19 curated medical datasets across categories such as historical clinical trials, oncology, and cardiology. The collection includes standardized data from landmark studies, ranging from the 1747 scurvy trial to modern observational studies on blood storage and cancer recurrence.
Use Cases
- Analyze treatment efficacy for scurvy using the treatment and symptom_severity variables
- Model the risk of cancer recurrence using the age, p_vol, and recurrence columns in the blood_storage data
- Practice Poisson regression on longitudinal counts using the number0 and number12 columns in the polyps dataset
- Evaluate the impact of streptomycin on tuberculosis using the radiologic_improvement and gender variables in the strep_tb dataset
Strengths
- Includes the scurvy dataset documenting 12 patients across 8 variables from the first controlled clinical trial in 1747
- Contains the blood_storage dataset with 316 rows and 21 variables investigating the relationship between blood storage duration and cancer recurrence
- Features the strep_tb dataset containing 107 observations from the first randomized clinical trial of streptomycin
- Provides the polyps dataset containing longitudinal data on 22 patients with familial adenomatous polyposis