Movatterモバイル変換

re-export Surv from survival

Description

re-export Surv from survival

Apply a Trained Model to New Data

Description

Applies a trained diagnostic model (single or ensemble) to a newdataset to generate predictions. It can handle various model objects createdby the package, including single caret models, Bagging, Stacking, Voting,and EasyEnsemble objects.

Usage

apply_dia(  trained_model_object,  new_data,  label_col_name = NULL,  pos_class = "Positive",  neg_class = "Negative")

Arguments

Value

A data frame with three columns:sample (the sample IDs),label(the true labels fromnew_data, orNA if not available/specified), andscore(the predicted probability for the positive class).

Examples

# Assuming `bagging_results` and `test_dia` are available from previous steps# bagging_model <- bagging_results$model_object# Example 1: Default behavior - use the second column of test_dia as label# predictions <- apply_dia(#   trained_model_object = bagging_model,#   new_data = test_dia# )# Example 2: Explicitly specify the label column by name# predictions_explicit <- apply_dia(#   trained_model_object = bagging_model,#   new_data = test_dia,#   label_col_name = "outcome"# )# Example 3: Predict on data without labels# test_data_no_labels <- test_dia[, -2] # Remove outcome column# predictions_no_label <- apply_dia(#   trained_model_object = bagging_model,#   new_data = test_data_no_labels,#   label_col_name = NA # Explicitly disable label extraction# )

Apply Prognostic Model to New Data

Description

Generates risk scores for new patients using a trained model.

Usage

apply_pro(trained_model_object, new_data, time_unit = "day")

Arguments

Value

Data frame with IDs, outcomes (if available), and risk scores.

Train a Bagging Diagnostic Model

Description

Implements a Bagging (Bootstrap Aggregating) ensemble fordiagnostic models. It trains multiple base models on bootstrapped samplesof the training data and aggregates their predictions by averaging probabilities.

Usage

bagging_dia(  data,  base_model_name,  n_estimators = 50,  subset_fraction = 0.632,  tune_base_model = FALSE,  threshold_choices = "default",  positive_label_value = 1,  negative_label_value = 0,  new_positive_label = "Positive",  new_negative_label = "Negative",  seed = 456)

Arguments

Value

A list containing themodel_object,sample_score, andevaluation_metrics.

See Also

initialize_modeling_system_dia,evaluate_model_dia

Examples

# This example assumes your package includes a dataset named 'train_dia'.# If not, create a toy data frame first.if (exists("train_dia")) {  initialize_modeling_system_dia()  bagging_rf_results <- bagging_dia(    data = train_dia,    base_model_name = "rf",    n_estimators = 5, # Reduced for a quick example    threshold_choices = "youden",    positive_label_value = 1,    negative_label_value = 0,    new_positive_label = "Case",    new_negative_label = "Control"  )  print_model_summary_dia("Bagging (RF)", bagging_rf_results)}

Train Bagging Ensemble for Prognosis

Description

Implements Bootstrap Aggregating (Bagging) for survival models.It trains multiple base models on bootstrapped subsets and averages the risk scores.This method reduces variance and improves stability.

Usage

bagging_pro(  data,  base_model_name,  n_estimators = 10,  subset_fraction = 0.632,  tune_base_model = FALSE,  time_unit = "day",  years_to_evaluate = c(1, 3, 5),  seed = 456)

Arguments

Value

A list containing the ensemble object, sample scores, and evaluation metrics.

Calculate Classification Metrics at a Specific Threshold

Description

Calculates various classification performance metrics (Accuracy,Precision, Recall, F1-score, Specificity, True Positives, etc.) for binaryclassification at a given probability threshold.

Usage

calculate_metrics_at_threshold_dia(  prob_positive,  y_true,  threshold,  pos_class,  neg_class)

Arguments

Value

A list containing:

• Threshold: The threshold used.

• Accuracy: Overall prediction accuracy.

• Precision: Precision for the positive class.

• Recall: Recall (Sensitivity) for the positive class.

• F1: F1-score for the positive class.

• Specificity: Specificity for the negative class.

• TP,TN,FP,FN,N: Counts of True Positives, True Negatives,False Positives, False Negatives, and total samples.

Examples

y_true_ex <- factor(c("Negative", "Positive", "Positive", "Negative", "Positive"),                    levels = c("Negative", "Positive"))prob_ex <- c(0.1, 0.8, 0.6, 0.3, 0.9)metrics <- calculate_metrics_at_threshold_dia(  prob_positive = prob_ex,  y_true = y_true_ex,  threshold = 0.5,  pos_class = "Positive",  neg_class = "Negative")print(metrics)

Train a Decision Tree Model for Classification

Description

Trains a single Decision Tree model usingcaret::train (viarpart method)for binary classification.

Usage

dt_dia(X, y, tune = FALSE, cv_folds = 5)

Arguments

Value

Acaret::train object representing the trained Decision Tree model.

Examples

set.seed(42)n_obs <- 50X_toy <- data.frame(  FeatureA = rnorm(n_obs),  FeatureB = runif(n_obs, 0, 100))y_toy <- factor(sample(c("Control", "Case"), n_obs, replace = TRUE),                levels = c("Control", "Case"))# Train the modeldt_model <- dt_dia(X_toy, y_toy)print(dt_model)

Train an Elastic Net (L1 and L2 Regularized Logistic Regression) Model for Classification

Description

Trains an Elastic Net-regularized logistic regression modelusingcaret::train (viaglmnet method) for binary classification.

