An overview and some recent advances in statistical methods for populationbased cancer survival analysis

 Maude Rachel McBride
 9 days ago
 Views:
Transcription
1 An overview and some recent advances in statistical methods for populationbased cancer survival analysis Paul W Dickman 1 Paul C Lambert 1,2 1 Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, Sweden 2 Department of Health Sciences, University of Leicester, UK 9 April 214
2 About me Born in Sydney Australia; studied mathematics and statistics in Newcastle (Australia). Worked in health services research; dabbled in industrial process control and quality improvement. Arrived in Sweden November 1993 for a 1 month visit to cancer epidemiology unit at Radiumhemmet. Stayed in Sweden for most of my PhD. Short Postdoc periods at Finnish Cancer Registry and Karolinska Institutet (clinical epidemiology). Joined HansOlov Adami s new department (now MEB) in March 1999, attracted by the strong research environment and possibilities for registerbased epidemiology. Paul Dickman PopulationBased Cancer Survival 9 April Research interests Primary research interests are in the development and application of methods for populationbased cancer survival analysis, particularly the estimation and modeling of relative survival. Recent interest has been in presenting information on patient survival in a manner relevant for patients and clinicians. General interest in statistical aspects of the design, analysis, and reporting of epidemiological studies along with studies of disease aetiology, with particular focus on cancer epidemiology and perinatal/reproductive epidemiology. Collaborate closely with Paul Lambert (Biostatistician at University of Leicester) and Magnus Björkholm (Haematologist). Paul Dickman PopulationBased Cancer Survival 9 April Overview of today s talk (to what I understand is a heterogeneous audience) Measures used in cancer control; why study patient survival. Intro to relative survival (excess mortality) and why it is the measure of choice for populationbased cancer survival analysis. Flexible parametric models (RoystonParmar models). The concept of statistical cure; cure models. Estimating crude and net probabilities of death. Partitioning excess mortality; treatmentrelated CVD mortality. Loss in expectation of life. Paul Dickman PopulationBased Cancer Survival 9 April 214 4
3 r year 1, per y rate per 1 In ncidence or mortality Incidence Mortality Survival Lung cancer incidence, mortality and survival (agestandardised) England, , by sex Men Women Women Men Fiveye ear relativ ve surviva al (%) Year of death / Year of diagnosis Paul Dickman PopulationBased Cancer Survival 9 April Lung cancer incidence in Sweden Paul Dickman PopulationBased Cancer Survival 9 April How might we measure the prognosis of cancer patients? Total mortality (among the patients). Our interest is typically in net mortality (mortality associated with a diagnosis of cancer). Causespecific mortality provides an estimate of net mortality (under certain assumptions). When estimating causespecific mortality only those deaths which can be attributed to the cancer in question are considered to be events. causespecific mortality = number of deaths due to cancer persontime at risk The survival times of patients who die of causes other than cancer are censored. Paul Dickman PopulationBased Cancer Survival 9 April 214 7
4 Need to consider competing risks [1] Figure 1 The competing risks multistate model. Paul Dickman PopulationBased Cancer Survival 9 April Many synonyms for the same concept Net probability of death due to cancer = Probability of death in a hypothetical world where the cancer under study is the only possible cause of death Crude probability of death due to cancer = Probability of death in the real world where you may die of other causes before the cancer kills you Net probability also known as the marginal probability. Crude probability also known as the causespecific cumulative incidence function (Geskus) or the cumulative incidence function. Paul Dickman PopulationBased Cancer Survival 9 April Net (left) and crude (right) probabilities of death in men with localized prostate cancer aged 7+ at diagnosis (Cronin and Feuer [2]) Paul Dickman PopulationBased Cancer Survival 9 April 214 1
5 lable at nal homepage: EUROPEAN UROLOGY 65 (214) Should we use crude or net survival? tate Cancer 1 Comparing patient survival between countries. 2 Studying temporal trends in patient survival. 3 Communicating prognosis to patients. ociation Between Use of bblockers and Prostate cer Specific Survival: A Cohort Study of 3561 Prostate cer Patients with HighRisk or Metastatic Disease ne Hartvedt Grytli a, Morten Wang Fagerland b, Sophie D. Fosså c,d, tin Austlid Taskén a,d, * Paul Dickman PopulationBased Cancer Survival 9 April rtment of Tumor Biology, Institute of Cancer Research, Oslo University Hospital, Oslo, Norway; b Unit of Biostatistics and Epidemiology, Oslo University al, Oslo, Norway; c Department of Oncology, Oslo University Hospital, Oslo, Norway; d Institute of Clinical Medicine, University of Oslo, Oslo, Norway le info Should we use crude or net survival? Abstract le history: pted January 6, 213 shed online ahead of on January 14, 213 ords: renergic receptor onist cker miology risk prostate cancer stasis ay ate cancer ate cancer specific ality Background: We recently reported reduced prostate cancer (PCa) specific mortality for bblocker users among patients receiving androgendeprivation therapy in a health survey cohort including 655 PCa patients. Information on clinical characteristics was limited. Objective: To assess the association between bblockers and PCaspecific mortality in a cohort of 3561 prostate cancer patients with highrisk or metastatic disease, and to address potential confounding from the use of statins or acetylsalicylic acid (ASA). Design, setting, and participants: Clinical information from all men reported to the Cancer Registry of Norway with a PCa diagnosis between 24 and 29 (n = ) was coupled with information on filled prescriptions between 24 and 211 from the Norwegian Prescription Database. Exclusion criteria were low or intermediaterisk disease; planned radiotherapy or radical prostatectomy; initiation of bblocker, ASA, or statin use after diagnosis where applicable; missing information on baseline Gleason score, prostatespecific antigen level, T stage or performance status; and missing followup. Outcome measurements and statistical analysis: Cox proportional hazards modelling and competing risk regression modelling were used to analyse the effects of bblocker use on allcause and PCaspecific mortality, respectively. Differences between bblocker users and nonusers regarding baseline clinical characteristics were assessed by the WilcoxonMannWhitney U test, Pearson chisquare test, and Student t test. Results and limitations: Median followup was 39 mo. bblocker use was associated with reduced PCa mortality (adjusted subhazard ratio:.79; 95% confidence interval [CI],.68.91; p value:.1). The observed reduction in PCa mortality was independent of the use of statins or ASA. We observed no association with allcause mortality Paul Dickman PopulationBased Cancer Survival 9 April (adjusted hazard ratio:.92; 95% CI, ). The main limitations of the study were the observational study design and short followup. Conclusions: bblocker use was associated with reduced PCaspecific mortality in patients with highrisk or metastatic disease at the time of diagnosis. Our findings need validation from further observational studies. # 213 European Association of Urology. Published by Elsevier B.V. All rights reserved. Causespecific survival can estimate net survival (assuming conditional independence) * Corresponding author. Oslo University Hospital, Institute of Cancer Research, Department of Tumor Biology, P.O. Box 4953 Nydalen, NO424 Oslo, Norway. Tel ; Fax: Using causespecific methods requires that reliably coded address: (K.A. Taskén). information on cause of death is available. Even when cause of death information is available to the cancer registry via death certificates, it is often vague and difficult to determine whether or not cancer is the primary cause of death. 2838/$ see back matter # 213 European Association of Urology. Published by Elsevier B.V. All rights reserved. /dx.doi.org/1.116/j.eururo How do we classify, for example, deaths due to treatment complications? Consider a patient treated with radiation therapy and chemotherapy who dies of cardiovascular disease. Do we classify this death as due entirely to cancer or due entirely to other causes? Paul Dickman PopulationBased Cancer Survival 9 April
6 Allcause mortality for males with colon cancer and Finnish population Mortality Rate (per 1, person years) General population Colon cancer patients Age Paul Dickman PopulationBased Cancer Survival 9 April Relative survival aims to estimate net survival (still need conditional independence) We estimate excess mortality: the difference between observed (allcause) and expected mortality. excess = observed expected mortality mortality mortality Relative survival is the survival analog of excess mortality the relative survival ratio is defined as the observed survival in the patient group divided by the expected survival of a comparable group from the general population. relative survival ratio = observed survival proportion expected survival proportion Paul Dickman PopulationBased Cancer Survival 9 April Cervical cancer in New Zealand Life table estimates of patient survival Women diagnosed with followup to the end of 22 Interval Interval Effective specific specific Cumulative Cumulative Cumulative number observed relative observed expected relative I N D W at risk survival survival survival survival survival Paul Dickman PopulationBased Cancer Survival 9 April
