Relative survival is the standard measure of excess mortality due to cancer in population-based cancer survival studies. In relative survival analysis, the observed hazard for cancer patients is the sum of the expected hazard for the general cancer-free population and the excess hazard associated with a cancer diagnosis. Previous models for relative survival analysis have assumed that the excess hazard rate is related to covariates by additive or multiplicative regression models. In this paper, a transformation covariate regression model is developed for estimation of the excess hazard rate, which includes both the additive and the multiplicative regression models as special cases. The baseline excess hazard rate and time-dependent hazard ratios can be approximated by means of regression splines, and the parameter estimates can be obtained using a standard statistical package. As is demonstrated through simulation, the proposed transformation hazards model provides a reasonably good fit to typical relative survival data. For illustration purposes, the sex difference in relative survival for lung and bronchus cancer patients is examined using data from population-based cancer registries (1973–2003).
additive hazards; multiplicative hazards; relative survival; transformation hazards
The purpose of this study was to develop life tables by smoking status removing lung cancer as a cause of death. These life tables are inputs to studies that compare the effectiveness of lung cancer treatments or interventions, and provide a way to quantify time until death from causes other than lung cancer. The study combined actuarial and statistical smoothing methods, as well as data from multiple sources, to develop separate life tables by smoking status, birth cohort, by single year of age, and by sex. For current smokers, separate life tables by smoking quintiles were developed based on the average number of cigarettes smoked per day by birth cohort. The end product is the creation of six non-lung cancer life tables for males and six tables for females: five current smoker quintiles and one for never smokers. Tables for former smokers are linear combinations of the appropriate table based on the current smoker quintile prior to quitting smoking and the never smoker probabilities, plus added covariates for the smoking quit age and time since quitting.
Life Tables; Competing Risks; Lung Cancer and Smoking
Botanicals rich with phytochemicals have numerous health benefits. Dietary restriction (DR) extends lifespan in diverse species. We previously demonstrated that an oregano–cranberry (OC) mixture can promote longevity in the Mexican Fruit fly (Mexfly, Anastrepha ludens Loew). However, little is known about the interaction between botanicals and DR, and the age-dependent effect of botanicals on lifespan and reproduction. Here we investigated these issues by feeding Mexflies a full or DR diet supplemented with or without 2% OC. Lifespan and daily egg production of individual flies were recorded. The effect of short-term OC supplementation was evaluated by implementing the supplementation at three age intervals—young, middle, and old age. We found that OC increased lifespan of Mexflies on the full or DR diet when compared to their respective controls. OC increased reproduction of females on the full diet and, to a lesser extent, on the DR diet. Short-term OC supplementation was not sufficient to extend lifespan for males at all three age intervals nor for females at young and old age intervals. However, OC supplementation at the middle age interval was sufficient to extend lifespan in females, while only OC supplementation at the young age interval increased reproduction in females. Our findings suggest that OC extends lifespan and promotes reproduction partly through DR-independent pathways, and short-term supplementation have varied impact on longevity and reproduction. This also suggests a positive interaction between non-genetic interventions in promoting longevity and provides guidance for using botanicals as aging interventions in humans.
Lifespan; Cranberry; Oregano; Dietary restriction; Reproduction; Aging intervention; Dietary nutrient; Anastrepha ludens Loew
The phosphorylated form of histone H2AX (γ-H2AX) forms immunohistochemically detectable foci at DNA double strand breaks. In peripheral blood mononuclear cells (PBMCs) derived from leukapheresis from patients enrolled in the Baltimore Longitudinal Study of Aging, γ-H2AX foci increased in a linear fashion with regards to age, peaking at ∼57 years. The relationship between the frequency of γ-H2AX foci and age-related pathologies was assessed. We found a statistically significant (p = 0.023) 50% increase in foci in PBMCs derived from patients with a known history of vitamin D deficiency. In addition, there were trends toward increased γ-H2AX foci in patients with cataracts (34% increase, p<0.10) and in sleep apnea patients (44%, p<0.10). Among patients ≥57 y/o, we found a significant (p = 0.037) 36% increase in the number of γ-H2AX foci/cell for patients with hypertension compared to non-hypertensive patients. Our results support a role for increased DNA damage in the morbidity of age-related diseases. γ -H2AX may be a biomarker for human morbidity in age-related diseases.
