Search

Background. We present updated features to a model developed by Dana-Farber investigators within the Cancer Intervention and Surveillance Modeling Network (CISNET). The initial model was developed to evaluate the impact of mammography screening strategies. Methods. This major update includes the incorporation of ductal carcinoma in situ (DCIS) as part of the natural history of breast cancer. The updated model allows DCIS in the pre-clinical state to regress to undetectable early-stage DCIS, or to transition to invasive breast cancer, or to clinical DCIS. We summarize model assumptions for DCIS natural history and model parameters. Another new development is the derivation of analytical expressions for overdiagnosis. Overdiagnosis refers to mammographic identification of breast cancer that would never have resulted in disease symptoms in the patient’s remaining lifetime (i.e., lead time longer than residual survival time). This is an inevitable consequence of early detection. Our model uniquely assesses overdiagnosis using an analytical formulation. We derive the lead time distribution resulting from the early detection of invasive breast cancer and DCIS, and formulate the analytical expression for overdiagnosis. Results. This formulation was applied to assess overdiagnosis from mammography screening. Other model updates involve implementing common model input parameters with updated treatment dissemination and effectiveness, and improved mammography performance. Lastly, the model was expanded to incorporate subgroups by breast density and molecular subtypes. Conclusions. The incorporation of DCIS and subgroups and the derivation of an overdiagnosis estimation procedure improve the model for evaluating mammography screening programs.

Background A challenge in quantifying the effect of screening mammography on breast-cancer mortality is to provide valid comparison groups. The use of historical control subjects does not take into account chronologic trends associated with advances in breastcancer awareness and treatment. Methods The Norwegian breast-cancer screening program was started in 1996 and expanded geographically during the subsequent 9 years. Women between the ages of 50 and 69 years were offered screening mammography every 2 years. We compared the incidence-based rates of death from breast cancer in four groups: two groups of women who from 1996 through 2005 were living in counties with screening (screening group) or without screening (nonscreening group); and two historical-comparison groups that from 1986 through 1995 mirrored the current groups. Results We analyzed data from 40,075 women with breast cancer. The rate of death was reduced by 7.2 deaths per 100,000 person-years in the screening group as compared with the historical screening group (rate ratio, 0.72; 95% confidence interval [CI], 0.63 to 0.81) and by 4.8 deaths per 100,000 person-years in the nonscreening group as compared with the historical nonscreening group (rate ratio, 0.82; 95% CI, 0.71 to 0.93; P

Randomization is widely recognized as a fundamental principle in the design of Phase III clinical trials. It is a way to minimize conscious and unconscious bias among patients and physicians with regard to treatment assignment and treatment acceptability. This paper outlines the advantages and disadvantages of randomization in clinical trials with discussions in permuted blocks, stratified randomization, cluster randomization, and the role of randomization as a basis for inference. Copyright © 2009 John Wiley & Sons, Inc. For further resources related to this article, please visit the WIREs website.

This paper proposes a new distribution-free statistical method for testing hypotheses about covariates for survival data having simultaneously right-, left- and interval-censored survival times. The new test is motivated by the analogue between urn sampling and the Cox’s proportional hazard models. Investigations of the significance levels and power as a function of the proportion of interval-censored observations and interval length show that the test performs well for most censoring situations encountered in practice. Simulation results also suggest that there is negligible loss of power in the practical situation in which the mean interval length for interval-censored observations is less than the mean survival time. This holds even with heavy interval censoring. Comparison with the widely used Mantel’s method for comparing two groups shows that the power of the new method appears to be superior. Furthermore, the test is relatively simple to carry out and generalizes to comparing k populations as well as the testing of general linear hypothesis for arbitrary covariates.