7 Relative survival example (skin melanoma) Table 1: Number of cases (N) and 5year observed (p), expected (p ), and relative (r) survival for males diagnosed with localised skin melanoma in Finland during Age N p p r Relative survival controls for the fact that expected mortality depends on demographic characteristics (age, sex, etc.). In addition, relative survival may, and usually does, depend on such factors. Paul Dickman PopulationBased Cancer Survival 9 April Breakthrough paper in 212; Biometrics 68, An unbiased estimator for net survival [3] March 212 DOI: /j x On Estimation in Relative Survival Maja Pohar Perme, 1, Janez Stare, 1 and Jacques Estève 2 1 Department of Biostatistics and Medical Informatics, University of Ljubljana, Vrazov trg 2, SI1 Ljubljana, Slovenia 2 Université Claude Bernard, Hospices Civils de Lyon, Service de Biostatistique, 162, Avenue Lacassagne Lyon Cedex 3, France Summary. Estimation of relative survival has become the first and the most basic step when reporting cancer survival statistics. Standard estimators are in routine use by all cancer registries. However, it has been recently noted that these estimators do not provide information on cancer mortality that is independent of the national general population mortality. Thus they are not suitable for comparison between countries. Furthermore, the commonly used interpretation of the relative survival curve is vague and misleading. The present article attempts to remedy these basic problems. The population quantities of the traditional estimators are carefully described and their interpretation discussed. We then propose a new estimator of net survival probability that enables the desired comparability between countries. The new estimator requires no modeling and is accompanied with a straightforward variance estimate. The methods are described on real as well as simulated data. Key words: Age standardization; Cancer registry data; Competing risks; Net survival; Relative survival; Survival analysis. 1. Introduction observed hazard is larger than the population hazard. Survival probability Paul Dickman of cancer patients PopulationBased has been used Cancer for many Survival Under 9 April this 214 assumption, we use the term excess hazard for the hazard due to the disease and we have the 18 years as one of the main tools for evaluation of therapeutic advances. With improved treatments and prognosis, studies relation often now have long followup times and it is common to have observed hazard = population hazard+ excess hazard. a substantial proportion of deaths from causes other than the cancer under study. In the usual situation, the cause of death (1) is unavailable or unreliable. Hence the field of relative survival has developed in which observed deaths are compared with A survival function derived from the excess hazard alone is termed the net survival. those expected from general population life tables. We distinguish two goals: In this article, we shall focus on three estimators in widespread use in relative survival. We will refer to them (1) To compare the observed survival (SO) tothesurvival as Ederer I (Ederer, Axtell, and Cutler, 1961), Hakulinen of Aa diseasefree common groupquestion having the same indemographic our teaching. (Hakulinen, 1982), and Ederer II (Ederer et al., 1961, p. 11) characteristics as the study group. If the expected general population survival SP, the comparison is made and define them in Section 3 below. using Unless the ratiothere is reason to prefer aalthough causespecific all three were proposed approach, as variants for we estimat the denominator of the relative survival ratio, they have recommend oneso of (t) the following: also been interpreted as estimators of net survival. We will SR (t) = SP (t). show that this is not generally correct. When the excess Ederer II (1959 [?]) and the population hazard are not affected by any common This has been named the relative survival ratio. covariates, all methods to be discussed in this article estimate the same population quantity. In practice, however, ex (2) To estimate Pohar survival in Perme the hypothetical (212 situation [3]) where the disease under study would be the only possible cess hazard almost always depends on demographic variables cause of death. Modelbased (e.g., age) and one of the aims of this article is to find the This estimation is made possible by decomposing the population quantities that the estimators are estimating in observed hazard into the hazard due to the disease and such situations (Sections 2 and 3). The choice of method depends on the research question and that due to other causes. This decomposition can be Although the concept of net survival may seem too hypothetical to be of interest by itself, it becomes crucial carried out if the time to death due to the disease and practical considerations. the time to death due to other causes are conditionally when trying to compare cancer burden between countries, because it is independent of the general population mortality. independent given a known set of covariates. We then assume We that were the hazard recently due to other critical causes is [4] givenof Up a to paper now, most [5] authors that whoadvocated have produced large the sets of by the population mortality and, therefore, that the survival statistics (Sant et al., 29, and references therein) Pohar Perme approach; our critisism was of that particular paper C 211, The International Biometric Society 113 Which approach for estimating net survival? and not the Pohar Perme approach per se, of which we are great admirers. Paul Dickman PopulationBased Cancer Survival 9 April
8 We are not suggesting Ederer II is superior We are not suggesting that the Ederer II approach is superior to the Pohar Perme approach. However, we argue that it is not as inferior as some others (e.g., Roche et al [5]) would have us believe. We do not agree with Roche et al [5] that In estimating net survival, cancer registries should abandon all classical methods and adopt the new PoharPerme estimator because great errors may occur.... Internally standardised, or agespecific, Ederer II estimates of 5year and 1year net survival are biased, although the bias is generally so small that it makes no practical difference. In short, don t panic if you have used, or are using, Ederer II. Paul Dickman PopulationBased Cancer Survival 9 April European Journal of Cancer 4 (24) Review Period analysis for uptodate cancer survival data: theory, empirical evaluation, computational realisation and applications H. Brenner a, *, O. Gefeller b, T. Hakulinen c,d a Department of Epidemiology, German Centre for Research on Ageing, Bergheimer Str. 2, D Heidelberg, Germany b Department of Medical Informatics, Biometry and Epidemiology, University of ErlangenNuremberg, Waldstrasse 6, D9154 Erlangen, Germany c Finnish Cancer Registry, Liisankatu 21 B, FIN17 Helsinki, Finland d Department of Public Health, University of Helsinki, FIN17 Helsinki, Finland Received 6 August 23; received in revised form 3 September 23; accepted 21 October 23 Abstract Longterm survival rates are the most commonly used outcome measures for patients with cancer. However, traditional longterm survival statistics, which are derived by cohortbased types of analysis, essentially reflect the survival expectations of patients diagnosed many years ago. They are therefore often severely outdated at the time they become available. A couple of years ago, a new method of survival analysis, denoted period analysis, has been introduced to derive more uptodate estimates of longterm survival rates. Paul WeDickman give a comprehensive PopulationBased review of the Cancer new methodology, Survival its 9 statistical April 214background, empirical evaluation, computational realisation and applications. We conclude that period analysis is a powerful tool to provide more uptodate cancer sur 21 vival rates. More widespread use by cancer registries should help to increase the use of cancer survival statistics for patients, clinicians, and public health authorities. # 23 Elsevier Ltd. All rights reserved. Modelling Keywords: Neoplasms; Prognosis; excess Registries; Survival mortality 1. Introduction Relative Survival Model Longterm survival rates are the most commonly used outcome measures for patients with cancer. They are widely used to monitor progress in cancer care over time, or to compare quality of cancer care between different populations (e.g. [1 4]). Furthermore, cancer survival statistics are increasingly accessible through the Internet to clinicians and cancer patients, and their knowledge has Observed a strong impact on both clinicians management of the disease as well as patients coping strategies. However, traditional longterm survival rates, which have been derived by cohortbased types of analysis [5 7], have essentially reflected the survival expectations of patients diagnosed many years ago. They have often been severely outdated at the time they became available as they failed to account for ongoing improvements in survival over time. A few years ago, a new method of * Corresponding author. Tel.: ; fax address: (H. Brenner) /$  see front matter # 23 Elsevier Ltd. All rights reserved. doi:1.116/j.ejca h(t) = h (t) + λ(t) survival analysis, denoted period analysis, has been introduced to derive more uptodate estimates of longterm survival rates [8,9]. Meanwhile, this methodology has undergone extensive empirical evaluation [1 14], which showed that the method provides much more uptodate estimates of longterm survival rates than traditional methods of survival analysis indeed. Furthermore, software has been developed which allows easy implementation of this new analytical tool for both absolute and relative survival rates [15]. The method is now applied to derive more uptodate longterm survival rates in an increasing Mortality number of Rate countries [16 24]. These analyses suggest that longterm survival rates achieved by the end of the 2th century are much higher than previously suggested by traditional cohortbased analysis. For example, a recent period analysis of cancer patient survival in the United States [22] indicated that 2year relative survival rates for all cancers combined are now approximately 51% rather than 4% as suggested by traditional cohortbased analysis (see Fig. 1). Even larger differences are seen for many common forms of cancer, such as breast cancer (65% versus 52%) or ovarian cancer (5% versus 35%). Mortality Rate = Expected Mortality Rate + Excess Cox model cannot be applied to model a difference in two rates. It is the observed mortality that drives the variance. Can use Poisson regression (Dickman et al. 24) [6]. Even better: flexible parametric models (Royston and Parmar 22 [7], Nelson et al. [8]). Paul Dickman PopulationBased Cancer Survival 9 April