In prospective cohort studies individuals are usually recruited according to a certain cross-sectional sampling criterion. The prevalent cohort is defined as a group of individuals who are alive but possibly with disease at the beginning of the study. It is appealing to incorporate the prevalent cases to estimate the incidence rate of disease before the enrollment. The method of back calculation of incidence rate has been used to estimate the incubation time from HIV infection to AIDS. The time origin is defined as the time of HIV infection. In aging cohort studies, the primary time scale is age of disease onset, subjects have to survive certain years to be enrolled into the study, thus creating left truncation (delay entry). The current methods usually assume that either the disease incidence is rare or the excess mortality due to disease is small compared to the healthy subjects. By far the validity of the results based on these assumptions has not been examined. In this paper, a simple alternative method is proposed to estimate dementia incidence rate before enrollment using prevalent cohort data with left truncation. Furthermore simulations are used to examine the performance of the estimation of disease incidence under different assumptions of disease incidence rates and excess mortality hazards due to disease. As application, the method is applied to the prevalent cases of dementia from the Honolulu Asia Aging Study to estimate dementia incidence rate and to assess the effect of hypertension, Apoe 4 and education on dementia onset.
Dementia incidence; prevalent cohort; penalized likelihood
One of the major problems in dietary assessment is inaccuracy in reporting diet.
To examine the association between self-reported energy intake by food frequency questionnaire (FFQ) and energy expenditure (EE), measured by doubly labeled water (DLW) among the elderly.
EE was assessed in 298 high-functioning, community-dwelling older adults over 2 weeks using DLW. Dietary intake was assessed using a Block Food Frequency Questionnaire (FFQ). The ratio between reported energy intake (EI) and total energy expenditure (TEE) was calculated. Misreporting was defined as: participants with an EI/TEE ratio of <0.77 were categorized as low energy reporters (LER) while participants with an EI/TEE ratio >1.28 were categorized as high energy reporters (HER). Participants with an EI/TEE ratio of 0.77–1.28 were categorized as “true” energy reporters (TER). One year percent weight change prior to EE visit was used as another validation indicator. Participants who were low energy reporters but lost >2% of their body weight were categorized as undereaters.
296 participants had both FFQ and DLW measurements. 43% of participants were low energy reporters among them, almost 30% lost weight and, therefore, were categorized as undereaters. The undereaters consumed significantly less calories. No difference in the frequency of low energy reporting was detected between gender or race groups. Underreporters had significantly higher body weight than “true” or high reporters. Undereaters tended to have higher BMI than the underreporters.
Undereating is prevalent in the elderly and may be falsely perceived as underreporting. It should be further addressed and characterized in future studies.
Doubly labeled water; missreporting; dietary inatke; true energy reporters; undereating
Receiver Operating Characteristic (ROC) curves are commonly used to summarize the classification accuracy of diagnostic tests. It is not uncommon in medical practice that multiple diagnostic tests are routinely performed or multiple disease markers are available for the same individuals. When the true disease status is verified by a gold standard test, a variety of methods have been proposed to combine such potential correlated tests to increase the accuracy of disease diagnosis. In this article, we propose a method of combining multiple diagnostic tests in the absence of a gold standard. We assume that the test values and their classification accuracies are dependent on covariates. Simulation studies are performed to examine the performance of the combination method. The proposed method is applied to data from a population-based aging study to compare the accuracy of three screening tests for kidney function and to estimate the prevalence of moderate kidney impairment.