Usage

en_dia(X, y, tune = FALSE, cv_folds = 5)

Arguments

Value

Acaret::train object representing the trained Elastic Net model.

Examples

set.seed(42)n_obs <- 50X_toy <- data.frame(  FeatureA = rnorm(n_obs),  FeatureB = runif(n_obs, 0, 100))y_toy <- factor(sample(c("Control", "Case"), n_obs, replace = TRUE),                levels = c("Control", "Case"))# Train the modelen_model <- en_dia(X_toy, y_toy)print(en_model)

Train Elastic Net Cox Model

Description

Fits a Cox model with Elastic Net regularization (mixture of L1 and L2 penalties).Alpha is fixed at 0.5.

Usage

en_pro(X, y_surv, tune = FALSE)

Arguments

Value

An object of classsurvival_glmnet andpro_model.

Evaluate Diagnostic Model Performance

Description

Evaluates the performance of a trained diagnostic model usingvarious metrics relevant to binary classification, including AUROC, AUPRC,and metrics at an optimal or specified probability threshold.

Usage

evaluate_model_dia(  model_obj = NULL,  X_data = NULL,  y_data,  sample_ids,  threshold_choices = "default",  pos_class,  neg_class,  precomputed_prob = NULL,  y_original_numeric = NULL)

Arguments

Value

A list containing:

• sample_score: A data frame withsample (ID),label (original numeric),andscore (predicted probability for positive class).

• evaluation_metrics: A list of performance metrics:

  • Threshold_Strategy: The strategy used for threshold selection.

  • ⁠_Threshold⁠: The chosen probability threshold.

  • Accuracy,Precision,Recall,F1,Specificity: Metricscalculated at⁠_Threshold⁠.

  • AUROC: Area Under the Receiver Operating Characteristic curve.

  • AUROC_95CI_Lower,AUROC_95CI_Upper: 95% confidence interval for AUROC.

  • AUPRC: Area Under the Precision-Recall curve.

Examples

set.seed(42)n_obs <- 50X_toy <- data.frame(  FeatureA = rnorm(n_obs),  FeatureB = runif(n_obs, 0, 100))y_toy <- factor(sample(c("Control", "Case"), n_obs, replace = TRUE),                levels = c("Control", "Case"))ids_toy <- paste0("Sample", 1:n_obs)# 2. Train a modelrf_model <- rf_dia(X_toy, y_toy)# 3. Evaluate the model using F1-score optimal thresholdeval_results <- evaluate_model_dia(  model_obj = rf_model,  X_data = X_toy,  y_data = y_toy,  sample_ids = ids_toy,  threshold_choices = "f1",  pos_class = "Case",  neg_class = "Control")str(eval_results)

Evaluate Prognostic Model Performance

Description

Comprehensive evaluation of survival models using:

1. Harrell's Concordance Index (C-index).

2. Time-dependent Area Under the ROC Curve (AUROC) at specified years.

3. Kaplan-Meier analysis comparing high vs. low risk groups (based on median split).

Usage

evaluate_model_pro(  trained_model_obj = NULL,  X_data = NULL,  Y_surv_obj,  sample_ids,  years_to_evaluate = c(1, 3, 5),  precomputed_score = NULL,  meta_normalize_params = NULL)

Arguments

Value

A list containing a dataframe of scores and a list of evaluation metrics.

Evaluate Predictions from a Data Frame

Description

Evaluates model performance from a data frame of predictions,calculating metrics like AUROC, AUPRC, F1 score, etc. This function is designedfor use with prediction results, such as the output fromapply_dia.

Usage

evaluate_predictions_dia(  prediction_df,  threshold_choices = "default",  pos_class = "Positive",  neg_class = "Negative")

Arguments

Details

This function strictly requires thelabel column inprediction_df to adhereto the following format:

• 1: Represents the positive class.

• 0: Represents the negative class.

• NA: Will be ignored during calculation.

The function will stop with an error if any other values are found in thelabel column.

Value

A named list containing all calculated performance metrics.

Examples

# # Create a sample prediction data frame# predictions_df <- data.frame(#   sample = 1:10,#   label = c(1, 0, 1, 1, 0, 0, 1, 0, 1, 0),#   score = c(0.9, 0.2, 0.8, 0.6, 0.3, 0.4, 0.95, 0.1, 0.7, 0.5)# )## # Evaluate the predictions using the 'f1' threshold strategy# evaluation_results <- evaluate_predictions_dia(#   prediction_df = predictions_df,#   threshold_choices = "f1"# )## print(evaluation_results)

Evaluate External Predictions

Description

Calculates performance metrics for external prediction sets.

Usage

evaluate_predictions_pro(prediction_df, years_to_evaluate = c(1, 3, 5))

Arguments

Value

List of evaluation metrics.

Plot Diagnostic Model Evaluation Figures

Description

Generates and returns a ggplot object for Receiver OperatingCharacteristic (ROC) curves, Precision-Recall (PRC) curves, or confusion matrices.

Usage

figure_dia(type, data, file = NULL)

Arguments

Value

A ggplot object. If thefile argument is provided, the plot is alsosaved to the specified path.

Examples

# Create example data for a diagnostic modelexternal_eval_example_dia <- list(  sample_score = data.frame(    ID = paste0("S", 1:100),    label = sample(c(0, 1), 100, replace = TRUE),    score = runif(100, 0, 1)  ),  evaluation_metrics = list(    Final_Threshold = 0.53  ))# Generate an ROC curve plot objectroc_plot <- figure_dia(type = "roc", data = external_eval_example_dia)# To display the plot, simply run:# print(roc_plot)# Generate a PRC curve and save it to a temporary file# tempfile() creates a safe, temporary path as required by CRANtemp_prc_path <- tempfile(fileext = ".png")figure_dia(type = "prc", data = external_eval_example_dia, file = temp_prc_path)# Generate a Confusion Matrix plotmatrix_plot <- figure_dia(type = "matrix", data = external_eval_example_dia)

Plot Prognostic Model Evaluation Figures

Description

Generates and returns a ggplot object for Kaplan-Meier (KM)survival curves or time-dependent ROC curves.

