Lab 5

Post-op sore throat trial

Postoperative sore throat is an annoying complication of intubation after surgery, particularly with wider gauge double-lumen tubes. Reutzler et al. (2013) performed an experimental study among patients having elective surgery who required intubation with a double-lumen tube. Prior to anesthesia, patients were randomly assigned to gargle either a licorice-based solution or sugar water (as placebo). Sore throat was evaluated 30 minutes, 90 minutes, and 4 hours after conclusion of the surgery. Keep in mind that this was a randomized clinical trial; we may make causal conclusions regarding licorice as a potential treatment for post-op sore throat from these data.

This week's data were made available by The Cleveland Clinic. Relevant variables in the dataset are as follows (though note that there are quite a few other variables as well:

• treat: treatment (0 = sugar placebo, 1 = licorice solution)
• preOp_gender: gender (0 = male, 1 = female)
• preOp_calcBMI: body mass index in kg/m2
• preOp_age: age in years
• preOp_asa: ASA severity category (1 = health, 2 = mild disease, 3 = severe disease)
• pacu30min_throatPain: Sore throat pain score 30 minutes after surgery (treat this as a continuous scale, where 0 = no pain and 10 = worst pain)

Exercises

1. We are interested in the treatment effect of licorice. Fit a linear model with PACU 30 minute throat pain as the outcome, and treatment, gender, BMI, age, and ASA category as predictors. Use only main effects, and treat each predictor in the most appropriate way (e.g., ASA category should be used as a categorical variable). Is there evidence that licorice is effective in reducing sore throat?
2. The researchers were also interested in whether there might be differential effects based on patient type. Is there evidence that, while controlling for the same variables as in Exercise 1, the treatment effect of licorice differs based on gender? Assess this using a relevant model and hypothesis test, and further provide treatment efficacy estimates for each gender in the dataset.
3. The researchers are similarly interested in whether licorice might be differentially effective based on ASA severity category. Perform a similar analysis as in Exercise 2, this time providing efficacy estimates for each severity category in the dataset.
4. Finally, researchers are interested in whether licorice might be differentially effective based on BMI. Perform a similar analysis as in Exercise 2, and specifically quantify the efficacy of licorice in this model.

There should only be one submission per team on Gradescope. All team members must make at least one meaningful commit to the repository for this week's lab.