Diagnostic test; Gold standard; Markov chain Monte-Carlo; Sensitivity; Specificity
The Study of Tamoxifen and Raloxifene (STAR) demonstrated that raloxifene was as effective as tamoxifen in reducing the risk of invasive breast cancer (IBC) in postmenopausal women and had lower risks of thromboembolic events, endometrial cancer, and cataracts but had a nonstatistically significant higher risk of noninvasive breast cancer. There is a need to summarize the risks and benefits of these agents.
Patients and Methods
Baseline incidence rates of IBC and other health outcomes, absent raloxifene and tamoxifen, were estimated from breast cancer chemoprevention trials; the Surveillance, Epidemiology and End Results Program; and the Women's Health Initiative. Effects of raloxifene and tamoxifen were estimated from STAR and the Breast Cancer Prevention Trial. We assigned weights to health outcomes to calculate the net benefit from raloxifene compared with placebo and tamoxifen compared with placebo.
Risks and benefits of treatment with raloxifene or tamoxifen depend on age, race, breast cancer risk, and history of hysterectomy. Over a 5-year period, postmenopausal women with an intact uterus had a better benefit/risk index for raloxifene than for tamoxifen. For postmenopausal women without a uterus, the benefit/risk ratio was similar. The benefits and risks of raloxifene and tamoxifen are described in tables that can help identify groups of women for whom the benefits outweigh the risks.
We developed a benefit/risk index to quantify benefits from chemoprevention with tamoxifen or raloxifene. This index can complement clinical evaluation in deciding whether to initiate chemoprevention and in comparing the benefits and risks of raloxifene versus tamoxifen.
Background and aims
Cross-sectional studies suggest that Obstructive Lung Disease (OLD) and smoking affect lean mass and mobility. We aimed to investigate whether OLD and smoking accelerate aging-related decline in lean mass and physical functioning.
260 persons with OLD (FEV1 63±18 %predicted), 157 smoking controls (FEV1 95±16 %predicted), 866 formerly smoking controls (FEV1 100±16 %predicted) and 891 never-smoking controls (FEV1 104±17 %predicted) participating in the Health, Aging and Body Composition (ABC) Study were studied. At baseline, the mean age was 74±3 y and participants reported no functional limitations. Baseline and seven-year longitudinal data were investigated of body composition (by Dual-energy X-ray absorptiometry), muscle strength (by hand and leg dynamometry) and Short Physical Performance Battery (SPPB).
Compared to never-smoking controls, OLD persons and smoking controls had a significantly lower weight, fat mass, lean mass and bone mineral content (BMC) at baseline (p<0.05). While the loss of weight, fat mass, lean mass and strength was comparable between OLD persons and never-smoking controls, the SPPB declined 0.12 points/yr faster in OLD men (p=0.01) and BMC 4 g/yr faster in OLD women (p=0.02). In smoking controls, only lean mass declined 0.1 kg/yr faster in women (p=0.03) and BMC 8 g/yr faster in men (p=0.02) compared to never-smoking controls.
Initially well-functioning older adults with mild-to-moderate OLD and smokers without OLD have a comparable compromised baseline profile of body composition and physical functioning, while seven-year longitudinal trajectories are to a large extent comparable to those observed in never-smokers without OLD. This suggests a common insult earlier in life related to smoking. 3
Obstructive Lung Disease; Body Composition; Aging
In the United States cancer as a whole is the second leading cause of death and a major burden to health care, thus the medical progress against cancer is a major public health goal. There are many individual studies to suggest that cancer treatment breakthroughs and early diagnosis have significantly improved the prognosis of cancer patients. To better understand the relationship between medical improvements and the survival experience for the patient population at large, it is useful to evaluate cancer survival trends on the population level, e.g., to find out when and how much the cancer survival rates changed. In this paper, we analyze the population-based grouped cancer survival data by incorporating joinpoints into the survival models. A joinpoint survival model facilitates the identification of trends with significant change points in cancer survival, when related to cancer treatments or interventions. The Bayesian Information Criterion is used to select the number of joinpoints. The performance of the joinpoint survival models is evaluated with respect to cancer prognosis, joinpoint locations, annual percent changes in death rates by year of diagnosis, and sample sizes through intensive simulation studies. The model is then applied to the grouped relative survival data for several major cancer sites from the Surveillance, Epidemiology and End Results (SEER) Program of the National Cancer Institute. The change points in the survival trends for several major cancer sites are identified and the potential driving forces behind such change points are discussed.
