Presentation is loading. Please wait.

Presentation is loading. Please wait.

Induction and latency (J-F Boivin, March 2006)

Similar presentations


Presentation on theme: "Induction and latency (J-F Boivin, March 2006)"— Presentation transcript:

1 Induction and latency (J-F Boivin, March 2006)
Introduction Rothman’s model of induction Analysis: largest estimate methods Modelling approaches Thomas 1983 Rachet et al. 2003 Version: 28 February 2006 (abbreviated)

2 Point exposures

3 Point exposure, fixed induction period
Disease initiation Disease detection Exposure Induction period Latent period Empirical induction period In practice, induction and latent period can rarely be be separated

4 Point exposure, variable induction period
Disease detection 12 yr 17 yr Empirical induction period (12 to 17 yr)

5 Excess incidence

6 Incidence Time Exposed Unexposed

7 Analysis Two simultaneous goals:
Estimate the mode of the distribution of empirical induction periods Estimate the effect of the exposure on disease risk without bias due to inappropriate assumption about induction period

8 Principle Measures of effect are reduced if an inappropriate assumption is used for the empirical induction period (nondifferential misclassification)

9 In utero DES No exposure RR 0–9 yr 1/10 000 1/10 000 1 1 1/10 000 10–19 yr 1000 1/10 000 1 000/10 000 20–29 yr 334 3/30 000 1 002/30 000 all yr

10 Estimate the measure of association repeatedly with different assumptions about the induction period
The maximum point estimate of the measure of association corresponds to the most appropriate assumption about induction period and simultaneously offers an estimate of the maximum effect relatively unobscured by an inappropriate assumption

11 Limitation of largest estimate methods (Rothman-Greenland 1998, pp

12

13

14

15 Alternative approach Estimate the effects for each time window
while adjusting for the exposures from other windows Sharpe et al. British Journal of Cancer 2002

16

17

18 Multiple time-windows approach
Problem:

19 Modelling Thomas 1983

20 (RE-R0) (T) = b S d(t) f (T-t) dose T “weight” of the dose at time t
d(t) f (T-t) dose at time t “weight” of the dose at time t

21 (RE-R0) (T) = b S d(t) f (T-t) excess risk = excess risk per unit dose
d(t) f (T-t) excess risk = excess risk per unit dose weighted dose

22 (RE-R0) (T) = b S d(t) f (T-t) Some functional form is assumed:
d(t) f (T-t) Some functional form is assumed: Rothman’s approach (AJE 1981): weight is between times a and b at other times 1 DES example f = 1 between ages 20 and 29 f = 0 at other times a and b determined by trial and error

23 E+ 10/10,000 55/10,000 100/10,000 E- 10/10,000 10/10,000 10/10,000 yr RE-R0 45/10,000 90/10,000

24 E+ E- 165/30,000 = 55/10,000 30/30,000 = 10/10,000 RE-R = /10,000 RE-R = (45/10,000) x 1

25 E+ E- 10/10,000 155/20,000 = 77.5/10,000 10/10,000 20/20,000 = 10/10,000 RE-R = /10,000 RE-R = (67.5/10,000) x 0 + (67.5/10,000) x 1

26 E+ 10/10,000 55/10,000 100/10,000 E- 10/10,000 10/10,000 10/10,000 RE-R0 45/10,000 90/10,000 RE-R = (90/10,000) x 0 + (90/10,000) x 0.5 + (90/10,000) x 1

27 ER (T) = b  d(t) f (T-t) dt Lundin et al. (1979)
Lung cancer in uranium miners ER (T) = b T d(t) f (T-t) dt f: assumed to be log normal (based on leukemia risk after single exposure to radiation and an incubation period for infectious diseases) Values of 5, 10, 15 yr for induction period are fitted Standard deviation of log t units is assumed

28 Complexities of modelling
Relevant exposure may be a complex function of the intensity of the exposure and time (Rothman-Greenland, p. 83) Influence of intensity Influence of age at exposure atomic bomb survivors

29

30 Rachet et al. Statistics in Medicine 2003

31 Limitation of Thomas’ approach

32 Rachet et al. no strong a priori assumptions
however: dichotomous point exposure

33 Rachet et al. Overall hazard ratio (HR) represents weighted average of


Download ppt "Induction and latency (J-F Boivin, March 2006)"

Similar presentations


Ads by Google