Consider a cohort of women, identifi ed by year of birth, some of whom will eventually be diagnosed with breast cancer. A stochastic model is developed for predicting the U.S. breast cancer mortality that depends on advances in therapy and dissemination of mammographic screening. The predicted mortality can be compared with the same cohort having usual care with no screening program and absence of modern therapy, or a cohort in which only a proportion participate in a screening program and have modern therapy. The model envisions that a woman may be in four health states: i.e., 1) no disease or breast cancer that cannot be diagnosed ( S 0 ), 2) preclinical state ( S p ), 3) clinical state ( S c ), and 4) diseasespecifi c death ( S d ). The preclinical disease refers to breast cancer that is asymptomatic but that may be diagnosed with a special exam. The clinical state refers to symptomatic disease diagnosed under usual care. One of the basic assumptions of the model is that the disease is progressive; i.e., the transitions for the fi rst three states are S 0 → S p → S c . The other basic assumption is that any reduction in mortality associated with earlier diagnosis is due to a stage shift in diagnosis; i.e., early diagnosis results in a larger proportion of earlier stage patients. The model is used to predict changes in female breast cancer mortality in the U.S. women for 1975 – 2000. The model is general and may predict mortality for other chronic diseases that satisfy the two basic assumptions. [J Natl Cancer Inst Monogr 2006;36:79 – 86] The early detection of chronic diseases presents opportunities for using existing technologies to substantially improve patient benefi t. The possibility of diagnosing a disease early, while it is asymptomatic, may result in treating the disease in an earlier stage which may enhance the benefi t of treatment. This paper describes a stochastic model for predicting the mortality of breast cancer as a function of both treatment and an early detection screening program. The early detection modalities consist of mammogram exams possibly combined with physical exams. The screening program consists of a series of examinations. The mortality predictions may be for chronological time and/or age for a defi ned cohort group. The model integrates possible advances in therapy and the changing dissemination of screening by chronological time. Although motivated by breast cancer, the model is general and may be used for other chronic diseases that satisfy the basic assumptions inherent in the model.

Biostatistical Science is in a 'golden period'. The definition of Biostatistical Science is the application of statistics, probability, mathematics and computing to advance our understanding of the subject matter in the biomedical sciences. Our field is experiencing unparallel developments due of the advances in communication and computing. We are becoming more global, we have resources which can expand educational opportunities for distant learning; the growth of quantitative methods in the biomedical sciences has made biostatistical science a key component in many research areas. What about the future? Are we receptive to change as many new scientific areas expand? Will the interaction between academia and industry likely to grow-especially in the training of future practitioners of biostatistical science. This paper discusses some of challenges facing our profession if we are to continue to be relevant in the biomedical sciences.

SUMMARY Overdiagnosis refers to the situation where a screening exam detects a disease that would have otherwise been undetected in a person’s lifetime. The disease would have not have been diagnosed because the individual would have died of other causes prior to its clinical onset. Although the probability of overdiagnosis is an important quantity for understanding early detection programs it has not been rigorously studied. We analyze an idealized early detection program and derive the mathematical expression for the probability of overdiagnosis. The results are studied numerically for prostate cancer and applied to a variety of screening schedules. Our investigation indicates that the probability of overdiagnosis is remarkably high.

A mathematical model was developed to predict the outcome of early detection clinical trials or programs targeted at evaluating mortality benefit from earlier diagnosis of breast cancer. The model was applied to eight randomized breast cancer trials, which were carried out to evaluate the benefits of mammography, physical examination or their combination. The model assumes that breast cancer is a progressive disease and any mortality benefit from earlier diagnosis is generated from a favorable shift in the stage at diagnosis relative to usual care. The model predicted the reduction in mortality for seven of the eight trials within the reported confidence intervals. Input data required by the models are: stage shift distribution, examination schedules, population age distribution, follow up time, and survival conditional on stage at diagnosis. Survival distributions were obtained from the 1973-82 SEER database whereas the remaining data was obtained for each of the trials. Information on sensitivity and stage was ordinarily available during the early phase of the trials. The theoretical model has the promise of being able to predict the long-term outcome of early detection trials or programs during the initial examination phase. The theoretical model is general and may be applied to other chronic diseases, which satisfy the basic assumptions.

SUMMARY Although case-control studies are widely used for evaluating the benefit of early detection programs, the theoretical basis underlying this application has not been well developed. In this paper the properties of chronic disease case-control studies for evaluating early detection programs are investigated. An idealized case-control study is analyzed and the theoretical expression for the odds ratio associated with the benefit of screening is derived. The odds ratio is related to the natural history of disease and the screening program. Our results indicate that case-control studies result in odds ratios that are surprisingly close to unity and consequently have low power.

