As one of the most vital methods in drug development, drug repositioning emphasizes further analysis and research of approved drugs based on the existing large amount of clinical and experimental data to identify new indications of drugs. However, the existing drug repositioning methods didn't achieve enough prediction performance, and these methods do not consider the effectiveness information of drugs, which make it difficult to obtain reliable and valuable results. In this study, we proposed a drug repositioning framework termed DRONet, which make full use of effectiveness comparative relationships (ECR) among drugs as prior information by combining network embedding and ranking learning. We utilized network embedding methods to learn the deep features of drugs from a heterogeneous drug-disease network, and constructed a high-quality drug-indication data set including effectiveness-based drug contrast relationships. The embedding features and ECR of drugs are combined effectively through a designed ranking learning model to prioritize candidate drugs. Comprehensive experiments show that DRONet has higher prediction accuracy (improving 87.4% on Hit@1 and 37.9% on mean reciprocal rank) than state of the art. The case analysis also demonstrates high reliability of predicted results, which has potential to guide clinical drug development.

The standardization degree of traditional Chinese medicine clinical data in the real world is low and heterogeneous data aggregation among institutions is difficult, which leads to the difficulty of sharing clinical data and scientific research data of traditional Chinese medicine. This paper designs and implements a real world traditional Chinese medicine clinical scientific research information electronic medical record sharing system. The system consists mainly of two subsystems, namely electronic medical record collection system and electronic medical record integration system. The collection system can collect, normalize and structured storage inpatient electronic medical records, outpatient electronic medical records and cloud platform electronic medical records. The integration system can integrate heterogeneous data from different traditional Chinese medicine diagnostic and treatment institutions to realize the sharing of traditional Chinese medicine clinical and research data.

The knowledge of phenotype-genotype associations is crucial for the understanding of disease mechanisms. Numerous studies have focused on developing efficient and accurate computing approaches to predict disease genes. However, owing to the sparseness and complexity of medical data, developing an efficient deep neural network model to identify disease genes remains a huge challenge. Therefore, we develop a novel deep neural network model that fuses the multi-view features of phenotypes and genotypes to identify disease genes (termed PDGNet). Our model integrated the multi-view features of diseases and genes and leveraged the feedback information of training samples to optimize the parameters of deep neural network and obtain the deep vector features of diseases and genes. The evaluation experiments on a large data set indicated that PDGNet obtained higher performance than the state-of-the-art method (precision and recall improved by 9.55 and 9.63 percent). The analysis results for the candidate genes indicated that the predicted genes have strong functional homogeneity and dense interactions with known genes. We validated the top predicted genes of Parkinson's disease based on external curated data and published medical literatures, which indicated that the candidate genes have a huge potential to guide the selection of causal genes in the 'wet experiment'. The source codes and the data of PDGNet are available at https://github.com/yangkuoone/PDGNet.

Objective: Designs a XGBoost-based data quality control model for the traditional chinese medicine (TCM) inpatient medical record home page. Exploring the method of data normalization on the TCM inpatient medical record home page. Methods: Taking the data on the TCM inpatient medical record home page of a hospital in Jiangsu Province as the original data. Using correlation analysis to filter out some data items that have a higher degree of correlation with the data items to be quality control. Establishing a XGBoost-based data quality control model for the TCM inpatient medical record home page. Using the hierarchical 10-fold cross-validation to evaluate the model. Results: The experimental results show that the accuracy rate of the model can reach 88.60%. Conclusion: The data quality control model on the TCM inpatient medical record home page is conducive to improving the quality of the data on the TCM inpatient medical record home page and provides data support for medical research.