Annual percentage change; BIC; relative survival; joinpoint model; proportional hazards; SEER
According to the American Cancer Society report (1999), cancer surpasses heart disease as the leading cause of death in the United States of America (USA) for people of age less than 85. Thus, medical research in cancer is an important public health interest. Understanding how medical improvements are affecting cancer incidence, mortality and survival is critical for effective cancer control. In this paper, we study the cancer survival trend on the population level cancer data. In particular, we develop a parametric Bayesian joinpoint regression model based on a Poisson distribution for the relative survival. To avoid identifying the cause of death, we only conduct analysis based on the relative survival. The method is further extended to the semiparametric Bayesian joinpoint regression models wherein the parametric distributional assumptions of the joinpoint regression models are relaxed by modeling the distribution of regression slopes using Dirichlet process mixtures. We also consider the effect of adding covariates of interest in the joinpoint model. Three model selection criteria, namely, the conditional predictive ordinate (CPO), the expected predictive deviance (EPD), and the deviance information criteria (DIC), are used to select the number of joinpoints. We analyze the grouped survival data for distant testicular cancer from the Surveillance, Epidemiology, and End Results (SEER) Program using these Bayesian models.
Art auction catalogs provide a pre-sale prediction interval for the price each item is expected to fetch. When the owner consigns art work to the auction house, a reserve price is agreed upon, which is not announced to the bidders. If the highest bid does not reach it, the item is brought in. Since only the prices of the sold items are published, analysts only have a biased sample to examine due to the selective sale process. Relying on the published data leads to underestimating the forecast error of the pre-sale estimates. However, we were able to obtain several art auction catalogs with the highest bids for the unsold items as well as those of the sold items. With these data we were able to evaluate the accuracy of the predictions of the sale prices or highest bids for all item obtained from the original Heckman selection model that assumed normal error distributions as well as those derived from an alternative model using the t2 distribution, which yielded a noticeably better fit to several sets of auction data. The measures of prediction accuracy are of more than academic interest as they are used by auction participants to guide their bidding or selling strategy, and similar appraisals are accepted by the US Internal Revenue Services to justify the deductions for charitable contributions donors make on their tax returns.
Art auction; forecast error; nonignorable missing data; selection model
To estimate the potential benefits towards preventing late-life dementia, of lowering systolic blood pressure [SBP] we estimated the population attributable risk (PAR) of elevated SBP on dementia. Analyses are based on the cohort of 8006 Japanese American men (b. 1900 – 1919) followed since 1965 as a part of the Honolulu Heart Program, continued as the Honolulu Asia Aging Study. Mid-life cardiovascular risk factors and late-life brain function are well described. We estimated the PAR of dementia cases attributed to mid-life SBP, grouped by JCN-7 criteria [<120, 120 – < 140, and ≥ 140 mmHG], taking into account treatment history, confounding factors, and competitive risk for death. The analysis is based on 7878 subjects, including 491 cases of dementia, with a mean interval of 25 years between measurement of BP and dementia diagnosis. Compared to those with SBP <120 mmHG, untreated and <50 years at baseline, 17.7% (95% CI 4.6% – 29.1%) of the cases are attributable to prehypertensive levels (SBP 120 – <140 mmHG) of SBP, translating into 11 excess cases per 1000. Among those who did not report taking anti-hypertensive medication in mid-life, 27% [95%CI 8.9%, 42.1%] of dementia cases can be attributed to systolic BP >120 mmHG, translating into 17 excess cases per 1000. Although PAR estimates for population sub –groups may differ by relative risk for dementia or prevalence of elevated levels of BP, these data suggest reducing mid-life systolic BP is an effective prevention strategy to reduce risk for late-life dementia.