This concluding session has the ambitious title of Biostatistical Training in the 21st Century. The Biomedical Sciences are changing so rapidly that it would be foolhardy for us to project training needs very much in the future. I am certain that if the biometricians and statisticians contemplating training needs at the turn of the 20th century were alive today they would be stunned as they would not even recognize the proper nouns and verbs that we use every day in our profession. Looking ahead another hundred years from now, the Biostatistical Scientists would look back at our time and comment on the 'quaint' way we planned and analysed studies. They might very well wonder why it was necessary to carry out clinical trials, enlisting hundreds if not thousands of patients, taking many years to complete, when in fact they need only look at a therapeutic drug's chemical composition and predict benet, conditional on knowing an individual's genetic prole. But of course that is a hundred years from now and we must grapple with today's problems. My remarks are targeted at training biostatistical scientists. Not at training biostatisticians. My denition of a biostatistical scientist is an individual trained in statistics, probability, com- puter science and applied mathematics that uses these disciplines to advance our understanding and enlarge our knowledge of important problems in the health and biomedical sciences. Our profession continues to be in a golden period. Mainly because the number of biosta- tistical scientists continues to grow and we are major contributors to the advancement of the health sciences. The major issue in the education of biostatistical scientists is how can we keep the training relevant and make the education meet not only today's needs—but tomorrow's as well. My remarks will be mainly directed at doctoral training—although we would all acknowl- edge that individuals without formal doctoral training could make important contributions. One role model was Jerry Corneld who did not have a doctorate. Sam Greenhouse had made many important contributions to the biomedical sciences long before he received a doctorate. I believe a biostatistical scientist should be broadly trained in statistics, probability, com- puting and applied mathematics. It is possible to be a successful investigator in theoretical statistics by focusing on a very narrow topic. Even a person who is not particularly gifted can make contributions by virtue of long-term contact with the same class of problems. However, a biostatistical scientist must be familiar with a broad range of methodology must have a sound knowledge of theory and must be a capable data analyst. The biostatistical scientist

PURPOSE: To estimate sensitivities of breast cancer screening modalities and preclinical duration of the disease from eight breast cancer screening clinical trials. PATIENTS AND METHODS: Screening programs invariably lead to diagnosis of disease before signs or symptoms are present. Two key quantities of screening programs are the sensitivity of the disease detection modality and the mean sojourn time (MST). The observed screening histories in a periodically screened cohort make it possible to estimate these quantities of interest. We applied recently developed statistical methods to data from eight randomized breast cancer screening trials to estimate the sensitivities of early detection modalities and MST. Moreover, when a screening trial involved two screening modalities, our methods enabled the estimation of the individual sensitivity of each screening modality. RESULTS: We analyzed breast cancer data from several screening trials and have relatively complete data from the Health Insurance Plan (HIP), Edinburgh, and two Canadian studies. The screening sensitivity for mammography, physical examination, and MST were, respectively, HIP: 0.39, 0.47, and 2.5 years; Edinburgh: 0.63, 0.40, and 4.3 years; Canadian (age 40 to 49 at entry): 0.61, 0.59, and 1.9 years; Canadian (age 50 to 59 at entry): 0.66, 0.39, and 3.1 years. CONCLUSION: The public debate on early breast cancer detection is mainly centered on mammograms. However, the current study indicates that a physical examination is of comparable importance. Cautious interpretation of trial differences is required as a result of various experimental designs and the age dependency of screening sensitivity and MST.

Consider a subject entered on a clinicaltrial in which the major endpoint is a time metric such as deathor time to reach a well defined event. During the observationalperiod the subject may experience an intermediate clinical event.The intermediate clinical event may induce a change in the survivaldistribution. We consider models for the one and two sample problem.The model for the one sample problem enables one to test if theoccurrence of the intermediate event changed the survival distribution.This models provides a way of carrying out non-randomized clinicaltrial to determine if a therapy has benefit. The two sample problemconsiders testing if the probability distributions, with andwithout an intermediate event, are the same. Statistical testsare derived using a semi-Markov or a time dependent mixture model.Simulation studies are carried out to compare these new procedureswith the log rank, stratified log rank and landmark tests. Thenew tests appear to have uniformly greater power than these competitortests. The methods are applied to a randomized clinical trialcarried out by the Aids Clinical Trial Group (ACTG) which comparedlow versus high doses of zidovudine (AZT).

The exponential distribution is a fundamental model in parametric survival analysis. In this paper the exponential regression model with a canonical parameterization, λ=β t x , is explored. Large sample and exact significance tests are developed to test the relationship between survival and one covariate. The standard unconditional likelihood approach is compared with two new tests, which are based on the conditional distribution of the sufficient statistics. The various testing procedures are compared numerically. Finally, the relationship with the semiparametric proportional hazard model is investigated.

