Liverpool Centre for Cardiovascular Science at University of Liverpool, Liverpool John Moores University and Liverpool Heart and Chest Hospital, Liverpool, L7 8TX, UK.
Danish Center for Clinical Health Services Research, Department of Clinical Medicine, Aalborg University, Aalborg, Denmark.
Intern Emerg Med. 2023 Aug;18(5):1373-1383. doi: 10.1007/s11739-023-03297-6. Epub 2023 Jun 9.
There is limited information on predicting incident cardiovascular outcomes among high- to very high-risk populations such as the elderly (≥ 65 years) in the absence of prior cardiovascular disease and the presence of non-cardiovascular multi-morbidity. We hypothesized that statistical/machine learning modeling can improve risk prediction, thus helping inform care management strategies. We defined a population from the Medicare health plan, a US government-funded program mostly for the elderly and varied levels of non-cardiovascular multi-morbidity. Participants were screened for cardiovascular disease (CVD), coronary or peripheral artery disease (CAD or PAD), heart failure (HF), atrial fibrillation (AF), ischemic stroke (IS), transient ischemic attack (TIA), and myocardial infarction (MI) for a 3-yr period in the comorbid history. They were followed up for up to 45.2 months. Analyses included descriptive approaches in terms of incidence rates and density ratios, and inferential in terms of main effect statistical/complex machine learning modeling. The contemporary risk factors of interest spanned across the domains of comorbidity, lifestyle, and healthcare utilization history. The cohort consisted of 154,551 individuals (mean age 68.8 years; 62.2% female). The overall crude incidence rate of CVD events was 9.9 new cases per 100 person-years. The highest rates among its component outcomes were obtained for CAD or PAD (3.6 for each), followed by HF (2.2) and AF (1.8), then IS (1.3), and finally TIA (1.0) and MI (0.9).Model performance was modest in terms of discriminatory power (C index: 0.67, 95%CI 0.667-0.674 for training; and 0.668, 95%CI 0.663-0.673 for validation data), equal agreement between predicted and observed events for calibration purposes, and good clinical utility in terms of a net benefit of 15 true positives per 100 patients relative to the All-patient treatment strategy. Complex models based on machine learning algorithms yielded incrementally better discriminatory power and much improved goodness-of-fitness tests from those based on main effect statistical modeling. This Medicare population represents a highly vulnerable group for incident CVD events. This population would benefit from an integrated approach to their care and management, including attention to their comorbidities and lifestyle factors, as well as medication adherence.
对于没有先前心血管疾病且存在非心血管多种合并症的高风险至极高风险人群（如≥65 岁的老年人），预测心血管事件的发生率的信息有限。我们假设统计/机器学习模型可以改善风险预测，从而帮助制定护理管理策略。我们从医疗保险健康计划（Medicare health plan）中定义了一个人群，这是一个美国政府资助的计划，主要面向老年人和不同程度的非心血管多种合并症。在 3 年的共病史中，参与者接受了心血管疾病（CVD）、冠状动脉或外周动脉疾病（CAD 或 PAD）、心力衰竭（HF）、心房颤动（AF）、缺血性中风（IS）、短暂性脑缺血发作（TIA）和心肌梗死（MI）的筛查。他们的随访时间最长可达 45.2 个月。分析包括发生率和密度比方面的描述性方法，以及主要效应统计/复杂机器学习模型方面的推断性方法。当前关注的风险因素跨越了合并症、生活方式和医疗保健利用史等领域。该队列由 154551 人组成（平均年龄 68.8 岁；62.2%为女性）。CVD 事件的总体粗发生率为每 100 人年 9.9 例新发病例。其各组成部分结局的最高发生率为 CAD 或 PAD（各 3.6），其次是 HF（2.2）和 AF（1.8），然后是 IS（1.3），最后是 TIA（1.0）和 MI（0.9）。从区分能力来看，模型性能一般（C 指数：训练时为 0.67，95%CI 0.667-0.674；验证数据为 0.668，95%CI 0.663-0.673），校准目的预测与观察事件之间的一致性相等，从主要效应统计建模的增量更好的区分能力和改进的拟合优度检验，根据相对于所有患者治疗策略的每 100 例患者 15 例真实阳性的净获益，具有良好的临床实用性。基于机器学习算法的复杂模型产生了更好的区分能力和拟合优度检验，优于基于主要效应统计建模的模型。该医疗保险人群代表了心血管事件发生率高的脆弱人群。此类人群将从其护理和管理的综合方法中受益，包括关注他们的合并症和生活方式因素以及药物依从性。