Usage

figure_pro(type, data, file = NULL, time_unit = "days")

Arguments

Value

ggplot object

Generate and Plot SHAP Explanation Figures

Description

Creates SHAP (SHapley Additive exPlanations) plots to explainfeature contributions by training a surrogate model on the original model's scores.

Usage

figure_shap(data, raw_data, target_type, file = NULL, model_type = "xgboost")

Arguments

Value

A patchwork object combining SHAP summary and importance plots. Iffile isprovided, the plot is also saved.

Examples

# --- Example for a Diagnosis Model ---set.seed(123)train_dia_data <- data.frame(  SampleID = paste0("S", 1:100),  Label = sample(c(0, 1), 100, replace = TRUE),  FeatureA = rnorm(100, 10, 2),  FeatureB = runif(100, 0, 5))model_results <- list(  sample_score = data.frame(ID = paste0("S", 1:100), score = runif(100, 0, 1)))# Generate SHAP plot objectshap_plot <- figure_shap(  data = model_results,  raw_data = train_dia_data,  target_type = "diagnosis",  model_type = "xgboost")# To display the plot:# print(shap_plot)

Find Optimal Probability Threshold

Description

Determines an optimal probability threshold for binaryclassification based on maximizing F1-score or Youden's J statistic.

Usage

find_optimal_threshold_dia(  prob_positive,  y_true,  type = c("f1", "youden"),  pos_class,  neg_class)

Arguments

Value

A numeric value, the optimal probability threshold.

Examples

y_true_ex <- factor(c("Negative", "Positive", "Positive", "Negative", "Positive"),                    levels = c("Negative", "Positive"))prob_ex <- c(0.1, 0.8, 0.6, 0.3, 0.9)# Find threshold maximizing F1-scoreopt_f1_threshold <- find_optimal_threshold_dia(  prob_positive = prob_ex,  y_true = y_true_ex,  type = "f1",  pos_class = "Positive",  neg_class = "Negative")print(opt_f1_threshold)# Find threshold maximizing Youden's Jopt_youden_threshold <- find_optimal_threshold_dia(  prob_positive = prob_ex,  y_true = y_true_ex,  type = "youden",  pos_class = "Positive",  neg_class = "Negative")print(opt_youden_threshold)

Train a Gradient Boosting Machine (GBM) Model for Classification

Description

Trains a Gradient Boosting Machine (GBM) model usingcaret::trainfor binary classification.

Usage

gbm_dia(X, y, tune = FALSE, cv_folds = 5, tune_length = 10)

Arguments

Value

Acaret::train object representing the trained GBM model.

Examples

set.seed(42)n_obs <- 200X_toy <- data.frame(  FeatureA = rnorm(n_obs),  FeatureB = runif(n_obs, 0, 100))y_toy <- factor(sample(c("Control", "Case"), n_obs, replace = TRUE),                levels = c("Control", "Case"))# Train the model with default parametersgbm_model <- gbm_dia(X_toy, y_toy)print(gbm_model)# Train with extensive tuning (random search)gbm_model_tuned <- gbm_dia(X_toy, y_toy, tune = TRUE, tune_length = 30)print(gbm_model_tuned)

Train Gradient Boosting Machine (GBM) for Survival

Description

Fits a stochastic gradient boosting model using the Cox Partial Likelihood distribution.Supports random search for hyperparameter optimization.

Usage

gbm_pro(X, y_surv, tune = FALSE, cv.folds = 5, max_tune_iter = 10)

Arguments

Value

An object of classsurvival_gbm andpro_model.

Get Registered Diagnostic Models

Description

Retrieves a list of all diagnostic model functions currentlyregistered in the internal environment.

Usage

get_registered_models_dia()

Value

A named list where names are the registered model names and valuesare the corresponding model functions.

See Also

register_model_dia,initialize_modeling_system_dia

Examples

# Ensure system is initialized to see the default modelsinitialize_modeling_system_dia()models <- get_registered_models_dia()# See available model namesprint(names(models))

Get Registered Prognostic Models

Description

Retrieves the list of available models.

Usage

get_registered_models_pro()

Value

Named list of functions.

Train an EasyEnsemble Model for Imbalanced Classification

Description

Implements the EasyEnsemble algorithm. It trains multiple basemodels on balanced subsets of the data (by undersampling the majority class)and aggregates their predictions.

Usage

imbalance_dia(  data,  base_model_name = "rf",  n_estimators = 10,  tune_base_model = FALSE,  threshold_choices = "default",  positive_label_value = 1,  negative_label_value = 0,  new_positive_label = "Positive",  new_negative_label = "Negative",  seed = 456)

Arguments

Value

A list containing themodel_object,sample_score, andevaluation_metrics.