9 Flexible Parametric Survival Models [7, 1, 11] First introduced by Royston and Parmar (22) [7]. Parametric estimate of the baseline hazard without the usual restrictions on the shape (i.e, flexible). Applicable for standard and relative survival models. Can fit relative survival cure models (Andersson 211) [9]. Once we have a parametric expression for the baseline hazard we derive other quantities of interest (e.g., survival, hazard ratio, hazard differences, expectation of life). Paul Dickman PopulationBased Cancer Survival 9 April This paper has been cited over 27, times [12] Paul Dickman PopulationBased Cancer Survival 9 April The Cox model[12] h i (t x i, β) = h (t) exp (x i β) Advantage: The baseline hazard, h (t) is not directly estimated from a Cox model. Disadvantage: The baseline hazard, h (t) is not directly estimated from a Cox model. Paul Dickman PopulationBased Cancer Survival 9 April
10 Quote from Sir David Cox (Reid 1994 [13]) Reid What do you think of the cottage industry that s grown up around [the Cox model]? Cox In the light of further results one knows since, I think I would normally want to tackle the problem parametrically.... I m not keen on nonparametric formulations normally. Reid So if you had a set of censored survival data today, you might rather fit a parametric model, even though there was a feeling among the medical statisticians that that wasn t quite right. Cox That s right, but since then various people have shown that the answers are very insensitive to the parametric formulation of the underlying distribution. And if you want to do things like predict the outcome for a particular patient, it s much more convenient to do that parametrically. Paul Dickman PopulationBased Cancer Survival 9 April Example: survival of patients diagnosed with colon carcinoma in Finland Patients diagnosed with colon carcinoma in Finland Potential followup to end of 1995; censored after 1 years. Outcome is death due to colon carcinoma. Interest is in the effect of clinical stage at diagnosis (distant metastases vs no distant metastases). How might we specify a statistical model for these data? Paul Dickman PopulationBased Cancer Survival 9 April Smoothed empirical hazards (cancerspecific mortality rates) sts graph, by(distant) hazard kernel(epan2) Empirical hazard Not distant Distant Paul Dickman PopulationBased Cancer Survival 9 April
11 Smoothed empirical hazards on log scale sts graph, by(distant) hazard kernel(epan2) yscale(log) Empirical hazard Not distant Distant Paul Dickman PopulationBased Cancer Survival 9 April Fit a Cox model to estimate the mortality rate ratio. stcox distant No. of subjects = 1328 Number of obs = 1328 No. of failures = 7122 Time at risk = LR chi2(1) = Log likelihood = Prob > chi2 = _t Haz. Ratio Std. Err. z P> z [95% C.I.] distant Paul Dickman PopulationBased Cancer Survival 9 April Fitted hazards from Cox model with Efron method for ties stcox distant, efron Hazard Hazard ratio: 6.64 Not distant Distant Paul Dickman PopulationBased Cancer Survival 9 April
12 Hazard Fitted hazards from parametric survival model (exponential) Not distant Distant Hazard ratio: 1.4 Hazard Ratios Cox: 6.64 Exponential: Paul Dickman PopulationBased Cancer Survival 9 April Fitted hazards from parametric survival model (Weibull) Hazard Hazard ratio: 7.41 Hazard Ratios Cox: 6.64 Exponential: 1.4 Weibull: 7.41 Not distant Distant Paul Dickman PopulationBased Cancer Survival 9 April Fitted hazards from parametric survival model (Weibull) Not distant Distant Hazard Paul Dickman PopulationBased Cancer Survival 9 April
13 Fitted cumulative hazards from Weibull model Not distant Distant Cumulative Hazard Paul Dickman PopulationBased Cancer Survival 9 April Demography and epidemiology: Practical use of the Lexis diagram in the computer age. or: Who needs the Coxmodel anyway? Annual meeting of Finnish Statistical Society May 25 Revised December 25. Bendix Carstensen Steno Diabetes Center, Gentofte, Denmark & Department of Biostatistics, University of Copenhagen Paul Dickman PopulationBased Cancer Survival 9 April Hazard Fitted hazards from Poisson model (yearly intervals) Hazard Ratios Cox: 6.64 Exponential: 1.4 Weibull: 7.41 Poisson (annual): 6.89 Not distant Distant The contents of this paper was presented at the meeting of the Finnish Statistical Society in May 25 in Oulu. TheHazard slides presented ratio: 6.89 can be found on my homepage as Paul Dickman PopulationBased Cancer Survival 9 April
14 Hazard Fitted hazards from Poisson model (3months) Hazard ratio: 6.65 Hazard Ratios Cox: 6.64 Exponential: 1.4 Weibull: 7.41 Poisson (annual): 6.89 Poisson (quarter): 6.65 Not distant Distant Paul Dickman PopulationBased Cancer Survival 9 April Hazard Fitted hazards from Poisson model (months) Hazard ratio: 6.64 Hazard Ratios Cox: 6.64 Exponential: 1.4 Weibull: 7.41 Poisson (annual): 6.89 Poisson (quarter): 6.65 Poisson (months): 6.64 Not distant Distant Paul Dickman PopulationBased Cancer Survival 9 April Hazard Hazard ratio: 6.64 Poisson (rcs 5df for ln(time)) Hazard Ratios Cox: 6.64 Exponential: 1.4 Weibull: 7.41 Poisson (annual): 6.89 Poisson (quarter): 6.65 Poisson (months): 6.64 Not distant Distant Poisson (spline): Paul Dickman PopulationBased Cancer Survival 9 April 214 4
15 Hazard Fitted hazards from flexible parametric model (5df) Hazard ratio: 6.63 Hazard Ratios Cox: 6.64 Exponential: 1.4 Weibull: 7.41 Poisson (annual): 6.89 Poisson (quarter): 6.65 Poisson (months): 6.64 Not distant Distant Poisson (spline): 6.65 Flexible parametric: Paul Dickman PopulationBased Cancer Survival 9 April Flexible Parametric Models: Basic Idea Consider a Weibull survival curve. S(t) = exp ( λt γ ) If we transform to the log cumulative hazard scale. ln [H(t)] = ln[ ln(s(t))] ln [H(t)] = ln(λ) + γ ln(t) This is a linear function of ln(t) Introducing covariates gives ln [H(t x i )] = ln(λ) + γ ln(t) + x i β Rather than assuming linearity with ln(t) flexible parametric models use restricted cubic splines for ln(t). Paul Dickman PopulationBased Cancer Survival 9 April Fitted cumulative hazards from Weibull model Not distant Distant Cumulative Hazard Paul Dickman PopulationBased Cancer Survival 9 April
16 Flexible Parametric Models: Incorporating Splines We thus model on the log cumulative hazard scale. ln[h(t x i )] = ln [H (t)] + x i β This is a proportional hazards model. Restricted cubic splines with knots, k, are used to model the log baseline cumulative hazard. ln[h(t x i )] = η i = s (ln(t) γ, k ) + x i β For example, with 4 knots we can write ln [H(t x i )] = η i = γ + γ 1 z 1i + γ 2 z 2i + γ 3 z }{{ 3i } log baseline cumulative hazard + x i β }{{} log hazard ratios Paul Dickman PopulationBased Cancer Survival 9 April We are fitting a linear predictor on the log cumulative hazard scale. Survival and Hazard Functions We can transform to the survival scale S(t x i ) = exp( exp(η i )) The hazard function is a bit more complex. h(t x i ) = ds (ln(t) γ, k ) dt exp(η i ) This involves the derivatives of the restricted cubic splines functions, although these are relatively easy to calculate. Paul Dickman PopulationBased Cancer Survival 9 April Paul Dickman PopulationBased Cancer Survival 9 April
17 Sensitivity to choice of knots; Simulation study by Rutherford et al. [14] Through the use of simulation, we show that provided a sufficient number of knots are used, the approximated hazard functions given by restricted cubic splines fit closely to the true function for a range of complex hazard shapes. The simulation results also highlight the insensitivity of the estimated relative effects (hazard ratios) to the correct specification of the baseline hazard. Paul Dickman PopulationBased Cancer Survival 9 April
18 Simulation Study (Rutherford et al.) [14] Generate data assuming a mixture Weibull distribution. 2.5 Scenario Scenario Hazard rate Hazard rate Time Since Diagnosis (Years) Time Since Diagnosis (Years) 2.5 Scenario Scenario Hazard rate Hazard rate Time Since Diagnosis (Years) Time Since Diagnosis (Years) Fit models using restricted cubic splines. Paul Dickman PopulationBased Cancer Survival 9 April Scenario 3 comparison of Log Hazard Ratios .4 Cox Model Flexible Parametric Model Paul Dickman PopulationBased Cancer Survival 9 April Choice of knots: Scenario 3 8 knots (7 df) 1. Survival Function 1.6 Hazard Function S(t) h(t) Time since diagnosis (years) Paul Dickman PopulationBased Cancer Survival 9 April
