Skip to content

Commit

Permalink
adding pages to website
Browse files Browse the repository at this point in the history 
- adding benchmark tasks and constrained predictors to website
  • Loading branch information
@jreps
jreps committed Sep 7, 2023
1 parent 39aabd1 commit 5a08d8a
Show file tree
Hide file tree
Showing 4 changed files with 415 additions and 3 deletions.
8 changes: 8 additions & 0 deletions _pkgdown.yml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,8 @@ navbar:
- reference
- articles
- tutorial
- benchmarks
- predictors
- bestpractice
- news
right: [hades, github]
Expand All @@ -39,6 +41,12 @@ navbar:
bestpractice:
text: Best Practices
href: articles/BestPractices.html
benchmarks:
text: Benchmarks
href: articles/BenchmarkTasks.html
predictors:
text: Predictors
href: articles/ConstrainedPredictors.html
news:
text: Changelog
href: news/index.html
Expand Down
306 changes: 306 additions & 0 deletions vignettes/BenchmarkTasks.Rmd
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,306 @@
---
title: "Benchmark Tasks"
author: "Jenna Reps, Ross Williams, Peter R. Rijnbeek"
date: '`r Sys.Date()`'
header-includes:
- \usepackage{fancyhdr}
- \pagestyle{fancy}
- \fancyhead{}
- \fancyhead[CO,CE]{Installation Guide}
- \fancyfoot[CO,CE]{PatientLevelPrediction Package Version `r utils::packageVersion("PatientLevelPrediction")`}
- \fancyfoot[LE,RO]{\thepage}
- \renewcommand{\headrulewidth}{0.4pt}
- \renewcommand{\footrulewidth}{0.4pt}
output:
pdf_document:
includes:
in_header: preamble.tex
number_sections: yes
toc: yes
word_document:
toc: yes
html_document:
number_sections: yes
toc: yes
---
<!--
%\VignetteEngine{knitr}
%\VignetteIndexEntry{Best Practices}
-->

## Benchmark Tasks For Large-Scale Empirical Analyses

Here we provide a set of diverse prediction tasks that can be used when evaluating the impact of the model design choice when developing models using observational data.

<table>
<tr>
<th>
Target Cohort (index)
</th>
<th>
Outcome
</th>
<th>
Time-at-risk
</th>
<th>
Link
</th>
</tr>


<tr>
<td>
Patients with an outpatient visit in 2017 with no prior cancer (first visit in 2017)
</td>
<td>
Lung cancer
</td>
<td>
1 day - 3 years after index
</td>
<td>
</td>
</tr>

<tr>
<td>
Patients newly diagnosed with major depressive disorder (date of first record)
</td>
<td>
Bipolar
</td>
<td>
1 day - 365 day after index
</td>
<td>
</td>
</tr>

<tr>
<td>
Patients with an outpatient visit in 2019
</td>
<td>
Dementia
</td>
<td>
1 day - 3 years after index
</td>
<td>
</td>
</tr>

<tr>
<td>
Patients with an outpatient visit and a positive COVID test
</td>
<td>
Hospitalization with pneumonia
</td>
<td>
1 day - 30 days after index
</td>
<td>
</td>
</tr>

<tr>
<td>
Patients with an outpatient visit and a positive COVID test
</td>
<td>
Hospitalization with pneumonia that required intensive services (ventilation, intubation, tracheotomy, or extracorporeal membrane oxygenation) or death
</td>
<td>
1 day - 30 days after index
</td>
<td>
</td>
</tr>

<tr>
<td>
Patients with an outpatient visit and a positive COVID test
</td>
<td>
Death
</td>
<td>
1 day - 30 days after index
</td>
<td>
</td>
</tr>

<tr>
<td>
Patients with T2DM who were treated with metformin and who became new adult users of one of sulfonylureas, thiazolidinediones, dipeptidyl peptidase-4 inhibitors, glucagon-like peptide-1 receptor agonists, or sodium-glucose co-transporter-2 inhibitors (date of secondary drug). Patients with HF or patients treated with insulin on or prior to the index date were excluded from the analysis. Patients were required to have been enrolled for at least 365 days before cohort entry.
</td>
<td>
Heart Failure
</td>
<td>
1 to 365 days
</td>
<td>
</td>
</tr>

<tr>
<td>
Patients newly diagnosed with atrial fibrilation (date of initial afib record)
</td>
<td>
Ischemic stroke
</td>
<td>
1 to 365 days
</td>
<td>
</td>
</tr>

<tr>
<td>
Patients undergoing elective major non-cardiac surgery (date of surgery). Patients were required to have been enrolled for at least 365 days before cohort entry.
</td>
<td>
Earliest of AMI cardiac arrest or death (MACE)
</td>
<td>
O to 30 days
</td>
<td>
</td>
</tr>

<tr>
<td>
Patients starting intravitreal Anti-VEGF (date of administration)
</td>
<td>
Kidney Failure
</td>
<td>
1 to 365 days
</td>
<td>
</td>
</tr>

<tr>
<td>
Pregnancy women (start of pregnancy)
</td>
<td>
Preeclampsia
</td>
<td>
During pregnancy
</td>
<td>
</td>
</tr>

<tr>
<td>
Pregnancy women (start of pregnancy)
</td>
<td>
Still birth
</td>
<td>
During pregnancy
</td>
<td>
</td>
</tr>


<tr>
<td>
Patients with COPD (first record)
</td>
<td>
Cardiovascular event and death
</td>
<td>
1-30 days and 1-90 days
</td>
<td>
</td>
</tr>

<tr>
<td>
Patients starting menopause (first record)
</td>
<td>
Depression
</td>
<td>
1 day - 3-years
</td>
<td>
</td>
</tr>

<tr>
<td>
Patients with anemia (date of first anemia record)
</td>
<td>
Colorectal cancer
</td>
<td>
1 day - 1-year
</td>
<td>
</td>
</tr>

<tr>
<td>
Patients with quadriplegia (date of first quadriplegia record)
</td>
<td>
Death
</td>
<td>
1 day - 1-year
</td>
<td>
</td>
</tr>

<tr>
<td>
Patient undergoing
</td>
<td>

</td>
<td>

</td>
<td>
</td>
</tr>

<tr>
<td>

</td>
<td>

</td>
<td>

</td>
<td>
</td>
</tr>

</table>

18 changes: 15 additions & 3 deletions vignettes/BestPractices.rmd
View file
Original file line number Diff line number Diff line change
Expand Up @@ -101,7 +101,7 @@ Data Creation
Impact of over/under-sampling
</td>
<td>
Study being developed
Paper under review
</td>
</tr>

Expand All @@ -125,7 +125,7 @@ Model development
How much data do we need for prediction - Learning curves at scale
</td>
<td>
<a href='https://arxiv.org/abs/2008.07361'>Preprint link</a>
<a href='https://www.sciencedirect.com/science/article/pii/S1386505622000764'>International Journal of Medical Informatics</a>
</td>
</tr>

Expand Down Expand Up @@ -165,6 +165,18 @@ Study needs to be done
</td>
</tr>

<tr>
<td>
Model development
</td>
<td>
Can we use ensembles to combine different algorithm models within a database to improve models transportability?
</td>
<td>
Study Complete
</td>
</tr>

<tr>
<td>
Model development
Expand All @@ -173,7 +185,7 @@ Model development
Can we use ensembles to combine models developed using different databases to improve models transportability?
</td>
<td>
<a href=''> Paper under review at BMC </a>
<a href='https://link.springer.com/article/10.1186/s12911-022-01879-6'> BMC Medical Informatics and Decision Making </a>
</td>
</tr>

Expand Down
Loading

0 comments on commit 5a08d8a

Please sign in to comment.