Background and Objective: The Coronavirus Disease 2019 pandemic situation is remaining severe worldwide. A single outbreak data source is not adequate for comprehensive analyses of the response to the pandemic. Such analyses need to seek proper integration of epidemic data for subsequent statistical analyses. Methods: 1) Considering reputations of publishers, activities, public users' accessibility, and retrievable historical data among several platforms, the World Health Organization (WHO), the US Centers for Disease Control (CDC), and Baidu's Real-time Epidemics (BRE) websites were selected as our data sources. 2) Data for 32 weeks until August 15th, 2020, were followed, including the US cumulative confirmed cases (CCCs), cumulative death cases (CDCs), cumulative discharged or cured cases (CD$\vert$ CCs), daily new infective confirmed cases (DNCCs), and daily new death cases (DNDCs). 3) Estimators for the weekly current active infected confirm cases (CACs) and the weekly COVID19 fatal rate in the US hospitals (WFRUSH) were derived. Graphic display modules demonstrated the risks associated with demographic data. Results: 1) CCCs reached 5,285,546 cases in the US on August 15th, 2020, which initially climbed from the 9th-11th week; the CDCs were 167,546. The fatality rate initially climbed from the 12th-13th week, but fast turned over to decrease from the 18th week, then gradually flattened out near 3.17% till the mid of August 2020. 2) The WFRUSH first rose sharply at the 10th-11th week and started to decline in the 12th week, although there was a repeated smaller fluctuation in the 13th-14th week, during the generally downward process. 3) The US demographic characteristics and CDCs showed that the proportion of fatal cases in the senior Americans (age group over 65) accounted was 78.8%, about 4 (3.83) times the proportions of the other age groups. Supposed the death cases of seniors, directly caused by the COVID-19 rather than caused by the fundamental diseases, the $\gamma$ value of the seniors, a ratio between the senior CDCs proportion over the senior population proportion was 4.81. Such a $\gamma$ value for seniors, indicated a much higher fatality risk than other age groups. Conclusion: Integrative capture data from the publicly web-published COVID-19 statistics helps extend analyzable data and estimate or derive new-useful indicators CACs, WFRUSH, and $\gamma$ value for the demographic group. As of the including the working population age of over 45, would have a much higher fatality rate than younger ages. It seemed necessary to study further if these death were caused directly by the COVID-19. Additionally, the African Americans, and male Americans, had relatively higher fatality rates. These high risks require more attention to strengthening health prevention; including the working-age population, even although the WFRUSH as a more appropriate and vital indication becomes stable to a low level after July 2020, meaning the clinical interventions and treatments were improved, or the virus fatality power was declined.

Synonym mapping between phenotype concepts from different terminologies is difficult because terminology databases have been developed largely independently. Existing maps of synonymous phenotype concepts from different terminology databases are highly incomplete, and manually mapping is time consuming and laborious. Therefore, building an automatic method for predictive mapping of synonymous phenotypes is of special importance. We propose a classifier-based phenotype mapping prediction model (CPM) to predict synonymous relationships between phenotype concepts from different terminology databases. The model takes network semantic representations of phenotypes as input and predicts synonymous relationships by training binary classifiers with a voting strategy. We compared the performance of the CPM with a similarity-based phenotype mapping prediction model (SPM), which predicts mapping based on the ranked cosine similarity of candidate mapping concepts. Based on a network representation N2V-TFIDF, with a majority voting strategy method MV, the CPM achieved accuracy of 0.943, which was 15.4% higher than that of the SPM using the cosine similarity method (0.789) and 23.8% higher than that of the SSDTM method (0.724) proposed in our previous work.

