Discrimination of prediction models between cold-heat and deficiency-excess patterns.

Citation metadata

Publisher: Elsevier B.V.
Document Type: Report
Length: 615 words

Document controls

Main content

Abstract :

Keywords Decision support system; International Classification of Diseases; Machine learning; Traditional medicine pattern Highlights * We collected questionnaire items, constructed prediction models and extracted the important items. * The new sentence is 'The important items of deficiency-excess and cold-heat patterns overlapped if we ignored an unbalanced proportion of them. * We changed our training data sampling method to a balanced one. * Our new balanced prediction model successfully excluded the interaction between deficiency--excess and cold--heat pattern. Abstract Objective The purpose of this study was to extract important patient questionnaire items by creating random forest models for predicting pattern diagnosis considering an interaction between deficiency-excess and cold-heat patterns. Design A multi-centre prospective observational study. Setting Participants visiting six Kampo speciality clinics in Japan from 2012 to 2015. Main outcome measure Deficiency--excess pattern diagnosis made by board-certified Kampo experts. Methods We used 153 items as independent variables including, age, sex, body mass index, systolic and diastolic blood pressures, and 148 subjective symptoms recorded through a questionnaire. We sampled training data with an equal number of the different patterns from a 2 x 2 factorial combination of deficiency--excess and cold--heat patterns. We constructed the prediction models of deficiency--excess and cold--heat patterns using the random forest algorithm, extracted the top 10 essential items, and calculated the discriminant ratio using this prediction model. Results BMI and blood pressure, and subjective symptoms of cold or heat sensations were the most important items in the prediction models of deficiency--excess pattern and of cold--heat patterns, respectively. The discriminant ratio was not inferior compared with the result ignoring the interaction between the diagnoses. Conclusions We revised deficiency--excess and cold--heat pattern prediction models, based on balanced training sample data obtained from six Kampo speciality clinics in Japan. The revised important items for diagnosing a deficiency--excess pattern and cold--heat pattern were compatible with the definition in the 11.sup.th version of international classification of diseases. Author Affiliation: (a) Division of Pharmaceutical Care Sciences, Graduate School of Pharmacy, Keio University, 1-5-30 Shibakoen, Minato-ku, Tokyo 105-8512, Japan (b) Center for Kampo Medicine, Keio University School of Medicine, 35 Shinanomachi, Shinjuku-ku, Tokyo 160-8582, Japan (c) Human Genome Center, the Institute of Medical Science, University of Tokyo, 4-6-1 Shirokanedai, Minato-ku, Tokyo 108-8639, Japan (d) Shikino Care Center, 480 Washikitashin, Takaoka, Toyama 933-0071, Japan (e) Department of Japanese Oriental (Kampo) Medicine, Graduate School of Medicine and Pharmaceutical Sciences, University of Toyama, 2630 Sugitani, Toyama 930-0194, Japan (f) Department of Japanese Oriental (Kampo) Medicine, Graduate School of Medicine, Chiba University, 1-8-1 Inohana, Chuo-ku, Chiba, Chiba 260-8760, Japan (g) Department of Japanese Oriental (Kampo) Medicine, Oriental Medical Center, Iizuka Hospital, 3-83 Yoshio-cho, Iizuka, Fukuoka 920-8505, Japan (h) Department of Oriental Medicine, Kameda Medical Center, 929 Higashi-cho, Kamogawa, Chiba 296-8602, Japan (i) Division of Oriental Medicine, Center of Community Medicine, Jichi Medical University, 3311-1 Yakushiji, Shimotsuke, Tochigi 329-0498, Japan (j) Division of System Analysis, Aichi Cancer Center Research Institute, 1-1 Kanokoden, Nagoya Chikusa-ku, Aichi 464-8681, Japan (k) Division of Health Medical Data Science, Health Intelligence Center, The Institute of Medical Science, The University of Tokyo, 4-6-1 Shirokanedai, Minato-ku, Tokyo 108-8639, Japan (l) Center for Research and Development of Higher Education, University of Tokyo, 7-3-1 Hongou, Bunkyo-ku, Tokyo 113-0033, Japan * Corresponding author. Article History: Received 3 October 2019; Revised 22 January 2020; Accepted 19 February 2020 Byline: Ayako Maeda-Minami [ayako373@keio.jp] (a), Tetsuhiro Yoshino [tetta213@keio.jp] (b), Kotoe Katayama [k-kataya@hgc.jp] (c), Yuko Horiba [mannta217@keio.jp] (b), Hiroaki Hikiami [hhikiami1327@gmail.com] (d), Yutaka Shimada [shimada@med.u-toyama.ac.jp] (e), Takao Namiki [tnamiki@faculty.chiba-u.jp] (f), Eiichi Tahara [etaharah1@aih-net.com] (g), Kiyoshi Minamizawa [k-mnmzw@kameda.jp] (h), Shinichi Muramatsu [muramats@ms2.jichi.ac.jp] (i), Rui Yamaguchi [r.yamaguchi@aichi-cc.jp] (j), Seiya Imoto [imoto@ims.u-tokyo.ac.jp] (k), Satoru Miyano [miyano@hgc.jp] (c), Hideki Mima [mima@he.u-tokyo.ac.jp] (l), Masaru Mimura [mimura@keio.jp] (b), Tomonori Nakamura [nakamura-tm@pha.keio.ac.jp] (a), Kenji Watanabe [watanabekenji@keio.jp] (b)

Source Citation

Source Citation   

Gale Document Number: GALE|A616454579