1. Satistics 2621 Statistics 262: Intermediate Biostatistics Jonathan Taylor and Kristin Cobb April 20, 2004: Introduction to Survival Analysis

2. Satistics 2622 What is survival analysis? Statistical methods for analyzing longitudinal data on the occurrence of events. Events may include death, injury, onset of illness, recovery from illness (binary variables) or transition above or below the clinical threshold of a meaningful continuous variable (e.g. CD4 counts). Accommodates data from randomized clinical trial or cohort study design.

3. Randomized Clinical Trial (RCT) Target population Intervention Control Disease Disease-free Disease Disease-free TIME Random assignment Disease-free, at-risk cohort

4. Target population Treatment Control Cured Not cured Cured Not cured TIME Random assignment Patient population Randomized Clinical Trial (RCT)

5. Target population Treatment Control Dead Alive Dead Alive TIME Random assignment Patient population Randomized Clinical Trial (RCT)

6. Cohort study (prospective/retrospective) Target population Exposed Unexposed Disease Disease-free Disease Disease-free TIME Disease-free cohort

7. Satistics 2627 Estimate time-to-event for a group of individuals, such as time until second heart- attack for a group of MI patients. To compare time-to-event between two or more groups, such as treated vs. placebo MI patients in a randomized controlled trial. To assess the relationship of co-variables to time-to-event, such as: does weight, insulin resistance, or cholesterol influence survival time of MI patients? Note: expected time-to-event = 1/incidence rate Objectives of survival analysis

8. Satistics 2628 Examples of survival analysis in medicine

9. RCT: Women’s Health Initiative (JAMA, 2001) On hormones On placebo Cumulative incidence

10. Satistics 26210 Prospective cohort study: From April 15, 2004 NEJM: Use of Gene-Expression Profiling to Identify Prognostic Subclasses in Adult Acute Myeloid Leukemia

11. Satistics 26211 Retrospective cohort study: From December 2003 BMJ: Aspirin, ibuprofen, and mortality after myocardial infarction: retrospective cohort study

12. Satistics 26212 Why use survival analysis? 1. Why not compare mean time-to-event between your groups using a t-test or linear regression? -- ignores censoring 2. Why not compare proportion of events in your groups using logistic regression? --ignores time

13. Satistics 26213 Cox regression vs.logistic regression Distinction between rate and proportion: Incidence (hazard) rate: number of new cases of disease per population at-risk per unit time (or mortality rate, if outcome is death) Cumulative incidence: proportion of new cases that develop in a given time period

14. Satistics 26214 Cox regression vs.logistic regression Distinction between hazard/rate ratio and odds ratio/risk ratio: Hazard/rate ratio: ratio of incidence rates Odds/risk ratio: ratio of proportions By taking into account time, you are taking into account more information than just binary yes/no. Gain power/precision. Logistic regression aims to estimate the odds ratio; Cox regression aims to estimate the hazard ratio

15. Satistics 26215 Rates vs. risks Relationship between risk and rates:

16. Satistics 26216 Rates vs. risks For example, if rate is 5 cases/1000 person-years, then the chance of developing disease over 10 years is: Compare to.005(10) = 5% The loss of persons at risk because they have developed disease within the period of observation is small relative to the size of the total group.

17. Satistics 26217 Rates vs. risks If rate is 50 cases/1000 person-years, then the chance of developing disease over 10 years is: Compare to.05(10) = 50%

18. Satistics 26218 Rates vs. risks Relationship between risk and rates (derivation): Exponential density function for waiting time until the event (constant hazard rate) Preview: Waiting time distribution will change if the hazard rate changes as a function of time: h(t)

19. Survival Analysis: Terms Time-to-event: The time from entry into a study until a subject has a particular outcome Censoring: Subjects are said to be censored if they are lost to follow up or drop out of the study, or if the study ends before ends before they die or have an outcome of interest. They are counted as alive or disease-free for the time they were enrolled in the study. If dropout is related to both outcome and treatment, dropouts may bias the results

20. Satistics 26220 Right Censoring (T>t) Common examples Termination of the study Death due to a cause that is not the event of interest Loss to follow-up We know that subject survived at least to time t.