Objective: To develop a secure data capture system in XHTML (eXtensible Hyper Text Markup Language) format, which can collect health records in Traditional Chinese Medicine (TCM) Clinics with capability of electronic signature at client, exchange data from internet to transmit or to receive EHRs for business and research usage, and retrieve ICD-11 MMS for traditional medicine (TM) that is stored with XML in SQL database server (DBS) within intranet. General Design: 1. To define two basic tables for ICD-11 table (tICD11) information and electronic medical record (EMR) table (EMRT). Fields of DEV (Data Element Value) for ICD codes and DEVM (Data Element Value Meaning) for ICD code meanings or terms are the essential fields of the tICD11; In EMRT, fields are defined, involving type of XML for EHRs built with Extensible Hypertext Markup Language (XHTML) and type of text for MD5 of EHRs. Besides, type of datetime for creating or updating record is affiliated in all tables. Microsoft Window's SQL server (WINSQLS) 2008, a kind of relation-type database management system for data of SQL or non-SQL, is selected as experiment environment within intranet. 2. To design views and storage procedures querying tICD11 or submitting EHRs. To create a series of Structure Query Language (SQL) such as views and SQL storage procedures (SPs) for managing the tICD11 data transaction (TRSs); and exchanging EHRs built with Extensible Hypertext Markup Language (XHTML) with SQL plus XPath, a non-SQL language, to express clinical or patient's demands, such as voice messages of patient reported outcomes (PROs) or electronic signatures (E-signature, ES). SPs may include parameters (PSPs) and end with a SQL term of FOR XMLAUTO, ROOT(`ROOTNAME'). 3. To deploy web service (WS) site with functional web-interface. According to a model with three-tier architecture and relative functions, we developed an interface of WS corresponding PSPs in the Window's server 2008 (64bits), a gateway web site accessing with heading of “https://” supported with the protocol of Secure Sockets Layer (SSL), and an account-administrative server ordinarily referred as Active Directory (AD). As one of keys, a function in WS solution is to get specified values of the attributes contained in the start tag of XHTML's data elements (XDE), which are parameters for DEV or DEVM required by SPs. Result: 1. More than 17,000 records of the codes and terms from the ICD-11 MMS were captured. Codes and terms in ICD-11 for symptoms, signs, clinical finding, diagnostic and treatment and even those for TM such as disorder, pattern and acupuncture, other than those in the ICD-10. These codes and terms can be retrieved from tICD11 to XDE involved DEV or/and DEVM via SPs and be bonded to list views of optional inputs, which will be selected as standardized inputs into EHRs. 2. Voice records of clinical visits and/or PROs post-clinical visits, and ES for XDE on EHRs can also be captured at local device, securely submitted to the remote servers to integrate into EDC system. 3. The system that runs at the intranet allows remote requests from internet clients to query with XHTML involving keywords and returns deidentified XHTML involving DEV and DEVM to the EHRs at client sites. The data-exchange-interface web site as the gateway (GW, URL: https://www.meacm.com/icd11ws) at a server (GWS) is marked with the SSL certificate so that these exchanges are commonly referred as secure and effective between different platforms and the inside of WINSQLS. Conclusion: The system offers a secure XHTML-structured web solution for high quality EHRs plus coding and terming input with the standard of ICD-11 MMS, legally binding input via electronic signature and sensitive masking input via encryption with public key and deidentified data exchanges for research. Such a system has the advantages of being flexible for application needs but rigorous in collection of real high qualitive data for scientific research and decision; and can be conveniently deployed in a distributed system. An integration of traditional medicine data into the entire EHRs system will collect broad and comprehensive healthcare data and generate real-world evidence for the role and effectiveness of TCM in patient care.

Traditional Chinese medicine (TCM) can provide important complementary medical care to modern medicine, and is widely practiced in China and many other countries. Unfortunately, due to its empirical nature and history of trial and error, effective diagnosis and prescription methods are not well-defined. This setback results in a significant challenge in retaining, sharing, and inheriting knowledge among physicians. In this paper, we propose a new asymmetric probabilistic model for the joint analysis of symptoms, diseases, and herbs in patient records to discover and extract latent TCM knowledge. We base our model on the comprehensive evaluation of modern medicine and TCM-specific symptoms in addition to herb prescriptions for particular diseases. Experimental results on a large dataset demonstrate the effectiveness of the proposed model for discovering useful knowledge and its potential clinical applications.