There is growing interest in the design and implementation of cancer prevention trials. The key idea is to have agents which interfere with carcinogenesis and/or the preclinical stage. In this article we develop multi-stage stochastic models for the planning of cancer prevention trials. For known inputs it is possible to calculate the incidence of disease for the control and intervention groups. Consequently we find designs that balance the required sample size and follow-up time while guaranteeing prespecified error probabilities. Moreover such models can incorporate the mode of action of the intervention as well as compliance. The model has been applied to breast cancer to determine the implications for planning breast cancer intervention trials. Although the model addresses issues in cancer prevention, it is quite general and may be suitable for other chronic diseases.

SUMMARY This paper develops methods for estimating the parameters associated with early detection programmes. Disease is considered to have three states: a disease-free state or a state in which the disease cannot be detected, a preclinical state and a clinical state. The natural history of the disease is assumed to be progressive. The parameters to be estimated are the sensitivity of one or two disease detection modalities and the characteristics of the preclinical sojourn time distribution under both the stable disease and nonstable disease models. The stable-disease model assumes that the incidence or prevalence of a disease is independent of age or chronological time, while the nonstable disease model allows these quantities to depend on time. With the nonstable disease model, the relevant parameters can be jointly estimated by a two-step iteration procedure from the likelihood function. For the stable disease model, the sensitivity and the parameters of the sojourn time distribution of the preclinical state can be obtained directly from a conditional likelihood function. Applications are made to recent clinical trials for the early detection of breast cancer.

This article develops and extends previous investigations on stochastic models for selecting examination schedules targeted at earlier diagnosis of chronic diseases. The general aim is to provide guidelines for public health programs in the choice of examination schedules. The main features of such schedules are the initial age to begin a scheduled examination program, the intervals between subsequent examinations, and the number of examinations. Our basic model consists of three health states: a disease-free or nondetectable state; a preclinical state, in which an individual has disease but is asymptomatic and is unaware of it; and a clinical state in which the disease has been diagnosed by routine methods. The aim of early detection programs is to identify individuals in a preclinical local state, which may result in higher cure rates or longer survival. We introduce two basic ideas that either individually or together can lead to satisfactory examinations schedules. The threshold method constr...

This paper investigates the urn sampling analogue for the score statistic relating survival to covariates assuming a proportional hazard model. The exact permutation distribution can be calculated as well as the exact low order moments for arbitrary censoring patterns. The asymptotic distribution of the score statistic is an easy consequence. The method is naturally extended to deal with the multivariate case, time varying covariates and interval censoring. Finally the relationship between the censoring process, the survival times and covariates are studied considering different reference sets for the distribution of the score statistic. Some assumptions about the censoring process are investigated and as a consequence the effect of censoring is clarified.

SUMMARY The lack of statistical theory for the planning of early detection trials has resulted in current trials being sub-optimal. We develop probability models that address three characteristics of early detection trials: (i) the optimal time of analysis and length of follow-up, (ii) the optimal spacing between examinations, and (iii) the planning of trials where the numbers of examinations versus sample size are balanced for fixed costs. The optimisation criterion is to maximise the power of the statistical test for comparing mortality. Application is made to breast cancer early detection trials.

The Department of Biostatistics was founded in 1922 (initially as the Department of Vital Statistics) with the creation of the Harvard School of Public Health. Its first chair was E. B. Wilson, who served from 1922–1946. The department was renamed the Department of Biostatistics with the appointment of Hugo Muench as chair in 1946. Subsequent chairs were Robert Reed (1961-1963), Jane Worcester (1973-1977), Fred Mosteller (1977-1981), Marvin Zelen (1981-1990), Nan Laird (1990-1999), Stephen Lagakos (1999-2007), Louise Ryan (2007-2009), and Victor DeGruttola (2009-present). The department offers both doctoral and master’s degree programs; currently there are approximately 90 graduate students in these programs. The department is home to 56 primary and secondary faculty, as well as 100+ postdoctoral fellows, research associates, and scientists. The department’s faculty work in a wide variety of methodological areas of research, including the design and analysis of clinical trials, survival analysis, sequential methods, statistical genetics, longitudinal analysis, semi-parametric methods, causal inference, measurement errors, Bayesian methods, surveillance, screening for the early detection of disease, bioinformatics and computational biology, personalized medicine, comparative effectiveness, network analysis, signal and imaging processing, and computationally intensive methods. They direct the statistical coordinating centers for the AIDS Clinical Trials Group (ACTG), the Eastern Cooperative Oncology Group (ECOG), and the International Breast Cancer Study Group (IBCSG). In addition, the department has a very active research program in environmental health.

