Using R for Healthcare Improvement

class: center, middle

background-image: url("./snips/abuja R ladies.jpg")
background-size: 100px
background-position: 95% 5%

# Using R for Healthcare Improvement

![](./snips/stbalo.jpg)
## Balogun Stephen Taiye
Saturday, 24th April 2021
---
background-image: url("https://upload.wikimedia.org/wikipedia/commons/b/be/Sharingan_triple.svg")
background-size: 100px
background-position: 95% 95%

## Outline

- About me

- A little about what I do

- The Nigeria National Data Repository

- {tidyndr}

- The AchieveR app

- Q & A

- Demo

- Q & A

---
background-image: url("./snips/abuja R ladies.jpg")
background-size: 100px
background-position: 95% 5%

## About me

- A Medical Doctor

- A public health physician

- A quality improvement professional and patient safety expert

- Sometimes a data scientist

- Co-founder: [r4hds](https://r4hds.netlify.app/)

- [My personal website](https://taiye.rbind.io) 👨

- Twitter <svg viewBox="0 0 512 512" style="height:1em;position:relative;display:inline-block;top:.1em;" xmlns="http://www.w3.org/2000/svg"> <path d="M459.37 151.716c.325 4.548.325 9.097.325 13.645 0 138.72-105.583 298.558-298.558 298.558-59.452 0-114.68-17.219-161.137-47.106 8.447.974 16.568 1.299 25.34 1.299 49.055 0 94.213-16.568 130.274-44.832-46.132-.975-84.792-31.188-98.112-72.772 6.498.974 12.995 1.624 19.818 1.624 9.421 0 18.843-1.3 27.614-3.573-48.081-9.747-84.143-51.98-84.143-102.985v-1.299c13.969 7.797 30.214 12.67 47.431 13.319-28.264-18.843-46.781-51.005-46.781-87.391 0-19.492 5.197-37.36 14.294-52.954 51.655 63.675 129.3 105.258 216.365 109.807-1.624-7.797-2.599-15.918-2.599-24.04 0-57.828 46.782-104.934 104.934-104.934 30.213 0 57.502 12.67 76.67 33.137 23.715-4.548 46.456-13.32 66.599-25.34-7.798 24.366-24.366 44.833-46.132 57.827 21.117-2.273 41.584-8.122 60.426-16.243-14.292 20.791-32.161 39.308-52.628 54.253z"></path></svg>: follow @eppydoc 😄

---
background-image: url("https://upload.wikimedia.org/wikipedia/commons/7/7e/Mudra-Naruto-KageBunshin.svg")
background-size: 100px
background-position: 95% 95%

## About what I do

- Developmental sector - HIV/AIDS

- Over [38 million people estimated to be living with HIV globally](https://www.unaids.org/en).

- Nigeria has up to [1.9 million PLHIV](https://naiis.ng/Summary_Sheet) with about [1.3 million of these are already on treatment](https://ndr.shieldnigeriaproject.com/public/dashboard).

- [UNAIDS 2030 targets (95-95-95)](https://www.togetheractnow.org/endaids.html)
    -   95% of people living with HIV are aware of their status
    -   95% of people who are aware of their status are on ART
    -   95% of people on ART are virally suppressed.

- Indicators are used to monitor progress/performance. For the [PEPFAR](https://www.state.gov/pepfar/) supported program the [MER indicators](https://datim.zendesk.com/hc/en-us/articles/360000084446-MER-Indicator-Reference-Guides) are used. These are grouped into:

-     Prevention indicators
    -     Testing indicators
    -     Treatment indicators
    -     Viral Suppression indicators
    -     Health Systems indicators

---
background-image: url("./snips/abuja R ladies.jpg")
background-size: 100px
background-position: 95% 5%

## About what I do - Cont'd
<center><img src="./snips/unaids.gif" height="400px" /></center>

Image credit: [UNAIDS](https://www.togetheractnow.org/endaids.html)

---
background-image: url(https://upload.wikimedia.org/wikipedia/commons/3/39/Naruto_Shiki_Fujin.svg)
background-size: 100px
background-position: 95% 95%

## The National Data Repository - NDR

- A repository of de-identified patient-level data from facilities across the country.
- Contains records of over 1000 reporting facilities and over 1 million PLHIV currently on treatment.

- Requires login access. [A public dashboard is available](https://ndr.shieldnigeriaproject.com/public/dashboard).

