PDF(Pubmed)
Abstract：
BACKGROUND: Warfarin dosing in cardiac surgery patients is complicated by a heightened sensitivity to the drug, predisposing patients to adverse events. Predictive algorithms are therefore needed to guide warfarin dosing in cardiac surgery patients.
OBJECTIVE: This study aimed to develop and validate an algorithm for predicting the warfarin dose needed to attain a therapeutic international normalized ratio (INR) at the time of discharge in cardiac surgery patients.
METHODS: We abstracted variables influencing warfarin dosage from the records of 1031 encounters initiating warfarin between April 1, 2011, and November 29, 2019, at St Michael\'s Hospital in Toronto, Ontario, Canada. We compared the performance of penalized linear regression, k-nearest neighbors, random forest regression, gradient boosting, multivariate adaptive regression splines, and an ensemble model combining the predictions of the 5 regression models. We developed and validated separate models for predicting the warfarin dose required for achieving a discharge INR of 2.0-3.0 in patients undergoing all forms of cardiac surgery except mechanical mitral valve replacement and a discharge INR of 2.5-3.5 in patients receiving a mechanical mitral valve replacement. For the former, we selected 80% of encounters (n=780) who had initiated warfarin during their hospital admission and had achieved a target INR of 2.0-3.0 at the time of discharge as the training cohort. Following 10-fold cross-validation, model accuracy was evaluated in a test cohort comprised solely of cardiac surgery patients. For patients requiring a target INR of 2.5-3.5 (n=165), we used leave-p-out cross-validation (p=3 observations) to estimate model performance. For each approach, we determined the mean absolute error (MAE) and the proportion of predictions within 20% of the true warfarin dose. We retrospectively evaluated the best-performing algorithm in clinical practice by comparing the proportion of cardiovascular surgery patients discharged with a therapeutic INR before (April 2011 and July 2019) and following (September 2021 and May 2, 2022) its implementation in routine care.
RESULTS: Random forest regression was the best-performing model for patients with a target INR of 2.0-3.0, an MAE of 1.13 mg, and 39.5% of predictions of falling within 20% of the actual therapeutic discharge dose. For patients with a target INR of 2.5-3.5, the ensemble model performed best, with an MAE of 1.11 mg and 43.6% of predictions being within 20% of the actual therapeutic discharge dose. The proportion of cardiovascular surgery patients discharged with a therapeutic INR before and following implementation of these algorithms in clinical practice was 47.5% (305/641) and 61.1% (11/18), respectively.
CONCLUSIONS: Machine learning algorithms based on routinely available clinical data can help guide initial warfarin dosing in cardiac surgery patients and optimize the postsurgical anticoagulation of these patients.
OBJECTIVE: This study aimed to develop and validate an algorithm for predicting the warfarin dose needed to attain a therapeutic international normalized ratio (INR) at the time of discharge in cardiac surgery patients.
METHODS: We abstracted variables influencing warfarin dosage from the records of 1031 encounters initiating warfarin between April 1, 2011, and November 29, 2019, at St Michael\'s Hospital in Toronto, Ontario, Canada. We compared the performance of penalized linear regression, k-nearest neighbors, random forest regression, gradient boosting, multivariate adaptive regression splines, and an ensemble model combining the predictions of the 5 regression models. We developed and validated separate models for predicting the warfarin dose required for achieving a discharge INR of 2.0-3.0 in patients undergoing all forms of cardiac surgery except mechanical mitral valve replacement and a discharge INR of 2.5-3.5 in patients receiving a mechanical mitral valve replacement. For the former, we selected 80% of encounters (n=780) who had initiated warfarin during their hospital admission and had achieved a target INR of 2.0-3.0 at the time of discharge as the training cohort. Following 10-fold cross-validation, model accuracy was evaluated in a test cohort comprised solely of cardiac surgery patients. For patients requiring a target INR of 2.5-3.5 (n=165), we used leave-p-out cross-validation (p=3 observations) to estimate model performance. For each approach, we determined the mean absolute error (MAE) and the proportion of predictions within 20% of the true warfarin dose. We retrospectively evaluated the best-performing algorithm in clinical practice by comparing the proportion of cardiovascular surgery patients discharged with a therapeutic INR before (April 2011 and July 2019) and following (September 2021 and May 2, 2022) its implementation in routine care.
RESULTS: Random forest regression was the best-performing model for patients with a target INR of 2.0-3.0, an MAE of 1.13 mg, and 39.5% of predictions of falling within 20% of the actual therapeutic discharge dose. For patients with a target INR of 2.5-3.5, the ensemble model performed best, with an MAE of 1.11 mg and 43.6% of predictions being within 20% of the actual therapeutic discharge dose. The proportion of cardiovascular surgery patients discharged with a therapeutic INR before and following implementation of these algorithms in clinical practice was 47.5% (305/641) and 61.1% (11/18), respectively.
