DOI 10.3389/fphar.2026.1870914
Evaluation and AI-powered prediction of the efficacy of alirocumab use among patients with cardiovascular disease.
Аннотация
BACKGROUND
Elevated low-density lipoprotein cholesterol (LDL-C) is a major risk factor for atherosclerotic cardiovascular disease (ASCVD). Despite statins and ezetimibe, many high-risk patients fail to reach lipid targets. Alirocumab, a PCSK9 inhibitor, is an effective alternative, but real-world data are limited.
OBJECTIVES
This study evaluated the real-world effectiveness of Alirocumab in improving lipid profiles among patients with established cardiovascular disease and assessed the impact of patient characteristics, comorbidities, and concurrent medications. Additionally, artificial intelligence (AI) models were explored to predict treatment outcomes.
METHODS
A retrospective observational study was conducted at the Royal Commission Health Services Program in Aljubail, Saudi-Arabia. Data from 206 adults receiving Alirocumab (75 mg every 2 weeks) from July 2021 to July 2023 were analyzed. Lipid profiles were assessed at baseline, 12 weeks, and 24 weeks. Logistic regression identified factors associated with lipid target achievement. Machine learning models including Logistic-Regression, K-Neighbors, XGBoost, Support Vector Machine (SVM), Gaussian Naive Bayes, Decision Tree, and Random Forest were used to predict outcomes, and an AI-based SVM tool was developed as an exploratory research prototype.
RESULTS
Alirocumab significantly reduced LDL-C, total cholesterol, and triglycerides while increasing HDL-C at 12 and 24 weeks (p < 0.001). Ezetimibe and metformin improved lipid outcomes, whereas aspirin and anticoagulants were associated with lower target achievement. AI model accuracies ranged from 0.50 to 0.63, with the SVM classifier performing best (accuracy 0.625, F1 score 0.61).
CONCLUSION
Alirocumab is effective in lowering lipids in real-world cardiovascular patients. Certain medications may enhance outcomes. AI models provide moderate predictive ability, supporting potential personalized treatment strategies.
Подготовка и перевод публикации
Обработка статьи · этапы, ошибки и управление
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Тип публикации указан по данным источника. Уровень доказательности автоматически не присваивается.