Purpose: To study and establish the platform of information collection and analysis of the first page of medical records in the key Medical College of TCM(Traditional Chinese Medicine). Method: According to the formulated by the State Administration of traditional Chinese medicine, the Part of the Project Filling Explanation of Inpatient Medical Record Home Page, the key indicator system for the acquisition of the first page of medical record, verification data, as well as system platform function system, the overall architecture and technology implementation were determined. Results: As the unified platform for the collection, analysis and standardization management in common use of the first page of the medical record for state, provinces (municipalities and autonomous regions), administration of traditional Chinese medicine, key medical college of traditional Chinese Medicine, was used practically in the 578 units, and was verified the feasibility of the design platform. Conclusion: Through the practical application of medical units in various provinces and cities, the platform is proved to be ease of operation and feasibility, which provides a basic platform for the construction of traditional Chinese medicine.

Treatment based on the syndrome differentiation is the key of traditional Chinese medicine (TCM) treating acquired immune deficiency syndrome (AIDS). Syndrome differentiation, where the patients suffering from a western medicine disease are divided into several classes based on their symptoms and signs, is an important diagnostic method and affects the effective use of TCM treatments. Some researches show that the clustering algorithms make it possible to classify the AIDS patients into several syndrome types. These algorithms improve the precision of syndrome differentiation so as to promote the TCM treatment efficacy. However, because of the complexity of AIDS disease, the AIDS clinical data usually have a large number of dimensions. The previous cluster algorithms assign equal weights to these dimensions and become confounded in the process of dealing with these dimensions. In this paper, we use a top-down subspace clustering algorithm as a solution to the syndrome differentiation. For a given cluster, we determine the relevant symptoms based on histogram analysis and assign greater weight to the relevant symptoms as compared to less relevant symptoms. Then, the symptoms with greater weight are used to differentiate the syndrome type of AIDS patients. Finally, the proposed method is compared with the traditional k-means algorithm based on the collected AIDS dataset. We evaluate their performance by the precision and the consistency. The experimental results show that the proposed algorithm is better than the traditional ones for aided TCM syndrome differentiation of AIDS patients.

Symptoms and signs (symptoms in brief) are the essential clinical manifestations for traditional Chinese medicine (TCM) diagnosis and treatments. To gain insights into the molecular mechanism of symptoms, this paper presents a network-based data mining method to integrate multiple phenotype-genotype data sources and predict the prioritizing gene rank list of symptoms. The result of this pilot study suggested some insights on the molecular mechanism of symptoms.

Traditional Chinese Medicine (TCM) is a discipline of clinical medicine, which focuses on individualized diagnosis and treatment based on observation of the clinical manifestations of real-world patients. The complicated interactions between different medical entities play significant role for individualized treatment. In this paper, we aim to find out the meaningful herb-symptom relationship from large number of clinical data with using complex network approach. We construct two different patient networks to verify the positive correlations between herbs and symptoms in TCM clinical treatment.

In the TCM clinical and research information sharing system, structured electronic medical records (EHR) have captured a large amount of clinical case information. There are some exist problems about TCM data integration and information sharing. The purpose of this paper is to discuss the significance and causality of using ontology matching application in TCM data integration and information sharing, and present its promising future in TCM medical informatics domain.

Chinese Patent Medicine is widely used to treat many disease in China since better efficacy can be achieved in the clinical practice. However, because of lack of Traditional Chinese Medicine (TCM) knowledge, many western physicians are confusing with the utility of Chinese Patent Medicine, which are exactly the main force of clinical prescriptions. Therefore, the aid decision method is urgent and necessary to help the western physicians rationally use Chinese Patent Medicine. In this paper, Manifold Ranking (MR) is employed to developing the aid decision model of Chinese Patent Medicine. There are two stages in the aid decision model Firstly, the underlying relation between the symptoms and the Chinese Patent Medicines is obtained based on MR during the learning process. Secondly, given the symptoms of a new patient, the aid decision of Chinese Patent Medicine is able to be given during the decision process. 115 patients with stroke are taken as the examples of training and testing the aid decision models. The experimental results reveal that Chinese Patent Medicine is able to be differentiated and the high accuracy of aid decision is also obtained based on some symptoms.