.pull-left[![description of the image](./snips/ndr1.png)]

.pull-right[![description of the image](./snips/ndr2.png)]

.pull-right[Image credit: [NDR](https://ndr.shieldnigeriaproject.com/public/dashboard)]

---
background-image: url("./snips/abuja R ladies.jpg")
background-size: 100px
background-position: 95% 5%

## NDR - 2

.footnote[Source: Stephen Balogun]

---
background-image: url("https://upload.wikimedia.org/wikipedia/commons/b/be/Sharingan_triple.svg")
background-size: 100px
background-position: 95% 95%

## NDR - 3

> “To measure is to know. If you cannot measure it, you cannot improve it.”
>
> \- Lord Kelvin

Analysis is traditionally conducted using spreadsheets. Challenges include:

+   The software must be installed on the user’s computer.

+   The user must be familiar with the formula for calculation of the indicator of interest.

+   Because of the point-and-click nature of the analysis, it is error-prone. Sometimes these errors go unnoticed by the users giving a rather false result.

+   Performing the same analysis periodically can be quite tedious and time-consuming as the analysis is usually done afresh every time.

---
background-image: url("./snips/abuja R ladies.jpg")
background-size: 100px
background-position: 95% 5%

## {tidyndr} - Workflow
<center><img src="./snips/r4ds-general.png" height="500px" /></center>

.footnote[Artwork by @allison_horst]
---
background-image: url("https://upload.wikimedia.org/wikipedia/commons/7/7e/Mudra-Naruto-KageBunshin.svg")
background-size: 100px
background-position: 95% 95%

## {tidyndr} ~ tidyverse
.pull-left[
- tidyverse group of packages

- janitor

- vroom

- lubridate

- purrr
]
.pull-right[<img src="./snips/tidyverse_celestial.png" height="450px" />]

.footnote[Artwork by @allison_horst]
---
background-image: url("./snips/abuja R ladies.jpg")
background-size: 100px
background-position: 95% 5%

## {tidyndr} - the package

```r
# from CRAN
install.packages("tidyndr", dependencies = TRUE)

# developmental version from github
devtools::install_github("stephenbalogun/tidyndr", build_vignettes = TRUE)

## practice data
file_path <- "https://raw.githubusercontent.com/stephenbalogun/abuja_r_ladies/main/ndr_example.csv"
```

why do:

`$$s = \sum_{i=1}^nX_i\frac{(x - \bar{x})^2}{n}$$`
When you can just do:
`$$s = var(x)$$`
---
background-image: url(https://upload.wikimedia.org/wikipedia/commons/3/39/Naruto_Shiki_Fujin.svg)
background-size: 100px
background-position: 95% 95%

## Package Organization

#### Importing function

```
read_ndr()
```
#### Treatment function

```
1. tx_new()
2. tx_curr()
3. tx_appointment()
4. tx_ml()
5. tx_ml_outcomes()
6. tx_rtt()
7. tx_mmd()
```
---
background-image: url("./snips/abuja R ladies.jpg")
background-size: 100px
background-position: 95% 5%

## Package Organization - 2

#### Viral Load functions

```
1. tx_vl_eligible()
2. tx_pvls_den()
3. tx_pvls_num()
4. tx_vl_unsuppressed()
```
#### Summary functions

```
1. summarise_ndr()
2. disaggregate()
```
See:
```
vignette(package = "tidyndr", topic = "tidyndr")
vignette(package = "tidyndr", topic = "Augmenting-tidyndr")
```
---
background-image: url("https://upload.wikimedia.org/wikipedia/commons/b/be/Sharingan_triple.svg")
background-size: 100px
background-position: 95% 95%

## The AchieveR app

- A shiny application.

- Interactive dashboard built on the {tidyndr} functions.

> A package is good, a dashboard is (probably) better!!

- Still a work in progress, far from the final version.

- Uses both NDR and EMR data.

- Can help compare concurrence or otherwise of the EMR and the NDR.

- patient-level data can be downloaded based on the specific indicator of interest.
---
background-image: url("./snips/abuja R ladies.jpg")
background-size: 100px
background-position: 95% 5%

## The AchieveR dashboard

.pull-left[![description of the image](./snips/achiever1.png)]

.pull-right[![description of the image](./snips/achiever.png)]
---
background-image: url("https://upload.wikimedia.org/wikipedia/commons/7/7e/Mudra-Naruto-KageBunshin.svg")
background-size: 100px
background-position: 95% 95%

## Questions please!

.footnote[Artwork by @allison_horst]
---
class: inverse, middle, center
background-image: url(https://upload.wikimedia.org/wikipedia/commons/3/39/Naruto_Shiki_Fujin.svg)
background-size: contain

# Demo

---
class: center, middle

# Thanks!

Slides created via the R packages:

[**xaringan**](https://github.com/yihui/xaringan) 
[gadenbuie/xaringanthemer](https://github.com/gadenbuie/xaringanthemer)

The chakra comes from [remark.js](https://remarkjs.com), [**knitr**](http://yihui.name/knitr), and [R Markdown](https://rmarkdown.rstudio.com).