Predicting Japanese Kampo formulas by analyzing database of medical records: A preliminary observational study

Tetsuhiro Yoshino, Kotoe Katayama, Yuko Horiba, Kaori Munakata, Rui Yamaguchi, Seiya Imoto, Satoru Miyano, Hideki Mima, Kenji Watanabe

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Background: Approximately 90 % of physicians in Japan use Kampo medicine in daily practice. However, it is a challenge for physicians who do not specialize in Kampo medicine to select a proper Kampo formula out of the 148 officially approved formulas, as the decision relies on traditional measurements and traditional medicine pattern diagnoses. The present study tries to evaluate the feasibility of a decision support system for frequently used Kampo formulas. Methods: Our study included 393 patients who visited the Kampo Clinic at Keio University Hospital for the first time between May 2008 and March 2013. We collected medical records through a browser-based questionnaire system and applied random forests to predict commonly prescribed Kampo formulas. Results: The discriminant rate was the highest (87.0 %) when we tried to predict a Kampo formula from two candidates using age, sex, body mass index, subjective symptoms, and the two essential and predictable traditional medicine pattern diagnoses (excess-deficiency and heat-cold) as predictor variables. The discriminant rate decreased as the candidate Kampo formulas increased, with the greatest drop occurring between three (76.7 %) and four (47.5 %) candidates. Age, body mass index, and traditional medicine pattern diagnoses had higher importance according to the characteristics of each Kampo formula when we utilized the prediction model, which predicted a Kampo formula from among three candidates. Conclusions: These results suggest that our decision support system for non-specialist physicians works well in selecting appropriate Kampo formulas from among two or three candidates. Additional studies are required to integrate the present statistical analysis in clinical practice.

Original languageEnglish
Article number118
JournalBMC Medical Informatics and Decision Making
Volume16
Issue number1
DOIs
Publication statusPublished - 2016 Sep 13

Fingerprint

Kampo Medicine
Medical Records
Observational Studies
Databases
Traditional Medicine
Physicians
Body Mass Index
Japan

Keywords

  • Decision support system
  • Japanese Kampo medicine
  • Random forests
  • Traditional medicine pattern diagnosis

ASJC Scopus subject areas

  • Health Policy
  • Health Informatics

Cite this

Predicting Japanese Kampo formulas by analyzing database of medical records : A preliminary observational study. / Yoshino, Tetsuhiro; Katayama, Kotoe; Horiba, Yuko; Munakata, Kaori; Yamaguchi, Rui; Imoto, Seiya; Miyano, Satoru; Mima, Hideki; Watanabe, Kenji.

In: BMC Medical Informatics and Decision Making, Vol. 16, No. 1, 118, 13.09.2016.

Research output: Contribution to journalArticle

Yoshino, Tetsuhiro ; Katayama, Kotoe ; Horiba, Yuko ; Munakata, Kaori ; Yamaguchi, Rui ; Imoto, Seiya ; Miyano, Satoru ; Mima, Hideki ; Watanabe, Kenji. / Predicting Japanese Kampo formulas by analyzing database of medical records : A preliminary observational study. In: BMC Medical Informatics and Decision Making. 2016 ; Vol. 16, No. 1.
@article{e73a5a5120304725acd686ace977299c,
title = "Predicting Japanese Kampo formulas by analyzing database of medical records: A preliminary observational study",
abstract = "Background: Approximately 90 {\%} of physicians in Japan use Kampo medicine in daily practice. However, it is a challenge for physicians who do not specialize in Kampo medicine to select a proper Kampo formula out of the 148 officially approved formulas, as the decision relies on traditional measurements and traditional medicine pattern diagnoses. The present study tries to evaluate the feasibility of a decision support system for frequently used Kampo formulas. Methods: Our study included 393 patients who visited the Kampo Clinic at Keio University Hospital for the first time between May 2008 and March 2013. We collected medical records through a browser-based questionnaire system and applied random forests to predict commonly prescribed Kampo formulas. Results: The discriminant rate was the highest (87.0 {\%}) when we tried to predict a Kampo formula from two candidates using age, sex, body mass index, subjective symptoms, and the two essential and predictable traditional medicine pattern diagnoses (excess-deficiency and heat-cold) as predictor variables. The discriminant rate decreased as the candidate Kampo formulas increased, with the greatest drop occurring between three (76.7 {\%}) and four (47.5 {\%}) candidates. Age, body mass index, and traditional medicine pattern diagnoses had higher importance according to the characteristics of each Kampo formula when we utilized the prediction model, which predicted a Kampo formula from among three candidates. Conclusions: These results suggest that our decision support system for non-specialist physicians works well in selecting appropriate Kampo formulas from among two or three candidates. Additional studies are required to integrate the present statistical analysis in clinical practice.",
keywords = "Decision support system, Japanese Kampo medicine, Random forests, Traditional medicine pattern diagnosis",
author = "Tetsuhiro Yoshino and Kotoe Katayama and Yuko Horiba and Kaori Munakata and Rui Yamaguchi and Seiya Imoto and Satoru Miyano and Hideki Mima and Kenji Watanabe",
year = "2016",
month = "9",
day = "13",
doi = "10.1186/s12911-016-0361-9",
language = "English",
volume = "16",
journal = "BMC Medical Informatics and Decision Making",
issn = "1472-6947",
publisher = "BioMed Central",
number = "1",