CONCLUSIONS: Machine learning algorithms based on routinely available clinical data can help guide initial warfarin dosing in cardiac surgery patients and optimize the postsurgical anticoagulation of these patients.
摘要：
背景：在心脏手术患者中服用华法林会增加对药物的敏感性，诱发患者不良事件。因此需要预测算法来指导心脏手术患者的华法林给药。
目的：本研究旨在开发和验证一种算法，用于预测心脏手术患者出院时达到治疗国际标准化比率（INR）所需的华法林剂量。
方法：我们从2011年4月1日至2019年11月29日在多伦多圣迈克尔医院开始使用华法林的1031次相遇记录中提取了影响华法林剂量的变量，安大略省,加拿大。我们比较了惩罚线性回归的性能，k-最近的邻居，随机森林回归，梯度增强，多元自适应回归样条，以及结合5个回归模型预测的集成模型。我们开发并验证了单独的模型，用于预测接受所有形式心脏手术的患者的出院INR为2.0-3.0所需的华法林剂量，除了机械二尖瓣置换术和接受机械二尖瓣置换术的患者的出院INR为2.5-3.5。对于前者,我们选择了80%(n=780)在入院期间开始使用华法林,并且在出院时达到2.0-3.0的目标INR作为训练队列.经过10倍交叉验证，在仅由心脏手术患者组成的测试队列中评估了模型准确性.对于需要2.5-3.5目标INR的患者（n=165），我们使用离开p交叉验证(p=3个观察)来估计模型性能.对于每种方法，我们确定了平均绝对误差(MAE)和预测比例在华法林真实剂量的20%以内.我们通过比较在常规护理中实施治疗性INR之前（2011年4月和2019年7月）和之后（2021年9月和2022年5月2日）出院的心血管手术患者比例，回顾性评估了临床实践中表现最佳的算法。
结果：随机森林回归是目标INR为2.0-3.0，MAE为1.13mg的患者表现最佳的模型，39.5%的预测落在实际治疗出院剂量的20%以内。对于目标INR为2.5-3.5的患者，集成模型表现最好，MAE为1.11毫克，43.6%的预测在实际治疗出院剂量的20%以内。在临床实践中实施这些算法之前和之后，心血管手术患者出院的INR比例分别为47.5％（305/641）和61.1％（11/18），分别。
结论：基于常规可用临床数据的机器学习算法可以帮助指导心脏手术患者的初始华法林给药，并优化这些患者的术后抗凝治疗。
目的：本研究旨在开发和验证一种算法，用于预测心脏手术患者出院时达到治疗国际标准化比率（INR）所需的华法林剂量。
方法：我们从2011年4月1日至2019年11月29日在多伦多圣迈克尔医院开始使用华法林的1031次相遇记录中提取了影响华法林剂量的变量，安大略省,加拿大。我们比较了惩罚线性回归的性能，k-最近的邻居，随机森林回归，梯度增强，多元自适应回归样条，以及结合5个回归模型预测的集成模型。我们开发并验证了单独的模型，用于预测接受所有形式心脏手术的患者的出院INR为2.0-3.0所需的华法林剂量，除了机械二尖瓣置换术和接受机械二尖瓣置换术的患者的出院INR为2.5-3.5。对于前者,我们选择了80%(n=780)在入院期间开始使用华法林,并且在出院时达到2.0-3.0的目标INR作为训练队列.经过10倍交叉验证，在仅由心脏手术患者组成的测试队列中评估了模型准确性.对于需要2.5-3.5目标INR的患者（n=165），我们使用离开p交叉验证(p=3个观察)来估计模型性能.对于每种方法，我们确定了平均绝对误差(MAE)和预测比例在华法林真实剂量的20%以内.我们通过比较在常规护理中实施治疗性INR之前（2011年4月和2019年7月）和之后（2021年9月和2022年5月2日）出院的心血管手术患者比例，回顾性评估了临床实践中表现最佳的算法。
结果：随机森林回归是目标INR为2.0-3.0，MAE为1.13mg的患者表现最佳的模型，39.5%的预测落在实际治疗出院剂量的20%以内。对于目标INR为2.5-3.5的患者，集成模型表现最好，MAE为1.11毫克，43.6%的预测在实际治疗出院剂量的20%以内。在临床实践中实施这些算法之前和之后，心血管手术患者出院的INR比例分别为47.5％（305/641）和61.1％（11/18），分别。
结论：基于常规可用临床数据的机器学习算法可以帮助指导心脏手术患者的初始华法林给药，并优化这些患者的术后抗凝治疗。
