An Interpretable Machine Learning-Based Automatic Clinical Score Generator


[Up] [Top]

Documentation for package ‘AutoScore’ version 1.0.0

Help Pages

add_baseline Internal Function: Add baselines after second-step logistic regression (part of AutoScore Module 3)
assign_score Internal Function: Automatically assign scores to each subjects given new data set and scoring table (Used for intermediate and final evaluation)
AutoScore_fine_tuning AutoScore STEP(iv): Fine-tune the score by revising cut_vec with domain knowledge (AutoScore Module 5)
AutoScore_fine_tuning_Ordinal AutoScore STEP(iv) for ordinal outcomes: Fine-tune the score by revising 'cut_vec' with domain knowledge (AutoScore Module 5)
AutoScore_fine_tuning_Survival AutoScore STEP(iv) for survival outcomes: Fine-tune the score by revising cut_vec with domain knowledge (AutoScore Module 5)
AutoScore_parsimony AutoScore STEP(ii): Select the best model with parsimony plot (AutoScore Modules 2+3+4)
AutoScore_parsimony_Ordinal AutoScore STEP(ii) for ordinal outcomes: Select the best model with parsimony plot (AutoScore Modules 2+3+4)
AutoScore_parsimony_Survival AutoScore STEP(ii) for survival outcomes: Select the best model with parsimony plot (AutoScore Modules 2+3+4)
AutoScore_rank AutoScore STEP(i): Rank variables with machine learning (AutoScore Module 1)
AutoScore_rank_Ordinal AutoScore STEP (i) for ordinal outcomes: Generate variable ranking list by machine learning (AutoScore Module 1)
AutoScore_rank_Survival AutoScore STEP (1) for survival outcomes: Generate variable ranking List by machine learning (Random Survival Forest) (AutoScore Module 1)
AutoScore_testing AutoScore STEP(v): Evaluate the final score with ROC analysis (AutoScore Module 6)
AutoScore_testing_Ordinal AutoScore STEP(v) for ordinal outcomes: Evaluate the final score (AutoScore Module 6)
AutoScore_testing_Survival AutoScore STEP(v) for survival outcomes: Evaluate the final score with ROC analysis (AutoScore Module 6)
AutoScore_weighting AutoScore STEP(iii): Generate the initial score with the final list of variables (Re-run AutoScore Modules 2+3)
AutoScore_weighting_Ordinal AutoScore STEP(iii) for ordinal outcomes: Generate the initial score with the final list of variables (Re-run AutoScore Modules 2+3)
AutoScore_weighting_Survival AutoScore STEP(iii) for survival outcomes: Generate the initial score with the final list of variables (Re-run AutoScore Modules 2+3)
change_reference Internal Function: Change Reference category after first-step logistic regression (part of AutoScore Module 3)
check_data AutoScore function for datasets with binary outcomes: Check whether the input dataset fulfill the requirement of the AutoScore
check_data_ordinal AutoScore function for ordinal outcomes: Check whether the input dataset fulfil the requirement of the AutoScore
check_data_survival AutoScore function for survival data: Check whether the input dataset fulfill the requirement of the AutoScore
check_link Internal function: Check link function
check_predictor Internal function: Check predictors
compute_auc_val Internal function: Compute AUC based on validation set for plotting parsimony (AutoScore Module 4)
compute_auc_val_ord Internal function: Compute mean AUC for ordinal outcomes based on validation set for plotting parsimony
compute_auc_val_survival Internal function for survival outcomes: Compute AUC based on validation set for plotting parsimony
compute_descriptive_table AutoScore function: Descriptive Analysis
compute_final_score_ord Internal function: Compute risk scores for ordinal data given variables selected, cut-off values and scoring table
compute_mauc_ord Internal function: Compute mAUC for ordinal predictions
compute_multi_variable_table AutoScore function: Multivariate Analysis
compute_multi_variable_table_ordinal AutoScore-Ordinal function: Multivariate Analysis
compute_multi_variable_table_survival AutoScore function for survival outcomes: Multivariate Analysis
compute_prob_observed Internal function: Based on given labels and scores, compute proportion of subjects observed in each outcome category in given score intervals.
compute_prob_predicted Internal function: Based on given labels and scores, compute average predicted risks in given score intervals.
compute_score_table Internal function: Compute scoring table based on training dataset (AutoScore Module 3)
compute_score_table_ord Internal function: Compute scoring table for ordinal outcomes based on training dataset
compute_score_table_survival Internal function: Compute scoring table for survival outcomes based on training dataset
compute_uni_variable_table AutoScore function: Univariable Analysis
compute_uni_variable_table_ordinal AutoScore-Ordinal function: Univariable Analysis
compute_uni_variable_table_survival AutoScore function for survival outcomes: Univariate Analysis
conversion_table AutoScore function: Print conversion table based on final performance evaluation
conversion_table_ordinal AutoScore function: Print conversion table for ordinal outcomes to map score to risk
conversion_table_survival AutoScore function for survival outcomes: Print conversion table
estimate_p_mat Internal function: generate probability matrix for ordinal outcomes given thresholds, linear predictor and link function
evaluate_model_ord Internal function: Evaluate model performance on ordinal data
eva_performance_iauc Internal function survival outcome: Calculate iAUC for validation set
extract_or_ci_ord Extract OR, CI and p-value from a proportional odds model
find_one_inds Internal function: Find column indices in design matrix that should be 1
find_possible_scores Internal function: Compute all scores attainable.
get_cut_vec Internal function: Calculate cut_vec from the training set (AutoScore Module 2)
group_score Internal function: Group scores based on given score breaks, and use friendly names for first and last intervals.
induce_informative_missing Internal function: induce informative missing to sample data in the package to demonstrate how AutoScore handles missing as a separate category
induce_median_missing Internal function: induce informative missing in a single variable
inv_cloglog Internal function: Inverse cloglog link
inv_logit Internal function: Inverse logit link
inv_probit Internal function: Inverse probit link
make_design_mat Internal function: Based on 'find_one_inds', make a design matrix to compute all scores attainable.
plot_auc Internal function: Make parsimony plot
plot_importance Internal Function: Print plotted variable importance
plot_predicted_risk AutoScore function for binary and ordinal outcomes: Plot predicted risk
plot_roc_curve Internal Function: Plotting ROC curve
plot_survival_km AutoScore function for survival outcomes: Print scoring performance (KM curve)
print_performance_ci_survival AutoScore function for survival outcomes: Print predictive performance with confidence intervals
print_performance_ordinal AutoScore function for ordinal outcomes: Print predictive performance
print_performance_survival AutoScore function for survival outcomes: Print predictive performance
print_roc_performance AutoScore function: Print receiver operating characteristic (ROC) performance
print_scoring_table AutoScore Function: Print scoring tables for visualization
sample_data 20000 simulated ICU admission data, with the same distribution as the data in the MIMIC-III ICU database
sample_data_ordinal Simulated ED data with ordinal outcome
sample_data_ordinal_small Simulated ED data with ordinal outcome (small sample size)
sample_data_small 1000 simulated ICU admission data, with the same distribution as the data in the MIMIC-III ICU database
sample_data_survival 20000 simulated MIMIC sample data with survival outcomes
sample_data_survival_small 1000 simulated MIMIC sample data with survival outcomes
sample_data_with_missing 20000 simulated ICU admission data with missing values
split_data AutoScore Function: Automatically splitting dataset to train, validation and test set, possibly stratified by label
transform_df_fixed Internal function: Categorizing continuous variables based on cut_vec (AutoScore Module 2)