TPGen: Prescription Generation Using Knowledge-guided Translator

Abstract

Background: Prescriptions contain a lot of clinical information and play a pivotal role in the clinical diagnosis of Traditional Chinese Medicine (TCM), which is a combination of herb to treat the symptoms of a patient from decision-making of doctors. In the process of clinical decision-making, a large number of prescriptions have been invented and accumulated based on TCM theories. Mining complex and the regular relationships between symptoms and herbs in the prescriptions are important for both clinical practice and novel prescription development. Previous work used several machine learning methods to discover regularities and generate prescriptions but rarely used TCM knowledge to guide prescription generation and described why each herb is predicted for treating a symptom. Methods: In this work, we employ a machine translation mechanism and propose a novel sequence-to-sequence (seq2seq) architecture termed TPGen to generate prescriptions. TPGen consisting of an encoder and a decoder is a well-known framework for resolving the machine translation problem in the natural language processing (NLP) domain. We use the lite transformer and Bi-directional Gate Recurrent Units(Bi-GRUS) as a fundamental model in TPGen, and integrate TCM clinical knowledge to guide the model improvement termed TPGen+. Results: We conduct extensive experiments on a public TCM dataset and clinical data. The experimental results demonstrate that our proposed model is effective and outperforms other state-of-the-art methods in TCM expert evaluation. The approach will be beneficial for clinical prescription discovery and diagnosis

TCM Prescription Generation via Knowledge Source Guidance Network Combined with Herbal Candidate Mechanism

“…This paper chooses the following baseline models for comparison. KDHR [ 18 ]: a graph convolution model for multilayer information fusion with herbal attributes as auxiliary knowledge PTM [ 21 ]: the topic model that can describe the prescription generation process according to the theory of TCM, and it used the connection between herbs and symptoms and the respective internal connections between the two as the implementation of the TCM domain knowledge guidance model Coverage-Soft-Model [ 44 ]: it is a seq2seq model with a decoder having a coverage mechanism and a soft loss function Herb-Know [ 24 ]: a seq2seq model that incorporated external knowledge of herbs TPGen [ 23 ]: a seq2seq model using lite Transformer and bidirectional gated recurrent unit combined with TCM clinical knowledge …”

“…TPGen [ 23 ]: a seq2seq model using lite Transformer and bidirectional gated recurrent unit combined with TCM clinical knowledge…”

“…In this work, we use two datasets: the “symptoms-prescription” data pairs set (SP) and the “prescription-efficacy” data pairs set (PE). (1) There are three sources of the “symptoms-prescription” data pair set (SP), namely the public data set (CKCEST) [ 23 ], the traditional diagnostic records extracted from the ancient Chinese medical books (ACMB), and the clinical diagnosis records provided by cooperative Chinese medicine company (CCMC). Among them, the CKCEST and ACMB, respectively, contain 33,765 and 80,420 “symptoms-prescription” data pairs.…”

“…The second type of attention achieves the effect that the herbs treating the main symptoms were first predicted. Ruan et al [ 23 ] also studied the attention mechanism in the generation of TCM prescriptions. They used attention mechanisms to explore the relationships between different symptoms and different herbs.…”

“…In order to obtain prescriptions which are more in line with TCM prescribing concepts and achieve prescription "generation" rather than herbal "mapping", more researches on prescription generation have focused on the use of seq2seq structures [22][23][24]. Wang et al [25] viewed TCM prescription generation as a machine translation problem.…”