See Also

initialize_modeling_system_dia,evaluate_model_dia

Examples

# 1. Initialize the modeling systeminitialize_modeling_system_dia()# 2. Create an imbalanced toy datasetset.seed(42)n_obs <- 100n_minority <- 10data_imbalanced_toy <- data.frame(  ID = paste0("Sample", 1:n_obs),  Status = c(rep(1, n_minority), rep(0, n_obs - n_minority)),  Feat1 = rnorm(n_obs),  Feat2 = runif(n_obs))# 3. Run the EasyEnsemble algorithm# n_estimators is reduced for a quick exampleeasyensemble_results <- imbalance_dia(  data = data_imbalanced_toy,  base_model_name = "rf",  n_estimators = 3,  threshold_choices = "f1")print_model_summary_dia("EasyEnsemble (RF)", easyensemble_results)

Initialize Diagnostic Modeling System

Description

Initializes the diagnostic modeling system by loading requiredpackages and registering default diagnostic models (Random Forest, XGBoost,SVM, MLP, Lasso, Elastic Net, Ridge, LDA, QDA, Naive Bayes, Decision Tree, GBM).This function should be called once before usingmodels_dia() or ensemble methods.

Usage

initialize_modeling_system_dia()

Value

Invisible NULL. Initializes the internal model registry.

Examples

# Initialize the system (typically run once at the start of a session or script)initialize_modeling_system_dia()# Check if a default model like Random Forest is now registered"rf" %in% names(get_registered_models_dia())

Initialize Prognosis Modeling System

Description

Initializes the environment and registers default survival models(Lasso, Elastic Net, Ridge, RSF, StepCox, GBM, XGBoost, PLS).

Usage

initialize_modeling_system_pro()

Comprehensive Diagnostic Modeling Pipeline

Description

Executes a complete diagnostic modeling workflow including singlemodels, bagging, stacking, and voting ensembles across training and multipletest datasets. Returns structured results with AUROC values for visualization.

Usage

int_dia(  ...,  model_names = NULL,  tune = TRUE,  n_estimators = 10,  seed = 123,  positive_label_value = 1,  negative_label_value = 0,  new_positive_label = "Positive",  new_negative_label = "Negative")

Arguments

Value

A list containing all_results, auroc_matrix, model_categories, dataset_names.

Imbalanced Data Diagnostic Modeling Pipeline

Description

Extendsint_dia by adding imbalance-specific models (EasyEnsemble).Produces a comprehensive set of models optimized for imbalanced datasets.

Usage

int_imbalance(  ...,  model_names = NULL,  tune = TRUE,  n_estimators = 10,  seed = 123,  positive_label_value = 1,  negative_label_value = 0,  new_positive_label = "Positive",  new_negative_label = "Negative")

Arguments

Value

Same structure asint_dia with additional imbalance-handling models.

Examples

## Not run: imbalanced_results <- int_imbalance(train_imbalanced, test_imbalanced)## End(Not run)

Comprehensive Prognostic Modeling Pipeline

Description

Executes a complete prognostic (survival) modeling workflow includingsingle models, bagging, and stacking ensembles. Returns C-index and time-dependentAUROC metrics.

Usage

int_pro(  ...,  model_names = NULL,  tune = TRUE,  n_estimators = 10,  seed = 123,  time_unit = "day",  years_to_evaluate = c(1, 3, 5))

Arguments

Value

A list with:

• all_results: All model outputs

• cindex_matrix: C-index values (models × datasets)

• avg_auroc_matrix: Average time-dependent AUROC (models × datasets)

• model_categories: Model category labels

• dataset_names: Dataset identifiers

Examples

## Not run: prognosis_results <- int_pro(train_pro, test_pro1, test_pro2)## End(Not run)

Train a Lasso (L1 Regularized Logistic Regression) Model for Classification

Description

Trains a Lasso-regularized logistic regression model usingcaret::train(viaglmnet method) for binary classification.

Usage

lasso_dia(X, y, tune = FALSE, cv_folds = 5)

Arguments

Value

Acaret::train object representing the trained Lasso model.

Examples

set.seed(42)n_obs <- 50X_toy <- data.frame(  FeatureA = rnorm(n_obs),  FeatureB = runif(n_obs, 0, 100))y_toy <- factor(sample(c("Control", "Case"), n_obs, replace = TRUE),                levels = c("Control", "Case"))# Train the modellasso_model <- lasso_dia(X_toy, y_toy)print(lasso_model)

Train Lasso Cox Proportional Hazards Model

Description

Fits a Cox proportional hazards model regularized by the Lasso (L1) penalty.Uses cross-validation to select the optimal lambda.

Usage

lasso_pro(X, y_surv, tune = FALSE)

Arguments

Value

An object of classsurvival_glmnet andpro_model.

Examples

  library(survival)  # Create dummy data  set.seed(123)  df <- data.frame(time = rexp(50), status = sample(0:1, 50, replace=TRUE),                   var1 = rnorm(50), var2 = rnorm(50))  y <- Surv(df$time, df$status)  x <- df[, c("var1", "var2")]  model <- lasso_pro(x, y)  print(class(model))

Train a Linear Discriminant Analysis (LDA) Model for Classification

Description

Trains a Linear Discriminant Analysis (LDA) model usingcaret::trainfor binary classification.

Usage

lda_dia(X, y, tune = FALSE, cv_folds = 5)

Arguments

Value

Acaret::train object representing the trained LDA model.

Examples

set.seed(42)n_obs <- 50X_toy <- data.frame(  FeatureA = rnorm(n_obs),  FeatureB = runif(n_obs, 0, 100))y_toy <- factor(sample(c("Control", "Case"), n_obs, replace = TRUE),                levels = c("Control", "Case"))# Train the modellda_model <- lda_dia(X_toy, y_toy)print(lda_model)

Load and Prepare Data for Diagnostic Models

Description

Loads a CSV file containing patient data, extracts features,and converts the label column into a factor suitable for classificationmodels. Handles basic data cleaning like trimming whitespace and type conversion.

