Upload
wyome
View
87
Download
0
Tags:
Embed Size (px)
DESCRIPTION
A STUDY OF DETERMINANTS OF PLASMA RETINOL AND BETA-CAROTENE. Tutor: Dr . Kaibo Wang Applied Statistics, Industrial Engineering, Tsinghua University Team member: Wang Jun 2009210552 Cui Wen 2009210554 Sun Ningning 2009210571 Lv Shikun 2009210566. Outline. - PowerPoint PPT Presentation
Citation preview
A STUDY OF DETERMINANTS OF PLASMA RETINOL AND BETA-CAROTENE
Tutor: Dr. Kaibo WangApplied Statistics, Industrial Engineering, Tsinghua UniversityTeam member:
– Wang Jun 2009210552 Cui Wen 2009210554– Sun Ningning 2009210571 Lv Shikun 2009210566
Page 2
I. INTRODUCTIONII. LITERATURE REWIEWIII. PURPOSE OF THE STUDYIV. ANALYSYS RESULTSV. REFERANCE
Outline
Page 3
I. INTRODUCTIONII. LITERATURE REWIEWIII. PURPOSE OF THE STUDYIV. ANALYSYS RESULTSV. REFERANCE
Outline
Page 4
INTRODUCTION
Past research: low dietary intake or low plasma concentrations of retinol, beta-carotene, or other carotenoids might be associated with increased risk of developing certain types of cancer.
Cross-sectional study: to investigate the relationship between personal characteristics and dietary factors, and plasma concentrations of retinol, beta-carotene and other carotenoids.
Experimernt: – N=315– Patients:
• Had an elective surgical procedure during a three-year period• Removed a lesion of the lung, colon, breast, skin, ovary or uterus• Non-cancerous
Page 5
I. INTRODUCTIONII. LITERATURE REWIEWIII. PURPOSE OF THE STUDYIV. ANALYSYS RESULTSV. REFERANCE
Outline
Page 6
1 、 Observational studies have suggested that low dietary intake or low plasma
concentrations of retinol, beta-carotene, or other carotenoids might be
associated with increased risk of developing certain types of cancer ;
2 、 The relationship between plasma carotenoids, plasma cholesterol, cigarette
smoking, vitamin supplement use, and intakes of alcohol, vitamin A, and
carotene were investigated in 1981 by in the research of Russell-Briefel R ;
3 、 The relationship of diet and nutritional supplements, cigarette use, alcohol
consumption, and blood lipids to plasma levels of beta-carotene was studied
among 330 men and women aged 18–79 years in the research of Stryker WS.
LITERATURE REWIEW
Page 7
1 、 Many epidemiologic studies have been conducted primarily as dietary studies
of vitamin A and carotene, or as blood studies of serum retinol.
2 、 Willett WC showed that, with higher levels of retinol plasma, the risks of get
cancer may be decreased. However, plasma retinol levels are under strict
control and a high intake of preformed vitamin does not seem to be relevant
for cancer prevention;
3 、 Stähelin, H. B. suggested an inverse relationship between vitamin A and
cancer risk, although some studies have found no relationship. Then people
find that a lower retinol levels is not the cause of an invasive cancer. Instead,
it is the cancer that brings about a lower retinol level in human body;
LITERATURE REWIEW
Page 8
I. INTRODUCTIONII. LITERATURE REWIEWIII. PURPOSE OF THE STUDYIV. ANALYSYS RESULTSV. REFERANCE
Outline
Page 9
PURPOSE OF THE STUDY
Tofind out internal factors which may have some effect or relationship with the beta-carotene and retinol in people’s plasma.
