We’re excited to introduce Critical Appraisal in Silvi!

With this new feature, Silvi makes it easier to keep the entire literature review workflow in one place — from screening and data extraction to quality assessment and analysis. Projects in Silvi can now include a dedicated Risk of Bias phase, allowing researchers to assess study quality using established frameworks such as RoB2, NOS, and AMSTAR2.

Save time with transparent AI suggestions

Assessing the quality of included studies is an essential part of reviewing scientific literature, but it is often one of the most time-consuming steps in the review process. With Critical Appraisal in Silvi, researchers can choose to complete assessments manually or use AI suggestions to speed up the process.

With a single click, Silvi suggests answers to signaling questions, explains the reasoning behind each suggestion, and highlights the relevant sections directly in the article. As with all other AI-assisted workflows in Silvi, transparency remains a core principle. Every suggestion is accompanied by a rationale and supporting highlights, allowing researchers to review, approve, adjust, or reject each suggestion before finalizing their assessment.

Available in all Silvi projects

Critical Appraisal can be added to any Silvi project. Once enabled, researchers can choose an appraisal framework and complete an assessment for each included study. While the process often requires careful manual evaluation, AI suggestions help reduce repetitive work and make assessments more efficient.

Since each framework calculates overall Risk of Bias differently, Silvi automatically handles scoring based on the official methodology behind each tool. Assessment results become part of the overall project analysis and are available in tables, plots, and upcoming meta-analysis and network meta-analysis workflows, making it possible to keep the full review process organized within a single platform.

Why assess Risk of Bias?

Assessing the risk of bias of included studies is a fundamental part of evidence synthesis. Also referred to as critical appraisal, the process helps researchers evaluate how reliable individual studies are and how much confidence can be placed in the overall body of evidence.

The strength of scientific evidence depends not only on how many studies exist, but also on how those studies were designed and conducted. For example, multiple studies may report that a treatment has a strong positive effect, but if most of those studies have a high risk of bias due to poor randomization, missing outcome data, or weak study design, the overall conclusion may still be unreliable.

Critical appraisal helps researchers move beyond simply asking what does the evidence show? and instead evaluate how much confidence should be placed in those findings?

What tools are supported in Silvi?

Different study designs require different critical appraisal frameworks. These frameworks typically consist of signaling questions, often grouped into domains, together with scoring systems that lead to an overall assessment of study quality.

At launch, Silvi supports the following tools:

• RoB2 — The Revised Cochrane Risk of Bias Tool for randomized trials, widely used in systematic reviews and meta-analyses.

• AMSTAR2 — A MeaSurement Tool to Assess Systematic Reviews, commonly used in umbrella reviews to evaluate the methodological quality of systematic reviews.

• NOS — The Newcastle–Ottawa Scale, designed for assessing cohort studies and case-control studies.

Additional frameworks are already planned, but if there is a specific appraisal tool you would like to use in Silvi, feel free to get in touch with us.