How to Enhance AI Performance for Optimal Results?

How to Enhance AI Performance for Optimal Results?

EasySLR’s AI can streamline screening by providing inclusion/exclusion suggestions based on your protocol. However, to get the best results, it's important to first calibrate the AI to ensure it aligns with your decision-making. The steps below outline how to do this effectively.

Step 1: Upload a Sample Set for Evaluation
Start by uploading a sample of 100–200 citations to your project. This smaller, controlled dataset is ideal for testing how well the AI performs in comparison to human reviewers. We recommend using a representative sample that includes both clear includes and excludes for balanced evaluation.

Step 2: Use Protocol Optimiser for Targeted Suggestions
EasySLR’s Protocol Optimiser helps you strengthen your protocol to improve AI alignment:
  • It suggests specific edits to clarify ambiguous criteria.
  • Recommendations may include refining definitions, adding examples, or adjusting key inclusion/exclusion phrases.
  • Apply suggested changes.
Refer to the help article for a step by step guide on Protocol Text Review & AI Performance Analysis.

Step 3: Enable and Run AI Screening
Once your sample set is uploaded:
  • Enable Title & Abstract AI in the Settings. 
  • Allow the AI to generate inclusion/exclusion suggestions based on the protocol.
  • The AI will provide suggestions along with rationale.
Step 4: Manually Screen the Same Sample
Review and screen the same sample manually:
  • Include or exclude articles based on your judgment.
  • This creates a reference dataset for comparing the AI’s decisions.
Step 5: Compare AI and Human Decisions
Refer to the help article for a step by step guide on how to Compare AI and Human Reviewer Decisions.

Step 6: Recalibrate and Rerun AI
If more protocol changes are required, update and:
  • Rerun the AI on the sample to see if performance improves.
  • This calibration process may take a few iterations, but it’s critical to ensure accuracy in large-scale reviews.
Once you're confident in the AI’s decisions:
  • Upload the remaining citations.
  • Run the AI on the remaining citations and complete the screening.
Pro Tips:
  • Try to include a mix of relevant/irrelevant articles in the sample set.
  • Use the AI notes and rationale to understand how the AI is interpreting protocol.
Checklist before moving to full dataset:
  • Protocol finalized and saved
  • Sample set reviewed manually
  • Conflicts between AI and human resolved
  • Protocol Optimiser suggestions applied (if needed)
  • AI performance metrics (recall, conflict %) within acceptable range

    • Related Articles

    • List of AI Models Used Across EasySLR

      EasySLR uses purpose-specific GPT models across different review stages to optimise accuracy, performance, and cost efficiency. Each model has been selected based on the complexity and nature of the task it supports, ensuring reliable AI assistance ...

    • How to run AI on the articles that are already screened by Human Reviewers?

      EasySLR allows you to run AI on articles after they’ve been screened by human reviewers. Just follow the steps below to initiate the AI run and compare with the human decisions. If any differences arise, the Conflict Analysis tool helps you ...

    • Protocol Text Review & AI Performance Analysis

      EasySLR is designed to help reviewers streamline their workflows and make evidence-based decisions faster. Two powerful features — Protocol Text Review and AI Performance Analysis —ensure your review protocol is aligned, AI-ready, and easy to ...

    • How to Download AI Models Used Across Different Processes in EasySLR?

      EasySLR provides full transparency into how AI is applied across different stages of the review workflow. Users can now download details of the AI models used at each stage, helping teams meet documentation, audit, and reporting requirements. ...

    • Comparing AI Assistant and AI Reviewer in EasySLR

      EasySLR utilises advanced artificial intelligence to streamline and enhance the article screening process. Within the platform, two key AI features play pivotal roles: the AI Assistant and the AI Reviewer. While both are designed to enhance ...