Alan R. Dyer

Statistical methods to assess and minimize the role of intra-individual variability in obscuring the relationship between dietary lipids and serum cholesterol.

Abstract Investigations involving comparisons of populations, as well as intervention studies on groups, both under free-living and metabolic ward conditions, unequivocally demonstrate significant relationships between lipid components of the diet and serum cholesterol levels. However, low order or no correlations have been reported when these dietary variables and serum cholesterol are related for individuals. Several factors underlie this apparent paradox. This paper discusses at length the role of intra-individual variation in this apparent paradox, with particular emphasis on the errors caused by intra-individual variation in classification and estimation of correlation coefficients. Methods are presented for estimating the number of measurements required to achieve a suitable degree of accuracy for both classification and correlation analysis. Based on these theoretical considerations and practical examples illustrating their application, an assessment is made of commonly used dietary survey methods in terms of their appropriateness for measuring individual dietary intake. Suggestions are made for improving the design and methods of nutritional surveys, especially with regard to reducing errors introduced by intra-individual variation.

Alcohol consumption, cardiovascular risk factors, and mortality in two Chicago epidemiologic studies.

Multivariate analysis of the association at baseline between problem drinking and cardiovascular risk factors among 1,233 white male employees of the Chicago Peoples Gas Company age 40-59 showed the 38 problem drinkers with significantly higher blood pressures and cigarette consumption and significantly lower relative weights than the others. Similar analyses among 1,899 white male employees of the Hawthorne Works of the Western Electric Company in Chicago age 40-55 showed the 117 men consuming 5 or more drinks per day with significantly higher blood pressures and cigarette use than the others. No significant differences were recorded between heavy drinkers and the others in serum cholesterol level. The gas company problem drinkers had significantly higher 15- year mortality rates from all causes, cardiovascular diseases, coronary heart disease, and sudden death. These differences could not be entirely explained by their blood pressure, smoking, and relative weight status. The Western Electric heavy drinkers had increased 10-year mortality rates both for all causes and noncardiovascular causes.

Hypertension in the elderly.

The available data indicate that classical hypertension, defined here as a diastolic blood pressure greater than or equal to 95 mm Hg, is a widely prevalent and as important a risk factor for the cardiovascular diseases in those aged 65 and over as it is in those under 65. The limited available data also indicate that pure systolic hypertension, defined here as a systolic blood pressure exceeding 160 mm Hg with a diastolic pressure under 95 mm Hg, also very common at age 65 and over, is also related to excess cardiovascular morbidity and mortality in the elderly. However, it is not clear whether this latter relationship is indicative of cause and effect, or merely reflects the fact that in the elderly pure systolic hypertension is a sign of extensive sclerosis of large arteries. The results of Veterans Administration studies on antihypertensive therapy indicate that the elderly patient with classical hypertension is amenable to effective treatment, and that the benefits of such treatment significantly outweigh the risks. Great care is needed in the use of drugs for the management of hypertension in elderly patients, especially to minimize risk of hypotensive episodes and their possible harmful consequences; but with judicious and careful therapy, hypertension of this type can be controlled with reduction in excess risk of morbidity and mortality, at least for those with average diastolic pressures greater than or equal to 105 mm Hg. The lack of data on the benefits of treatment for those with pure systolic hypertension precludes any recommendations in regard to pharmacologic treatment of this condition.

Multivariate analysis of the relationship of seven variables to blood pressure: Findings of the Chicago Heart Association Detection Project in Industry, 1967–1972

