Bottaci L, Drew P J, Hartley J E, Hadfield M B, Farouk R, Lee P W, Macintyre I M, Duthie G S, Monson J R
Department of Computer Science, University of Hull.
Lancet. 1997 Aug 16;350(9076):469-72. doi: 10.1016/S0140-6736(96)11196-X.
Artificial neural networks are computer programs that can be used to discover complex relations within data sets. They permit the recognition of patterns in complex biological data sets that cannot be detected with conventional linear statistical analysis. One such complex problem is the prediction of outcome for individual patients treated for colorectal cancer. Predictions of outcome in such patients have traditionally been based on population statistics. However, these predictions have little meaning for the individual patient. We report the training of neural networks to predict outcome for individual patients from one institution and their predictive performance on data from a different institution in another region.
5-year follow-up data from 334 patients treated for colorectal cancer were used to train and validate six neural networks designed for the prediction of death within 9, 12, 15, 18, 21, and 24 months. The previously trained 12-month neural network was then applied to 2-year follow-up data from patients from a second institution; outcome was concealed. No further training of the neural network was undertaken. The network's predictions were compared with those of two consultant colorectal surgeons supplied with the same data.
All six neural networks were able to achieve overall accuracy greater than 80% for the prediction of death for individual patients at institution 1 within 9, 12, 15, 18, 21, and 24 months. The mean sensitivity and specificity were 60% and 88%. When the neural network trained to predict death within 12 months was applied to data from the second institution, overall accuracy of 90% (95% CI 84-96) was achieved, compared with the overall accuracy of the colorectal surgeons of 79% (71-87) and 75% (66-84).
The neural networks were able to predict outcome for individual patients with colorectal cancer much more accurately than the currently available clinicopathological methods. Once trained on data from one institution, the neural networks were able to predict outcome for patients from an unrelated institution.
人工神经网络是一种计算机程序，可用于发现数据集中的复杂关系。它们能够识别复杂生物数据集中的模式，而这些模式是传统线性统计分析无法检测到的。其中一个复杂问题是预测接受结直肠癌治疗的个体患者的预后。传统上，此类患者的预后预测是基于群体统计数据。然而，这些预测对个体患者而言意义不大。我们报告了训练神经网络以预测来自一个机构的个体患者的预后，以及它们对来自另一个地区不同机构的数据的预测性能。
使用334例接受结直肠癌治疗患者的5年随访数据来训练和验证六个神经网络，这些网络旨在预测9、12、15、18、21和24个月内的死亡情况。然后将先前训练的12个月神经网络应用于来自第二个机构患者的2年随访数据；结果是保密的。未对神经网络进行进一步训练。将该网络的预测结果与两名提供相同数据的结直肠外科顾问医生的预测结果进行比较。
所有六个神经网络在预测机构1中个体患者在9、12、15、18、21和24个月内的死亡情况时，总体准确率均能超过80%。平均敏感性和特异性分别为60%和88%。当将训练用于预测12个月内死亡情况的神经网络应用于第二个机构的数据时，总体准确率达到了90%（95%置信区间84 - 96），相比之下，结直肠外科医生的总体准确率分别为79%（71 - 87）和75%（66 - 84）。
神经网络能够比目前可用的临床病理方法更准确地预测结直肠癌个体患者的预后。一旦在一个机构的数据上进行训练，神经网络就能预测来自不相关机构患者的预后。