Traditional Chinese Medicine (TCM) is a complementary alternative medical approach. Its holistic approach is drastically different from the western medicine (WM). Upon the gathering of various symptoms in a diagnosis, a TCM practitioner prescribes treatment methods, of which herbal medicine is still one of the most popular. Each formula consists of multiple herbs. Since it is not a one-to-one mapping between symptom and herb, overlapping subsets of herbs are meant to address sets of overlapping symptoms. As a result, the discovery of the symptoms-herbs relationship is a crucial step to the research of the underlying TCM principle. The discovery of many existing formulas took a long time to stabilize to the current configurations. In this paper, the relationship discovery is argued to be more than just an evolutionary process, but a coevolutionary process, i.e. a set of symptoms searches for candidate sets of herbs, while a given set of herbs are appropriate for multiple sets of symptoms. In other words, a well recognized symptoms-herbs relationship is the result of a dynamic equilibrium of two inter-related evolutionary processes. This model of discovery was implemented using a Combined Gene Genetic Algorithm (CoGA1) where the symptoms and herbs are encoded in the same chromosome to evolve over time. The algorithm was tested with an insomnia dataset from a TCM hospital. The algorithm was able to find the symptoms-herbs relationships that are consistent with TCM principles and have better fitness from Simple GA.

Traditional Chinese medicine (TCM) is developed from clinical practice. Rich information can be obtained from the medical record of TCM. National clinical research data center of TCM is constructed to collect the clinical medical data of TCM from hospitals all over the country. The construction framework of national clinical data center of TCM includes infrastructure construction, software construction, local branch data center construction and institutional framework. In the mean time, a series of measures is implemented to guarantee the normal running of the national clinical data center of TCM. The construction of national clinical data center of TCM may promote the development of TCM and improve the level of medical care in China.

The construction of health service platform for the elderly must attach great importance to the health service demands of the elderly ,basing on innovation and whole process of health service by taking full advantage of IOT technology, data warehousing, data mining analysis technology, cloud computing technology and other modern information technologies, widely applying the modern trans-regional remote health information collection and transmission equipment, and setting up health service technology platform with the close connection between production and research so as to enhance the ability and level of health service of the elderly.

The research of traditional Chinese medicine clinical represented by the randomized controlled trial (RCT) has developed rapidly, But it also revealed two problem. The “combination between disease and syndrome” reflects the common law of disease and the patient's personality characteristics, and individual therapy focuses on dynamic effect which is more suitable for research environment in the real world the Institute of Medicine of the US National Academy of Science proposed the comparative effectiveness research (CER) to compare the research and analysis of different treatment methods. Building clinical research methods in the real world needs to carry on innovative exploration, and studies the methods and specifications of clinical research in the real world from the elements of clinical design, the control of bias, data management, statistical analysis, ethics and other clinical researches. On the basis, the comparative effectiveness research of “real world” and the “combination between disease and syndrome” needs to be carried out. The comparative effectiveness research of traditional Chinese medicine in the real world includes retrospective and prospective studies. The retrospective study is to analyze and compare based on historical data to provide clues and evidence for prospective study. The prospective study is to build follow-up platform for patients to carry on prospective study design.

This paper provides a survey of data mining methods that have been commonly applied to real-world TCM clinical data in recent years, and sets forth the requirements of data mining on real-world TCM clinical diagnosis and treatment data, in order to provide reference for better analyzing the syndrome differentiation and treatment principle hidden in the massive TCM clinical data in the future.

Because of the amount of missing values in our SARS data set is very large, to fill in them wholly with the existing methods is impossible or the results of being filled in are not reliable. Only taking two attributes into account can avoid using the large amount of missing values, which is the feature of rough set that other machine learning method cannot hold. In this paper, we induced some rules based on rough set from the SARS data set that have not been detected by medical experts in clinic practice.