19 Model Selection Estimated hazard and survival functions fairly insensitive to knot location. AIC and BIC can be used as rough guides to choose models. Not crucial (within reason) to inference based on the model. We often present a sensitivity analysis to show this. Could treat number of knots and their locations as unknowns. However, it is an area where more work is still required. Paul Dickman PopulationBased Cancer Survival 9 April Implementation in Stata [1] stpm2 available from SSC. ssc install stpm2 All cause survival. stpm2 eng, scale(hazard) df(5) Relative survival. stpm2 eng, scale(hazard) df(5) hazard(rate) Timedependent effects. stpm2 eng, scale(hazard) df(5) hazard(rate) tvc(eng) dftvc(3) Cure model. stpm2 eng, scale(hazard) df(5) hazard(rate) tvc(eng) dftvc(3) cure Paul Dickman PopulationBased Cancer Survival 9 April Example using attained age as the timescale Study from Sweden [6] comparing incidence of hip fracture of, 17,731 men diagnosed with prostate cancer treated with bilateral orchiectomy. 43,23 men diagnosed with prostate cancer not treated with bilateral orchiectomy. 362,354 men randomly selected from the general population. Study entry is 6 months post diagnosis. Outcome is femoral neck (hip) fracture. Risk of fracture varies by age. Attained age is used as the primary timescale. Actually, two timescales, but will initially ignore time from diagnosis. Paul Dickman PopulationBased Cancer Survival 9 April
20 Estimates from a proportional hazards model stset using age as the timescale. stset dateexit,fail(frac = 1) enter(datecancer) origin(datebirth) /// id(id) scale(365.25) exit(time datebirth + 1*365.25) Cox Model. stcox noorc orc Incidence rate ratio (no orchiectomy) = 1.37 (1.28 to 1.46) Incidence rate ratio (orchiectomy) = 2.9 (1.93 to 2.27) Flexible Parametric Model. stpm2 noorc orc, df(5) scale(hazard) Incidence rate ratio (no orchiectomy) = 1.37 (1.28 to 1.46) Incidence rate ratio (orchiectomy) = 2.9 (1.93 to 2.27) Paul Dickman PopulationBased Cancer Survival 9 April Proportional Hazards Incidence Rate (per 1 py's) Control No Orchiectomy Orchiectomy Age Paul Dickman PopulationBased Cancer Survival 9 April Non Proportional Hazards Incidence Rate (per 1 py's) Control No Orchiectomy Orchiectomy Age Paul Dickman PopulationBased Cancer Survival 9 April
21 Incidence Rate Ratio Orchiectomy vs Control Incidence Rate Ratio Age Paul Dickman PopulationBased Cancer Survival 9 April Incidence Rate Difference Difference in Incidence Rates (per 1 person years) Orchiectomy vs Control Age Paul Dickman PopulationBased Cancer Survival 9 April stpm2 postestimation commands Fit model (nonproportional hazards) stpm2 noorc orc, df(5) scale(h) tvc(noorc orc) dftvc(3) Fitted hazards predict h1, h zeros predict h2, h at(noorc 1 orc ) predict h3, h at(noorc orc 1) Hazard ratios predict hr2, hrnum(noorc 1) ci predict hr3, hrnum(orc 1) ci Hazard differences predict hdiff2, hdiff1(noorc 1) ci predict hdiff3, hdiff1(orc 1) ci Paul Dickman PopulationBased Cancer Survival 9 April
22 Net Survival (revisited) Relative Survival aims to estimate net survival. This is the probability of not dying of cancer in the hypothetical world where it is impossible to die of other causes. Key Assumptions Independence between mortality due to cancer and mortality due to other causes & an appropriate estimate of expected survival. Same interpretation/assumption for causespecific survival. We also assume that we have modelled covariates appropriately. Paul Dickman PopulationBased Cancer Survival 9 April Crude and Net Probabilities Net Probability of Death Due to Cancer = Probability of death due to cancer in a hypothetical world, where the cancer under study is the only possible cause of death Crude Probability of Death Due to Cancer = Probability of death due to cancer in the real world, where you may die of other causes before the cancer kills you Net probability also known as the marginal probability. Crude probability also known as the causespecific cumulative incidence function (Geskus) or the cumulative incidence function. Paul Dickman PopulationBased Cancer Survival 9 April Brief Mathematical Details [15] h(t) = h (t) + λ(t)  allcause mortality rate h (t)  expected mortality rate λ(t)  excess mortality rate S (t)  Expected Survival R(t)  Relative Survival ( t ) Net Prob of Death = 1 R(t) = 1 exp λ(t) Crude Prob of Death (cancer) = Crude Prob of Death (other causes) = t t S (t)r(t)λ(t) S (t)r(t)h (t) Paul Dickman PopulationBased Cancer Survival 9 April
23 Probabilities of death due to prostate cancer [16] Net probability of death (1 relative survival) Dead (PC) Alive Age 75 at diagnosis Crude probability of death Dead (PC) Dead (other causes) alive Age 75 at diagnosis Net probability of death (1 relative survival) Dead (PC) Alive Age 6 at diagnosis Crude probability of death Dead (PC) Dead (other causes) Alive Age 6 at diagnosis The inserted numbers represent the 1 year probabilities of death Paul Dickman PopulationBased Cancer Survival 9 April What is cure? Medical cure occurs when all signs of cancer have been removed in a patient; this is an individuallevel definition of cure. It is difficult to prove that a patient is medically cured. Population or statistical cure occurs when mortality among patients with the disease returns to the same level as that expected for the general population. Equivalently the excess mortality rate approaches zero. This is a populationlevel definition of cure. When the excess mortality reaches (and stays) at zero, the relative survival curve is seen to reach a plateau. Paul Dickman PopulationBased Cancer Survival 9 April Plateau for relative survival 1..8 Relative Survival Years from Diagnosis Paul Dickman PopulationBased Cancer Survival 9 April
24 Mixture cure model Mixture cure model S(t) = S (t)(π + (1 π)s u (t)); λ(t) = h (t) + (1 π)fu(t) π+(1 π)s u(t) S (t) is the expected survival. π is the proportion cured (the cure fraction). (1 π) is the proportion uncured (those bound to die ). S u (t) is the net survival for the uncured group. The excess mortality rate has an asymptote at zero. See De Angelis et al. [17], Verdecchia et al. [18] and Lambert et al.[19] for details. Paul Dickman PopulationBased Cancer Survival 9 April Cure models: Interpreting changes over time Survival of Uncured (c) Cure Fraction Adapted from Verdeccia (1998) (a) (d) (b) (a) General Improvement (b) Selective Improvment (c) Improved palliative care or lead time (d) Inclusion of subjects with no excess risk Paul Dickman PopulationBased Cancer Survival 9 April Time trends for cancer of the colon age <5 [2] Cure Fraction and Median Survival of Uncured Age Group: <5 1. Cure Fraction Median Survival Cure Fraction Median Survival Year of Diagnosis. Paul Dickman PopulationBased Cancer Survival 9 April 214 7
25 Andersson 21 [21]: trends for AML Aged 19 4 at diagnosis Aged 41 6 at diagnosis Cure proportion Median survival time Cure proportion Median survival time Year of diagnosis Year of diagnosis Aged 61 7 at diagnosis Aged 71 8 at diagnosis Cure proportion Median survival time Cure proportion Median survival time Year of diagnosis Year of diagnosis Cure proportion Median survival time 95% CI Paul Dickman PopulationBased Cancer Survival 9 April Flexible parametric cure models One limitation of parametric cure models is that a functional form has to be specified Hard to fit survival functions flexible enough to capture high excess hazard within a few months from diagnosis Hard to fit high cure proportion Flexible parametric approach for cure models enable inclusion of these patient groups Andersson et al. BMC Medical Research Methodology 211, 11:96 RESEARCH ARTICLE Open Access Estimating and modelling cure in populationbased cancer studies within the framework of flexible parametric survival models Therese ML Andersson 1*, Paul W Dickman 1, Sandra Eloranta 1 and Paul C Lambert 1,2 Paul Dickman PopulationBased Cancer Survival 9 April Flexible parametric cure models When cure is reached the excess hazard rate is zero, and the cumulative excess hazard is constant By incorporating an extra constraint on the log cumulative excess hazard after the last knot, so that we force it not only to be linear but also to have zero slope, we are able to estimate the cure proportion This is done by calculating the splines backwards and introduce a constraint on the linear spline parameter in the regression model Paul Dickman PopulationBased Cancer Survival 9 April
26 Flexible parametric cure models Paul Dickman PopulationBased Cancer Survival 9 April Flexible parametric cure models The relative survival function from the flexible parametric survival model, with splines calculated backwards and with restriction on the parameter for the linear spline variable is defined as R(t) = exp( exp(γ + γ 2 z γ K 1 z K 1 )) which can be written as where π = exp( exp(γ )). R(t) = π exp(γ 2z γ K 1 z K 1 ), Paul Dickman PopulationBased Cancer Survival 9 April Comparison with a nonmixture model The flexible parametric cure model is a special case of a nonmixture cure model with and π = exp( exp(γ )) F Z (t) = exp(γ 2 z γ K 1 z K 1 ). This is a proportional hazards model as long as no timedependent effects are modelled. Paul Dickman PopulationBased Cancer Survival 9 April