Dementia; population attributable risk; hypertension; older persons; cohort study; epidemiology
Dementia, Alzheimer’s disease in particular, is one of the major causes of disability and decreased quality of life among the elderly and a leading obstacle to successful aging. Given the profound impact on public health, much research has focused on the age-specific risk of developing dementia and the impact on survival. Early work has discussed various methods of estimating age-specific incidence of dementia, among which the illness-death model is popular for modeling disease progression. In this article we use multiple imputation to fit multi-state models for survival data with interval censoring and left truncation. This approach allows semi-Markov models in which survival after dementia may depend on onset age. Such models can be used to estimate the cumulative risk of developing dementia in the presence of the competing risk of dementia-free death. Simulations are carried out to examine the performance of the proposed method. We analyze data from the Honolulu Asia Aging Study to estimate the age-specific and cumulative risks of dementia and to examine the effect of major risk factors on dementia onset and death.
Competing risk; Dementia; Illness-death model; Interval censoring; Multiple imputation
To examine the association of hospitalization with annual changes in body composition and strength in older adults.
Design, Setting, & Participants
Participants in the Health, Aging and Body Composition study, a cohort study of well-functioning adults aged 70–79.
Hospitalizations were reported at annual clinic visits and semi-annual phone interviews. In the event of death or reported hospitalization, hospitalizations were adjudicated by medical record review. Dual x-ray absorptiometry (DXA) assessments of total, lean, and fat mass were conducted in six annual exams, and measures of knee extensor strength were conducted in two annual exams.
A total of 2309 hospitalizations were followed by DXA assessments. In men and women respectively, hospitalization in the previous year was associated with additional declines in total mass (−0.76 kg, −0.81 kg), fat mass (−0.41 kg, −0.54 kg) and lean mass (−0.33 kg, −0.25 kg) (p<.001 for all) relative to non-hospitalized participants, after adjustment for demographics and baseline values. Hospitalization was associated with strength declines in men (−4.02 Nm, p<0.05), but not in women. Relationships were similar adjusting for health behaviors and chronic conditions, although the association between hospitalization and strength was attenuated. Associations increased with number of days hospitalized; hospitalizations totaling ≥8 days in the previous year were associated with significantly greater loss of total, lean, and fat mass and loss of strength in both genders relative to non-hospitalized participants.
Hospitalization is associated with significant changes in body composition and strength in older persons. These effects appear particularly important among persons hospitalized for 8 or more days per year.
lean mass; weight loss; function; hospitalization; strength
Cancer patients are subject to multiple competing risks of death and may die from causes other than the cancer diagnosed. The probability of not dying from the cancer diagnosed, which is one of the patients’ main concerns, is sometimes called the “personal cure” rate. Two approaches of modeling competing-risk survival data, namely the cause-specific hazards approach and the mixture model approach, have been used to model competing-risk survival data. In this article, we first show the connection and differences between crude cause-specific survival in the presence of other causes and net survival in the absence of other causes. The mixture survival model is extended to population-based grouped survival data to estimate the personal cure rate. Using the colorectal cancer survival data from the Surveillance, Epidemiology and End Results (SEER) Program, we estimate the probabilities of dying from colorectal cancer, heart disease, and other causes by age at diagnosis, race and American Joint Committee on Cancer (AJCC) stage.
