Generalized additive models for the analysis of EQ-5D utility data.

BACKGROUND: Measured utility data have a discrete distribution, and the discreteness is particularly pronounced for EQ-5D utilities. Given the discreteness of the data, modeling the distribution parametrically is likely to be difficult. Moreover, since the distribution is bounded, the linearity assumptions made by many models are questionable. This article suggests using semi-parametric models and illustrates the use of generalized additive models (GAMs) for handling nonlinear associations. METHODS: A simulation study is used to explore whether bias arises when applying parametric models to discrete utility data. A further simulation investigates the bias in semi-parametric linear and quasi-beta regression models when the assumed linearity does not hold and also investigates the use of GAMs. The use of GAMs in practice is shown through a recent study of health utilities among patients with diabetes. RESULTS: Using parametric beta models to analyze discrete EQ-5D utility data led to substantial bias. Both semi-parametric linear regression and quasi-beta regression led to biased estimates of marginal and incremental effects when the mean model was misspecified. The use of GAMs reduced these biases. CONCLUSIONS: Parametric models for EQ-5D utility data should be used with caution. Semi-parametric modeling of utility data should check for nonlinearity. GAMs can help in diagnosing and accommodating nonlinearity.

Incidence of undiagnosed sleep apnea in patients scheduled for elective total joint arthroplasty.

We investigated the frequency of undiagnosed sleep apnea in patients scheduled for elective total joint arthroplasty. Two hundred fifty-four patients were assessed between September 1999 and May 2001. At intake, patients were given a standard systems review with the addition of targeted questions about sleep apnea. Ten patients reported symptoms consistent with undiagnosed obstructive sleep apnea (OSA). The identification of undiagnosed OSA is an issue for orthopedic practice because many patients referred to an arthroplasty service for hip and/or knee surgeries are obese. A few screening questions, readily incorporated into the preoperative assessment, may prevent perioperative complications such as postextubation airway obstruction, negative pressure pulmonary edema, or opioid-induced airway obstruction.

Organ donation: a pilot study of knowledge among medical and other university students.

BACKGROUND: Physicians' knowledge of and attitudes towards organ donation may be a factor in organ procurement rates. There is a lack of information about how Canadian medical students perceive organ donation, and what they know about it. OBJECTIVE: This pilot study assesses the knowledge and attitudes of university students toward organ donation. METHODS: Medical students completed a self-administered questionnaire after a lecture. Non-medical students completed the same questionnaire at the university student center. The questionnaire included a test that was used to assess knowledge about organ donation. Attitudes were assessed by determining whether the student carried a signed organ donor card, and their reasons if they did not. RESULTS: Of the 76 students in the first-year medical class, 39 responded. A sample of the first 40 non-medical students to visit a booth at the student centre was selected for comparative analysis. The mean age of medical students was 23.5 years; 23 for non-medical students. Of those surveyed, 56.6 per cent were women. Of medical students, 30.8 per cent reported carrying a signed card compared with 50 per cent of non-medical students. The most common reason for not carrying a card in both groups was apathy. Median test scores were 2.4/6 for both groups. Students carrying a signed card had a median test score of 2.7/6, with the median score for those not carrying signed cards being 2.2/6. CONCLUSION: More investigation of the knowledge and attitudes of medical students regarding organ donation is warranted.