Summary Objective Optimal US screening strategies remain controversial. We use six simulation models to evaluate screening outcomes under varying strategies. Methods The models incorporate common data on incidence, mammography characteristics, and treatment effects. We evaluate varying initiation and cessation ages applied annually or biennially and calculate mammograms, mortality reduction (vs. no screening), false-positives, unnecessary biopsies and over-diagnosis. Results The lifetime risk of breast cancer death starting at age 40 is 3% and is reduced by screening. Screening biennially maintains 81% (range 67% to 99%) of annual screening benefits with fewer false-positives. Biennial screening from 50-74 reduces the probability of breast cancer death from 3% to 2.3%. Screening annually from 40 to 84 only lowers mortality an additional one-half of one percent to 1.8% but requires substantially more mammograms and yields more false-positives and over-diagnosed cases. Conclusion Decisions about screening strategy depend on preferences for benefits vs. potential harms and resource considerations.

Consider a multinomial response model with (k+1) outcomes and p explanatory variables. The general logistic model for the multinomial probabilities results in a matrix of sufficient statistics having kp elements. The means and variances of the sufficient statistics are derived (under the null hypothesis) and can be written as a Kronecker product. Since the sufficient statistics have asymptotic normal distributions, large sample tests can be derived which uses a chi-square statistic. The conditional test for testing if a single explanatory variable affects the response is derived.

SUMMARY Consider a binary random variable having outcomes subject to misclassification errors where the probabilities of misclassification errors depend on outcome. The asymptotic relative efficiencies are derived for comparing two binomial populations, comparing stratified binomial populations and for paired comparisons. The probabilities of misclassification can vary with strata or be different for each pair. The criterion for optimum experimental designs is shown to be the ratio of the asymptotic relative efficiency to expected cost per observation. This criterion implies that mixtures of different experiments can never be optimal. A number of experimental strategies is discussed.

The purpose of this paper is to investigate and develop methods for analysis of multi-center randomized clinical trials which only rely on the randomization process as a basis of inference. Our motivation is prompted by the fact that most current statistical procedures used in the analysis of randomized multi-center studies are model based. The randomization feature of the trials is usually ignored. An important characteristic of model based analysis is that it is straightforward to model covariates. Nevertheless, in nearly all model based analyses, the effects due to different centers and, in general, the design of the clinical trials are ignored. An alternative to a model based analysis is to have analyses guided by the design of the trial. Our development of design based methods allows the incorporation of centers as well as other features of the trial design. The methods make use of conditioning on the ancillary statistics in the sample space generated by the randomization process. We have investigated the power of the methods and have found that, in the presence of center variation, there is a significant increase in power. The methods have been extended to group sequential trials with similar increases in power., Published in at http://dx.doi.org/10.1214/07-AOAS151 the Annals of Applied Statistics (http://www.imstat.org/aoas/) by the Institute of Mathematical Statistics (http://www.imstat.org)

Consider a group of subjects who are offered an opportunity to receive a sequence of periodic special examinations for the purpose of diagnosing a chronic disease earlier relative to usual care. The mortality for the early detection group is to be compared with a group receiving usual care. Benefit is reflected in a potential reduction in mortality. This article develops a general probability model that can be used to predict cumulative mortality for each of these groups. The elements of the model assume (i) a four-state progressive disease model in which a subject may be in a disease-free state (or a disease state that cannot be detected), preclinical disease state (capable of being diagnosed by a special exam), clinical state (diagnosis by usual care), and a death state; (ii) age-dependent transitions into the states; (iii) age-dependent examination sensitivity; (iv) age-dependent sojourn time in each state; and (v) the distribution of disease stages on diagnosis conditional on modality of detection. The model may be used to (i) compare mortality rates for different screening schedules; (ii) explore potential benefit of subpopulations; and (iii) compare relative reductions in disease-specific mortality due to advances and dissemination of both treatment and early detection screening programs.