Abstract 1. 1. As in the preceding cross-sectional study [1], four multivariate statistical methods —partial correlation, multiple cross classification, multiple logistical regression, and multiple linear regression—were used to evaluate the relationship between seven variables and blood pressure in over 21,000 employed men and women, white and black, ages 25–44 and 45–64 surveyed in almost 100 Chicago companies and organizations. The analyses were carried out separately for eight age-sex-race groups. The seven variables were relative weight, resting heart rate, plasma glucose one hr after 50 g oral load, serum uric acid and cholesterol, current cigarette smoking habit, and age. 2. 2. Consistent with the findings of the preceding report, the first three of these variables—relative weight, heart rate, and plasma glucose—were independently related to blood pressure with a high degree of consistency, with p values for statistical significance ≤0.01 or ≤0.001 in the great majority of analyses. 3. 3. Serum uric acid—a variable not evaluated in the preceding report—was also independently related to blood pressure in a great majority of the analyses with p values of ≤0.01 or ≤0.001. 4. 4. The findings with respect to serum cholesterol and blood pressure were generally negative, except for white males, an intriguing finding in view of a similar result from the preceding study. 5. 5. No positive relationship was found between cigarette smoking and blood pressure. 6. 6. Even within the narrow age bands studied—ages 25–44 and 45–64—age was significantly related to blood pressure in a great majority of analyses (p values ≤0.01 or ≤0.001), independent of the six other variables. 7. 7. As in the preceding paper, when multivariate regression equations and their coefficients, computed from this experience of an entire age-sex-race group, were used to calculate an expectation of elevated blood pressure for each person, and then persons were ordered from low to high in expectation, a high proportion of all persons with recorded elevations of blood pressure were in the highest decile and quintile of expected prevalence—e.g. for persons age 25–44 in the four sex-race groups, from 45 to 56 per cent of observed cases with diastolic pressure ≥95 mm Hg. were in the highest quintile (20 per cent) of expected prevalence. The observed prevalence of elevated blood pressure was many times greater for the highest quintile of expected prevalence than for the lowest. A similar but less effective concentration of cases of elevated blood pressure was obtained with the multiple cross classification method, by dichotomizing five of the independent variables and identifying the substratum with any three, four or all five high.

Alcohol consumption and 17-year mortality in the Chicago Western Electric Company study

Abstract The association between baseline alcohol intake and mortality from all causes and specific causes based on 17 years of follow-up experience was analyzed for 1,832 white males originally age 40–55 from the Chicago Western Electric Company study. Alcohol consumption was expressed as number of drinks per day for all intake combined, including hard liquor, beer, and wine, based on the maximum intake reported on three questionnaires. With mortality rates adjusted only for age, total intake was associated with increased risk of death from all causes, the cardiovascular diseases, coronary heart disease, cancer, and other causes at the level of six or more drinks per day. There was no increase in mortality with increasing alcohol consumption below this level. Only the associations between alcohol intake and death from the cardiovascular diseases and coronary heart disease failed to persist after adjustment for other risk factors, such as smoking and blood pressure. When the deaths were divided into those occurring within the first 10 years of follow-up and those occurring more than 10 years after entry, the association between baseline alcohol intake and mortality was generally stronger for those deaths occurring more than 10 years after entry.

Relationship of relative weight and body mass index to 14-year mortality in the Chicago Peoples Gas Company study.

Abstract The importance of relative weight and body mass index to 14-yr mortality of 1233 white males of the Chicago Peoples Gas Company Study is analyzed by the inclusion of a quadratic term for weight in the multiple logistic function. The endpoints of death, all causes, CVR death, and CHD death are found to have a significant quadratic relationship to body mass index for the total cohort of 1233 men, while relative weight is found to have a quadratic relationship only with death, all causes. When the group is broken into men aged 40–49 and 50–59, body mass continues to show an important quadratic relationship to all three endpoints, while relative weight shows only an important quadratic relationship to death, all causes, among men aged 50–59. When the cohort is divided into smokers and nonsmokers, body mass index shows a significant quadratic relationship to all endpoints except CHD death among nonsmokers. Relative weight, on the other hand, is related quadratically only to total mortality in both groups. The weights corresponding to the lowest mortality are found to be about 25–35 per cent above the ideal published by the Metropolitan Life Insurance Company. Thus, for this cohort moderate overweight appears to be a sign of good health. Those individuals with the highest risk are those near the so-called ideal weight and those who are markedly obese, say with a relative weight above 150 or 160.