Competing risks; grouped survival data; mixture model; personal cure; SEER Program
Doubly-censored data refers to time to event data for which both the originating and failure times are censored. In studies involving AIDS incubation time or survival after dementia onset, for example, data are frequently doubly-censored because the date of the originating event is interval-censored and the date of the failure event usually is right-censored. The primary interest is in the distribution of elapsed times between the originating and failure events and its relationship to exposures and risk factors. The estimating equation approach [Sun, et al. 1999. Regression analysis of doubly censored failure time data with applications to AIDS studies. Biometrics 55, 909-914] and its extensions assume the same distribution of originating event times for all subjects. This paper demonstrates the importance of utilizing additional covariates to impute originating event times, i.e., more accurate estimation of originating event times may lead to less biased parameter estimates for elapsed time. The Bayesian MCMC method is shown to be a suitable approach for analyzing doubly-censored data and allows a rich class of survival models. The performance of the proposed estimation method is compared to that of other conventional methods through simulations. Two examples, an AIDS cohort study and a population-based dementia study, are used for illustration. Sample code is shown in the appendix.
AIDS; dementia; doubly censored data; incubation period; MCMC; midpoint imputation
Red cell distribution width (RDW) is a quantitative measure of variability in the size of circulating erythrocytes with higher values reflecting greater heterogeneity in cell sizes. Recent studies have shown that higher RDW is associated with increased mortality risk in patients with clinically significant cardiovascular disease (CVD). Whether RDW is prognostic in more representative community-based populations is unclear.
Seven relevant community-based studies of older adults with RDW measurement and mortality ascertainment were identified. Cox proportional hazards regression and meta-analysis on individual participant data were performed.
Median RDW values varied across studies from 13.2% to 14.6%. During 68,822 person-years of follow-up of 11,827 older adults with RDW measured, there was a graded increased risk of death associated with higher RDW values (p < .001). For every 1% increment in RDW, total mortality risk increased by 14% (adjusted hazard ratio [HR]: 1.14; 95% confidence interval [CI]: 1.11–1.17). In addition, RDW was strongly associated with deaths from CVD (adjusted HR: 1.15; 95% CI: 1.12–1.25), cancer (adjusted HR: 1.13; 95% CI: 1.07–1.20), and other causes (adjusted HR: 1.13; 95% CI: 1.07–1.18). Furthermore, the RDW–mortality association occurred in all major demographic, disease, and nutritional risk factor subgroups examined. Among the subset of 1,603 older adults without major age-associated diseases, RDW remained strongly associated with total mortality (adjusted HR: 1.32; 95% CI: 1.21–1.44).
RDW is a routinely reported test that is a powerful predictor of mortality in community-dwelling older adults with and without age-associated diseases. The biologic mechanisms underlying this association merit investigation.
Aging; Erythrocyte Indices; Mortality; Risk Factors
Several studies have shown that resveratrol can extend lifespan in yeast, worm, fruit fly and short-lived fish, as well as mice under a high-fat diet, probably acting through molecular pathways similar to dietary restriction. However, the putative prolongevity effect of resveratrol has not been observed in other studies. To evaluate the robustness of the prolongevity effects of resveratrol, we designed a nutritional study to address the question, Under what nutritional conditions does resveratrol affect lifespan and reproduction? We fed 2592 individual tephritid fruit fly of the species, Anastrepha ludens, 24 diets of different sugar:yeast ratios supplemented with or without 100 μM resveratrol. Sex-specific survival and daily egg laying in females were recorded. Resveratrol was found to have no or little effect on lifespan of males in all the treatments, as well as on lifespan and reproduction of females. Only under one diet combination, resveratrol appears to increase mean lifespan of females but not at a statistically significant level after multiple comparison adjustment. These findings suggest that the prolongevity effect of resveratrol is at most limited to a narrow range of dietary composition and calorie content in this fruit fly. Coupled with a recent study indicating that resveratrol does not extend lifespan of mice fed the standard diet, our findings further question the ability of resveratrol to increase lifespan in organisms under normal conditions.