27 Flexible parametric cure models Incorporating covariates gives, and π = exp( exp(γ + xβ)) F Z (t) = exp(γ 2 z γ K 1 z K 1 + D s (ln(t); γ i ) x i ) the constant parameters are used to model the cure proportion i=1 the timedependent parameters are used to model the distribution function constraint of a zero effect for the linear spline term has to be incorporated for each spline function Paul Dickman PopulationBased Cancer Survival 9 April Flexible parametric cure models Flexible parametric cure models can be fitted in Stata by adding a cure option to the stpm2 command stpm2 cage2cage4, scale(h) df(5) bhazard(rate) /// tvc(cage2cage4) dftvc(3) cure The spline variables will be calculated backwards, the constraint will be added for the linear spline parameters and the default knot distribution will be slightly different Paul Dickman PopulationBased Cancer Survival 9 April Flexible parametric cure models Log likelihood = Number of obs = xb Coef. Std. Err. z P> z [95% Conf. Interval] cage cage cage _rcs _rcs _rcs _rcs _rcs5 (omitted) _rcs_cage _rcs_cage _rcs_cage23 (omitted) _rcs_cage _rcs_cage _rcs_cage33 (omitted) _rcs_cage _rcs_cage _rcs_cage43 (omitted) _cons Paul Dickman PopulationBased Cancer Survival 9 April
28 Flexible parametric cure models The cure proportion, the survival function for the uncured and the median survival time for uncured can be estimated using the predict command. predict cure, cure. predict medst, centile(5) uncured. predict survunc, survival uncured. predict surv, survival Paul Dickman PopulationBased Cancer Survival 9 April Flexible parametric cure models Paul Dickman PopulationBased Cancer Survival 9 April Flexible parametric cure models Paul Dickman PopulationBased Cancer Survival 9 April
29 Flexible parametric cure models Paul Dickman PopulationBased Cancer Survival 9 April Flexible parametric cure models Paul Dickman PopulationBased Cancer Survival 9 April Partitioning Excess Mortality (Eloranta [22, 23]) We have extended flexible parametric models for relative survival to simultaneously estimate the excess mortality due to diseases of the circulatory system (DCS) and the remaining excess mortality among patients diagnosed with Hodgkin lymphoma. Results are presented both as excess mortality rates and crude probabilities of death. The outcomes (DCS and nondcs mortality) can be regarded as competing events and the total excess mortality is partitioned using ideas from classical competing risks theory. The model requires population mortality files stratified on cause of death (i.e., DCS and other deaths) to identify those deaths in excess of expected. Paul Dickman PopulationBased Cancer Survival 9 April
30 Excess mortality for males with Hodgkin lymphoma 25 Age at Diagnosis: Age at Diagnosis: Excess Mortality (per 1, p yrs) Excess Mortality (per 1, p yrs) Years Since Diagnosis Years Since Diagnosis Excess DCS Mortality Remaining Excess Mortality 95% C.I Paul Dickman PopulationBased Cancer Survival 9 April Temporal trends in 2year probability of death 2 year Probability of Death Age at Diagnosis: Year of Diagnosis Predicted future 2 year Probability of Death Age at Diagnosis: Year of Diagnosis 2 year Probability of Death Age at Diagnosis: Year of Diagnosis Predicted future 2 year Probability of Death Age at Diagnosis: Year of Diagnosis Dead (Excess DCS Mortality) Dead (Other Causes) Dead (Remaining Excess HL Mortality) 95 % CI Paul Dickman PopulationBased Cancer Survival 9 April Loss in expectation of life A useful summary measure of survival is the mean survival, life expectancy The loss in expectation of life is the difference between the mean expected survival (if not diagnosed with cancer) and the mean observed survival (for cancer patients) Quantify disease burden in the society how many lifeyears are lost due to the disease? Quantify differences between socioeconomic groups or countries, how many lifeyears are lost in the population due to differences in cancer patient survival between groups? how many lifeyears would be gained if England had the same cancer patient survival as Sweden? Quantify the impact a cancer diagnosis has on a patient s life expectancy Paul Dickman PopulationBased Cancer Survival 9 April
31 Loss in expectation of life Survival Paul Dickman PopulationBased Cancer Survival 9 April Loss in expectation of life Survival Mean observed survival 5.3 years Paul Dickman PopulationBased Cancer Survival 9 April Loss in expectation of life Survival Mean expected survival 1.5 years Paul Dickman PopulationBased Cancer Survival 9 April
32 Loss in expectation of life Survival Difference 5.2 years Paul Dickman PopulationBased Cancer Survival 9 April Loss in expectation of life Survival Paul Dickman PopulationBased Cancer Survival 9 April Loss in expectation of life Even though we are now interested in the allcause survival we will use a relative survival approach S(t) = S (t) R(t) h(t) = h (t) + λ(t) Easier to extrapolate R(t) than S(t) Has been done for grouped data (life tables) [24], by assuming λ(t) = or λ(t) = c after some point in time Paul Dickman PopulationBased Cancer Survival 9 April
33 Loss in expectation of life Approaches for extrapolating relative survival 1 Assume cure, i.e no excess hazard after a certain point in time, λ(t) = 2 Assume constant excess hazard after a certain point in time, λ(t) = c (exponential) 3 Assume the excess hazard given by the spline parameters from the model without imposing extra constraints, (Weibull) The allcause survival can then be estimated by multiplying with the (extrapolated) expected survival Paul Dickman PopulationBased Cancer Survival 9 April Loss in expectation of life, colon cancer Survival Colon cancer, Age 6 69, Males Mean survival: 5.3 years 6.6 years 5.1 years 5.4 years Paul Dickman PopulationBased Cancer Survival 9 April Loss in expectation of life, breast cancer Breast cancer Survival Age 5 59 Age 6 69 Survival Age 7 79 Age K M estimates of all cause survival Extrapolating relative survival 95% CI for K M Relative survival, constant EH Paul Dickman PopulationBased Cancer Survival 9 April
34 Loss in expectation of life, melanoma Melanoma Survival Age 5 59 Age 6 69 Survival Age 7 79 Age K M estimates of all cause survival Extrapolating relative survival 95% CI for K M Relative survival, cure Paul Dickman PopulationBased Cancer Survival 9 April Loss in expectation of life, bladder cancer Bladder cancer Survival Age 5 59 Age 6 69 Survival Age 7 79 Age K M estimates of all cause survival Extrapolating relative survival 95% CI for K M Relative survival, constant EH Paul Dickman PopulationBased Cancer Survival 9 April Loss in expectation of life, colon cancer Relative survival 1 Males 1 Females year RSR year RSR Year of diagnosis Year of diagnosis Age 55 Age 65 Age 75 Age 85 Paul Dickman PopulationBased Cancer Survival 9 April 214 1
35 Loss in expectation of life, colon cancer Males, Age 55 Males, Age Years 15 1 Years Year of diagnosis Year of diagnosis Males, Age 75 Males, Age Years 15 1 Years Year of diagnosis Year of diagnosis Life expectancy of general population Life expectancy of cancer patients Paul Dickman PopulationBased Cancer Survival 9 April Loss in expectation of life, colon cancer Loss in expectation of life Males Females Years Years Year of diagnosis Year of diagnosis Age 55 Age 65 Age 75 Age 85 Paul Dickman PopulationBased Cancer Survival 9 April Loss in expectation of life Males Females Years Proportion Years Proportion Age at diagnosis Age at diagnosis Years of expected life lost (left y axis) Proportion of expected life lost (right y axis) Paul Dickman PopulationBased Cancer Survival 9 April
Quantifying cancer patient survival; extensions and applications of cure models and life expectancy estimation
From the Department of Medical Epidemiology and Biostatistics Karolinska Institutet, Stockholm, Sweden Quantifying cancer patient survival; extensions and applications of cure models and life expectancy
More informationEstimating and Modelling the Proportion Cured of Disease in Population Based Cancer Studies
Estimating and Modelling the Proportion Cured of Disease in Population Based Cancer Studies Paul C Lambert Centre for Biostatistics and Genetic Epidemiology, University of Leicester, UK 12th UK Stata Users
More informationAn Overview of Survival Statistics in SEER*Stat
An Overview of Survival Statistics in SEER*Stat National Cancer Institute SEER Program SEER s mission is to provide information on cancer statistics in an effort to reduce the burden of cancer among the
More informationCancer Incidence Predictions (Finnish Experience)
Cancer Incidence Predictions (Finnish Experience) Tadeusz Dyba Joint Research Center EPAAC Workshop, January 2223 2014, Ispra Rational for making cancer incidence predictions Administrative: to plan the
More informationMultivariate doseresponse metaanalysis: an update on glst
Multivariate doseresponse metaanalysis: an update on glst Nicola Orsini Unit of Biostatistics Unit of Nutritional Epidemiology Institute of Environmental Medicine Karolinska Institutet http://www.imm.ki.se/biostatistics/
More informationMeasuring and predicting cancer incidence, prevalence and survival in Finland
Measuring and predicting cancer incidence, prevalence and survival in Finland Timo Hakulinen and Karri Seppä Finnish Cancer Registry the Institute for Statistical and Epidemiological Cancer Research ABSTRACT
More informationApplication of EM Algorithm to Mixture Cure Model for Grouped Relative Survival Data
Journal of Data Science 5(2007), 4151 Application of EM Algorithm to Mixture Cure Model for Grouped Relative Survival Data Binbing Yu 1 and Ram C. Tiwari 2 1 Information Management Services, Inc. and
More informationBiostatistics II
Biostatistics II 5145509 Course Description: Modern multivariable statistical analysis based on the concept of generalized linear models. Includes linear, logistic, and Poisson regression, survival analysis,
More informationDeprivation and Cancer Survival in Scotland: Technical Report
Deprivation and Cancer Survival in Scotland: Technical Report 1 Foreword We are delighted to publish the first report from the Macmillan Cancer Support partnership with the Information Services Division.