}

TY - JOUR

T1 - Predicting Japanese Kampo formulas by analyzing database of medical records

T2 - A preliminary observational study

AU - Yoshino, Tetsuhiro

AU - Katayama, Kotoe

AU - Horiba, Yuko

AU - Munakata, Kaori

AU - Yamaguchi, Rui

AU - Imoto, Seiya

AU - Miyano, Satoru

AU - Mima, Hideki

AU - Watanabe, Kenji

PY - 2016/9/13

Y1 - 2016/9/13

N2 - Background: Approximately 90 % of physicians in Japan use Kampo medicine in daily practice. However, it is a challenge for physicians who do not specialize in Kampo medicine to select a proper Kampo formula out of the 148 officially approved formulas, as the decision relies on traditional measurements and traditional medicine pattern diagnoses. The present study tries to evaluate the feasibility of a decision support system for frequently used Kampo formulas. Methods: Our study included 393 patients who visited the Kampo Clinic at Keio University Hospital for the first time between May 2008 and March 2013. We collected medical records through a browser-based questionnaire system and applied random forests to predict commonly prescribed Kampo formulas. Results: The discriminant rate was the highest (87.0 %) when we tried to predict a Kampo formula from two candidates using age, sex, body mass index, subjective symptoms, and the two essential and predictable traditional medicine pattern diagnoses (excess-deficiency and heat-cold) as predictor variables. The discriminant rate decreased as the candidate Kampo formulas increased, with the greatest drop occurring between three (76.7 %) and four (47.5 %) candidates. Age, body mass index, and traditional medicine pattern diagnoses had higher importance according to the characteristics of each Kampo formula when we utilized the prediction model, which predicted a Kampo formula from among three candidates. Conclusions: These results suggest that our decision support system for non-specialist physicians works well in selecting appropriate Kampo formulas from among two or three candidates. Additional studies are required to integrate the present statistical analysis in clinical practice.

AB - Background: Approximately 90 % of physicians in Japan use Kampo medicine in daily practice. However, it is a challenge for physicians who do not specialize in Kampo medicine to select a proper Kampo formula out of the 148 officially approved formulas, as the decision relies on traditional measurements and traditional medicine pattern diagnoses. The present study tries to evaluate the feasibility of a decision support system for frequently used Kampo formulas. Methods: Our study included 393 patients who visited the Kampo Clinic at Keio University Hospital for the first time between May 2008 and March 2013. We collected medical records through a browser-based questionnaire system and applied random forests to predict commonly prescribed Kampo formulas. Results: The discriminant rate was the highest (87.0 %) when we tried to predict a Kampo formula from two candidates using age, sex, body mass index, subjective symptoms, and the two essential and predictable traditional medicine pattern diagnoses (excess-deficiency and heat-cold) as predictor variables. The discriminant rate decreased as the candidate Kampo formulas increased, with the greatest drop occurring between three (76.7 %) and four (47.5 %) candidates. Age, body mass index, and traditional medicine pattern diagnoses had higher importance according to the characteristics of each Kampo formula when we utilized the prediction model, which predicted a Kampo formula from among three candidates. Conclusions: These results suggest that our decision support system for non-specialist physicians works well in selecting appropriate Kampo formulas from among two or three candidates. Additional studies are required to integrate the present statistical analysis in clinical practice.

KW - Decision support system

KW - Japanese Kampo medicine

KW - Random forests

KW - Traditional medicine pattern diagnosis

UR - http://www.scopus.com/inward/record.url?scp=84986903174&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84986903174&partnerID=8YFLogxK

U2 - 10.1186/s12911-016-0361-9

DO - 10.1186/s12911-016-0361-9

M3 - Article

C2 - 27619018

AN - SCOPUS:84986903174

VL - 16

JO - BMC Medical Informatics and Decision Making

JF - BMC Medical Informatics and Decision Making

SN - 1472-6947

IS - 1

M1 - 118

ER -