Consider a cohort of women, identified by year of birth, some of whom will eventually be diagnosed with breast cancer. A stochastic model is developed for predicting the U.S. breast cancer mortality that depends on advances in therapy and dissemination of mammographic screening. The predicted mortality can be compared with the same cohort having usual care with no screening program and absence of modern therapy, or a cohort in which only a proportion participate in a screening program and have modern therapy. The model envisions that a woman may be in four health states: i.e., 1) no disease or breast cancer that cannot be diagnosed (S0), 2) preclinical state (Sp), 3) clinical state (Sc), and 4) disease-specific death (Sd). The preclinical disease refers to breast cancer that is asymptomatic but that may be diagnosed with a special exam. The clinical state refers to symptomatic disease diagnosed under usual care. One of the basic assumptions of the model is that the disease is progressive; i.e., the transitions for the first three states are S0--Sp--Sc. The other basic assumption is that any reduction in mortality associated with earlier diagnosis is due to a stage shift in diagnosis; i.e., early diagnosis results in a larger proportion of earlier stage patients. The model is used to predict changes in female breast cancer mortality in the U.S. women for 1975-2000. The model is general and may predict mortality for other chronic diseases that satisfy the two basic assumptions.

In early-detection clinical trials, quantities such as the sensitivity of the screening modality and the preclinical duration of the disease are important to describe the natural history of the disease and its interaction with a screening program. Assume that the schedule of a screening program is periodic and that the sojourn time in the preclinical state has a piecewise density function. Modeling the preclinical sojourn time distribution as a piecewise density function results in robust estimation of the distribution function. Our aim is to estimate the piecewise density function and the examination sensitivity using both generalized least squares and maximum likelihood methods. We carried out extensive simulations to evaluate the performance of the methods of estimation. The different estimation methods provide complimentary tools to obtain the unknown parameters. The methods are applied to three breast cancer early-detection trials.

Consider a chronic disease process which is beginning to be observed at a point in chronological time. The backward recurrence and forward recurrence times are defined for prevalent cases as the time with disease and the time to leave the disease state, respectively, where the reference point is the point in time at which the disease process is being observed. In this setting the incidence of disease affects the recurrence time distributions. In addition, the survival of prevalent cases will tend to be greater than the population with disease due to length biased sampling. A similar problem arises in models for the early detection of disease. In this case the backward recurrence time is how long an individual has had disease before detection and the forward recurrence time is the time gained by early diagnosis, i.e., until the disease becomes clinical by exhibiting signs or symptoms. In these examples the incidence of disease may be age related resulting in a non-stationary process. The resulting recurrence time distributions are derived as well as some generalization of length-biased sampling.

Special examinations exist for many chronic diseases, which can diagnose the disease while it is asymptomatic, with no signs or symptoms. The earlier detection of disease may lead to more cures or longer survival. This possibility has led to public health programs which recommend populations to have periodic screening examinations for detecting specific chronic diseases, for example, cancer, diabetes, cardiovascular disease and so on. Such examination schedules when embedded in a public health program are invariably costly and are ordinarily not chosen on the basis of possible trade-offs in costs and benefits for different screening schedules. The possible candidate number of examination schedules is so large that it is not feasible to carry out clinical trials to compare different schedules. Instead, this problem can be investigated by developing a theoretical model which can predict the eventual disease specific mortality for different examination schedules. We have developed such a model. It is a stochastic model which assumes that i) the natural history of the disease is progressive and ii) any benefit from earlier diagnosis is due to a change in the distribution of disease stages at diagnosis (stage shift). The model is general and can be applied to any chronic disease which satisfies our two basic assumptions. We discuss the basic ideas of schedule sensitivity and lifetime schedule sensitivity and its relation to the reduction in disease specific mortality. Our theory is illustrated by applications to breast cancer screening. The investigation of schedules compares not only examination schedules with equal intervals between examinations but also staggered schedules using the threshold method. (Examinations are carried out when an individual’s risk status reaches a preassigned threshold value.)

Consider a randomized clinical trial to evaluate the benefit of screening an asymptomatic population. Suppose that the subjects are randomized into a usual care and a study group. The study group receives one or more periodic early detection examinations aimed at diagnosing disease early, when there are no signs or symptoms. Early detection clinical trials differ from therapeutic trials in that power is affected by: i) the number of exams, ii) the time between exams and iii) the ages at which exams will be given. These design options do not exist in therapeutic trials. Furthermore; long-term follow-up may result in a reduction of power. In general, power increases with number of examinations, and the optimal follow-up time is dependent on the spacing between examinations. Clinical trials in which the usual care group receives benefit are also discussed. Two designs are discussed, for example the ‘up-front design’ in which all subjects receive an initial exam and then are randomized to the usual care and study groups and the ‘close-out design’ in which the usual care group receives an exam which is timed to be given at the same time as the last exam in the study group. Both families of designs significantly reduce the power. Power calculations are made for two clinical trials, which actually used these two designs.