Dietary restriction; Calorie Restriction; Lifespan; Anastrepha ludens; aging intervention
Dementia is characterized by accelerated cognitive decline before and after diagnosis as compared to normal aging. It has been known that cognitive impairment occurs long before the diagnosis of dementia. For individuals who develop dementia, it is important to determine the time when the rate of cognitive decline begins to accelerate and the subsequent gap time to dementia diagnosis. For normal aging individuals, it is also useful to understand the trajectory of cognitive function until their death. A Bayesian change-point model is proposed to fit the trajectory of cognitive function for individuals who develop dementia. In real life, people in older ages are subject to two competing risks, e.g, dementia and dementia-free death. Because the majority of people do not develop dementia, a mixture model is used for survival data with competing risks, which consists of dementia onset time after the change-point of cognitive function decline for demented individuals and death time for non-demented individuals. The cognitive trajectories and the survival process are modeled jointly and the parameters are estimated using the Markov chain Monte Carlo method. Using data from the Honolulu Asia Aging Study, we show the trajectories of cognitive function and the effect of education, apolipoprotein E 4 genotype and hypertension on cognitive decline and the risk of dementia.
Change point; competing risks; dementia; Markov chain Monte Carlo
Botanicals have numerous health benefits. Here, we used the Mexican fruit fly to screen 14 compounds and botanicals for their prolongevity effects and found an oregano and cranberry mixture (OC) improved survival. We then evaluated prolongevity effects of OC within the context of diet composition. Individual flies were fed 0%, 1%, or 2% OC in one of the three diets containing sugar and yeast extract (SY) at a ratio of 3:1, 9:1, or 24:1. We found that prolongevity effects of OC depended upon dose, gender, and diet composition. The greatest increase in longevity was observed in females fed the SY24:1 diet with 2% OC compared to the non-supplemented diet. OC did not reduce egg laying and, hence, did not compromise fecundity under any dietary condition tested here. This study reveals the prolongevity effects of OC and supports the emerging view that benefits of botanicals on aging depend on diet composition and gender.
Life span; Botanical extract; Aging intervention; Reproduction; Egg laying
In disease screening and diagnosis, often multiple markers are measured and they are combined in order to improve the accuracy of diagnosis. McIntosh and Pepe (2002, Biometrics 58, 657-644) showed that the risk score, defined as the probability of disease conditional on multiple markers, is the optimal function for classification based on the Neyman-Pearson Lemma. They proposed a two-step procedure to approximate the risk score. However, the resulted ROC curve is only defined in a subrange (L, h) of the false-positive rates in (0,1) and determination of the lower limit L needs extra prior information. In practice, most diagnostic tests are not perfect and it is usually rare that a single marker is uniformly better than the other tests. Using simulation, I show that multivariate adaptive regression spline (MARS) is a useful tool to approximate the risk score when combining multiple markers, especially when the ROC curves from multiple tests cross. The resulted ROC is defined in the whole range of (0,1) and it is easy to implement and has intuitive interpretation. The sample code of the application is shown in the appendix.
Multivariate adaptive regression spline (MARS); Neyman-Pearson Lemma; risk score; ROC
Self-reported screening behaviors from national surveys often over-estimate screening utilization, and the amount of overestimation may vary by demographic characteristics. We examine self-report bias in mammography screening rates overall, by age, and by race/ethnicity.
We use mammography registry data (1999–2000) from the Breast Cancer Surveillance Consortium (BCSC) to estimate the validity of self-reported mammography screening collected by two national surveys. First we compare mammography use from 1999–2000 for a geographically-defined population (Vermont) with self-reported rates in the prior two years from the 2000 Vermont Behavioral Risk Factor Surveillance System (BRFSS). We then use a screening dissemination simulation model to assess estimates of mammography screening from the 2000 National Health Interview Survey (NHIS).
Self-report estimates of mammography use in the prior two years from the Vermont BRFSS are 14–27 percentage points higher than actual screening rates across age groups. The differences in NHIS screening estimates from models are similar for women 40–49 and 50–59 years and greater than for those 60–69, or 70–79 (27 and 26 percentage points vs. 14, and 14, respectively). Over reporting is highest among African American women (24.4 percentage points) and lowest among Hispanic women (17.9) with non-Hispanic white women in between (19.3). Values of sensitivity and specificity consistent with our results are similar to previous validation studies of mammography.