Usage

load_and_prepare_data_dia(  data_path,  label_col_name,  positive_label_value = 1,  negative_label_value = 0,  new_positive_label = "Positive",  new_negative_label = "Negative")

Arguments

Value

A list containing:

• X: A data frame of features (all columns except ID and label).

• y: A factor vector of class labels, with levelsnew_negative_labelandnew_positive_label.

• sample_ids: A vector of sample IDs (the first column of the input data).

• pos_class_label: The character string used for the positive class factor level.

• neg_class_label: The character string used for the negative class factor level.

• y_original_numeric: The original numeric/character vector of labels.

Examples

# Create a dummy CSV file in a temporary directory for demonstrationtemp_csv_path <- tempfile(fileext = ".csv")dummy_data <- data.frame(  ID = paste0("Patient", 1:50),  Disease_Status = sample(c(0, 1), 50, replace = TRUE),  FeatureA = rnorm(50),  FeatureB = runif(50, 0, 100),  CategoricalFeature = sample(c("X", "Y", "Z"), 50, replace = TRUE))write.csv(dummy_data, temp_csv_path, row.names = FALSE)# Load and prepare data from the temporary fileprepared_data <- load_and_prepare_data_dia(  data_path = temp_csv_path,  label_col_name = "Disease_Status",  positive_label_value = 1,  negative_label_value = 0,  new_positive_label = "Case",  new_negative_label = "Control")# Check prepared data structurestr(prepared_data$X)table(prepared_data$y)# Clean up the dummy fileunlink(temp_csv_path)

Min-Max Normalization

Description

Performs linear transformation of data to the range 0 to 1.Essential for stacking ensembles to normalize risk scores from heterogeneous base learners.

Usage

min_max_normalize(x, min_val = NULL, max_val = NULL)

Arguments

Value

A numeric vector of normalized values.

Train a Multi-Layer Perceptron (Neural Network) Model for Classification

Description

Trains a Multi-Layer Perceptron (MLP) neural network modelusingcaret::train for binary classification.

Usage

mlp_dia(X, y, tune = FALSE, cv_folds = 5)

Arguments

Value

Acaret::train object representing the trained MLP model.

Examples

set.seed(42)n_obs <- 50X_toy <- data.frame(  FeatureA = rnorm(n_obs),  FeatureB = runif(n_obs, 0, 100))y_toy <- factor(sample(c("Control", "Case"), n_obs, replace = TRUE),                levels = c("Control", "Case"))# Train the modelmlp_model <- mlp_dia(X_toy, y_toy)print(mlp_model)

Run Multiple Diagnostic Models

Description

Trains and evaluates one or more registered diagnostic models on a given dataset.

Usage

models_dia(  data,  model = "all_dia",  tune = FALSE,  seed = 123,  threshold_choices = "default",  positive_label_value = 1,  negative_label_value = 0,  new_positive_label = "Positive",  new_negative_label = "Negative")

Arguments

Value

A named list, where each element corresponds to a run model andcontains its trainedmodel_object,sample_score data frame, andevaluation_metrics.

See Also

initialize_modeling_system_dia,evaluate_model_dia

Examples

# This example assumes your package includes a dataset named 'train_dia'.# If not, you should create a toy data frame similar to the one below.## train_dia <- data.frame(#   ID = paste0("Patient", 1:100),#   Disease_Status = sample(c(0, 1), 100, replace = TRUE),#   FeatureA = rnorm(100),#   FeatureB = runif(100)# )# Ensure the 'train_dia' dataset is available in the environment# For example, if it is exported by your package:# data(train_dia)# Check if 'train_dia' exists, otherwise skip the exampleif (exists("train_dia")) {  # 1. Initialize the modeling system  initialize_modeling_system_dia()  # 2. Run selected models  results <- models_dia(    data = train_dia,    model = c("rf", "lasso"), # Run only Random Forest and Lasso    threshold_choices = list(rf = "f1", lasso = 0.6), # Different thresholds    positive_label_value = 1,    negative_label_value = 0,    new_positive_label = "Case",    new_negative_label = "Control",    seed = 42  )  # 3. Print summaries  for (model_name in names(results)) {    print_model_summary_dia(model_name, results[[model_name]])  }}

Run Multiple Prognostic Models

Description

High-level API to train and evaluate multiple survival models in batch.

Usage

models_pro(  data,  model = "all_pro",  tune = FALSE,  seed = 123,  time_unit = "day",  years_to_evaluate = c(1, 3, 5))

Arguments

Value

A list of model results.

Train a Naive Bayes Model for Classification

Description

Trains a Naive Bayes model usingcaret::train for binary classification.

Usage

nb_dia(X, y, tune = FALSE, cv_folds = 5)

Arguments

Value

Acaret::train object representing the trained Naive Bayes model.

Examples

set.seed(42)n_obs <- 50X_toy <- data.frame(  FeatureA = rnorm(n_obs),  FeatureB = runif(n_obs, 0, 100))y_toy <- factor(sample(c("Control", "Case"), n_obs, replace = TRUE),                levels = c("Control", "Case"))# Train the modelnb_model <- nb_dia(X_toy, y_toy)print(nb_model)

Visualize Integrated Modeling Results

Description

Creates a heatmap visualization with performance metrics acrossmodels and datasets, including category annotations and summary bar plots.

Usage

plot_integrated_results(results_obj, metric_name = "AUROC", output_file = NULL)

Arguments

Value

A ggplot object (invisibly).

