visualize_icd10: Generate and Visualize Embeddings of ICD-10 Codes
In adamgdobrakowski/memr: Multisource Embeddings for Medical Records

Description Usage Arguments Value Examples

Generate and visualize embeddings of ICD-10 codes. An embedding of the code is the simple average of embeddings of all visits assigned by this code. The visualization is generated on the 2D plane by t-SNE algorithm and plotted with ggplot. If t-SNE cannot be generated (because for example perplexity is too large for the number of samples), there are plotted two main components from PCA. The plot can be optionally saved to the given PDF file.

1 2	visualize_icd10(visits_vectors, visit_table, method = "tsne", save = FALSE, path_to_save)

`visit_table`	A data frame with columns: `visit_id` `icd10` ICD-10 code of the visit
`method`	One of "tsne" (default) or "pca" - a method of generating the plot
`save`	A logical indicating if the plot should be saved to the file
`path_to_save`	An optional string of the path to the target PDF file
`visit_vectors`	A matrix of embeddings of visits

A generated plot of embeddings.

inter_term_vectors <- embed_terms(interviews, embedding_size = 10L,
                                  term_count_min = 1L)
exam_term_vectors <- embed_terms(examinations, embedding_size = 10L,
                                 term_count_min = 1L)
visits_vectors <- embed_list_visits(interviews,
                                    examinations, inter_term_vectors, exam_term_vectors)

visualize_icd10(visits_vectors, visits)