Familial risk of disease is often assessed using case control studies based on referent databases. A referent database is a collection of family histories of cases typically assembled as a result of one family member being diagnosed with disease. This sampling scheme is equivalent to sampling families proportional to their size. The larger the family, the greater the probability of finding the family in the referent registry. This phenomena is known as length-biased sampling. The consequence of this kind of sampling is to bias the regression estimate associated with family history. The estimate is typically inflated in comparison to what is true for the actual population.

SUMMARY This paper investigates two experimental designs which have been used to evaluate the benefit of the early detection of breast cancer. They have some advantages over a classical design (the screening program versus usual medical care) in that subjects in a control group may benefit by participating in the study. We refer to the two experimental designs as the up-front (UFD) and close-out (COD) designs. The UFD consists of offering an initial exam to all participants. Then they can be randomized to a usual care group or a screening group receiving one or more special examinations. If the outcome of the initial examination is included in the analysis, then the study can answer the question of the benefit of an additional screening program after an initial examination. If the analysis excludes all the cases diagnosed at the initial examination, then the analysis evaluates the benefit of a screening program after elimination of the prevalent cases. These prevalent cases are most likely to be affected by length bias sampling and consequently will tend to have less aggressive disease and live longer. As a result, the UFD can answer two scientific questions. The COD consists of randomizing subjects to a usual care group and a screened group. However, the usual care group receives an examination which coincides at the time of the last exam in the study group. In this paper the power of these two designs have been evaluated. In both cases the power is severely reduced compared to the usual control group receiving no special exams. The power is a function of the sensitivity of the exam, the number and spacings of the exams given to the screened group as well as the sample size, disease incidence of the population and the survival distribution. The theoretical results on power are applied to the Canadian National Breast Cancer Study (ages 40–49) which used an UFD and the Stockholm Mammography Breast Cancer Screening Trial which utilized a COD.

L'efficacite des strategies de depistage des maladies depend pour beaucoup du moment ou l'on procede aux tests et aux examens qui peuvent permettre de les diagnostiquer. Dans cet article, qui voudrait definir des cadres flexibles de prise de decision pour une meilleure politique de detection, nous nous penchons sur le choix du moment ou proceder au depistage dans le cas ou celui-ci n'est applique a chaque personne qu'a une seule reprise. Pour ce faire, nous nous concentrons sur la relation theorique entre le moment optimal de l'examen et les distributions des temps passes par les patients dans differentes categories d'etats de sante relatifs a la maladie, puis nous derivons, a partir de deux fonctions d'utilite distinctes, des solutions approchees de l'âge optimal pour le depistage. Nous discutons la maniere dont cette solution optimale est influencee par les antecedents des patients et par la specification des fonctions d'utilite. Enfin, nous presentons une application dans la detection du cancer du colon par sigmoidoscopie ou coloscopie uniques.

There is increasing interest in using special diagnostic examinations to detect a potential disease or condition in an individual who has no signs or symptoms. The motivation behind such efforts is that earlier detection, when combined with an effective therapy, will lead to enhanced benefit. The benefit is usually reflected in a higher cure rate or longer survival. In ordinary circumstances most cancers—especially solid tumors, are usually diagnosed when an individual experiences pain or a vital organ is not functioning properly or a “lump” beneath the skin is palpated. Diagnosing a disease without these signs or symptoms often results in the disease being diagnosed in an earlier stage. Many therapies are enhanced when given to earlier disease stage patients. The primary treatment modalities for most cancer sites is surgery and/or radiation. These are essentially treatments which are targeted at localized disease. If the cancer site has metastasized, then resecting or radiating the primary tumor will not result in cures. Effective chemotherapy can be significantly enhanced if the metastatic disease consists of microscopic cells which have not seriously interfered with a vital organ.

The previous chapter discusses the general ideas associated with modeling the early detection of disease. In particular, the chapter discusses the role of models in considering the quantitative aspects of the early detection of disease. In this chapter, it will be assumed that clinical trials have established the benefit of early detection of disease and we will discuss the issues in bringing these benefits to widespread public health use.