– Age (years)– Quetelet: – Number of calories consumed per day.– Grams of fat consumed per day.– Grams of fiber consumed per day.– Number of alcoholic drinks consumed per week.– Cholesterol consumed (mg per day).– Dietary beta-carotene consumed (mcg per day).– Dietary retinol consumed (mcg per day)– Sex (1=Male, 2=Female).– Smoking status (1=Never, 2=Former, 3=Current Smoker)– Vitamin Use (1=Yes, fairly often, 2=Yes, not often, 3=No)
Page 10
PURPOSE OF THE STUDY
Page 11
I. INTRODUCTIONII. LITERATURE REWIEWIII. PURPOSE OF THE STUDYIV. ANALYSYS RESULTSV. REFERANCE
Outline
Page 12
Content:1. Variables Types and Levels Quantitative variables & Categorical variables2. Descriptive Analysis For all 12 independent variables, with: Summary Statistics/Histogram/Scatter Plot3. Data Analysis via Regression & General Linear Model 3.1 BETA-CAROTENE 3.2 RETINOL
ANALYSYS RESULTS
Page 13
Variable: SEX
1 : Male 2 : FemalePlasma Retinol: Male is higher than femaleBeta-Carotene: Female is a little higher and more outliers
2.Descriptive Analysis
Page 14
Variable: VITUSE(Vitamin use)
1=Yes, fairly often, 2=Yes, not often, 3=NoPlasma Retinol: No much difference, almost in the same levelBeta-Carotene: Often users>Not-often users>Non-users
2.Descriptive Analysis
Page 15
Variable: SMOKSTAT(Smoking Status)
1=Never, 2=Former, 3=Current SmokerPlasma Retinol: Former smokers has the highest levelBeta-Carotene: Never smokers contains higher level
2.Descriptive Analysis
Page 16
An example for continuous variables
2.Descriptive Analysis
Mean StDev Min Q1 Median Q3 Max
Age 50.146 14.575 19.000 39.000 48.000 63.000 83.000
Page 17
Variable : AGE, QUETELET , CALORIES
AGE(age): Most in the area between 32 and 77who are basically middle-age or elderly people.
QUETELET( ): Most between 18.5 and 30 who are normal and some are a little overweight.
CALORIES(calories): Most are concentrated between 1000 and 2200.
2.Descriptive Analysis
Page 18
Variable: QUETELET( )Standard category from WHO:
Quetelet is a statistical measurement which compares a person's weight and height.
2.Descriptive Analysis
Category BMI range – kg/m2
Severely underweight
less than 16.5
Underweight from 16.5 to 18.4
Normal from 18.5 to 24.9
Overweight from 25 to 30
Obese Class I from 30.1 to 34.9
Obese Class II from 35 to 40
Obese Class III over 40
Page 19
Variable: FAT, FIBER, ALCOHOL
FAT: Grams of fat consumed per day. Most are between 45 and 135.FIBER: Grams of fiber consumed per day. Between 6 and 18ALCOHOL: Number of alcoholic drinks consumed per week. Most rarely
drink, but there is an obvious outlier, which reaches 203 alcohol per week.
2.Descriptive Analysis
Page 20
Variable: CHOLESTEROL, BETADIET, RETDIET
CHOLESTEROL: milligram of cholesterol consumed per dayBETADIET : microgram of dietary beta-carotene consumed per dayRETDIET : microgram of dietary retinol consumed per day Most are between 500 and 1500.
2.Descriptive Analysis
Page 21
3.1 data analysis about BETA-CAROTENE
AGEQUETELETCALORIES
FATFIBER
ALCOHOLCHOLESTEROL
BETADIETRETDIET
SEXSMOKSTAT
VITUSE
Beta-carotene content in
plasma1 、 Regression2 、 GLM
?
Page 22
Steps of Regression:1 、 Check data distribution through scatter plots 2 、 Best subset and stepwise regression to select predictors3 、 Do regression and residual check4 、 Do transformation5 、 The final model
3.1.1 data analysis via Regression ( BETA-CAROTENE )
Page 23
1 、 Check data distribution through scatter plots transformation can not avoid data aggregations, and therefore delete the outliers
906030 4000200001600
800
090
60
30
50
35
20
16008000
4000
2000
0503520
Pl asma beta- carotene
Age
Quetel et
CALORI ES
Pl asma beta- carotene, Age, Quetel et, CALORI ES 的矩阵图
3.1.1 data analysis via Regression ( BETA-CAROTENE )
Page 24
2 、 Use best subset and stepwise regression to select predictors Use dummy variables to take place of discreet variables:
SEX, SMOKSTAT and VITUSE Result of stepwise regression :
Variables T-Value P-value
QUETLET -4.11 0.000
BETADIET 3.57 0.000
Vitamin_status_3 -3.17 0.002
Smoking_status_3 -2.04 0.042
