Dr. Answer AI for prostate cancer: Clinical outcome prediction model and service.

OBJECTIVES: The importance of clinical outcome prediction models using artificial intelligence (AI) is being emphasized owing to the increasing necessity of developing a clinical decision support system (CDSS) employing AI. Therefore, in this study, we proposed a "Dr. Answer" AI software based on the clinical outcome prediction model for prostate cancer treated with radical prostatectomy. METHODS: The Dr. Answer AI was developed based on a clinical outcome prediction model, with a user-friendly interface. We used 7,128 clinical data of prostate cancer treated with radical prostatectomy from three hospitals. An outcome prediction model was developed to calculate the probability of occurrence of 1) tumor, node, and metastasis (TNM) staging, 2) extracapsular extension, 3) seminal vesicle invasion, and 4) lymph node metastasis. Random forest and k-nearest neighbors algorithms were used, and the proposed system was compared with previous algorithms. RESULTS: Random forest exhibited good performance for TNM staging (recall value: 76.98%), while k-nearest neighbors exhibited good performance for extracapsular extension, seminal vesicle invasion, and lymph node metastasis (80.24%, 98.67%, and 95.45%, respectively). The Dr. Answer AI software consisted of three primary service structures: 1) patient information, 2) clinical outcome prediction, and outcomes according to the National Comprehensive Cancer Network guideline. CONCLUSION: The proposed clinical outcome prediction model could function as an effective CDSS, supporting the decisions of the physicians, while enabling the patients to understand their treatment outcomes. The Dr. Answer AI software for prostate cancer helps the doctors to explain the treatment outcomes to the patients, allowing the patients to be more confident about their treatment plans.

Research trends in Korean medicine based on temporal and network analysis.

BACKGROUND: Much research on Korean medicine has been recently published in Korea. The aim of this study was to determine the research trends in Korean medicine by performing a comprehensive analysis of articles that have been published in Korea using temporal and network analysis methods. METHODS: A total of 29,876 articles from 1963 to 2018 were prepared from OASIS (Oriental Medicine Advanced Searching Integrated System), the largest portal for Korean medicine. After the keywords and years were extracted from the metadata of the articles, an annual frequency matrix was obtained for the keywords. By using the matrix, the temporal trends of the keywords were analyzed by comparing the changes in similarity between the lists of keywords by year. Moreover, to analyze the relationship among research topics, a clustered network was constructed in which a node was a keyword and an edge was a similarity between two keywords. RESULTS: The temporal trend of the keywords was classified into six chronological phases. The appearance frequency of most keywords tended to increase gradually, but only the keywords "mibyeong," "systems biology" and "korean medicine hospital" appeared in the most recent phase. The network of keywords was clustered and visualized into thirteen groups with the Gephi software. The main keywords in each group were related to effects such as "anti-inflammation" and "antioxidant," to diseases such as "allergic rhinitis" and "diabetes" and to therapies such as "herbal acupuncture" and "herbal formula." CONCLUSIONS: The analysis of the trends determined in this study provides a systematic understanding as well as future research directions in Korean medicine to researchers. In the future, an overall analysis of the research trends in Korean medicine will be done by analyzing articles published in Korea and other countries.

DisArticle: a web server for SVM-based discrimination of articles on traditional medicine.

BACKGROUND: Much research has been done in Northeast Asia to show the efficacy of traditional medicine. While MEDLINE contains many biomedical articles including those on traditional medicine, it does not categorize those articles by specific research area. The aim of this study was to provide a method that searches for articles only on traditional medicine in Northeast Asia, including traditional Chinese medicine, from among the articles in MEDLINE. RESULTS: This research established an SVM-based classifier model to identify articles on traditional medicine. The TAK + HM classifier, trained with the features of title, abstract, keywords, herbal data, and MeSH, has a precision of 0.954 and a recall of 0.902. In particular, the feature of herbal data significantly increased the performance of the classifier. By using the TAK + HM classifier, a total of about 108,000 articles were discriminated as articles on traditional medicine from among all articles in MEDLINE. We also built a web server called DisArticle ( http://informatics.kiom.re.kr/disarticle ), in which users can search for the articles and obtain statistical data. CONCLUSIONS: Because much evidence-based research on traditional medicine has been published in recent years, it has become necessary to search for articles on traditional medicine exclusively in literature databases. DisArticle can help users to search for and analyze the research trends in traditional medicine.

TM-MC: a database of medicinal materials and chemical compounds in Northeast Asian traditional medicine.

BACKGROUND: In traditional medicine, there has been a great deal of research on the effects exhibited by medicinal materials. To study the effects, resources that can systematically describe the chemical compounds in medicinal materials are necessary. In recent years, numerous databases on medicinal materials and constituent compounds have been constructed. However, because these databases provide differing information and the sources of such information are unclear or difficult to verify, it is difficult to decide which database to use. Moreover, there is much overlapping information. The aim of this study was to construct a database of medicinal materials and chemical compounds in Northeast Asian traditional medicine (TM-MC), for which medicinal materials are listed in the Korean, Chinese, and Japanese pharmacopoeias and information on the compound names of medicinal materials can easily be confirmed online. DESCRIPTION: To provide information on the chemical compounds of medicinal materials, chromatography articles from MEDLINE and PubMed Central were searched. After chemical compounds of medicinal materials were extracted by manually investigating the full-text of articles, a database of information on about 14,000 compounds from 536 medicinal materials was built. The database also provides links to the articles from which each medicinal material and chemical compound were extracted. CONCLUSION: TM-MC database provides information on medicinal materials and their chemical compounds from chromatography articles in MEDLINE and PubMed Central. Researchers can easily check relevant information through the links to articles.