Zhi Liu

The effectiveness of traditional Chinese medicine (TCM) has been proved by various researches in decades, especially in the COVID-19 pandemic. Numerous TCM-AI interdisciplinary researches have been proposed for trying to modeling its mechanism and knowledge, assisting efficient decision making of human doctors. Currently, most of the works are focus on supervised learning paradigm. Such methodology leads to the fact that models fail in scenario of rare disease (few samples are available). In this work, we focus on the knowledge–data-oriented mechanism and design a framework enables the model ability to interact the information between knowledge and samples, called TCM-KDIF. We build a TCM knowledge graph (KG) with the TCM concepts (macroscopic) and molecular biology (microcosmic). Based on it, models can interact the information of training samples with external KG by TCM-KDIF. The proposed framework extracts the features of training samples and its related knowledge subgraph first. Then, these two types of information communicate in both directions between samples and knowledge subgraph iteratively. The TCM-KDIF is evaluated on the TCM prescription generation task. The experimental results demonstrate that the TCM-KDIF outperforms all comparison baselines, reduces model’s dependency on training samples, and reveal the possible interact mechanisms between medicine and symptoms.

Intelligent traditional Chinese medicine (TCM) has become a popular research field by means of prospering of deep learning technology. Important achievements have been made in such representative tasks as automatic diagnosis of TCM syndromes and diseases and generation of TCM herbal prescriptions. However, one unavoidable issue that still hinders its progress is the lack of labeled samples, i.e., the TCM medical records. As an efficient tool, the named entity recognition (NER) models trained on various TCM resources can effectively alleviate this problem and continuously increase the labeled TCM samples. In this work, on the basis of in-depth analysis, we argue that the performance of the TCM named entity recognition model can be better by using the character-level representation and tagging and propose a novel word-character integrated self-attention module. With the help of TCM doctors and experts, we define 5 classes of TCM named entities and construct a comprehensive NER dataset containing the standard content of the publications and the clinical medical records. The experimental results on this dataset demonstrate the effectiveness of the proposed module.

The artificial potential field approach is an efficient path planning method. However, to deal with the local-stable-point problem in complex environments, it needs to modify the potential field and increases the complexity of the algorithm. This study combines improved black-hole potential field and reinforcement learning to solve the problems which are scenarios of local-stable-points. The black-hole potential field is used as the environment in a reinforcement learning algorithm. Agents automatically adapt to the environment and learn how to utilize basic environmental information to find targets. Moreover, trained agents adopt variable environments with the curriculum learning method. Meanwhile, the visualization of the avoidance process demonstrates how agents avoid obstacles and reach the target. Our method is evaluated under static and dynamic experiments. The results show that agents automatically learn how to jump out of local stability points without prior knowledge.

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.

Robertsonian translocations occur in approximately one in every 1000 newborns. Although most Robertsonian translocation carriers are healthy and have a normal lifespan, they are at increased risk of spontaneous abortions and risk of producing unbalanced gametes and, therefore unbalanced offspring. Here we reported a previously undescribed Robertsonian translocation. We identified three Robertsonian translocation carriers in this family. Two were heterozygous translocation carriers of 45,XX or XY,der(14;15)(q10;q10) and their son was a homozygous translocation carrier of a 44,XY,der(14;15)(q10;q10), der(14;15)(q10;q10) karyotype. Chromosomal analysis of sperm showed 99.7 % of sperm from the homozygous translocation carrier were normal/balanced while only 79.9 % of sperm from the heterozygous translocation carrier were normal/balanced. There was a significantly higher frequency of aneuploidy for sex chromosome in the heterozygous translocation carrier. The reproductive fitness of Robertsonian translocation carriers is reduced. Robertsonian translocation homozygosity can be a potential speciation in humans with 44 chromosomes.