Macrina Francesco, Puddu Paolo Emilio, Sciangula Alfonso, Trigilia Fausto, Totaro Marco, Miraldi Fabio, Toscano Francesca, Cassese Mauro, Toscano Michele
Department of the Heart and Great Vessels "Attilio Reale", UOC of Cardiac Surgery.
Open Cardiovasc Med J. 2009 Jul 7;3:81-95. doi: 10.2174/1874192400903010081.
There are few comparative reports on the overall accuracy of neural networks (NN), assessed only versus multiple logistic regression (LR), to predict events in cardiovascular surgery studies and none has been performed among acute aortic dissection (AAD) Type A patients.
We aimed at investigating the predictive potential of 30-day mortality by a large series of risk factors in AAD Type A patients comparing the overall performance of NN versus LR.
We investigated 121 plus 87 AAD Type A patients consecutively operated during 7 years in two Centres. Forced and stepwise NN and LR solutions were obtained and compared, using receiver operating characteristic area under the curve (AUC) and their 95% confidence intervals (CI) and Gini's coefficients. Both NN and LR models were re-applied to data from the second Centre to adhere to a methodological imperative with NN.
Forced LR solutions provided AUC 87.9±4.1% (CI: 80.7 to 93.2%) and 85.7±5.2% (CI: 78.5 to 91.1%) in the first and second Centre, respectively. Stepwise NN solution of the first Centre had AUC 90.5±3.7% (CI: 83.8 to 95.1%). The Gini's coefficients for LR and NN stepwise solutions of the first Centre were 0.712 and 0.816, respectively. When the LR and NN stepwise solutions were re-applied to the second Centre data, Gini's coefficients were, respectively, 0.761 and 0.850. Few predictors were selected in common by LR and NN models: the presence of pre-operative shock, intubation and neurological symptoms, immediate post-operative presence of dialysis in continuous and the quantity of post-operative bleeding in the first 24 h. The length of extracorporeal circulation, post-operative chronic renal failure and the year of surgery were specifically detected by NN.
Different from the International Registry of AAD, operative and immediate post-operative factors were seen as potential predictors of short-term mortality. We report a higher overall predictive accuracy with NN than with LR. However, the list of potential risk factors to predict 30-day mortality after AAD Type A by NN model is not enlarged significantly.
在心血管外科研究中，关于神经网络（NN）整体准确性的比较报告较少，仅与多重逻辑回归（LR）进行比较，且在急性A型主动脉夹层（AAD）患者中尚未进行此类比较。
我们旨在通过一系列危险因素研究A型主动脉夹层患者30天死亡率的预测潜力，比较神经网络与逻辑回归的整体性能。
我们对两个中心7年间连续接受手术的121例加87例A型主动脉夹层患者进行了研究。获得并比较了强制和逐步的神经网络及逻辑回归解决方案，使用曲线下面积（AUC）及其95%置信区间（CI）和基尼系数。神经网络和逻辑回归模型均重新应用于第二个中心的数据，以遵循神经网络的方法要求。
在第一个中心，强制逻辑回归解决方案的AUC为87.9±4.1%（CI：80.7至93.2%），在第二个中心为85.7±5.2%（CI：78.5至91.1%）。第一个中心的逐步神经网络解决方案的AUC为90.5±3.7%（CI：83.8至95.1%）。第一个中心逻辑回归和神经网络逐步解决方案的基尼系数分别为0.712和0.816。当将逻辑回归和神经网络逐步解决方案重新应用于第二个中心的数据时，基尼系数分别为0.761和0.850。逻辑回归和神经网络模型共同选择的预测因素较少：术前休克、插管和神经症状的存在、术后立即持续进行透析以及术后24小时内的出血量。神经网络特别检测到体外循环时间、术后慢性肾功能衰竭和手术年份。
与国际主动脉夹层注册研究不同，手术及术后即刻因素被视为短期死亡率的潜在预测因素。我们报告神经网络的整体预测准确性高于逻辑回归。然而，神经网络模型预测A型主动脉夹层术后30天死亡率的潜在危险因素列表并未显著扩大。