Serum cholesterol and risk of death from cancer and other causes in three Chicago epidemiological studies

Abstract Although hypercholesterolemia is established as a major risk factor for coronary heart disease, the finding in some epidemiological studies of no association between serum cholesterol and all causes mortality suggests that serum cholesterol may be inversely related to the risk of death from non-cardiovascular causes, e.g. cancer. This possibility led to the examination of this question in middle-aged white males from the Chicago Peoples Gas Company and Chicago Western Electric Company studies, and in middle-aged white males and females from the Chicago Heart Association Detection Project in Industry. In each of these studies, there was no significant association between initial serum cholesterol level and subsequent mortality from cancer, or from causes other than cancer and the cardiovascular diseases in men. There was, however, a significant inverse association with other causes of death in women. When the cancer deaths were examined by site, there was a significant inverse association between serum cholesterol and deaths from sarcoma, leukemia and Hodgkins disease in the Western Electric men and one that was nearly so in the Chicago Heart Association men. Serum cholesterol was not significantly related to lung cancer, colorectal cancer, oral cancer, pancreatic cancer, or to all other cancers combined in any of the three studies in men or in women. There was, however, the suggestion of a positive association for breast cancer in women. Thus, the results of these three studies do not generally support the hypothesis of an inverse association between serum cholesterol and cancer in urban middle-aged white American males and females.

Uric acid: a risk factor for coronary heart disease?

The association between serum uric acid the prevalence of ECG abnormalities was analyzed for 24,997 employed men women, white black, age 18–64 years, from the Chicago Heart Association (CHA) Detection Project in Industry. In addition, the relationships between uric acid 5-year mortality from all causes, from cardiovascular diseases (CVD), from coronary heart disease (CHD) were analyzed for 7804 white men women age 45-64 years from this study 967 white men age 44–63 years from the Chicago Peoples Gas Company Study. For men, the associations between uric acid the prevalence of ECG abnormalities with mortality appear to be secondary to associations between uric acid other risk factors. For women, however, the associations could not be explained by other risk factors.

HIGH BLOOD-PRESSURE: A RISK FACTOR FOR CANCER MORTALITY ?

Univariate and multivariate analyses have been made of the relationship of systolic and diastolic blood-pressure measured at study entry to subsequent 14-year mortality among 1233 White males originally age 40-59 in 1958 from the Chicago Peoples Gas Company prospective study. With age, serum-cholesterol, and cigarettes per day controlled, both elevated systolic and electaed diastolic blood-pressure in 1958 were found to be strongly related to subsequent mortality from cancer in the men of this study. The possibility that this finding was due either to an association between antihypertensive medication in general, and cancer, or to an association was found that could explain the excess cancer mortality among those with elevated blood-pressure in 1958, either with medication in general, or with reserpine and rauwolfia in particular. These findings thus pose the question, is high blood-pressure associated with an increased risk of death due to cancer?

Multivariate analysis of the relationship of six variables to blood pressure: findings from Chicago community surveys, 1965--1971.

Abstract 1. 1. Four multivariate statistical methods—partial correlation, multiple cross classification, multiple logistic regression, and multiple linear regression—were used to study the relationship between six variables and blood pressure in over 13,000 men and women, white and black, ages 30–44 and 45–64 surveyed in two low-income Chicago communities. The analyses were carried out separately for eight age-sex-race groups. The six variables were relative weight, resting heart rate, plasma glucose 1 hr after 100 g oral load, hematocrit, serum cholesterol and age. 2. 2. The first three of these variables—relative weight, heart rate, and plasma glucose —were independently related to blood pressure with a high degree of consistency, with p values for statistical significance ≤0.001. 3. 3. Hematocrit was independently and additively related to diastolic—but not to systolic—pressure for the four age-race groups of women, but only for one of the four age-race groups of men. 4. 4. The findings with respect to serum cholesterol and blood pressure were generally negative. 5. 5. Even within the narrow age groups studied—ages 30–44 and 45–64—age was significantly related to systolic level particularly ( p values ≤0.01 or ≤0.001), independent of the five other variables. 6. 6. When multivariate regression equations and their coefficients, computed from the experience of an entire age-sex-race group, were used to calculate an expectation of elevated blood pressure for each person, and then persons were ordered from low to high in expectation, a high proportion of all persons with recorded elevations of blood pressure were in the highest decile and quintile of expected prevalence—e.g. for persons age 30–44 in the four sex-race groups, from 47–69 per cent of observed cases with diastolic pressure ≥95 mm Hg were in the highest quintile (20 per cent) of expected prevalence. The observed prevalence of elevated blood pressure was as much as 20 times as high for the highest quintile of expected prevalence as for the lowest. A similar but less effective concentration of cases of elevated blood pressure was obtained with the multiple cross classification method, by dichotomizing four of the independent variables and identifying the substratum with any two, three or all four high.