한방진단설문지 임상자료에 근거한 기혈음양 허증병기 의사결정규칙 연구
A Study on Decision Rules for Qi·Blood·Yin·Yang Deficiency Pathogenic Factor Based on Clinical Data of Diagnosis System of Oriental Medicine
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
In order to deduce the pathogenic factor(PF) diagnosis logic of underlying in pattern identification of Korean medicine, 2,072 cases of DSOM(Diagnosis System of Oriental Medicine) data from May 2005 to April 2022 were collected and analyzed by means of decision tree model(DTM). The entire data were divided into training data and validation data at a ratio of 7:3. The CHAID algorithm was used for analysis of DTM, and then validity was tested by applying the validation data. The decision rules of items and pathways determined from the diagnosis data of Qi Deficiency, Blood Deficiency, Yin Deficiency and Yang Deficiency Pathogenic Factor of DSOM were as follows. Qi Deficiency PF had 7 decision rules and used 5 questions: Q124, Q116a, Q119, Q119a, Q55. The primary indicators(PI) were 'lack of energy' and 'weary of talking'. Blood deficiency PF had 7 decision rules and used 6 questions: Q113, Q84, Q85, Q114, Q129, Q130. The PI were 'numbness in the limbs', 'dizziness when standing up', and 'frequent cramps'. Yin deficiency PF had 3 decision rules and used 2 questions: Q144 and Q56. The PI were 'subjective heat sensation from the afternoon to night' and 'heat sensation in the limbs'. Yang deficiency PF had 3 decision rules and used 3 questions: Q55, Q10, and Q102. The PI were 'sweating even with small movements' and 'lack of energy'. Conclusively, these rules and symptom information to decide the Qi·Blood·Yin·Yang Deficiency PF would be helpful for Korean medicine diagnostics.
Abstract
In order to deduce the pathogenic factor(PF) diagnosis logic of underlying in pattern identification of Korean medicine, 2,072 cases of DSOM(Diagnosis System of Oriental Medicine) data from May 2005 to April 2022 were collected and analyzed by means of decision tree model(DTM). The entire data were divided into training data and validation data at a ratio of 7:3. The CHAID algorithm was used for analysis of DTM, and then validity was tested by applying the validation data. The decision rules of items and pathways determined from the diagnosis data of Qi Deficiency, Blood Deficiency, Yin Deficiency and Yang Deficiency Pathogenic Factor of DSOM were as follows. Qi Deficiency PF had 7 decision rules and used 5 questions: Q124, Q116a, Q119, Q119a, Q55. The primary indicators(PI) were 'lack of energy' and 'weary of talking'. Blood deficiency PF had 7 decision rules and used 6 questions: Q113, Q84, Q85, Q114, Q129, Q130. The PI were 'numbness in the limbs', 'dizziness when standing up', and 'frequent cramps'. Yin deficiency PF had 3 decision rules and used 2 questions: Q144 and Q56. The PI were 'subjective heat sensation from the afternoon to night' and 'heat sensation in the limbs'. Yang deficiency PF had 3 decision rules and used 3 questions: Q55, Q10, and Q102. The PI were 'sweating even with small movements' and 'lack of energy'. Conclusively, these rules and symptom information to decide the Qi·Blood·Yin·Yang Deficiency PF would be helpful for Korean medicine diagnostics.
참고문헌 (21)
- 김미진, "한방진단설문지 DSOM (r) S.1.1의 신뢰도연구", 동의생리병리학회지, 19(5), pp.1146~1153 (2005), 한의병리학회
- 이인선, "한방진단설문지 DSOM (r) S.1.1의 Upgrade를 위한 신뢰도 연구", 동의생리병리학회지, 26(1), pp.88~97 (2012), 한의병리학회
- 이인선, "한방부인과 진단용 설문지의 病機 연구", 동의생리병리학회지, 18(2), pp.401~407 (2004), 한의병리학회
- 민병화, "韓方婦人科 診斷設問紙의 信賴度硏究", 대한한의학회지, 26(2), pp.126~139 (2005), 대한한의학회
- 권혁, "설문지 분석법에 의한 肝？心？脾？肺？腎病의 標準 症狀 및 男女差異 硏究", 동의생리병리학회지, 20(4), pp.1057~1062 (2006), 한의병리학회
- 진희정, "사상체질 임상자료 기반 의사결정나무 생성 알고리즘 비교", 한국한의학연구원논문집, 17(2), pp.121~128 (2011), 한국한의학연구원
- 김규곤, "의사결정나무모형을 이용한 사상체질분류함수의 개발에 관한 연구 (I) - 크론박 알파 계수에 의한 변수선택 -", Journal of The Korean Data Analysis Society, 6(3), pp.751~766 (2004), 한국자료분석학회
- 박은경, "의사결정나무법을 이용한 체질진단에 관한 연구", 사상체질의학회지, 13(2), pp.144~155 (2001), 사상체질의학회
- 진희정, "사상체질 임상정보 분석을 위한 웹 기반의 의사결정 나무 프로그램 개발", 한국한의학연구원논문집, 14(3), pp.81~87 (2008), 한국한의학연구원
- 신상훈, "맥파를 이용한 사상체질의 진단에 있어서 분류방법에 따른 진단의 정확도 비교", 한국콘텐츠학회 논문지, 9(10), pp.249~257 (2009), 한국콘텐츠학회
- 이인선, "한방부인과 진단 설문지에 대한 평가와 硏究(Ⅱ)", 대한한방부인과학회지, 17(1), pp.160~166 (2004), 대한한방부인과학회
- 배경미, "한방부인과 辨證 診斷 설문지에 대한 評價와 硏究", 대한한방부인과학회지, 15(4), pp.111~127 (2002), 대한한방부인과학회
- 이인선, "한방부인과 진단 설문지의 병기가중치 부여연구", 대한한방부인과학회지, 18(4), pp.119~135 (2005), 대한한방부인과학회
- Kang HC, "Data Mining Methodology for Big Data analysis" (2014), Freeacademy
- G. V. Kass, "An Exploratory Technique for Investigating Large Quantities of Categorical Data", Appl. Statist, 29(2), pp.119~127 (1980)[DOI]
- J. V. Ryzin, "Classification and Regression Trees", J Am Stat Assoc, 81(393), pp.253~ (1986)
- Salzberg SL, "C4.5: Programs for Machine Learning by J. Ross Quinlan. Morgan Kaufmann Publishers, Inc., 1993", Machine Learning, 16, pp.235~240 (1994)
- Textbook Compilation Committee of Pathology of Korean Medicine, "Pathology of Korean Medicine", pp.233~234 (2019), Hanuimunhwasa
- National Health Commission, State Administration of traditional Chinese medicine, "Clinic terminology of traditional Chinese medical diagnosis and treatment—Part 2:syndromes", 132~137 (2020)
- Shen ZY, "TCM Deficiency Syndrome Differentiation Reference Standards", Chinese Journal of Integrated Traditional And Western Medicine, (10), pp.598~ (1986)
- Heo J, "Donguibogam", pp.71~ (2005), Donguibogam Publishing Co