Exploration on Generating Traditional Chinese Medicine Prescriptions from Symptoms with an End-to-End Approach

Li, Wei; Zheng, Yang

doi:10.1007/978-3-030-32233-5_38

Cited by 25 publications

(24 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After that we verified its validity through experiments. The performance of the proposed method is outstanding in a very small number of similar studies [48]. However, the tongue image is not the only basis for a doctor to make a diagnosis and treatment.…”

Section: Discussionmentioning

confidence: 97%

Automatic Construction of Chinese Herbal Prescriptions From Tongue Images Using CNNs and Auxiliary Latent Therapy Topics

Wen

Liao

et al. 2021

IEEE Trans. Cybern.

View full text Add to dashboard Cite

The tongue image provides important physical information of humans. It is of great importance for diagnoses and treatments in clinical medicine. Herbal prescriptions are simple, noninvasive, and have low side effects. Thus, they are widely applied in China. Studies on the automatic construction technology of herbal prescriptions based on tongue images have great significance for deep learning to explore the relevance of tongue images for herbal prescriptions, it can be applied to healthcare services in mobile medical systems. In order to adapt to the tongue image in a variety of photographic environments and construct herbal prescriptions, a neural network framework for prescription construction is designed. It includes single/double convolution channels and fully connected layers. Furthermore, it proposes the auxiliary therapy topic loss mechanism to model the therapy of Chinese doctors and alleviate the interference of sparse output labels on the diversity of results. The experiment use the real-world tongue images and the corresponding prescriptions and the results can generate prescriptions that are close to the real samples, which verifies the feasibility of the proposed method for the automatic construction of herbal prescriptions from tongue images. Also, it provides a reference for automatic herbal prescription construction from more physical information.

show abstract

Section: Discussionmentioning

confidence: 97%

Automatic Construction of Chinese Herbal Prescriptions From Tongue Images Using CNNs and Auxiliary Latent Therapy Topics

Wen

Liao

et al. 2021

IEEE Trans. Cybern.

View full text Add to dashboard Cite

show abstract

“…In this paper, taking both multi-label learning and feature extraction into consideration, we propose MCC model with an end-to-end approach [16] for MMML problem, which is inspired by adaptive decision methods. Different from previous feature selection or dimensionality reduction methods, MCC extracts different modalities for different instances and different labels.…”

Section: Related Workmentioning

confidence: 99%

Many Could be Better Than All: A Novel Instance-Oriented Algorithm for Multi-modal Multi-label Problem

Zhang

Zeng

Cheng

et al. 2019

2019 IEEE International Conference on Multimedia and Expo (ICME)

View full text Add to dashboard Cite

With the emergence of diverse data collection techniques, objects in real applications can be represented as multi-modal features. What's more, objects may have multiple semantic meanings. Multi-modal and Multi-label [1] (MMML) problem becomes a universal phenomenon. The quality of data collected from different channels are inconsistent and some of them may not benefit for prediction. In real life, not all the modalities are needed for prediction. As a result, we propose a novel instance-oriented Multi-modal Classifier Chains (MCC) algorithm for MMML problem, which can make convince prediction with partial modalities. MCC extracts different modalities for different instances in the testing phase. Extensive experiments are performed on one real-world herbs dataset and two public datasets to validate our proposed algorithm, which reveals that it may be better to extract many instead of all of the modalities at hand.

show abstract

“…Hu et al [17] propose a dual-CNN and latent Dirichlet allocation (LDA) based model to construct a prescription from tongue images, which is consisted of two separated CNNs where the smaller CNN is regarded as auxiliary therapy topic feature extractor and trained by the multi-task learning strategy. However, in this form of prescription generation, no sequential information between herbs and symptoms are taken into account which is important in TCM prescription generation as described in our work and [18]. It only uses tongue information to generate herbs, which can only learn the projection from tongue features to herbs.…”

Section: Introductionmentioning

confidence: 99%

“…It only uses tongue information to generate herbs, which can only learn the projection from tongue features to herbs. Li et al [18] use seq2seq framework to generate TCM prescription from symptom of a patient. In order to solve the repetition problem caused by seq2seq framework, they utilize the coverage mechanism and soft loss function.…”

Section: Introductionmentioning

confidence: 99%

“…Even through it has the same foundation with ours, its main purpose is different. In our work, our goal is that the designed two attention mechanisms can empower our model the ability of learning the herb-symptom interaction knowledge, the compatibility of herbs and the TCM principles such as treatment based on syndrome differentiation, while [18] relieves repetition problem in prescription generation. We have added the performance comparison between ours and the model proposed in [18], which is showed in the following section.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

AttentiveHerb: A Novel Method for Traditional Medicine Prescription Generation

et al. 2019

View full text Add to dashboard Cite

In this paper, we propose a novel intelligent model, called AttentiveHerb, for simulating the doctor's inquiry and prescription that is composed by a series of herbs. It can automatically simulate some principles and learns the interaction between symptoms and herbs from clinical records of traditional herbal medicine. This model consists of two different attention mechanisms for distinguishing the main symptoms and paying different attention to different symptoms. By experiments, in terms of the predicted prescriptions, 51% of the total cases are in full accordance with the labels; in 1.09% of cases, all herbs of a label can be found in the predicted prescription and the predicted prescription have other additional herbs; in 15.4% of cases, all herbs of a predicted prescription can be found in their corresponding label; in 22.41% of cases, several herbs in each predicted prescription overlap with its label; and 10.1% of cases are completely different from the label. In summary, 67.49% of the predicted prescriptions are close to the labels, and 89.9% contain the same herbs with the labels, which indicates that the prescriptions generated by our model are close to those by doctors. Besides, our model can recommend herbs that do not appear in the label prescriptions but are useful for relieving symptoms. It shows that our model can learn some interactions between herbs and symptoms. With enough normalized traditional herbal medical records, this model works more accurately. This study also provides a benchmark for the upcoming researches in intelligent inquiry and prescription generation of traditional herbal medicine.

show abstract

Exploration on Generating Traditional Chinese Medicine Prescriptions from Symptoms with an End-to-End Approach

Cited by 25 publications

References 14 publications

Automatic Construction of Chinese Herbal Prescriptions From Tongue Images Using CNNs and Auxiliary Latent Therapy Topics

Automatic Construction of Chinese Herbal Prescriptions From Tongue Images Using CNNs and Auxiliary Latent Therapy Topics

Many Could be Better Than All: A Novel Instance-Oriented Algorithm for Multi-modal Multi-label Problem

AttentiveHerb: A Novel Method for Traditional Medicine Prescription Generation

Contact Info

Product

Resources

About