Examples

## Not run: results <- int_dia(train_dia, test_dia)plot_integrated_results(results, "AUROC")## End(Not run)

Train Partial Least Squares Cox (PLS-Cox)

Description

Fits a Cox model using Partial Least Squares reduction for high-dimensional data.

Usage

pls_pro(X, y_surv, tune = FALSE)

Arguments

Value

An object of classsurvival_plsRcox andpro_model.

Generic Prediction Interface for Prognostic Models

Description

A unified S3 generic method to generate prognostic risk scores fromvarious trained model objects. This decouples the prediction implementationfrom the high-level evaluation logic, facilitating extensibility.

Usage

predict_pro(object, newdata, ...)

Arguments

Value

A numeric vector representing the prognostic risk score (higher values typically indicate higher risk).

Print Diagnostic Model Summary

Description

Prints a formatted summary of the evaluation metrics for adiagnostic model, either from training data or new data evaluation.

Usage

print_model_summary_dia(model_name, results_list, on_new_data = FALSE)

Arguments

Value

NULL. Prints the summary to the console.

Examples

# Example for a successfully evaluated modelsuccessful_results <- list(  evaluation_metrics = list(    Threshold_Strategy = "f1",    `_Threshold` = 0.45,    AUROC = 0.85, AUROC_95CI_Lower = 0.75, AUROC_95CI_Upper = 0.95,    AUPRC = 0.80, Accuracy = 0.82, F1 = 0.78,    Precision = 0.79, Recall = 0.77, Specificity = 0.85  ))print_model_summary_dia("MyAwesomeModel", successful_results)# Example for a failed modelfailed_results <- list(evaluation_metrics = list(error = "Training failed"))print_model_summary_dia("MyFailedModel", failed_results)

Print Prognostic Model Summary

Description

Formatted console output of model performance.

Usage

print_model_summary_pro(model_name, results_list)

Arguments

Train a Quadratic Discriminant Analysis (QDA) Model for Classification

Description

Trains a Quadratic Discriminant Analysis (QDA) model usingcaret::trainfor binary classification.

Usage

qda_dia(X, y, tune = FALSE, cv_folds = 5)

Arguments

Value

Acaret::train object representing the trained QDA model.

Examples

set.seed(42)n_obs <- 50X_toy <- data.frame(  FeatureA = rnorm(n_obs),  FeatureB = runif(n_obs, 0, 100))y_toy <- factor(sample(c("Control", "Case"), n_obs, replace = TRUE),                levels = c("Control", "Case"))# Train the modelqda_model <- qda_dia(X_toy, y_toy)print(qda_model)

Register a Diagnostic Model Function

Description

Registers a user-defined or pre-defined diagnostic model functionwith the internal model registry. This allows the function to be calledlater by its registered name, facilitating a modular model management system.

Usage

register_model_dia(name, func)

Arguments

Value

NULL. The function registers the model function invisibly.

See Also

get_registered_models_dia,initialize_modeling_system_dia

Examples

# Example of a dummy model function for registrationmy_dummy_rf_model <- function(X, y, tune = FALSE, cv_folds = 5) {  message("Training dummy RF model...")  # This is a placeholder and doesn't train a real model.  # It returns a list with a structure similar to a caret train object.  list(method = "dummy_rf")}# Initialize the system before registeringinitialize_modeling_system_dia()# Register the new modelregister_model_dia("dummy_rf", my_dummy_rf_model)# Verify that the model is now in the list of registered models"dummy_rf" %in% names(get_registered_models_dia())

Register a Prognostic Model

Description

Registers a model function into the internal system environment, making it available for batch execution.

Usage

register_model_pro(name, func)

Arguments

Train a Random Forest Model for Classification

Description

Trains a Random Forest model usingcaret::train for binary classification.

Usage

rf_dia(X, y, tune = FALSE, cv_folds = 5)

Arguments

Value

Acaret::train object representing the trained Random Forest model.

Examples

set.seed(42)n_obs <- 50X_toy <- data.frame(  FeatureA = rnorm(n_obs),  FeatureB = runif(n_obs, 0, 100))y_toy <- factor(sample(c("Control", "Case"), n_obs, replace = TRUE),                levels = c("Control", "Case"))# Train the modelrf_model <- rf_dia(X_toy, y_toy)print(rf_model)

Train a Ridge (L2 Regularized Logistic Regression) Model for Classification

Description

Trains a Ridge-regularized logistic regression model usingcaret::train(viaglmnet method) for binary classification.

Usage

ridge_dia(X, y, tune = FALSE, cv_folds = 5)

Arguments

Value

Acaret::train object representing the trained Ridge model.

Examples

set.seed(42)n_obs <- 50X_toy <- data.frame(  FeatureA = rnorm(n_obs),  FeatureB = runif(n_obs, 0, 100))y_toy <- factor(sample(c("Control", "Case"), n_obs, replace = TRUE),                levels = c("Control", "Case"))# Train the modelridge_model <- ridge_dia(X_toy, y_toy)print(ridge_model)

Train Ridge Cox Model

Description

Fits a Cox model with Ridge (L2) regularization.

Usage

ridge_pro(X, y_surv, tune = FALSE)

Arguments

Value

An object of classsurvival_glmnet andpro_model.

Train Random Survival Forest (RSF)

Description

Fits a Random Survival Forest using the log-rank splitting rule.Includes capabilities for hyperparameter tuning via grid search overntree,nodesize, andmtry.

Usage

rsf_pro(X, y_surv, tune = FALSE, tune_params = NULL)

Arguments

Value

An object of classsurvival_rsf andpro_model.