FAT -1.88 0.061
3.1.1 data analysis via Regression ( BETA-CAROTENE )
Page 25
3 、 Do regression and residual check
3.1.1 data analysis via Regression ( BETA-CAROTENE )
Page 26
4 、 Do transformation use log (plasma beta-carotene) to replace plasma beta-carotene Redo step1—step3
Variables P-value coefficient
QUETLET 0.000 -0.0140
BETADIET 0.054 0.000025Vitamin_status_3 0.001 -0.124
Smoking_status_3 0.023 -0.116
FAT 0.048 -0.00113
AGE 0.046 0.00248
Sex_2 0.085 0.0934
FIBER 0.132 0.00632
3.1.1 data analysis via Regression ( BETA-CAROTENE )
Page 27
5 、 The final model
Log (plasma beta-carotene) = 2.32 - 0.0140QUETLET -
0.124vitamin_status_3- 0.116 smoking_status_3 +
0.000025 BETADIET - 0.00113 FAT+ 0.00248 AGE+
0.0934 sex_2 + 0.00632 FIBER
3.1.1 data analysis via Regression ( BETA-CAROTENE )
Page 28
Steps of GLM:1 、 Check data distribution through scatter plots 2 、 Select predictors by trial3 、 GLM model4 、 Residual check
3.1.2 data analysis via GLM ( BETA-CAROTENE )
Page 29
1 、 Check data distribution through scatter plots similar to step 1 of regression
2 、 Select predictors by trial Variables P-value coefficient
AGE 0.090 0.002224QUETLET 0.000 -0.014010
CALORIES 0.385 -0.000082FAT 0.758 0.000447
FIBER 0.139 0.00818ALCOHOL 0.750 0.001381
CHOLESTEROL 0.603 -0.000109BETADIET 0.111 0.000021RETDIET 0.337 0.000033BETADIET*Vitami
n
Vitamin_1 0.027 0.000034Vitamin_2 0.858 0.000003
3.1.2 data analysis via GLM ( BETA-CAROTENE )
Page 30
3 、 GLM model
Log (plasma beta-carotene) =2.3061+0.002224 AGE-
0.014010QUETLET+0.00818FIBER+0.000021BETADIE
T+0.000034BETADIET*Vitamin_1
3.1.2 data analysis via GLM ( BETA-CAROTENE )
Page 31
4 、 Residual check
3.1.2 data analysis via GLM ( BETA-CAROTENE )
Page 32
Conclusion :
1 、 The coefficient of QUETLET, vitamin_status_3, smoking_status_3 and FAT are
negative, which indicates that with the increase of these variables, there would
be a decrease of the content of beta-carotene in plasma;
2 、 The coefficient of BETADIET, AGE, Sex_2 and FIBER are positive, which
indicates that with the increase of average number of these variables, there
would also be an increase of the content of beta-carotene in plasma.
Log (plasma beta-carotene) = 2.32 - 0.0140QUETLET -0.124vitamin_status_3- 0.116 smoking_status_3 + 0.000025 BETADIET - 0.00113 FAT+ 0.00248 AGE+ 0.0934 sex_2 + 0.00632 FIBER
3.1 data analysis about BETA-CAROTENE
Page 33
Steps of Regression:1 、 Check data distribution through scatter plots 2 、 Best subset and stepwise regression (3 methods) to select predictors3 、 Do regression and residual check4 、 Draw conclusion
3.2.1 data analysis via Regression ( RETINOL )
Page 34
1 、 Check data distribution through scatter plots
3.2.1 data analysis via Regression ( RETINOL )
Page 35
1 、 Check data distribution through scatter plots
3.2.1 data analysis via Regression ( RETINOL )
Page 36
2 、 Use best subset and stepwise regression to select predictors Using dummy variables to transform the Categorical variables
Define SEX_F=SEX-1, so SEX_F=1, when SEX=Female; SEX_F=0, when SEX=Male.
3.2.1 data analysis via Regression ( RETINOL )
SMOKSTAT SMOK_1 SMOK_21 0 02 0 13 1 0
VITUSE VITUSE _1 VITUSE _21 0 02 0 13 1 0
Page 37
2 、 Use best subset and stepwise regression to select predictors Select 7 variables : AGE, QUETELET, ALCOHOL, BETADIET, SEX_F, SMOK_2, and VITUSE_1 Result of stepwise regression :
3.2.1 data analysis via Regression ( RETINOL )
Variables T-Value P-value
AGE 3.32 0.002
QUETELET 1.72 0.295
ALCOHOL 3.24 0.053
BETADIET -2.04 0.031
SEX_F -1.97 0.027
SMOK_2 1.70 0.035
VITUSE_1 -2.95 0.033
R-sq.= 13.55; R-Sq.(adj)=11.42
Page 38
2 、 Use best subset and stepwise regression to select predictors The model is :
3.2.1 data analysis via Regression ( RETINOL )
RETPLASMA = 517 + 2.09 AGE - 0.0149 BETADIET+5.228 ALCOHOL- 71.7 SEX_F + 41.9 SMOK_2 - 43.4 VITUSE_1
Page 39
Steps of GLM:1 、 Select interaction predictors by trial2 、 GLM model3 、 Residual check
3.2.2 data analysis via GLM ( RETINAL )
Page 40
1 、 Select predictors by trial Finally find no interaction predictor.
