop new tools that can help doctors provide better care tailored to women's unique health needs, ultimately aiming to reduce the incidence of heart disease in this population. While the trial is not yet recruiting participants, it's an important step toward improving health outcomes for menopausal and perimenopausal women.

Gender

FEMALE

Eligibility criteria

• Inclusion Criteria:
• • Self-identified as female in the electronic health record (EHR). Age between 40 and 60 years at the time of data collection/index date. Availability of at least 5-6 years of retrospective data in the EHR, depending on the research objective.
• • At least one healthcare encounter (visit, imaging, lab test, diagnosis, etc.) within the defined age range.
• • For imaging substudies (e.g., RO3-RO5): availability of at least one relevant imaging test (e.g., DXA, digital mammography, cMRI, CCTA, US) during the age range.
• • For signal-based analysis (RO6): presence of ECG monitoring data from implanted devices and at least 2 years of follow-up.
• Exclusion Criteria:
• • Prior diagnosis of cardiovascular disease before the observation window (only applicable to specific ROs, e.g., RO2, RO4).
• • Insufficient data quality or missing key variables needed for modeling (e.g., absence of blood pressure or lipid profile).
• • Patients with incomplete or inconsistent records (e.g., duplicate IDs, mismatched time frames).
• • For signal-based RO6: hospitalizations or diagnoses unrelated to cardiovascular health that may bias AI model training.