Biomedical Engineering Department, Michigan Technological University, Houghton, MI, USA.
Department of Civil, Environmental and Geospatial Engineering, Michigan Technological University, Houghton, MI, USA.
Ann Biomed Eng. 2022 Aug;50(8):941-950. doi: 10.1007/s10439-022-02971-8. Epub 2022 Apr 26.
Predicting potential complications after aortic valve replacement (AVR) is a crucial task that would help pre-planning procedures. The goal of this work is to generate data-driven models based on logistic regression, where the probability of developing transvalvular pressure gradient (DP) that exceeds 20 mmHg under different physiological conditions can be estimated without running extensive experimental or computational methods. The hemodynamic assessment of a 26 mm SAPIEN 3 transcatheter aortic valve and a 25 mm Magna Ease surgical aortic valve was performed under pulsatile conditions of a large range of systolic blood pressures (SBP; 100-180 mmHg), diastolic blood pressures (DBP; 40-100 mmHg), and heart rates of 60, 90 and 120 bpm. Logistic regression modeling was used to generate a predictive model for the probability of having a DP > 20 mmHg for both valves under different conditions. Experiments on different pressure conditions were conducted to compare the probabilities of the generated model and those obtained experimentally. To test the accuracy of the predictive model, the receiver operation characteristics curves were generated, and the areas under the curve (AUC) were calculated. The probabilistic predictive model of DP > 20 mmHg was generated with parameters specific to each valve. The AUC obtained for the SAPIEN 3 DP model was 0.9465 and that for Magna Ease was 0.9054 indicating a high model accuracy. Agreement between the DP probabilities obtained between experiments and predictive model was found. This model is a first step towards developing a larger statistical and data-driven model that can inform on certain valves reliability during AVR pre-procedural planning.
预测主动脉瓣置换术 (AVR) 后的潜在并发症是一项至关重要的任务，有助于预先规划手术。本工作的目的是基于逻辑回归生成数据驱动的模型，在不进行广泛的实验或计算方法的情况下，可以根据不同的生理条件预测发生跨瓣压力梯度 (DP) 超过 20mmHg 的概率。在大范围的收缩压 (SBP；100-180mmHg)、舒张压 (DBP；40-100mmHg) 和心率为 60、90 和 120bpm 的脉动条件下，对 26mm SAPIEN 3 经导管主动脉瓣和 25mm Magna Ease 外科主动脉瓣进行了血流动力学评估。使用逻辑回归建模生成了在不同条件下两种瓣膜 DP>20mmHg 的概率预测模型。对不同压力条件下的实验进行了比较，以比较生成模型和实验获得的概率。为了测试预测模型的准确性，生成了接收器操作特性曲线，并计算了曲线下面积 (AUC)。针对每个瓣膜生成了 DP>20mmHg 的概率预测模型。SAPIEN 3 DP 模型的 AUC 为 0.9465，Magna Ease 的 AUC 为 0.9054，表明模型准确性较高。实验和预测模型获得的 DP 概率之间存在一致性。该模型是开发更大的统计和数据驱动模型的第一步，该模型可以为 AVR 术前规划提供有关某些瓣膜可靠性的信息。
