SNP 자료를 이용한 B형 간암환자의 만성간염으로부터 이행예측 심볼릭 나무구조 모형연구 (Symbolic Tree Based Progression Model for B-viral Hepatocellular Carcinoma from Chronic Hepatitis using SNP Data)

서지정보

· 발행기관 : 한국보건정보통계학회
· 수록지 정보 : 보건정보통계학회지 / 37권 / 1호 / 109 ~ 120페이지
· 저자명 : 이태림

초록

Objectives: Using the new knowledge mining of symbolic data analysis which extends the data mining and exploratory data analysis, this paper would like to fitting the tree structured survival model on continuous response variable.
Methods: Visualization with SDA clustering for hidden relationship of SNP for HCC, we can show the characteristics of data structure and produce the quantitative statistics for evaluation of validity and stability of clustering. We can confirm validity of application of SDA to the tree structured progression model to quantify the clinical lab data and SNP data for early diagnosis of HCC.
Results: Our proposed model constructs the representative model for HCC survival time and with SNP gene data which contribute to promote the more healthy condition for old HCC patients. To fit the simple and easy interpretation tree structured survival model which could reduced from huge clinical and gene data under the new statistical theory of knowledge mining SDA.
Conclusions: Using SDA analysis survival tree of HCC could be derived with clinical lab data and SNP data. The tumor type, TACE number, diuretics, encephalopathy results were significant clinical variable and IL6R_q1-24013, IL6_572, IL1B_p1_511, IL13_p_1055, IKB_p1_673, IL6R_p1_183, TNFA_p2_863, IFNG_q1_2459 were selected as a significant splitting variables.

영어초록

Objectives: Using the new knowledge mining of symbolic data analysis which extends the data mining and exploratory data analysis, this paper would like to fitting the tree structured survival model on continuous response variable.
Methods: Visualization with SDA clustering for hidden relationship of SNP for HCC, we can show the characteristics of data structure and produce the quantitative statistics for evaluation of validity and stability of clustering. We can confirm validity of application of SDA to the tree structured progression model to quantify the clinical lab data and SNP data for early diagnosis of HCC.
Results: Our proposed model constructs the representative model for HCC survival time and with SNP gene data which contribute to promote the more healthy condition for old HCC patients. To fit the simple and easy interpretation tree structured survival model which could reduced from huge clinical and gene data under the new statistical theory of knowledge mining SDA.
Conclusions: Using SDA analysis survival tree of HCC could be derived with clinical lab data and SNP data. The tumor type, TACE number, diuretics, encephalopathy results were significant clinical variable and IL6R_q1-24013, IL6_572, IL1B_p1_511, IL13_p_1055, IKB_p1_673, IL6R_p1_183, TNFA_p2_863, IFNG_q1_2459 were selected as a significant splitting variables.

참고자료

· 없음