3.2.2 data analysis via GLM ( RETINAL )
Variables T-Value P-value
Constant 6.57 0.000
AGE 2.50 0.013
QUETLET 0.90 0.370
CALORIES -0.70 0.486
FAT -1.43 0.153
FIBER -0.79 0.428
ALCOHOL 1.77 0.079
CHOLESTEROL 0.92 0.360
BETADIET -1.66 0.097
RETDIET 0.40 0.688
R-sq.= 14.75%; R-Sq.(adj)= 9.52%
Page 41
3 、 GLM model
3.2.2 data analysis via GLM ( RETINAL )
RETPLASMA=510.86+1.8777AGE+5.002ALCOHOL-0.013507BETADIET
Page 42
4 、 Residual check
3.2.2 data analysis via GLM ( RETINAL )
5002500-250-500
99. 999
90
50
10
10. 1
Resi dual
Perc
ent
800700600500400
400
200
0
-200
-400
Fi tted Val ue
Resi
dual
4003002001000-100-200-300
40
30
20
10
0
Resi dual
Freq
uenc
y
260240220200180160140120100806040201
400
200
0
-200
-400
Observati on Order
Resi
dual
Normal Probabi l i ty Pl ot Versus Fi ts
Hi stogram Versus Order
Resi dual Pl ots for RETPLASMA
Page 43
Conclusion :
1. The coefficient of AGE is positive in both models, indicating that as people get
older, the plasma retinal level will raise.
2. Both model shows that people drink more wine will have higher plasma retinal
level. But the data of ALCOHOL is almost all less than 10, so its influence is
not obivous.
3.2.2 data analysis via GLM ( RETINAL )
RETPLASMA = 517 + 2.09 AGE +5.228 ALCOHOL- 0.0149 BETADIET- 71.7 SEX_F + 41.9 SMOK_2 - 43.4 VITUSE_1
RETPLASMA=510.86+1.8777AGE+5.002ALCOHOL-0.013507BETADIET
Regression:
GLM:
Page 44
3.2.2 data analysis via GLM ( RETINAL )
RETPLASMA = 517 + 2.09 AGE +5.228 ALCOHOL- 0.0149 BETADIET- 71.7 SEX_F + 41.9 SMOK_2 - 43.4 VITUSE_1
RETPLASMA=510.86+1.8777AGE+5.002ALCOHOL-0.013507BETADIET
Regression:
GLM:
Conclusion :
3. The coefficient of BETADIET is negative in both models, which means that
people consuming more beta-carotene have lower level of plasma retinal. So
balance of different vitamin is very important.
4. The coefficient of 3 dummy variables in regression model is -71.7, 41.9 and -
43.4, indicating women’s average plasma retinal level is lower than men’s.
People who are former smokers or never use vitamin have lower plasma retinal
level .
Page 45
We conclude that there is wide variability in plasma concentrations
of these micronutrients in humans, and that much of this variability is
associated with dietary habits and personal characteristics. A better
understanding of the physiological relationship between some personal
characteristics and plasma concentrations of these micronutrients will
require further study.
Discussion
Page 46
I. INTRODUCTIONII. LITERATURE REWIEWIII. PURPOSE OF THE STUDYIV. ANALYSYS RESULTSV. REFERANCE
Outline
Page 47
Peto R, Doll R, Buckley JD, et al. Can dietary beta-carotene materially reduce human cancer rates? Nature 1981;290:201-8.
Russell-Briefel R, Bates MW, Kuller LH. The relationship of plasma carotenoids to health andbiochemical factors in middle-aged men. Am J Epidemiol 1986;122:741-9.
Stryker WS, Kaplan LA, Stein EA, et al. The relation of diet, cigarette smoking, and alcohol consumption to plasma beta-carotene and alphatocopherol levels. Am J Epidemiol 1988;127:283- 96.
Adams-Campbell, L. L., M. U. Nwankwo, et al. (1992). Serum retinol, carotenoids, vitamin E, and cholesterol in Nigerian women. Nutritional Biochemistry 3(2): 58-61.
REFERANCE
Page 48
Comstock, G. W., M. S. Menkes, et al. (1988). Serum levels of retinol, beta-carotene, and alpha-tocopherol in older adults.American Journal of Epidemiology 127(1): 114-123.
Russellbriefel, R., M. W. Bates, et al. (1985). The relationship of plasma carotenoids to health and biohchemical factors in middle-aged men. American Journal of Epidemiology 122(5): 741-749.
Stähelin, H. B., E. Buess, et al. (1982). vitamin A, cardiovascular risk factors, and mortality. The Lancet 319(8268): 394-395.
Van Poppel, G. and H. van den Berg (1997). Vitamins and cancer. Cancer Letters 114(1-2): 195-202.
REFERANCE
Page 49
Thank YouFor
For Attention