Train a Stacking Diagnostic Model

Description

Implements a Stacking ensemble. It trains multiple base models,then uses their predictions as features to train a meta-model.

Usage

stacking_dia(  results_all_models,  data,  meta_model_name,  top = 5,  tune_meta = FALSE,  threshold_choices = "f1",  seed = 789,  positive_label_value = 1,  negative_label_value = 0,  new_positive_label = "Positive",  new_negative_label = "Negative")

Arguments

Value

A list containing themodel_object,sample_score, andevaluation_metrics.

See Also

models_dia,evaluate_model_dia

Examples

# 1. Initialize the modeling systeminitialize_modeling_system_dia()# 2. Create a toy dataset for demonstrationset.seed(42)data_toy <- data.frame(  ID = paste0("Sample", 1:60),  Status = sample(c(0, 1), 60, replace = TRUE),  Feat1 = rnorm(60),  Feat2 = runif(60))# 3. Generate mock base model results (as if from models_dia)# In a real scenario, you would run models_dia() on your full datasetbase_model_results <- models_dia(  data = data_toy,  model = c("rf", "lasso"),  seed = 123)# 4. Run the stacking ensemblestacking_results <- stacking_dia(  results_all_models = base_model_results,  data = data_toy,  meta_model_name = "gbm",  top = 2,  threshold_choices = "f1")print_model_summary_dia("Stacking (GBM)", stacking_results)

Train Stacking Ensemble for Prognosis

Description

Implements a Stacking Ensemble (Super Learner).It uses the risk scores from top-performing base models as meta-featuresto train a second-level meta-learner.

Usage

stacking_pro(  results_all_models,  data,  meta_model_name,  top = 3,  tune_meta = FALSE,  time_unit = "day",  years_to_evaluate = c(1, 3, 5),  seed = 789)

Arguments

Value

A list containing the stacking object and evaluation results.

Train Stepwise Cox Model (AIC-based)

Description

Fits a Cox model and performs backward stepwise selection based on AIC.

Usage

stepcox_pro(X, y_surv, tune = FALSE)

Arguments

Value

An object of classsurvival_stepcox andpro_model.

Train a Support Vector Machine (Linear Kernel) Model for Classification

Description

Trains a Support Vector Machine (SVM) model with a linear kernelusingcaret::train for binary classification.

Usage

svm_dia(X, y, tune = FALSE, cv_folds = 5)

Arguments

Value

Acaret::train object representing the trained SVM model.

Examples

set.seed(42)n_obs <- 50X_toy <- data.frame(  FeatureA = rnorm(n_obs),  FeatureB = runif(n_obs, 0, 100))y_toy <- factor(sample(c("Control", "Case"), n_obs, replace = TRUE),                levels = c("Control", "Case"))# Train the modelsvm_model <- svm_dia(X_toy, y_toy)print(svm_model)

Test Data for Diagnostic Models

Description

A test dataset for evaluating diagnostic models, with a structureidentical totrain_dia.

Usage

test_dia

Format

A data frame with rows for samples and 22 columns:

sample

character. Unique identifier for each sample.

outcome

integer. The binary outcome (0 or 1).

AC004637.1

numeric. Gene expression level.

AC008459.1

numeric. Gene expression level.

AC009242.1

numeric. Gene expression level.

AC016735.1

numeric. Gene expression level.

AC090125.1

numeric. Gene expression level.

AC104237.3

numeric. Gene expression level.

AC112721.2

numeric. Gene expression level.

AC246817.1

numeric. Gene expression level.

AL135841.1

numeric. Gene expression level.

AL139241.1

numeric. Gene expression level.

HYMAI

numeric. Gene expression level.

KCNIP2.AS1

numeric. Gene expression level.

LINC00639

numeric. Gene expression level.

LINC00922

numeric. Gene expression level.

LINC00924

numeric. Gene expression level.

LINC00958

numeric. Gene expression level.

LINC01028

numeric. Gene expression level.

LINC01614

numeric. Gene expression level.

LINC01644

numeric. Gene expression level.

PRDM16.DT

numeric. Gene expression level.

Source

Stored indata/test_dia.rda.

Test Data for Prognostic (Survival) Models

Description

A test dataset for evaluating prognostic models, with a structureidentical totrain_pro.

Usage

test_pro

Format

A data frame with rows for samples and 31 columns:

sample

character. Unique identifier for each sample.

outcome

integer. The event status (0 or 1).

time

numeric. The time to event or censoring.

AC004990.1

numeric. Gene expression level.

AC055854.1

numeric. Gene expression level.

AC084212.1

numeric. Gene expression level.

AC092118.1

numeric. Gene expression level.

AC093515.1

numeric. Gene expression level.

AC104211.1

numeric. Gene expression level.

AC105046.1

numeric. Gene expression level.

AC105219.1

numeric. Gene expression level.

AC110772.2

numeric. Gene expression level.

AC133644.1

numeric. Gene expression level.

AL133467.1

numeric. Gene expression level.

AL391845.2

numeric. Gene expression level.

AL590434.1

numeric. Gene expression level.

AL603840.1

numeric. Gene expression level.

AP000851.2

numeric. Gene expression level.

AP001434.1

numeric. Gene expression level.

C9orf163

numeric. Gene expression level.

FAM153CP

numeric. Gene expression level.

HOTAIR

numeric. Gene expression level.

HYMAI

numeric. Gene expression level.

LINC00165

numeric. Gene expression level.

LINC01028

numeric. Gene expression level.

