ImportanceRisk estimation is an integral part of cardiovascular care. Local recalibration of guideline-recommended models could address the limitations of existing tools.ObjectiveTo provide a machine learning (ML) approach to augment the performance of the American Heart Association’s Predicting Risk of Cardiovascular Disease Events (AHA-PREVENT) equations when applied to a local population while preserving clinical interpretability.Design, Setting, and ParticipantsThis cohort study used a New England–based electronic health record cohort of patients without prior atherosclerotic cardiovascular disease (ASCVD) who had the data necessary to calculate the AHA-PREVENT 10-year risk of developing ASCVD in the event period (2007-2016). Patients with prior ASCVD events, death prior to 2007, or age 79 years or older in 2007 were subsequently excluded. The final study population of 95 326 patients was split into 3 nonoverlapping subsets for training, testing, and validation. The AHA-PREVENT model was adapted to this local population using the open-source ML model (MLM) Extreme Gradient Boosting model (XGBoost) with minimal predictor variables, including age, sex, and AHA-PREVENT. The MLM was monotonically constrained to preserve known associations between risk factors and ASCVD risk. Along with sex, race and ethnicity data from the electronic health record were collected to validate the performance of ASCVD risk prediction in subgroups. Data were analyzed from August 2021 to February 2024.Main Outcomes and MeasuresConsistent with the AHA-PREVENT model, ASCVD events were defined as the first occurrence of either nonfatal myocardial infarction, coronary artery disease, ischemic stroke, or cardiovascular death. Cardiovascular death was coded via government registries. Discrimination, calibration, and risk reclassification were assessed using the Harrell C index, a modified Hosmer-Lemeshow goodness-of-fit test and calibration curves, and reclassification tables, respectively.ResultsIn the test set of 38 137 patients (mean [SD] age, 64.8 [6.9] years, 22 708 [59.5]% women and 15 429 [40.5%] men; 935 [2.5%] Asian, 2153 [5.6%] Black, 1414 [3.7%] Hispanic, 31 400 [82.3%] White, and 2235 [5.9%] other, including American Indian, multiple races, unspecified, and unrecorded, consolidated owing to small numbers), MLM-PREVENT had improved calibration (modified Hosmer-Lemeshow P > .05) compared to the AHA-PREVENT model across risk categories in the overall cohort (χ23 = 2.2; P = .53 vs χ23 > 16.3; P < .001) and sex subgroups (men: χ23 = 2.1; P = .55 vs χ23 > 16.3; P < .001; women: χ23 = 6.5; P = .09 vs. χ23 > 16.3; P < .001), while also surpassing a traditional recalibration approach. MLM-PREVENT maintained or improved AHA-PREVENT’s calibration in Asian, Black, and White individuals. Both MLM-PREVENT and AHA-PREVENT performed equally well in discriminating risk (approximate ΔC index, ±0.01). Using a clinically significant 7.5% risk threshold, MLM-PREVENT reclassified a total of 11.5% of patients. We visualize the recalibration through MLM-PREVENT ASCVD risk charts that highlight preserved risk associations of the original AHA-PREVENT model.Conclusions and RelevanceThe interpretable ML approach presented in this article enhanced the accuracy of the AHA-PREVENT model when applied to a local population while still preserving the risk associations found by the original model. This method has the potential to recalibrate other established risk tools and is implementable in electronic health record systems for improved cardiovascular risk assessment.

中文翻译：

---

为当地人群定制风险预测模型


重要性风险评估是心血管护理不可或缺的一部分。指南推荐模型的局部重新校准可以解决现有工具的局限性。目标提供一种机器学习 （ML） 方法，以增强美国心脏协会的心血管疾病事件预测风险 （AHA-PREVENT） 方程在应用于当地人群时的性能，同时保持临床可解释性。设计、设置和参与者该队列研究使用了一个位于新英格兰的电子健康记录队列，该队列患者既往没有动脉粥样硬化性心血管疾病 （ASCVD），他们拥有计算 AHA-PREVENT 在事件期间（2007-2016 年）发生 ASCVD 的 10 年风险所需的数据。既往有 ASCVD 事件、2007 年之前死亡或 2007 年年龄在 79 岁或以上的患者随后被排除在外。最终研究人群 95 326 名患者被分成 3 个不重叠的子集进行训练、测试和验证。AHA-PREVENT 模型使用开源 ML 模型 （MLM） 极端梯度提升模型 （XGBoost） 对这一当地人群进行了调整，该模型具有最小的预测变量，包括年龄、性别和 AHA-PREVENT。MLM 被单调约束以保留风险因素与 ASCVD 风险之间的已知关联。除了性别、种族和民族数据外，还收集了来自电子健康记录的数据，以验证 ASCVD 风险预测在亚组中的性能。主要结局和措施与 AHA-PREVENT 模型一致，ASCVD 事件定义为非致死性心肌梗死、冠状动脉疾病、缺血性中风或心血管死亡的首次发生。心血管死亡通过政府登记处进行编码。 分别使用 Harrell C 指数、改良的 Hosmer-Lemeshow 拟合优度检验和校准曲线以及重分类表评估鉴别、校准和风险重分类。结果在 38 137 名患者（平均 [SD] 年龄，64.8 [6.9] 岁，22 708 [59.5]% 女性和 15 429 [40.5%] 男性;935 [2.5%] 亚洲人，2153 [5.6%] 黑人，1414 [3.7%] 西班牙裔，31 400 [82.3%] 白人和 2235 [5.9%] 其他，包括美洲印第安人、多个种族、未指定和未记录，由于数字小而合并），MLM-PREVENT 在整个队列中跨风险类别（χ23 = 2.2;P = .53 vs χ23 >16.3;P < .001） 和性别亚群 （男性： χ23 = 2.1;P = .55 vs χ23 >16.3;P < .001;女性：χ23 = 6.5;P = .09 与 χ23 >16.3;P < .001），同时也超越了传统的重新校准方法。MLM-PREVENT 维持或改进了 AHA-PREVENT 对亚洲、黑人和白人个体的校准。MLM-PREVENT 和 AHA-PREVENT 在区分风险方面表现相同 （近似 ΔC 指数，±0.01）。使用具有临床意义的 7.5% 风险阈值，MLM-PREVENT 对总共 11.5% 的患者进行了重新分类。我们通过 MLM-PREVENT ASCVD 风险图表可视化重新校准，这些图表突出显示了原始 AHA-PREVENT 模型的保留风险关联。结论和相关性本文提出的可解释 ML 方法在应用于当地人群时提高了 AHA-PREVENT 模型的准确性，同时仍然保留了原始模型发现的风险关联。 这种方法有可能重新校准其他已建立的风险工具，并且可以在电子健康记录系统中实施，以改进心血管风险评估。