Silvi vs Rayyan

1. Database Integration

Rayyan

When you start a project in Rayyan, you will need upload studies manually. Rayyan does not provide you with direction integrations with any academic databases.

To import studies into a Rayyan project, you will need a file in any of the following formats: EndNote XML, Refman/RIS, CSV, BibTeX, PubMed, Web of Science before you can upload it in your Rayyan project. Downloading several files from different databases and then uploading them to Rayyan makes the whole process lengthy and cumbersome.

Silvi

Silvi gives you direct integrations with three databases: PubMed, ERIC (Education Resources Information Center), and Open Alex. Silvi’s direction integration feature lets you take a search you’ve run and the import all the studies in the search directly from a given database. You won’t have to download an XML or a PubMed file from a database and then upload it to Silvi.

To import studies from PubMed, simply run a search and copy the search string by clicking on “Advanced” under the search bar. Paste the search string in Silvi and it will automatically fetch all the studies related to the search string.

For ERIC and Open Alex, you can simply copy the URL of your search results and paste it in Silvi, and it will retrieve all the relevant studies for you.

If you want to import studies from any other database like Web of Science or Scopus, you import them using an RIS file.

2. Bulk View

Rayyan

While screening titled and abstracts, you may want to include/exclude several studies depending on a specific criterion. Rayyan lets you select multiple studies and take a bulk decision. However, it does not show you the abstracts of the studies, making it hard to know what you are taking bulk decisions for.

You will have to read the abstracts of papers separately and then decide to include/exclude based on either your notes or memory since Rayyan does not show you abstracts of several papers simultaneously. This feature has significant potential to cause an error in the screening process.

Silvi

If you select several studies in Silvi, it will show you their abstracts together, so you don’t have to rely on your memory. You can include/exclude studies in bulk by using the Include all or Exclude all button at the bottom of your screen.

You can also use the Bulk View function in Silvi to screen studies based on certain keywords. Once you have created a certain keyword(s), Silvi will show you the keyword(s) in all the selected abstracts simultaneously.

The Bulk View feature in Silvi makes your screening process efficient without compromising on transparency or rigor.

3. Screening with AI

Rayyan

Rayyan has an AI-powered Predictions Classifier that learns from your screening (inclusion/exclusion) decisions in a review and then assigns a “rating” to undecided references, such as “Most likely to include,” “Likely to include,” “No recommendation,” “Likely to exclude,” and “Most likely to exclude.”

To use AI-powered Predictions Classifier, you will have to first screen at least 50 studies (with at least five included and five excluded). Then click on “Compute Ratings” to generate the predictions.

After that, you can sort and filter by the rating to figure out the most relevant studies.

Silvi

Unlike Rayyan, Silvi’s AI screening feature asks you explicitly about studies that are eligible for inclusion or exclusion instead of generating predictions based on your earlier screening patterns.

Silvi’s AI feature doesn’t require you to screen 50 studies like Rayyan. Instead, Silvi asks you to specify your inclusion/exclusion criteria, which is very similar to the way you would specify the criteria to your team members. Silvi’s AI feature requires you to include and exclude only one study each although if you screen more studies, it would certainly be helpful.

Based on the specified inclusion and exclusion criteria, Silvi will give you suggestions to include or exclude a given study. AI suggestions will appear in black color in the bottom-left corner of the abstract.

4. PDF Retrieval

Rayyan

After you are done with the title and abstract screening, you will move on to the full text screening phase. In Rayyan, you will have to upload PDFs for each paper yourself. Rayyan doesn’t retrieve PDFs of open access papers automatically. This requires you to look for PDFs of studies, download them, and then upload them to Rayyan, which makes the whole process lengthy and cumbersome.

Silvi

When you reach the full text phase in Silvi, it will automatically retrieve PDFs of open access papers for you. You will only have to upload PDFs of papers that are behind paywalls. This will help you save valuable time.

5. Transparent Data Extraction

Rayyan

While Rayyan lets you read full texts of articles with the app, it doesn’t let you create any tags to help you with data extraction. You can label certain parts of the text, but the labels are not linked to the relevant section. This could make the data extraction process slow and in certain cases unreliable. It can also make verifying the accuracy of the extracted data very difficult during data audits.

Silvi

Silvi will extract relevant data, and every bit of extracted data will be automatically linked to the relevant part in the text so you can see for yourself the place where it extracted the data from. This ensures transparency in the data extraction process.

Even though Silvi’s AI feature extract data for you, it gives you full control and decision-making authority. Once it has extracted data, you approve it if you agree with Silvi’s suggestion. Otherwise, you can easily delete these suggestions.