---
title: "Example data"
output: rmarkdown::html_vignette
vignette: >
  %\VignetteIndexEntry{Example data}
  %\VignetteEngine{knitr::rmarkdown}
  %\VignetteEncoding{UTF-8}
---

```{r, include = FALSE}
knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>"
)
```

```{r setup}
library(coder)
```

This vignette contains some example data used in the other vignettes.

# Patients

`ex_people` contains 100 patients (with random names from the [`randomNames`](https://centerforassessment.github.io/randomNames/) package) who received total hip arthroplasty (THA) surgery at given (random) dates (`surgery` column). This data represent a sample from a national quality register.

See also `?ex_people`.

```{r}
ex_people
```

# Diagnoses data

We are interested in comorbidity for the patients above and have collected some synthesized diagnostics data (`ex_icd10`) from a national patient register (we can at least assume that for now). Patients have one entry for every combination of recorded diagnoses codes according to the International classification of diseases version 10, `icd10`, and corresponding dates of hospital `admission`s for which those codes were recorded. (Column `hdia` is `TRUE` for main diagnoses and `FALSE` for underlying/less relevant codes).

See also `?ex_icd10`.

```{r}
ex_icd10
```

# Medical data

Assume we have some external code data from a national prescription register. Such register would likely cover additional patients but let's just consider a small sample with ATC codes for patients above, such that each patient can have zero, one, or several codes prescribed at different dates.

```{r}
ex_atc

```