We propose a Bayesian formulation of the sample size problem for planning clinical trials. The frequentist paradigm for calculating sample sizes for clinical trials is to prespecify the type I and II error probabilities. These error probabilities are conditional on the true hypotheses. Instead we propose prespecifying posterior probabilities which are conditional on the outcome of the trial. Our method is easy to implement and has intuitive interpretations. We illustrate an application of our method to the planning of cancer clinical trials for the Eastern Cooperative Oncology Group (ECOG).

A randomized clinical trial was carried out to evaluate the safety and helpfulness of the LactaPrev System (LPS) compared with disposable pads for milk leakage management for postpartum, nonlactating women (those who do not breastfeed). Fifty-five women completed the single-blind, randomized trial. Participants wore each device on each breast concurrently. Assignment of the LPS or pad to each breast was done randomly. Fifty-eight percent of participants preferred the LPS. The longer the participation in the study, which correlated with the duration of milk leakage, the greater the preference (p = 0.05). Preference was related to bra size (p = 0.05). The smaller the bra size, the greater the preference for the LPS. There was no greater incidence of complications from the LPS compared with the disposable breast pad.

This paper investigates one- and two-sample problems comparing survival times when an individual may experience an intermediate event prior to death or reaching some well defined endpoint. The intermediate event may be polychotomous. Patients experiencing the intermediate event may have an altered survival distribution after the intermediate event. Score tests are derived for testing if the occurrence of the intermediate event actually alters survival. These models have implications for evaluating therapies without randomization as well as strengthening the log rank test for comparing two survival distributions. The exact distribution of the score tests can be found by conditioning on both the waiting time and occurrence of the intermediate event.

This paper investigates one- and two-sample problems comparing survival times when an individual may experience an intermediate event prior to death or reaching some well defined endpoint. The intermediate event may be polychotomous. Patients experiencing the intermediate event may have an altered survival distribution after the intermediate event. Score tests are derived for testing if the occurrence of the intermediate event actually alters survival. These models have implications for evaluating therapies without randomization as well as strengthening the log rank test for comparing two survival distributions. The exact distribution of the score tests can be found by conditioning on both the waiting time and occurrence of the intermediate event.

Despite trials of mammography and widespread use, optimal screening policy is controversial.To evaluate U.S. breast cancer screening strategies.6 models using common data elements.National data on age-specific incidence, competing mortality, mammography characteristics, and treatment effects.A contemporary population cohort.Lifetime.Societal.20 screening strategies with varying initiation and cessation ages applied annually or biennially.Number of mammograms, reduction in deaths from breast cancer or life-years gained (vs. no screening), false-positive results, unnecessary biopsies, and overdiagnosis.The 6 models produced consistent rankings of screening strategies. Screening biennially maintained an average of 81% (range across strategies and models, 67% to 99%) of the benefit of annual screening with almost half the number of false-positive results. Screening biennially from ages 50 to 69 years achieved a median 16.5% (range, 15% to 23%) reduction in breast cancer deaths versus no screening. Initiating biennial screening at age 40 years (vs. 50 years) reduced mortality by an additional 3% (range, 1% to 6%), consumed more resources, and yielded more false-positive results. Biennial screening after age 69 years yielded some additional mortality reduction in all models, but overdiagnosis increased most substantially at older ages.Varying test sensitivity or treatment patterns did not change conclusions.Results do not include morbidity from false-positive results, patient knowledge of earlier diagnosis, or unnecessary treatment.Biennial screening achieves most of the benefit of annual screening with less harm. Decisions about the best strategy depend on program and individual objectives and the weight placed on benefits, harms, and resource considerations.National Cancer Institute.

Statisticians and clinicians involved in the design and conduct of trials of new treatments for the acquired immunodeficiency syndrome (AIDS) have realized that some traditional approaches to the c...

Randomized consent designs were introduced to make it easier for physicians to enter patients in randomized clinical trials. Physician reluctance to participate in randomized clinical trials is often a reflection that the physician-patient relationship could be compromised if the physician makes known to the patient his/her inability to select a preferred therapy. Clinical trials having a no-treatment control or placebo amplify this concern. This paper reviews the main ideas of randomized consent designs (single and double) and the statistical model underlying the analysis, and presents some recent experiences.