Colangelo Giorgio, Ribo Marc, Montiel Estefanía, Dominguez Didier, Olivé-Gadea Marta, Muchada Marian, Garcia-Tornel Álvaro, Requena Manuel, Pagola Jorge, Juega Jesús, Rodriguez-Luna David, Rodriguez-Villatoro Noelia, Rizzo Federica, Taborda Belén, Molina Carlos A, Rubiera Marta
Vall d'Hebron Research Institute, Passeig de la Vall d'Hebron, Barcelona, Spain (G.C., M. Ribo, M.O.-G., M.M., Á.G.-T., M. Requena, J.P., J.J., D.R.-L., N.R.-V., F.R., B.T., C.A.M., M. Rubiera).
Nora Health, Passeig de la Vall d'Hebron, Barcelona, Spain (G.C., E.M.).
Stroke. 2024 May;55(5):1200-1209. doi: 10.1161/STROKEAHA.123.043691. Epub 2024 Mar 28.
Predicting stroke recurrence for individual patients is difficult, but individualized prediction may improve stroke survivors' engagement in self-care. We developed PRERISK: a statistical and machine learning classifier to predict individual risk of stroke recurrence.
We analyzed clinical and socioeconomic data from a prospectively collected public health care-based data set of 41 975 patients admitted with stroke diagnosis in 88 public health centers over 6 years (2014-2020) in Catalonia-Spain. A new stroke diagnosis at least 24 hours after the index event was considered as a recurrent stroke, which was considered as our outcome of interest. We trained several supervised machine learning models to provide individualized risk over time and compared them with a Cox regression model. Models were trained to predict early, late, and long-term recurrence risk, within 90, 91 to 365, and >365 days, respectively. C statistics and area under the receiver operating characteristic curve were used to assess the accuracy of the models.
Overall, 16.21% (5932 of 36 114) of patients had stroke recurrence during a median follow-up of 2.69 years. The most powerful predictors of stroke recurrence were time from previous stroke, Barthel Index, atrial fibrillation, dyslipidemia, age, diabetes, and sex, which were used to create a simplified model with similar performance, together with modifiable vascular risk factors (glycemia, body mass index, high blood pressure, cholesterol, tobacco dependence, and alcohol abuse). The areas under the receiver operating characteristic curve were 0.76 (95% CI, 0.74-0.77), 0.60 (95% CI, 0.58-0.61), and 0.71 (95% CI, 0.69-0.72) for early, late, and long-term recurrence risk, respectively. The areas under the receiver operating characteristic curve of the Cox risk class probability were 0.73 (95% CI, 0.72-0.75), 0.59 (95% CI, 0.57-0.61), and 0.67 (95% CI, 0.66-0.70); machine learning approaches (random forest and AdaBoost) showed statistically significant improvement (<0.05) over the Cox model for the 3 recurrence time periods. Stroke recurrence curves can be simulated for each patient under different degrees of control of modifiable factors.
PRERISK is a novel approach that provides a personalized and fairly accurate risk prediction of stroke recurrence over time. The model has the potential to incorporate dynamic control of risk factors.
预测个体患者的卒中复发情况具有挑战性，但个体化预测可能会提高卒中幸存者自我护理的参与度。我们开发了PRERISK：一种用于预测卒中复发个体风险的统计和机器学习分类器。
我们分析了来自西班牙加泰罗尼亚地区88个公共卫生中心在6年（2014 - 2020年）期间前瞻性收集的以公共卫生保健为基础的数据集，该数据集包含41975例因卒中诊断入院的患者的临床和社会经济数据。在索引事件至少24小时后出现的新卒中诊断被视为复发性卒中，这被视为我们感兴趣的结果。我们训练了多个监督机器学习模型以提供随时间变化的个体化风险，并将它们与Cox回归模型进行比较。模型被训练用于分别预测90天内、91至365天以及超过365天的早期、晚期和长期复发风险。C统计量和受试者操作特征曲线下面积用于评估模型的准确性。
总体而言，在中位随访2.69年期间，16.21%（36114例中的5932例）患者出现卒中复发。卒中复发的最强预测因素是距上次卒中的时间、Barthel指数、心房颤动、血脂异常、年龄、糖尿病和性别，这些因素与可改变的血管危险因素（血糖、体重指数、高血压、胆固醇、烟草依赖和酒精滥用）一起被用于创建一个性能相似的简化模型。早期、晚期和长期复发风险的受试者操作特征曲线下面积分别为0.76（95%CI，0.74 - 0.77）、0.60（95%CI，0.58 - 0.61）和0.71（95%CI，0.69 - 0.72）。Cox风险类别概率的受试者操作特征曲线下面积分别为0.73（95%CI，0.72 - 0.75）、0.59（95%CI，0.57 - 0.61）和0.67（95%CI，0.66 - 0.70）；机器学习方法（随机森林和AdaBoost）在三个复发时间段内相对于Cox模型显示出统计学上的显著改善（<0.05）。可以针对每个患者在不同程度地控制可改变因素的情况下模拟卒中复发曲线。
PRERISK是一种新颖的方法，可随时间提供个性化且相当准确的卒中复发风险预测。该模型具有纳入危险因素动态控制的潜力。
