---
title: "Question-Driven Reviews"
output: rmarkdown::html_vignette
vignette: >
%\VignetteIndexEntry{Question-Driven Reviews}
%\VignetteEngine{knitr::rmarkdown}
%\VignetteEncoding{UTF-8}
resource_files:
- figures/logo.svg
- figures/logo-dark.svg
---
[](https://github.com/CTTIR/scimapR/actions/workflows/R-CMD-check.yaml)
[](https://cttir.github.io/scimapR/)
[](https://CRAN.R-project.org/package=scimapR)
[](https://app.codecov.io/gh/CTTIR/scimapR?branch=main)
[](https://cran.r-project.org/package=scimapR)
[](https://cran.r-project.org/package=scimapR)
[](https://opensource.org/licenses/MIT)
[](https://lifecycle.r-lib.org/articles/stages.html#experimental)
```{r, include = FALSE}
knitr::opts_chunk$set(
collapse = TRUE,
comment = "#>"
)
```
## Research questions as objects
scimapR treats research questions as structured objects, not just query
strings.
```{r setup}
library(scimapR)
```
```{r question}
rq <- sm_question(
text = "Does spatial transcriptomics improve outcome prediction in colorectal cancer?",
framework = "PICO",
population = "colorectal cancer patients",
intervention = "spatial transcriptomics",
outcome = "survival or recurrence"
)
print(rq)
```
## Building a corpus from a question
```r
# In production, this hits APIs:
corpus <- sm_corpus_for_question(rq, sources = c("pubmed", "openalex"))
```
For this vignette, we use the synthetic example corpus:
```{r synthetic}
corpus <- sm_example_corpus(with_screening = TRUE, seed = 42)
```
## Screening
### Regex-based (deterministic)
```{r regex}
screened <- sm_screen_regex(
corpus,
include_terms = c("transcriptom", "spatial"),
exclude_terms = c("mouse", "drosophila")
)
nrow(screened$works)
```
### LLM-grounded screening
```r
# Requires ellmer package and an API key
screened <- sm_screen_against_question(
corpus, rq,
llm = ellmer::chat_anthropic(),
stages = "title-abstract"
)
```
### Screening summary
```{r summary}
sm_screen_summary(corpus)
```
## PRISMA flow
```{r prisma, fig.width = 6, fig.height = 4}
prisma <- sm_screen_prisma(corpus)
prisma$counts
prisma$plot
```
## Export for Rayyan/Covidence
```r
sm_export_rayyan(corpus, "my_corpus.ris")
sm_export_covidence(corpus, "my_corpus_covidence.ris")
```
