Showing Predictor "PBC_Classic_Visit1"

This predictor was successfully trained!

Meta

Notes:

Using 312-patient classic PBC survival dataset, which has follow-up data for patients (but for this experiment we're only using what is presumed to be their initial visit)

This data is being used by a group in Russ' PGM class, that is being coached by me

Publicly Accessible: yes

Viewable by Administrators: yes

Actions:EditDelete

Hide

Dataset Show


Predictor Settings / Retrain Show

Cross-validation results
5-Fold Cross-Validation Statistics*
Measure PSSP Predictor (median) PSSP Predictor (mean) K-M Predictor
Concordance Index0.83 ± 0.030.83 ± 0.030.5 ± 0.0
Hinged L1 Loss589.0 ± 72.351008.3 ± 7.57
Uncensored L1 loss1097.77 ± 120.141313.87 ± 106.881946.07 ± 42.2
Marginal L1 Loss1051.33 ± 80.591129.94 ± 32.041815.32 ± 99.77
Marginal L2 Loss1407.35 ± 142.82011.58 ± 94.32
Hinged L1 Log-Loss0.34 ± 0.040.39 ± 0.020.54 ± 0.02
Uncensored L1 Log-Loss0.69 ± 0.070.82 ± 0.051.13 ± 0.04
Marginal L1 Log-Loss0.48 ± 0.040.54 ± 0.020.79 ± 0.04
Log-Likelihood Loss2.13 ± 0.16
D-calibration χ2 statistics13.02 ± 3.680.73 ± 0.19
D-calibration χ2 p-value0.8 ± 0.21.0 ± 0.0
*Mean value ± standard deviation.


Download Predictions (CSV)

Individual Predictions

D-Calibration Histogram

Kaplan Meier Visualization

Show Feature Weights

Examine Classification Accuracy

Statistics accuracy, specificity, sensitivity (1-calibration) for
classifier with Cutoff:   Day