Laboratory of Information Access and Synthesis of TCM Four Diagnosis, Basic Medical College, Shanghai University of Traditional Chinese Medicine, Shanghai 201203, China.
Evid Based Complement Alternat Med. 2012;2012:135387. doi: 10.1155/2012/135387. Epub 2012 Jun 3.
Background. In Traditional Chinese Medicine (TCM), most of the algorithms are used to solve problems of syndrome diagnosis that only focus on one syndrome, that is, single label learning. However, in clinical practice, patients may simultaneously have more than one syndrome, which has its own symptoms (signs). Methods. We employed a multilabel learning using the relevant feature for each label (REAL) algorithm to construct a syndrome diagnostic model for chronic gastritis (CG) in TCM. REAL combines feature selection methods to select the significant symptoms (signs) of CG. The method was tested on 919 patients using the standard scale. Results. The highest prediction accuracy was achieved when 20 features were selected. The features selected with the information gain were more consistent with the TCM theory. The lowest average accuracy was 54% using multi-label neural networks (BP-MLL), whereas the highest was 82% using REAL for constructing the diagnostic model. For coverage, hamming loss, and ranking loss, the values obtained using the REAL algorithm were the lowest at 0.160, 0.142, and 0.177, respectively. Conclusion. REAL extracts the relevant symptoms (signs) for each syndrome and improves its recognition accuracy. Moreover, the studies will provide a reference for constructing syndrome diagnostic models and guide clinical practice.
在中医（TCM）中，大多数算法用于解决仅关注一种证候的证候诊断问题，即单标签学习。然而，在临床实践中，患者可能同时存在多种证候，每种证候都有其自身的症状（体征）。方法：我们采用相关特征用于每个标签的多标签学习（REAL）算法，构建中医慢性萎缩性胃炎（CG）证候诊断模型。REAL 结合特征选择方法，选择 CG 的显著症状（体征）。该方法在 919 名患者中使用标准量表进行了测试。结果：当选择 20 个特征时，可获得最高预测精度。采用信息增益选择的特征与中医理论更为一致。使用多标签神经网络（BP-MLL）的平均精度最低为 54%，而使用 REAL 构建诊断模型的平均精度最高为 82%。在覆盖率、汉明损失和排序损失方面，REAL 算法的取值最低，分别为 0.160、0.142 和 0.177。结论：REAL 提取了每个证候的相关症状（体征），提高了其识别精度。此外，这些研究将为构建证候诊断模型提供参考，并指导临床实践。