21. Satistics 26221 Left censoring (T<t) The origin time, not the event time, is known only to be less than some value. For example, if you are studying menarche and you begin following girls at age 12, you may find that some of them have already begun menstruating. Unless you can obtain information about the start date for those girls, the age of menarche is left-censored at age 12. *from:Allison, Paul. Survival Analysis. SAS Institute. 1995.

22. Satistics 26222 Interval censoring (a<T<b) When we know the event has occurred between two time points, but don’t know the exact dates. For example, if you’re screening subjects for HIV infection yearly, you may not be able to determine the exact date of infection.* *from:Allison, Paul. Survival Analysis. SAS Institute. 1995.

23. Satistics 26223 Data Structure: survival analysis Time variable: t i = time at last disease- free observation or time at event Censoring variable: c i =1 if had the event; c i =0 no event by time t i

24. Satistics 26224 Choice of origin

25. Satistics 26225

26. Satistics 26226 Describing survival distributions T i the event time for an individual, is a random variable having a probability distribution. Different models for survival data are distinguished by different choice of distribution for T i.

27. Satistics 26227 Survivor function (cumulative distribution function) Survival analysis typically uses complement, or the survivor function: Example: If t=100 years, S(t=100) = probability of surviving beyond 100 years. Cumulative failure function

28. Satistics 26228 Corresponding density function The probability of the failure time occurring at exactly time t (out of the whole range of possible t’s). Also written:

29. Satistics 26229 Hazard function In words: the probability that if you survive to t, you will succumb to the event in the next instant. Derivation:

30. Satistics 26230 Relating these functions:

31. Satistics 26231 Introduction to Kaplan-Meier Non-parametric estimate of survivor function. Commonly used to describe survivorship of study population/s. Commonly used to compare two study populations. Intuitive graphical presentation.

32. Beginning of studyEnd of study  Time in months  Subject B Subject A Subject C Subject D Subject E Survival Data (right-censored) 1. subject E dies at 4 months X

33. 100%  Time in months  Corresponding Kaplan-Meier Curve Probability of surviving to just before 4 months is 100% = 5/5 Fraction surviving this death = 4/5 Subject E dies at 4 months

34. Beginning of studyEnd of study  Time in months  Subject B Subject A Subject C Subject D Subject E Survival Data 2. subject A drops out after 6 months 1. subject E dies at 4 months X 3. subject C dies at 7 months X

35. 100%  Time in months  Corresponding Kaplan-Meier Curve subject C dies at 7 months Fraction surviving this death = 2/3

36. Beginning of studyEnd of study  Time in months  Subject B Subject A Subject C Subject D Subject E Survival Data 2. subject A drops out after 6 months 4. Subjects B and D survive for the whole year-long study period 1. subject E dies at 4 months X 3. subject C dies at 7 months X

37. 100%  Time in months  Corresponding Kaplan-Meier Curve Product limit estimate of survival = P(surviving/at-risk through failure 1) * P(surviving/at-risk through failure 2) = 4/5 * 2/3=.5333

38. The product limit estimate The probability of surviving in the entire year, taking into account censoring = (4/5) (2/3) = 53% NOTE:  40% (2/5) because the one drop- out survived at least a portion of the year. AND <60% (3/5) because we don’t know if the one drop-out would have survived until the end of the year.

39. Satistics 26239 KM estimator, formally

40. Comparing 2 groups

41. Caveats Survival estimates can be unreliable toward the end of a study when there are small numbers of subjects at risk of having an event.

42. WHI and breast cancer Small numbers left

43. Satistics 26243 Overview of SAS PROCS LIFETEST - Produces life tables and Kaplan-Meier survival curves. Is primarily for univariate analysis of the timing of events. LIFEREG – Estimates regression models with censored, continuous-time data under several alternative distributional assumptions. Does not allow for time-dependent covariates. PHREG– Uses Cox’s partial likelihood method to estimate regression models with censored data. Handles both continuous-time and discrete-time data and allows for time-dependent covariables