More informationLiver Cancer Report on Cancer Statistics in Alberta. December Cancer Care. Cancer Surveillance
December 212 21 Report on Cancer Statistics in Alberta Acknowledgements 2 This report was made possible through Alberta Health Services,, and the many contributions of staff and management across Alberta
More information2012 Report on Cancer Statistics in Alberta
212 Report on Cancer Statistics in Alberta Kidney Cancer Surveillance & Reporting CancerControl AB February 215 Acknowledgements This report was made possible through Surveillance & Reporting, Cancer Measurement
More informationChallenges in design and analysis of large registerbased epidemiological studies
FMS/DSBS autumn meeting 2014 Challenges in design and analysis of large registerbased epidemiological studies Caroline Weibull & Anna Johansson Department of Medical Epidemiology and Biostatistics (MEB)
More informationLecture Outline. Biost 590: Statistical Consulting. Stages of Scientific Studies. Scientific Method
Biost 590: Statistical Consulting Statistical Classification of Scientific Studies; Approach to Consulting Lecture Outline Statistical Classification of Scientific Studies Statistical Tasks Approach to
More informationLOGO. Statistical Modeling of Breast and Lung Cancers. Cancer Research Team. Department of Mathematics and Statistics University of South Florida
LOGO Statistical Modeling of Breast and Lung Cancers Cancer Research Team Department of Mathematics and Statistics University of South Florida 1 LOGO 2 Outline Nonparametric and parametric analysis of
More informationRegression Discontinuity Designs: An Approach to Causal Inference Using Observational Data
Regression Discontinuity Designs: An Approach to Causal Inference Using Observational Data Aidan O Keeffe Department of Statistical Science University College London 18th September 2014 Aidan O Keeffe
More informationWhen PSA fails. Urology Grand Rounds Alexandra Perks. Rising PSA after Radical Prostatectomy
When PSA fails Urology Grand Rounds Alexandra Perks Rising PSA after Radical Prostatectomy Issues Natural History Local vs Metastatic Treatment options 1 10 000 men / year in Canada 4000 RRP 15year PSA
More informationEstimating relative survival: An analysis of bias introduced by outdated life tables. Larry Ellison Health Statistics Division Ottawa, June 24, 2014
Estimating relative survival: An analysis of bias introduced by outdated life tables Larry Ellison Health Statistics Division Ottawa, June 24, 2014 Background relative survival defined... The ratio of
More informationDo morphology and stage explain the inferior lung cancer survival in Denmark?
Eur Respir J 1999; 13: 430±435 Printed in UK ± all rights reserved Copyright #ERS Journals Ltd 1999 European Respiratory Journal ISSN 09031936 Do morphology and stage explain the inferior lung cancer
More informationLandmarking, immortal time bias and. Dynamic prediction
Landmarking and immortal time bias Landmarking and dynamic prediction Discussion Landmarking, immortal time bias and dynamic prediction Department of Medical Statistics and Bioinformatics Leiden University
More informationSpatiotemporal models for disease incidence data: a case study
Spatiotemporal models for disease incidence data: a case study Erik A. Sauleau 1,2, Monica Musio 3, Nicole Augustin 4 1 Medicine Faculty, University of Strasbourg, France 2 HautRhin Cancer Registry 3
More informationSurvival analysis beyond the Coxmodel
Survival analysis beyond the Coxmodel Hans C. van Houwelingen Department of Medical Statistics Leiden University Medical Center The Netherlands jcvanhouwelingen@lumc.nl http://www.medstat.medfac.leidenuniv.nl/ms/hh/
More informationNotes for laboratory session 2
Notes for laboratory session 2 Preliminaries Consider the ordinary leastsquares (OLS) regression of alcohol (alcohol) and plasma retinol (retplasm). We do this with STATA as follows:. reg retplasm alcohol
More informationA PopulationBased Study on the Uptake and Utilization of Stereotactic Radiosurgery (SRS) for Brain Metastasis in Nova Scotia
A PopulationBased Study on the Uptake and Utilization of Stereotactic Radiosurgery (SRS) for Brain Metastasis in Nova Scotia Gaurav Bahl, Karl Tennessen, Ashraf MahmoudAhmed, Dorianne Rheaume, Ian Fleetwood,
More informationSelection and Combination of Markers for Prediction
Selection and Combination of Markers for Prediction NACC Data and Methods Meeting September, 2010 Baojiang Chen, PhD Sarah Monsell, MS XiaoHua Andrew Zhou, PhD Overview 1. Research motivation 2. Describe
More informationShould relative survival be used with lung cancer data?
British Journal of Cancer (22) 6, 84 89 & 22 Cancer Research UK All rights reserved 7 92/2 www.bjcancer.com Should relative survival be used with lung cancer data? SR Hinchliffe*,, MJ Rutherford, MJ Crowther,
More informationReport on Cancer Statistics in Alberta. Melanoma of the Skin
Report on Cancer Statistics in Alberta Melanoma of the Skin November 29 Surveillance  Cancer Bureau Health Promotion, Disease and Injury Prevention Report on Cancer Statistics in Alberta  2 Purpose of
More informationAdvanced IPD metaanalysis methods for observational studies
Advanced IPD metaanalysis methods for observational studies Simon Thompson University of Cambridge, UK Part 4 IBC Victoria, July 2016 1 Outline of talk Usual measures of association (e.g. hazard ratios)
More informationNation nal Cancer Institute. Prevalence Projections: The US Experience
Nation nal Cancer Institute Prevalence Projections: The US Experience State of Art Methods for the Analysis of Population Based Cancer Data January 2223, 2014 Ispra, Italy U.S. DEPARTMENT OF HEALTH AND
More informationUptodate survival curves of children with cancer by period analysis
British Journal of Cancer (3) 88, 1693 1697 & 3 Cancer Research UK All rights reserved 7 9/3 $25. www.bjcancer.com Uptodate survival curves of children with cancer by period analysis *,1 1 Department
More informationA Competing Risk Analysis of Men Age Years at Diagnosis Managed Conservatively for Clinically Localized Prostate Cancer
A Competing Risk Analysis of Men Age 5574 Years at Diagnosis Managed Conservatively for Clinically Localized Prostate Cancer Peter C. Albertsen, MD 1 James A. Hanley, PhD 2 Donald F.Gleason, MD, PhD 3
More informationFundamental Clinical Trial Design
Design, Monitoring, and Analysis of Clinical Trials Session 1 Overview and Introduction Overview Scott S. Emerson, M.D., Ph.D. Professor of Biostatistics, University of Washington February 1719, 2003
More informationBenchmark Dose Modeling Cancer Models. Allen Davis, MSPH Jeff Gift, Ph.D. Jay Zhao, Ph.D. National Center for Environmental Assessment, U.S.
Benchmark Dose Modeling Cancer Models Allen Davis, MSPH Jeff Gift, Ph.D. Jay Zhao, Ph.D. National Center for Environmental Assessment, U.S. EPA Disclaimer The views expressed in this presentation are those
More informationTitle: Use of Betablockers and Mortality Following Ovarian Cancer Diagnosis: A PopulationBased Cohort Study
Author's response to reviews Title: Use of Betablockers and Mortality Following Ovarian Cancer Diagnosis: A PopulationBased Cohort Study Authors: Sigrun A Johannesdottir (saj@dce.au.dk) Morten Schmidt
More informationWhat is Multilevel Modelling Vs Fixed Effects. Will Cook Social Statistics
What is Multilevel Modelling Vs Fixed Effects Will Cook Social Statistics Intro Multilevel models are commonly employed in the social sciences with data that is hierarchically structured Estimated effects
More informationAN EMPIRICAL EVALUATION OF PERIOD SURVIVAL ANALYSIS USING DATA FROM THE CANADIAN CANCER REGISTRY. Larry F. Ellison MSc, Statistics Canada
AN EMPIRICAL EVALUATION OF PERIOD SURVIVAL ANALYSIS USING DATA FROM THE CANADIAN CANCER REGISTRY Larry F. Ellison MSc, Statistics Canada Introduction Longterm survival rates are important outcome measures
More informationPoisson regression. DaeJin Lee Basque Center for Applied Mathematics.
DaeJin Lee dlee@bcamath.org Basque Center for Applied Mathematics http://idaejin.github.io/bcamcourses/ D.J. Lee (BCAM) Intro to GLM s with R GitHub: idaejin 1/40 Modeling count data Introduction Response
More informationScore Tests of Normality in Bivariate Probit Models
Score Tests of Normality in Bivariate Probit Models Anthony Murphy Nuffield College, Oxford OX1 1NF, UK Abstract: A relatively simple and convenient score test of normality in the bivariate probit model
More informationCase Studies in Bayesian Augmented Control Design. Nathan Enas Ji Lin Eli Lilly and Company
Case Studies in Bayesian Augmented Control Design Nathan Enas Ji Lin Eli Lilly and Company Outline Drivers for innovation in Phase II designs Case Study #1 Pancreatic cancer Study design Analysis Learning
More informationTime Series Analysis for selected clinical indicators from the Quality and Outcomes Framework
Time Series Analysis for selected clinical indicators from the Quality and Outcomes Framework 2126 Title Document Type Time Series Analysis for selected clinical indicators from the Quality and Outcomes
More information1. Objective: analyzing CD4 counts data using GEE marginal model and random effects model. Demonstrate the analysis using SAS and STATA.
