An analysis for a cross-over cohort study with an application to the study of triggers of Menière's disease.

Centre for Mental Health Research, Australian National University, Canberra, Australia.
Statistics in Medicine (Impact Factor: 2.04). 03/2007; 26(5):1136-49. DOI: 10.1002/sim.2601
Source: PubMed

ABSTRACT When studying the effect of a transient exposure on the risk of a rare illness, for time and cost effectiveness it is desirable to follow a cohort of individuals who are 'prone' to the illness over an observation period. In this paper, we present a method of analysis for data arising from such a study. The proposed method can be used to estimate the relative risk of an exposure triggering the illness and the distribution of the time delay from exposure to the onset of illness. The model is extended to include covariate effects and to the situation where there are two types of exposure. For the two types of exposures situation, a model to handle a possible synergism of the exposures is proposed. Finally, the method is applied to study the potential triggers of attacks of Menière's disease.

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Menière's disease is defined as the presence of recurrent, spontaneous episodic vertigo, hearing loss (HL), aural fullness, and tinnitus. The occurrence of attacks is unpredictable. The etiology is still unknown, but the disease has a pathologic correlate in hydropic distension of the endolymphatic system. Earlier studies have shown increased incidence of stress on the same day as vertigo attacks, but it has not been determined whether stress occurring on the day of the vertiginous episode came before or after the onset of the vertigo. A case-crossover study including 46 patients with active Menière's disease. Relative risks with 95% confidence intervals (CI). During the study period, 153 Menière's attacks were reported. Twenty-four (52%) of the 46 patients reported attacks. Twelve of the 153 (8%) attacks occurred within 3 hours after exposure to emotional stress. The relative risk of having an attack was 5.10 (95% CI 2.37-10.98) during 3 hours after being exposed to emotional stress. Twenty-nine percent of the patients with attacks had at least one attack after exposure to emotional stress. For mental stress, the relative risk was 4.16 (95% CI 1.46-11.83) and the hazard period 1 hour, but only five attacks were exposed. No excess risk was found after physical stress. Being exposed to emotional stress increases the risk of getting an attack of Menière's disease during the next hour, and the hazard period is possibly extended up to 3 hours.
    The Laryngoscope 11/2004; 114(10):1843-8. · 2.03 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Simple tests are given for consistency of the data with additive and with multiplicative effects of two risk factors on a binary outcome. A combination of the procedures will show whether data are consistent with neither, one or both of the models of no additive or no multiplicative interaction. Implications for the size of the study needed to detect differences between the models are also addressed. Because of the simple form of the test statistics, combination of evidence from different studies or strata is straightforward. Illustration of how the method could be extended to data from a 2xRxC table is also given.
    Biostatistics 02/2005; 6(1):1-9. · 2.24 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: A case-control design involving only cases may be used when brief exposure causes a transient change in risk of a rare acute-onset disease. The design resembles a retrospective nonrandomized crossover study but differs in having only a sample of the base population-time. The average incidence rate ratio for a hypothesized effect period following the exposure is estimable using the Mantel-Haenszel estimator. The duration of the effect period is assumed to be that which maximizes the rate ratio estimate. Self-matching of cases eliminates the threat of control-selection bias and increases efficiency. Pilot data from a study of myocardial infarction onset illustrate the control of within-individual confounding due to temporal association of exposures.
    American Journal of Epidemiology 02/1991; 133(2):144-53. · 4.98 Impact Factor