LINC01152

numeric. Gene expression level.

LINC01497

numeric. Gene expression level.

LINC01614

numeric. Gene expression level.

LINC01929

numeric. Gene expression level.

LINC02408

numeric. Gene expression level.

SIRLNT

numeric. Gene expression level.

Source

Stored indata/test_pro.rda.

Training Data for Diagnostic Models

Description

A training dataset for diagnostic models, containing sample IDs,binary outcomes, and gene expression features.

Usage

train_dia

Format

A data frame with rows for samples and 22 columns:

sample

character. Unique identifier for each sample.

outcome

integer. The binary outcome, where 1 typically represents a positive case and 0 a negative case.

AC004637.1

numeric. Gene expression level.

AC008459.1

numeric. Gene expression level.

AC009242.1

numeric. Gene expression level.

AC016735.1

numeric. Gene expression level.

AC090125.1

numeric. Gene expression level.

AC104237.3

numeric. Gene expression level.

AC112721.2

numeric. Gene expression level.

AC246817.1

numeric. Gene expression level.

AL135841.1

numeric. Gene expression level.

AL139241.1

numeric. Gene expression level.

HYMAI

numeric. Gene expression level.

KCNIP2.AS1

numeric. Gene expression level.

LINC00639

numeric. Gene expression level.

LINC00922

numeric. Gene expression level.

LINC00924

numeric. Gene expression level.

LINC00958

numeric. Gene expression level.

LINC01028

numeric. Gene expression level.

LINC01614

numeric. Gene expression level.

LINC01644

numeric. Gene expression level.

PRDM16.DT

numeric. Gene expression level.

Details

This dataset is used to train machine learning models for diagnosis.The column names starting with 'AC', 'AL', 'LINC', etc., are feature variables.

Source

Stored indata/train_dia.rda.

Training Data for Prognostic (Survival) Models

Description

A training dataset for prognostic models, containing sample IDs,survival outcomes (time and event status), and gene expression features.

Usage

train_pro

Format

A data frame with rows for samples and 31 columns:

sample

character. Unique identifier for each sample.

outcome

integer. The event status, where 1 indicates an event occurred and 0 indicates censoring.

time

numeric. The time to event or censoring.

AC004990.1

numeric. Gene expression level.

AC055854.1

numeric. Gene expression level.

AC084212.1

numeric. Gene expression level.

AC092118.1

numeric. Gene expression level.

AC093515.1

numeric. Gene expression level.

AC104211.1

numeric. Gene expression level.

AC105046.1

numeric. Gene expression level.

AC105219.1

numeric. Gene expression level.

AC110772.2

numeric. Gene expression level.

AC133644.1

numeric. Gene expression level.

AL133467.1

numeric. Gene expression level.

AL391845.2

numeric. Gene expression level.

AL590434.1

numeric. Gene expression level.

AL603840.1

numeric. Gene expression level.

AP000851.2

numeric. Gene expression level.

AP001434.1

numeric. Gene expression level.

C9orf163

numeric. Gene expression level.

FAM153CP

numeric. Gene expression level.

HOTAIR

numeric. Gene expression level.

HYMAI

numeric. Gene expression level.

LINC00165

numeric. Gene expression level.

LINC01028

numeric. Gene expression level.

LINC01152

numeric. Gene expression level.

LINC01497

numeric. Gene expression level.

LINC01614

numeric. Gene expression level.

LINC01929

numeric. Gene expression level.

LINC02408

numeric. Gene expression level.

SIRLNT

numeric. Gene expression level.

Details

This dataset is used to train machine learning models for prognosis.The features are typically gene expression values.

Source

Stored indata/train_pro.rda.

Train a Voting Ensemble Diagnostic Model

Description

Implements a Voting ensemble, combining predictions from multiplebase models through soft or hard voting.

Usage

voting_dia(  results_all_models,  data,  type = c("soft", "hard"),  weight_metric = "AUROC",  top = 5,  seed = 789,  threshold_choices = "f1",  positive_label_value = 1,  negative_label_value = 0,  new_positive_label = "Positive",  new_negative_label = "Negative")

Arguments

Value

A list containing themodel_object,sample_score, andevaluation_metrics.

See Also

models_dia,evaluate_model_dia

Examples

# 1. Initialize the modeling systeminitialize_modeling_system_dia()# 2. Create a toy dataset for demonstrationset.seed(42)data_toy <- data.frame(  ID = paste0("Sample", 1:60),  Status = sample(c(0, 1), 60, replace = TRUE),  Feat1 = rnorm(60),  Feat2 = runif(60))# 3. Generate mock base model results (as if from models_dia)base_model_results <- models_dia(  data = data_toy,  model = c("rf", "lasso"),  seed = 123)# 4. Run the soft voting ensemblesoft_voting_results <- voting_dia(  results_all_models = base_model_results,  data = data_toy,  type = "soft",  weight_metric = "AUROC",  top = 2,  threshold_choices = "f1")print_model_summary_dia("Soft Voting", soft_voting_results)

Train an XGBoost Tree Model for Classification

Description

Trains an Extreme Gradient Boosting (XGBoost) model usingcaret::trainfor binary classification.

Usage

xb_dia(X, y, tune = FALSE, cv_folds = 5, tune_length = 20)

Arguments

Value

Acaret::train object representing the trained XGBoost model.

Train XGBoost Cox Model

Description

Fits an XGBoost model using the Cox proportional hazards objective function.

Usage

xgb_pro(X, y_surv, tune = FALSE)

Arguments

Value

An object of classsurvival_xgboost andpro_model.