Example 2: Real EHR Data
In PheCAP: High-Throughput Phenotyping with EHR using a Common Automated Pipeline

library(PheCAP)

Load Data.

data(ehr_data)
data <- PhecapData(ehr_data, "healthcare_utilization", "label", 0.4, patient_id = "patient_id")
data

Specify the surrogate used for surrogate-assisted feature extraction (SAFE). The typical way is to specify a main ICD code, a main NLP CUI, as well as their combination. In some cases one may want to define surrogate through lab test. The default lower_cutoff is 1, and the default upper_cutoff is 10. Feel free to change the cutoffs based on domain knowledge.

surrogates <- list(
  PhecapSurrogate(
    variable_names = "main_ICD",
    lower_cutoff = 1, upper_cutoff = 10),
  PhecapSurrogate(
    variable_names = "main_NLP",
    lower_cutoff = 1, upper_cutoff = 10),
  PhecapSurrogate(
    variable_names = c("main_ICD", "main_NLP"),
    lower_cutoff = 1, upper_cutoff = 10))

Run surrogate-assisted feature extraction (SAFE) and show result.

system.time(feature_selected <- phecap_run_feature_extraction(data, surrogates))

feature_selected

Train phenotyping model and show the fitted model, with the AUC on the training set as well as random splits

suppressWarnings(model <- phecap_train_phenotyping_model(data, surrogates, feature_selected))
model

Validate phenotyping model using validation label, and show the AUC and ROC

validation <- phecap_validate_phenotyping_model(data, model)
validation
round(validation$valid_roc[validation$valid_roc[, "FPR"] <= 0.2, ], 3)

phecap_plot_roc_curves(validation)

Apply the model to all the patients to obtain predicted phenotype.

phenotype <- phecap_predict_phenotype(data, model)
idx <- which.min(abs(validation$valid_roc[, "FPR"] - 0.05))
cut.fpr95 <- validation$valid_roc[idx, "cutoff"]
case_status <- ifelse(phenotype$prediction >= cut.fpr95, 1, 0)
predict.table <- cbind(phenotype, case_status)
predict.table[1:10, ]