Predicting Atrial Fibrillation Recurrence by Combining Population Data and Virtual Cohorts of Patient-Specific Left Atrial Models.
Predicting Atrial Fibrillation Recurrence by Combining Population Data and Virtual Cohorts of Patient-Specific Left Atrial Models.
复制标题
DOI：
10.1161/circep.121.010253
复制
发表时间：
2022-03
期刊：
影响因子：
--
通讯作者：
Niederer SA
中科院分区：
文献类型：
--
作者：
Roney CH;Sim I;Yu J;Beach M;Mehta A;Alonso Solis-Lemus J;Kotadia I;Whitaker J;Corrado C;Razeghi O;Vigmond E;Narayan SM;O'Neill M;Williams SE;Niederer SA
文本中提供了补充数字内容。目前的房颤消融治疗效果不佳，且长期疗效难以预测。临床试验确定的床边特性只能对人群的长期反应提供适度的预测，而小群体中的患者特异性模型主要解释消融的急性反应。我们的目的是通过编码更多的个体间变异性，使用机器学习来补充生物物理模拟，从而预测大群体消融后的长期房颤复发。为 100 名接受首次消融的房颤患者（43 名阵发性房颤、41 名持续性房颤和 16 名长期持续性房颤）构建了患者特异性模型。使用动态心电图监测对患者进行为期 1 年的随访。每个患者特定的生物物理模型结合了不同的纤维化模式、纤维取向图、电特性和消融模式，以捕获心房特性的不确定性并测试组织维持颤动的能力。对不同模型变体的这些模拟压力测试进行后处理，以计算心房颤动模拟指标。机器学习分类器经过训练，可以使用患者病史、影像学和心房颤动模拟指标的特征来预测心房颤动复发。我们在 100 个患者特定模型中进行了 1100 次房颤消融模拟。仅基于模拟压力测试的模型显示预测长期颤动复发的最大准确度为 0.63。经过历史、成像和模拟压力测试训练的分类器（平均 10 倍交叉验证曲线下面积，0.85±0.09；召回率，0.80±0.13；精度，0.74±0.13）优于经过历史和成像训练的分类器（曲线下面积，0.66±0.17）或仅历史（曲线下面积， 0.61±0.14）。一种新颖的计算流程通过将结果数据与患者特定的急性模拟反应相结合，准确预测个体患者的长期房颤复发。这项技术可以帮助个性化选择房颤消融术。
Supplemental Digital Content is available in the text. Current ablation therapy for atrial fibrillation is suboptimal, and long-term response is challenging to predict. Clinical trials identify bedside properties that provide only modest prediction of long-term response in populations, while patient-specific models in small cohorts primarily explain acute response to ablation. We aimed to predict long-term atrial fibrillation recurrence after ablation in large cohorts, by using machine learning to complement biophysical simulations by encoding more interindividual variability. Patient-specific models were constructed for 100 atrial fibrillation patients (43 paroxysmal, 41 persistent, and 16 long-standing persistent), undergoing first ablation. Patients were followed for 1 year using ambulatory ECG monitoring. Each patient-specific biophysical model combined differing fibrosis patterns, fiber orientation maps, electrical properties, and ablation patterns to capture uncertainty in atrial properties and to test the ability of the tissue to sustain fibrillation. These simulation stress tests of different model variants were postprocessed to calculate atrial fibrillation simulation metrics. Machine learning classifiers were trained to predict atrial fibrillation recurrence using features from the patient history, imaging, and atrial fibrillation simulation metrics. We performed 1100 atrial fibrillation ablation simulations across 100 patient-specific models. Models based on simulation stress tests alone showed a maximum accuracy of 0.63 for predicting long-term fibrillation recurrence. Classifiers trained to history, imaging, and simulation stress tests (average 10-fold cross-validation area under the curve, 0.85±0.09; recall, 0.80±0.13; precision, 0.74±0.13) outperformed those trained to history and imaging (area under the curve, 0.66±0.17) or history alone (area under the curve, 0.61±0.14). A novel computational pipeline accurately predicted long-term atrial fibrillation recurrence in individual patients by combining outcome data with patient-specific acute simulation response. This technique could help to personalize selection for atrial fibrillation ablation.