LDA lab Feb, 6 th, 2002 1 1. Objective: analyzing CD4 counts data using GEE marginal model and random effects model. Demonstrate the analysis using SAS and STATA. 2. Scientific question: estimate the average
More informationClinical Trials A Practical Guide to Design, Analysis, and Reporting
Clinical Trials A Practical Guide to Design, Analysis, and Reporting Duolao Wang, PhD Ameet Bakhai, MBBS, MRCP Statistician Cardiologist Clinical Trials A Practical Guide to Design, Analysis, and Reporting
More informationA Brief Introduction to Bayesian Statistics
A Brief Introduction to Statistics David Kaplan Department of Educational Psychology Methods for Social Policy Research and, Washington, DC 2017 1 / 37 The Reverend Thomas Bayes, 1701 1761 2 / 37 PierreSimon
More informationPresentation with lymphadenopathy
Presentation with lymphadenopathy Theo M. de Reijke MD PhD FEBU Department of Urology Academic Medical Center Amsterdam Rationale for RRP in N+ disease Prevention local problems Better survival in limited
More informationLecture Outline. Biost 517 Applied Biostatistics I. Purpose of Descriptive Statistics. Purpose of Descriptive Statistics
Biost 517 Applied Biostatistics I Scott S. Emerson, M.D., Ph.D. Professor of Biostatistics University of Washington Lecture 3: Overview of Descriptive Statistics October 3, 2005 Lecture Outline Purpose
More informationESM1 for Glucose, blood pressure and cholesterol levels and their relationships to clinical outcomes in type 2 diabetes: a retrospective cohort study
ESM1 for Glucose, blood pressure and cholesterol levels and their relationships to clinical outcomes in type 2 diabetes: a retrospective cohort study Statistical modelling details We used Cox proportionalhazards
More informationMetabolic factors and risk of prostate, kidney, and bladder cancer. Christel Häggström
Metabolic factors and risk of prostate, kidney, and bladder cancer Christel Häggström Department of Surgical and Perioperative Sciences, Urology and Andrology Umeå University, 2013 Metabolic factors and
More informationGeorge B. Ploubidis. The role of sensitivity analysis in the estimation of causal pathways from observational data. Improving health worldwide
George B. Ploubidis The role of sensitivity analysis in the estimation of causal pathways from observational data Improving health worldwide www.lshtm.ac.uk Outline Sensitivity analysis Causal Mediation
More informationSupplementary Appendix
Supplementary Appendix This appendix has been provided by the authors to give readers additional information about their work. Supplement to: Schaapveld M, Aleman BMP, van Eggermond AM, et al. Second cancer
More informationIndividualized Treatment Effects Using a Nonparametric Bayesian Approach
Individualized Treatment Effects Using a Nonparametric Bayesian Approach Ravi Varadhan Nicholas C. Henderson Division of Biostatistics & Bioinformatics Department of Oncology Johns Hopkins University
More informationCARDIOVASCULAR DISEASE AND DIABETES:
CARDIOVASCULAR DISEASE AND DIABETES: HOW OECD HEALTH SYSTEMS DELIVER BETTER OUTCOMES? Progress report 7 th November 2013 Outline Overview of the project Preliminary results Descriptive Analytical Next
More informationCrossvalidation. Miguel Angel Luque Fernandez Faculty of Epidemiology and Population Health Department of Noncommunicable Disease.
Crossvalidation Miguel Angel Luque Fernandez Faculty of Epidemiology and Population Health Department of Noncommunicable Disease. August 25, 2015 Cancer Survival Group (LSH&TM) Crossvalidation August
More informationEpidemiology: Overview of Key Concepts and Study Design. Polly Marchbanks
Epidemiology: Overview of Key Concepts and Study Design Polly Marchbanks Lecture Outline (1) Key epidemiologic concepts  Definition  What epi is not  What epi is  Process of epi research Lecture Outline
More informationStatistical Methods for the Evaluation of Treatment Effectiveness in the Presence of Competing Risks
Statistical Methods for the Evaluation of Treatment Effectiveness in the Presence of Competing Risks Ravi Varadhan Assistant Professor (On Behalf of the Johns Hopkins DEcIDE Center) Center on Aging and
More informationClinicalTrials.gov "Basic Results" Data Element Definitions (DRAFT)
ClinicalTrials.gov "Basic Results" Data Element Definitions (DRAFT) January 9, 2009 * Required by ClinicalTrials.gov [*] Conditionally required by ClinicalTrials.gov (FDAAA) May be required to comply with
More informationOngoing and planned colorectal cancer clinical outcome analyses
Ongoing and planned colorectal cancer clinical outcome analyses Eva Morris Cancer Research UK Bobby Moore Career Development Fellow National Cancer Data Repository Numerous routine health data sources
More informationTrends in Cure Fraction from Colorectal Cancer by Age and Tumour Stage Between 1975 and 2000, Using Populationbased Data, Osaka, Japan
Epidemiology Note Jpn J Clin Oncol 2012;42(10)974 983 doi:10.1093/jjco/hys132 Advance Access Publication 5 September 2012 Trends in Cure Fraction from Colorectal Cancer by Age and Tumour Stage Between
More informationStatistical, clinical and ethical considerations when minimizing confounding for overall survival in cancer immunotherapy trials
Statistical, clinical and ethical considerations when minimizing confounding for overall survival in cancer immunotherapy trials Dominik Heinzmann, PhD Global Development Team Leader HER2 Associate Director
More informationCANCER IN TASMANIA INCIDENCE AND MORTALITY 1995
CANCER IN TASMANIA INCIDENCE AND MORTALITY 1995 ACKNOWLEDGEMENTS The Department of Community and Health Services in Tasmania is acknowledged for financial support to the Registry. The work of collecting
More informationEstimands for time to event endpoints in oncology and beyond
Estimands for time to event endpoints in oncology and beyond Kaspar Rufibach, Hans Ulrich Burger Methods, Collaboration & Outreach Group (MCO) Department of Biostatistics, Roche Basel Context and problem
More informationHow to analyze correlated and longitudinal data?
How to analyze correlated and longitudinal data? Niloofar Ramezani, University of Northern Colorado, Greeley, Colorado ABSTRACT Longitudinal and correlated data are extensively used across disciplines
More informationOriginal Article INTRODUCTION. Alireza Abadi, Farzaneh Amanpour 1, Chris Bajdik 2, Parvin Yavari 3
www.ijpm.ir Breast Cancer Survival Analysis: Applying the Generalized Gamma Distribution under Different Conditions of the Proportional Hazards and Accelerated Failure Time Assumptions Alireza Abadi, Farzaneh
More informationMEASURE SPECIFICATIONS
QOPI REPTING REGISTRY (QCDR) 2018 QOPI5 Title Chemotherapy administered to patients with metastatic solid tumor with performance status of 3, 4, or undocumented (Lower Score  Better) Description Percentage
More informationGSK Medicine: Study Number: Title: Rationale: Study Period: Objectives: Indication: Study Investigators/Centers: Research Methods: Data Source
The study listed may include approved and nonapproved uses, formulations or treatment regimens. The results reported in any single study may not reflect the overall results obtained on studies of a product.
More informationReview of Veterinary Epidemiologic Research by Dohoo, Martin, and Stryhn
The Stata Journal (2004) 4, Number 1, pp. 89 92 Review of Veterinary Epidemiologic Research by Dohoo, Martin, and Stryhn Laurent Audigé AO Foundation laurent.audige@aofoundation.org Abstract. The new book
More informationComparison And Application Of Methods To Address Confounding By Indication In Non Randomized Clinical Studies
University of Massachusetts Amherst ScholarWorks@UMass Amherst Masters Theses 1911  February 2014 Dissertations and Theses 2013 Comparison And Application Of Methods To Address Confounding By Indication
More informationAnalysis methods for improved external validity
Analysis methods for improved external validity Elizabeth Stuart Johns Hopkins Bloomberg School of Public Health Department of Mental Health Department of Biostatistics www.biostat.jhsph.edu/ estuart estuart@jhsph.edu
More informationGENERAL ICD C61: Prostate cancer Page 2 of 18 ICD C61: Malignant neoplasm of prostate Period of diagnosis % Relative survival N=46,
Munich Cancer Registry Incidence and Mortality Selection Matrix Homepage Deutsch ICD C61: Prostate cancer Survival Year of diagnosis 19881997 1998215 Patients 7,45 49,513 Diseases 7,45 49,514 Cases
More informationNonhomogenous Poisson Process for Evaluating Stage I & II Ductal Breast Cancer Treatment
Journal of Modern Applied Statistical Methods Volume 10 Issue 2 Article 23 1112011 Nonhomogenous Poisson Process for Evaluating Stage I & II Ductal Breast Cancer Treatment Chris P Tsokos University
More informationSentinel node biopsy What is the status today?