Over-estimation of self-reported mammography usage from national surveys varies by age and race/ethnicity. A more nuanced approach that accounts for demographic differences is needed when adjusting for over-estimation or assessing disparities between populations.
breast neoplasms; data collection; mammography; recall; reproducibility of results
Mildly low hemoglobin concentration is associated with increased mortality in older adults. However, this relationship has not been well characterized in racial/ethnic minorities. Therefore, this study determined the hemoglobin threshold below which risk of death is significantly increased in older non-Hispanic whites, non-Hispanic blacks, and Mexican Americans. Data on 4,089 participants of the 1988-1994 US National Health and Nutrition Examination Survey who were ≥65 years of age were analyzed with mortality follow-up through December 31, 2000. Mean hemoglobin in non-Hispanic whites (n=2,686) and Mexican Americans (n=663) was 140 g/L, while in non-Hispanic blacks (n=740) the mean was 10 g/L lower. A total of 1,944 (47.5%) participants died. Among non-Hispanic whites and Mexican Americans, age- and sex-adjusted models showed that the hemoglobin thresholds below which mortality risk was significantly increased were 4 g/L and 2 g/L, respectively, above the World Health Organization (WHO) cutoffs for anaemia. In contrast, the threshold for non-Hispanic blacks was 7 g/L below the WHO criteria. Similar threshold effects were observed when analyzing hemoglobin in categories and adjusting for multiple confounders. In conclusion, the hemoglobin threshold below which mortality rises significantly is a full g/dL lower in non-Hispanic blacks than in non-Hispanic whites and Mexican Americans.
anaemia; hemoglobin concentration; race/ethnicity; ageing; NHANES
The General Population Nutrition Intervention Trial was a randomized primary esophageal and gastric cancer prevention trial conducted from 1985 to 1991, in which 29 584 adult participants in Linxian, China, were given daily vitamin and mineral supplements. Treatment with “factor D,” a combination of 50 μg selenium, 30 mg vitamin E, and 15 mg beta-carotene, led to decreased mortality from all causes, cancer overall, and gastric cancer. Here, we present 10-year follow-up after the end of active intervention.
Participants were assessed by periodic data collection, monthly visits by village health workers, and quarterly review of the Linxian Cancer Registry. Hazard ratios (HRs) and 95% confidence intervals (CIs) for the cumulative effects of four vitamin and mineral supplementation regimens were calculated using adjusted proportional hazards models.
Through May 31, 2001, 276 participants were lost to follow-up; 9727 died, including 3242 from cancer (1515 from esophageal cancer and 1199 from gastric cancer). Participants who received factor D had lower overall mortality (HR = 0.95, 95% CI = 0.91 to 0.99; P = .009; reduction in cumulative mortality from 33.62% to 32.19%) and gastric cancer mortality (HR = 0.89, 95% CI = 0.79 to 1.00; P = .043; reduction in cumulative gastric cancer mortality from 4.28% to 3.84%) than subjects who did not receive factor D. Reductions were mostly attributable to benefits to subjects younger than 55 years. Esophageal cancer deaths between those who did and did not receive factor D were not different overall; however, decreased 17% among participants younger than 55 (HR = 0.83, 95% CI = 0.71 to 0.98; P = .025) but increased 14% among those aged 55 years or older (HR = 1.14, 95% CI = 1.00 to 1.30; P = .47). Vitamin A and zinc supplementation was associated with increased total and stroke mortality; vitamin C and molybdenum supplementation, with decreased stroke mortality.
The beneficial effects of selenium, vitamin E, and beta-carotene on mortality were still evident up to 10 years after the cessation of supplementation and were consistently greater in younger participants. Late effects of other supplementation regimens were also observed.