An Interpretable Machine Learning-Based Automatic Clinical Score Generator
Internal Function: Add baselines after second-step logistic regression...
Internal Function: Automatically assign scores to each subjects given ...
AutoScore STEP(iv): Fine-tune the score by revising cut_vec with domai...
AutoScore STEP(iv) for ordinal outcomes: Fine-tune the score by revisi...
AutoScore STEP(iv) for survival outcomes: Fine-tune the score by revis...
AutoScore STEP(ii): Select the best model with parsimony plot (AutoSco...
AutoScore STEP(ii) for ordinal outcomes: Select the best model with pa...
AutoScore STEP(ii) for survival outcomes: Select the best model with p...
AutoScore STEP(i): Rank variables with machine learning (AutoScore Mod...
AutoScore STEP (i) for ordinal outcomes: Generate variable ranking lis...
AutoScore STEP (1) for survival outcomes: Generate variable ranking Li...
AutoScore STEP(v): Evaluate the final score with ROC analysis (AutoSco...
AutoScore STEP(v) for ordinal outcomes: Evaluate the final score (Auto...
AutoScore STEP(v) for survival outcomes: Evaluate the final score with...
AutoScore STEP(iii): Generate the initial score with the final list of...
AutoScore STEP(iii) for ordinal outcomes: Generate the initial score w...
AutoScore STEP(iii) for survival outcomes: Generate the initial score ...
Internal Function: Change Reference category after first-step logistic...
AutoScore function for datasets with binary outcomes: Check whether th...
AutoScore function for ordinal outcomes: Check whether the input datas...
AutoScore function for survival data: Check whether the input dataset ...
Internal function: Check link function
Internal function: Check predictors
Internal function: Compute AUC based on validation set for plotting pa...
Internal function: Compute mean AUC for ordinal outcomes based on vali...
Internal function for survival outcomes: Compute AUC based on validati...
AutoScore function: Descriptive Analysis
Internal function: Compute risk scores for ordinal data given variable...
Internal function: Compute mAUC for ordinal predictions
AutoScore function: Multivariate Analysis
AutoScore-Ordinal function: Multivariate Analysis
AutoScore function for survival outcomes: Multivariate Analysis
Internal function: Based on given labels and scores, compute proportio...
Internal function: Based on given labels and scores, compute average p...
Internal function: Compute scoring table based on training dataset (Au...
Internal function: Compute scoring table for ordinal outcomes based on...
Internal function: Compute scoring table for survival outcomes based o...
AutoScore function: Univariable Analysis
AutoScore-Ordinal function: Univariable Analysis
AutoScore function for survival outcomes: Univariate Analysis
AutoScore function: Print conversion table based on final performance ...
AutoScore function: Print conversion table for ordinal outcomes to map...
AutoScore function for survival outcomes: Print conversion table
Internal function: generate probability matrix for ordinal outcomes gi...
Internal function survival outcome: Calculate iAUC for validation set
Internal function: Evaluate model performance on ordinal data
Extract OR, CI and p-value from a proportional odds model
Internal function: Find column indices in design matrix that should be...
Internal function: Compute all scores attainable.
Internal function: Calculate cut_vec from the training set (AutoScore ...
Internal function: Group scores based on given score breaks, and use f...
Internal function: induce informative missing to sample data in the pa...
Internal function: induce informative missing in a single variable
Internal function: Inverse cloglog link
Internal function: Inverse logit link
Internal function: Inverse probit link
Internal function: Based on find_one_inds, make a design matrix to c...
Internal function: Make parsimony plot
Internal Function: Print plotted variable importance
AutoScore function for binary and ordinal outcomes: Plot predicted ris...
Internal Function: Plotting ROC curve
AutoScore function for survival outcomes: Print scoring performance (K...
AutoScore function for survival outcomes: Print predictive performance...
AutoScore function for ordinal outcomes: Print predictive performance
AutoScore function for survival outcomes: Print predictive performance
AutoScore function: Print receiver operating characteristic (ROC) perf...
AutoScore Function: Print scoring tables for visualization
AutoScore Function: Automatically splitting dataset to train, validati...
Internal function: Categorizing continuous variables based on cut_vec ...
A novel interpretable machine learning-based framework to automate the development of a clinical scoring model for predefined outcomes. Our novel framework consists of six modules: variable ranking with machine learning, variable transformation, score derivation, model selection, domain knowledge-based score fine-tuning, and performance evaluation.The details are described in our research paper<doi:10.2196/21798>. Users or clinicians could seamlessly generate parsimonious sparse-score risk models (i.e., risk scores), which can be easily implemented and validated in clinical practice. We hope to see its application in various medical case studies.