A larger and more comprehensive dataset for Decision Curve Analysis, including patient demographics, clinical risk factors, multiple risk model predictions, and outcome variables in both numeric and character formats.
Usage
data(dca_test_data)Format
A data frame with 800 rows and 19 variables:
- patient_id
Integer. Unique patient identifier.
- age
Integer. Patient's age in years.
- sex
Character. Patient's sex.
- diabetes
Character. Diabetes status.
- hypertension
Character. Hypertension status.
- smoking
Character. Smoking status.
- cholesterol
Integer. Cholesterol level.
- troponin
Numeric. Troponin level.
- creatinine
Numeric. Serum creatinine level.
- cardiac_event_numeric
Integer. Numeric indicator of cardiac event (e.g., 0 or 1).
- cardiac_event
Character. Character indicator of cardiac event (e.g., "Yes", "No").
- true_risk
Numeric. A simulated true underlying risk score for the patient.
- basic_model
Numeric. Predicted probability from a basic risk model.
- enhanced_model
Numeric. Predicted probability from an enhanced risk model.
- biomarker_model
Numeric. Predicted probability from a model incorporating a biomarker.
- miscalibrated_model
Numeric. Predicted probability from a model designed to be miscalibrated.
- poor_model
Numeric. Predicted probability from a model with poor discrimination.
- risk_category
Character. Categorized risk level based on some criteria.
- hospital
Character. Hospital or center identifier.
Examples
data(dca_test_data)
str(dca_test_data)
#> 'data.frame': 800 obs. of 19 variables:
#> $ patient_id : int 1 2 3 4 5 6 7 8 9 10 ...
#> $ age : num 72 74 64 60 72 43 73 62 62 54 ...
#> $ sex : chr "Male" "Male" "Male" "Male" ...
#> $ diabetes : chr "No" "Yes" "Yes" "No" ...
#> $ hypertension : chr "Yes" "No" "Yes" "No" ...
#> $ smoking : chr "Never" "Former" "Current" "Never" ...
#> $ cholesterol : num 213 164 248 228 211 223 225 226 183 203 ...
#> $ troponin : num 4.1 5.27 2.61 10.58 9.72 ...
#> $ creatinine : num 0.79 1.04 1.15 0.9 0.8 1.14 1.35 0.81 1.47 1.27 ...
#> $ cardiac_event_numeric: int 0 0 0 0 1 0 0 0 1 0 ...
#> $ cardiac_event : Factor w/ 2 levels "No","Yes": 1 1 1 1 2 1 1 1 2 1 ...
#> $ true_risk : num 0.072 0.175 0.338 0.065 0.049 0.05 0.106 0.056 0.178 0.064 ...
#> $ basic_model : num 0.117 0.13 0.135 0.071 0.037 0.016 0.064 0.026 0.104 0.039 ...
#> $ enhanced_model : num 0.111 0.148 0.443 0.065 0.06 0.044 0.078 0.063 0.106 0.134 ...
#> $ biomarker_model : num 0.093 0.217 0.508 0.064 0.036 0.066 0.169 0.039 0.155 0.093 ...
#> $ miscalibrated_model : num 0.21 0.233 0.243 0.129 0.066 0.028 0.115 0.047 0.187 0.069 ...
#> $ poor_model : num 0.024 0.264 0.135 0.204 0.137 0.093 0.036 0.088 0.1 0.047 ...
#> $ risk_category : Factor w/ 4 levels "Low","Moderate",..: 1 2 3 1 1 1 2 1 2 1 ...
#> $ hospital : chr "Hospital A" "Hospital C" "Hospital C" "Hospital C" ...
head(dca_test_data)
#> patient_id age sex diabetes hypertension smoking cholesterol troponin
#> 1 1 72 Male No Yes Never 213 4.10
#> 2 2 74 Male Yes No Former 164 5.27
#> 3 3 64 Male Yes Yes Current 248 2.61
#> 4 4 60 Male No No Never 228 10.58
#> 5 5 72 Female No No Never 211 9.72
#> 6 6 43 Male No No Current 223 8.30
#> creatinine cardiac_event_numeric cardiac_event true_risk basic_model
#> 1 0.79 0 No 0.072 0.117
#> 2 1.04 0 No 0.175 0.130
#> 3 1.15 0 No 0.338 0.135
#> 4 0.90 0 No 0.065 0.071
#> 5 0.80 1 Yes 0.049 0.037
#> 6 1.14 0 No 0.050 0.016
#> enhanced_model biomarker_model miscalibrated_model poor_model risk_category
#> 1 0.111 0.093 0.210 0.024 Low
#> 2 0.148 0.217 0.233 0.264 Moderate
#> 3 0.443 0.508 0.243 0.135 High
#> 4 0.065 0.064 0.129 0.204 Low
#> 5 0.060 0.036 0.066 0.137 Low
#> 6 0.044 0.066 0.028 0.093 Low
#> hospital
#> 1 Hospital A
#> 2 Hospital C
#> 3 Hospital C
#> 4 Hospital C
#> 5 Hospital B
#> 6 Hospital A
summary(dca_test_data$enhanced_model)
#> Min. 1st Qu. Median Mean 3rd Qu. Max.
#> 0.0100 0.0570 0.1015 0.1374 0.1772 0.6930
table(dca_test_data$hospital, dca_test_data$cardiac_event)
#>
#> No Yes
#> Hospital A 222 34
#> Hospital B 223 36
#> Hospital C 246 39