Determination Of Prevalence and Early Markers of Cardiovascular Disease Risk Factors in Women with Polycystic Ovary Syndrome (PCOS): An Artificial Intelligence-Based Predictive Modeling Approach
Year: 2026
Type: article
Abstract: This study presents a novel artificial intelligence-based framework for determining the prevalence and identifying early markers of cardiovascular disease risk factors in women with Polycystic Ovary Syndrome (PCOS). PCOS affects approximately 8-13% of reproductive-aged women worldwide and is associated with a significantly elevated risk of cardiovascular disease, yet early detection remains challenging due to the complex interplay of metabolic, hormonal, and inflammatory factors. This research leverages machine learning algorithms to analyze multidimensional clinical, biochemical, and imaging data to identify predictive biomarkers and quantify cardiovascular risk stratification. The proposed AI model integrates features including hormonal profiles, insulin resistance markers, lipid abnormalities, inflammatory biomarkers, and cardiovascular imaging parameters to establish prevalence patterns and early warning signatures. Findings from this approach demonstrate that AI-based predictive modeling can identify subclinical cardiovascular risk factors up to 5-7 years earlier than conventional screening methods, with particular emphasis on novel markers such as visceral adiposity index, lipoprotein particle profiles, and endothelial dysfunction biomarkers. The study further addresses critical ethical considerations including data privacy, algorithmic bias, and equitable access to AI-driven cardiovascular screening for diverse PCOS populations. This AI-powered methodology represents a paradigm shift in preventive cardiology for high-risk PCOS cohorts, enabling personalized intervention strategies and potentially reducing the long-term cardiovascular disease burden in this vulnerable population.
Authors: Agbetayo Oke Kehinde, Agbetayo Christianah Juwon; Oyedepo Kolade Emmanuel, Jaiyeola Joshua Sunday; Agboola Damilola Funmilola; Isijola Ibiso Bukola, Abiodun-Ojo Esther Olubukola; Owolabi Augustine Babajide; Aina Oluwole Olugbenga, Adaramodu Tosin Omolayo; Adeoba Oluwafemi Elisha; Adeoba O Esther
Institutions: Federal University Oye Ekiti, Ekiti State University
Language: English
Subfield: Reproductive Medicine
Field: Medicine
Domain: Health Sciences
Open Access status: bronze
OpenAlex ID: W7155163235
FWCI:
Cites:
Cited by:
Related to: