exam_forecast
Companion analysis to a paper published in the Journal of Digital Imaging.
Science Score: 67.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
✓DOI references
Found 4 DOI reference(s) in README -
✓Academic publication links
Links to: zenodo.org -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (11.8%) to scientific vocabulary
Keywords
Repository
Companion analysis to a paper published in the Journal of Digital Imaging.
Basic Info
Statistics
- Stars: 1
- Watchers: 1
- Forks: 1
- Open Issues: 0
- Releases: 1
Topics
Metadata Files
README.md
Paper Repository: Automatic Forecasting of Radiology Examination Volume Trends for Optimal Resource Planning and Allocation
<!-- badges: start -->
<!-- badges: end -->
by Anton S. Becker · Joseph P. Erinjeri · Joshua Chaim · Nicholas Kastango · Pierre Elnajjar · Hedvig Hricak · H. Alberto Vargas
This is the companion analysis to a paper published in the Journal of Digital Imaging.
Preparation
To run the analysis in ExamForecast.Rmd, the following packages need to be installed:
r
install.packages(
c(
"here",
"kableExtra",
"knitr",
"magrittr",
"prophet",
"readr",
"rmarkdown",
"stringr",
"tidyverse",
"timeDate"
# Recommended:
"rticles"
"skimr"
)
)
Data Format
The synthetic toy data is provided in the "Data" folder (gzipped csv). It can be read natively by {{readr::read_csv}} or alternatively unzipped by R's native read.csv function. To run a prophet forecast with our own data, replace the csv files with your own data with at least two columns: Date and number of examinations.
In order to recycle the code from this repository a column modality_code should be added containing either "CT" or "MRI".
r
library(dplyr)
here::here("Data", "per_diem_msk.csv.gz") %>%
readr::read_csv(show_col_types = FALSE) %>%
skimr::skim()
Simple forecast example
For a more comprehensive documentation please refer to the accompanying ExamForecast.Rmd and the official Prophet documentation. Below is a minimal example of a forecast for the next month:
```r library(dplyr) library(prophet)
exams <- here::here("Data", "perdiemmsk.csv.gz") %>% readr::readcsv() %>% filter(modalitycode == "CT") %>% transmute( ds = asdate(examdate), y = n_exams, )
m <- prophet(exams)
pred <- makefuturedataframe(m, 31, "days", include_history = TRUE)
forecast_exams <- predict(m, pred) ```
License
All source code is made available under a MIT or file-specific license. You can freely
use and modify the code, without warranty, so long as you provide attribution
to the authors/cite the article. See LICENSE.md for the full license text.
Owner
- Name: Anton Becker
- Login: ASBecker
- Kind: user
- Repositories: 1
- Profile: https://github.com/ASBecker
Citation (CITATION.cff)
cff-version: 1.2.0
message: "If you use (parts of) this analysis or data, please cite it as below."
authors:
- family-names: "Becker"
given-names: "Anton S."
orcid: "https://orcid.org/0000-0001-8372-6496"
- family-names: "Erinjeri"
given-names: "Joseph"
- family-names: "Kastango"
given-names: "Nicholas"
title: "Radiology exam volume forecast repository"
version: 1.0
doi: 10.5281/zenodo.5699476
date-released: 2017-12-18
url: "https://github.com/ASBecker/exam_forecast"
preferred-citation:
type: article
authors:
- family-names: "Becker"
given-names: "Anton S."
orcid: "https://orcid.org/0000-0001-8372-6496"
- family-names: "Erinjeri"
given-names: "Joseph P."
- family-names: "Chaim"
given-names: "Joshua"
- family-names: "Kastango"
given-names: "Nicholas"
- family-names: "Elnajjar"
given-names: "Pierre"
- family-names: "Hricak"
given-names: "Hedvig"
- family-names: "Vargas"
given-names: "H. Alberto"
doi: "10.1007/s10278-021-00532-4"
journal: "Journal of Digital Imaging"
title: "Automatic Forecasting of Radiology Examination Volume Trends for Optimal Resource Planning and Allocation"
year: 2021
GitHub Events
Total
Last Year
Dependencies
- dplyr * depends
- here * depends
- kableExtra * depends
- knitr * depends
- lubridate * depends
- magrittr * depends
- prophet * depends
- readr * depends
- rmarkdown * depends
- rticles * depends
- skimr * depends
- stringr * depends
- tidyverse * depends
- timeDate * depends
- rocker/binder 4.0.5 build