Sentinel node biopsy What is the status today? Robert H. I. Andtbacka M.D., C.M, FACS, FRCSC Associate Professor of Surgery Huntsman Cancer Institute University of Utah São Paulo, Brazil June 2223, 2017
More informationTemporal trends in the proportion cured for cancer of the colon and rectum: A populationbased study using data from the Finnish Cancer Registry
Int. J. Cancer: 121, 2052 2059 (2007) ' 2007 WileyLiss, Inc. Temporal trends in the proportion cured for cancer of the colon and rectum: A populationbased study using data from the Finnish Cancer Registry
More information1 Case Control Studies
Statistics April 11, 2013 Debdeep Pati 1 Case Control Studies 1. Casecontrol (retrospective) study: Select cases, Select controls, Compare cases and controls 2. Cutaneous melanoma (Autier, 1996). 420
More informationCauses of death in men with prostate cancer: an analysis of men from the Thames Cancer Registry
Causes of death in men with prostate cancer: an analysis of 5 men from the Thames Cancer Registry Simon Chowdhury, David Robinson, Declan Cahill*, Alejo RodriguezVida, Lars Holmberg and Henrik Møller
More informationCosteffectiveness of androgen suppression therapies in advanced prostate cancer Bayoumi A M, Brown A D, Garber A M
Costeffectiveness of androgen suppression therapies in advanced prostate cancer Bayoumi A M, Brown A D, Garber A M Record Status This is a critical abstract of an economic evaluation that meets the criteria
More informationDanish populationbased registries in cancer pharmacoepidemiology. Cancer Pharmacoepidemiology Meeting Dublin September 2013
Danish populationbased registries in cancer pharmacoepidemiology Deirdre Cronin Fenton dc@dce.au.dk Cancer Pharmacoepidemiology Meeting Dublin September 2013 Frank L. Science 2003 The Danish Cohort The
More informationCancer Waiting Times. 1 April Adjuvant Radical External Beam Radiotherapy Definitions. Version 1.0
Cancer Waiting Times Adjuvant Radical External Beam Radiotherapy Definitions Version 1.0 1 April 2015 Document Control Document Purpose Definitions for NHS Boards for the adjuvant radical external beam
More informationMultiple Mediation Analysis For General Models with Application to Explore Racial Disparity in Breast Cancer Survival Analysis
Multiple For General Models with Application to Explore Racial Disparity in Breast Cancer Survival Qingzhao Yu Joint Work with Ms. Ying Fan and Dr. Xiaocheng Wu Louisiana Tumor Registry, LSUHSC June 5th,
More informationStratified CostEffectiveness Analysis (with implications for subgroup analysis) (and applications to valuebased pricing)
Stratified CostEffectiveness Analysis (with implications for subgroup analysis) (and applications to valuebased pricing) Andrew H Briggs William R Lindsay Chair of Health Economics Stratified CEA: Overview
More informationCancer Prevention & Control in Adolescent & Young Adult Survivors
+ Cancer Prevention & Control in Adolescent & Young Adult Survivors NCPF Workshop July 1516, 2013 Patricia A. Ganz, MD UCLA Schools of Medicine & Public Health Jonsson Comprehensive Cancer Center + Overview
More informationStatin use and reduced cancerrelated mortality Journal Club 24/11/12
Statin use and reduced cancerrelated mortality Journal Club 24/11/12 Presenter: Anas Sarhan Moderator: Prof. Ronan Conroy The new england journal of medicine original article Statin Use and Reduced CancerRelated
More informationGeneralizing the right question, which is?
Generalizing RCT results to broader populations IOM Workshop Washington, DC, April 25, 2013 Generalizing the right question, which is? Miguel A. Hernán Harvard School of Public Health Observational studies
More informationSelected Topics in Biostatistics Seminar Series. Missing Data. Sponsored by: Center For Clinical Investigation and Cleveland CTSC
Selected Topics in Biostatistics Seminar Series Missing Data Sponsored by: Center For Clinical Investigation and Cleveland CTSC Brian Schmotzer, MS Biostatistician, CCI Statistical Sciences Core brian.schmotzer@case.edu
More informationNIH Public Access Author Manuscript World J Urol. Author manuscript; available in PMC 2012 February 1.
NIH Public Access Author Manuscript Published in final edited form as: World J Urol. 2011 February ; 29(1): 11 14. doi:10.1007/s0034501006254. Significance of preoperative PSA velocity in men with low
More informationEquity in use of procedures and survival among AMIpatients: Evidence from a modern welfare state*
Equity in use of procedures and survival among AMIpatients: Evidence from a modern welfare state* Terje P. Hagen 1, Unto Häkkinen 1,2, Tor Iversen 1 and Tron Anders Moger 1 1 Department of Health Management
More information1. Study Title. Exercise and Late Mortality in 5Year Survivors of Childhood Cancer: a Report from the Childhood Cancer Survivor Study.
CCSS Analysis Concept Proposal Exercise, Mortality, & Childhood Cancer 1 1. Study Title. Exercise and Late Mortality in 5Year Survivors of Childhood Cancer: a Report from the Childhood Cancer Survivor
More informationCollection of Recorded Radiotherapy Seminars
IAEA Human Health Campus Collection of Recorded Radiotherapy Seminars http://humanhealth.iaea.org Conservative Treatment of Invasive Bladder Cancer Luis Souhami, MD Professor Department of Radiation Oncology
More informationOverview of NonParametric Statistics
Overview of NonParametric Statistics LISA Short Course Series Mark Seiss, Dept. of Statistics April 7, 2009 Presentation Outline 1. Homework 2. Review of Parametric Statistics 3. Overview NonParametric
More informationLecture Outline Biost 517 Applied Biostatistics I
Lecture Outline Biost 517 Applied Biostatistics I Scott S. Emerson, M.D., Ph.D. Professor of Biostatistics University of Washington Lecture 2: Statistical Classification of Scientific Questions Types of
More informationBinary Diagnostic Tests Two Independent Samples
Chapter 537 Binary Diagnostic Tests Two Independent Samples Introduction An important task in diagnostic medicine is to measure the accuracy of two diagnostic tests. This can be done by comparing summary
More informationConcepts of Clinical Trials
Concepts of Clinical Trials Samiran Sinha Texas A&M University sinha@stat.tamu.edu November 18, 2017 Samiran Sinha (TAMU) Clinical trial November 18, 2017 1 / 56 What are clinical trials and why do people
More informationGeneralized Linear Models of Malaria Incidence in Jubek State, South Sudan
Science Journal of Applied Mathematics and Statistics 2017; 5(4): 134138 http://www.sciencepublishinggroup.com/j/sjams doi: 10.11648/j.sjams.20170504.12 ISSN: 23769491 (Print); ISSN: 23769513 (Online)
More informationDylan Small Department of Statistics, Wharton School, University of Pennsylvania. Based on joint work with Paul Rosenbaum
Instrumental variables and their sensitivity to unobserved biases Dylan Small Department of Statistics, Wharton School, University of Pennsylvania Based on joint work with Paul Rosenbaum Overview Instrumental
More informationQualityofLife Effects of ProstateSpecific Antigen Screening
QualityofLife Effects of ProstateSpecific Antigen Screening Eveline A.M. Heijnsdijk, Ph.D., Elisabeth M. Wever, M.Sc., Anssi Auvinen, M.D., Jonas Hugosson, M.D., Stefano Ciatto, M.D., Vera Nelen, M.D.,
More informationPresentation with lymphadenopathy
Presentation with lymphadenopathy Theo M. de Reijke MD PhD FEBU Department of Urology Academic Medical Center Amsterdam Rationale for RRP in N+ disease Prevention local problems Better survival in limited
More informationOutline. Introduction GitHub and installation Worked example Stata wishes Discussion. mrrobust: a Stata package for MREgger regression type analyses
mrrobust: a Stata package for MREgger regression type analyses London Stata User Group Meeting 2017 8 th September 2017 Tom Palmer Wesley Spiller Neil Davies Outline Introduction GitHub and installation
More informationIntroduction. Original Article
bs_bs_banner International Journal of Urology (2015) 22, 363 367 doi: 10.1111/iju.12704 Original Article Prostatespecific antigen level, stage or Gleason score: Which is best for predicting outcomes after
More informationEvidenceBased Medicine Journal Club. A Primer in Statistics, Study Design, and Epidemiology. August, 2013
EvidenceBased Medicine Journal Club A Primer in Statistics, Study Design, and Epidemiology August, 2013 Rationale for EBM Conscientious, explicit, and judicious use Beyond clinical experience and physiologic
More informationChapter 1: Exploring Data
Chapter 1: Exploring Data Key Vocabulary:! individual! variable! frequency table! relative frequency table! distribution! pie chart! bar graph! twoway table! marginal distributions! conditional distributions!
More informationCarrying out an Empirical Project
Carrying out an Empirical Project Empirical Analysis & Style Hint Special program: Pretraining 1 Carrying out an Empirical Project 1. Posing a Question 2. Literature Review 3. Data Collection 4. Econometric
More informationLecture Outline Biost 517 Applied Biostatistics I. Statistical Goals of Studies Role of Statistical Inference
Lecture Outline Biost 517 Applied Biostatistics I Scott S. Emerson, M.D., Ph.D. Professor of Biostatistics University of Washington Statistical Inference Role of Statistical Inference Hierarchy of Experimental
More informationForum for Health Economics & Policy
Forum for Health Economics & Policy Volume 13, Issue 2 2010 Article 11 (HEALTH ECONOMICS) Are Increasing 5Year Survival Rates Evidence of Success Against Cancer? A Reexamination Using Data from the U.S.
More information