---
title: "Working with the `socialrisk` Package"
author: "Wyatt P. Bensken"
date: "`r Sys.Date()`"
output: rmarkdown::html_vignette
vignette: >
  %\VignetteIndexEntry{socialrisk}
  %\VignetteEngine{knitr::rmarkdown}
  %\VignetteEncoding{UTF-8}
---

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

```{r setup, include = FALSE}

library(socialrisk)
```

# Introduction

The goal of `socialrisk` is to create an efficient way to identify social risk from administrative health care data using ICD-10 diagnosis codes.

# Load Sample Data

We've created a sample dataset of ICD-10 administrative data which we can load in.

```{r}
i10_wide
```

# Preparing the Data

We use the built-in `clean_data()` function to specify the: dataset, patient id, current data format (wide or long), and the prefix of the diagnoses variables.

```{r}
data <- clean_data(dat = i10_wide,
                   id = patient_id,
                   style = "wide",
                   prefix_dx = "dx")
```

```{r, echo = FALSE}
head(data, 10)
```

# Social Risk

Now, we can run our various social risk functions, with varying taxonomies.

## Centers for Medicare and Medicaid Services (CMS)

```{r}
cms <- socialrisk(dat = data, id = patient_id, dx = dx, taxonomy = "cms")
```

```{r, echo = FALSE}
head(cms, 5)
```

## Missouri Hospital Association

```{r}
mha <- socialrisk(dat = data, id = patient_id, dx = dx, taxonomy = "mha")
```

```{r, echo = FALSE}
head(mha, 5)
```

## SIREN - UCSF

```{r}
siren <- socialrisk(dat = data, id = patient_id, dx = dx, taxonomy = "siren")
```

```{r, echo = FALSE}
head(siren, 5)
```