Orr R K
Department of Surgery, Fallon Healthcare System, Worcester, MA 01606, USA.
Med Decis Making. 1997 Apr-Jun;17(2):178-85. doi: 10.1177/0272989X9701700208.
To develop a probabilistic neural network (PNN) to estimate mortality risk following cardiac surgery.
The PNN model was created using an institutional database obtained as part of routine quality assurance activity. Patient records (from 1991 to 1993) were randomly divided into training (n = 732) and validation (n = 380) sets. The model uses seven variables, each obtainable during routine clinical patient care. After completion of the initial validation phase, newer data (1994) became available and were used as an independent source of validation (n = 365).
1,477 consecutive cardiac surgery patients operated on in a teaching hospital during a four-year period (1991-94).
The overall accuracy of the neural network was 91.5% in the training set; it was 92.3% in the validation set. The model was well calibrated (p = 0.21 for the Hosmer-Lemeshow goodness-of-fit test) and discriminated well (areas under the ROC curves were 0.72 and 0.81 for the training and validation sets). The trained network also performed well on the 1994 data (ROC = 0.74, p = 0.19 for the Hosmer-Lemeshow test), albeit with a slight decrement in overall accuracy (88.2%).
A neural network may be implemented to estimate mortality risk following cardiac surgery. Implementation is relatively rapid, and it is an alternative to standard statistical approaches.
开发一种概率神经网络（PNN）以估计心脏手术后的死亡风险。
PNN模型是使用作为常规质量保证活动一部分获得的机构数据库创建的。患者记录（1991年至1993年）被随机分为训练集（n = 732）和验证集（n = 380）。该模型使用七个变量，每个变量在常规临床患者护理期间均可获得。在初始验证阶段完成后，有了更新的数据（1994年）并将其用作独立的验证来源（n = 365）。
在四年期间（1991 - 94年）于一家教学医院接受手术的1477例连续心脏手术患者。
神经网络在训练集中的总体准确率为91.5%；在验证集中为92.3%。该模型校准良好（Hosmer-Lemeshow拟合优度检验的p = 0.21）且区分能力良好（训练集和验证集的ROC曲线下面积分别为0.72和0.81）。训练后的网络在1994年的数据上也表现良好（ROC = 0.74，Hosmer-Lemeshow检验的p = 0.19），尽管总体准确率略有下降（88.2%）。
可以实施神经网络来估计心脏手术后的死亡风险。实施相对快速，并且是标准统计方法的一种替代方法。
