Classical Formula Nomenclature in Traditional Chinese Medicine based on Neural Network

Formula Nomenclature is an initial step to study Traditional Chinese Medicine (TCM) Prescription, especially for the Theory of Formula-Symptoms Correspondence in the Schools of Zhongjing (Shanghan), Koho and JingFang. It is common for a TCM practitioner to write only the Chinese medicinal composition in the prescription without any Formula name. Through generalising from the prescription the named prima-decoction, which helps to relieve the symptoms, the effectiveness of the decoction could then be evaluated. In this study, 261 Formulae and their compositions of 173 unique Chinese medicinals extracted from the original texts of the “Treatise on Cold Damage Disorders” and the “Synopsis of Prescriptions of the Golden Chamber” were used to train the classification model by neural network for Formula Nomenclature. The model was evaluated with satisfactory by a list of modified compositions from the selected decoctions representing different Meridians (see Table 2). The classification model trained could help in Formula Nomenclature by labelling the Formulae used in the prescription automatically and thereby the dimensionality of data could be minimised. This would also benefit in future the TCM research of Big Data, the assisted artificial intelligence prescription and expert system based on machine learning. To improve the model, further studies on identifying the sovereign, minister, assistant and courier roles of Chinese medicinals in Classical Formulae are recommended.