Rayyan's AI analyzes titles, abstracts, and full-text to highlight relevant keywords and phrases, and it learns from your inclusion/exclusion decisions to suggest labels for unscreened articles.
Multiple reviewers can work on the same review simultaneously while their decisions are hidden from each other to prevent bias, with a structured process for resolving conflicts.
Automatically identifies and removes duplicate references from imported datasets using fuzzy matching algorithms that go beyond simple title matching.
A dedicated iOS and Android app allows researchers to screen articles on-the-go, with full sync to their web projects.
Users can search PubMed and other supported databases directly within Rayyan and import results with one click, or upload files from reference managers like Zotero, EndNote, and Mendeley.
Upload PDFs of included articles to screen the full text within Rayyan. The viewer allows highlighting, adding notes, and marking inclusion/exclusion reasons directly on the document.
A team of medical researchers uses Rayyan to manage a systematic review on a new drug's efficacy. They import thousands of records from PubMed, EMBASE, and Cochrane. The AI deduplicates and highlights key PICO elements. Reviewers work blinded, screening independently. The tool's conflict resolution module helps them efficiently reconcile disagreements, ensuring a rigorous, reproducible methodology required for publication in high-impact journals.
A doctoral student conducting a scoping review uses Rayyan's free tier to organize and screen relevant literature. The AI suggestions help them quickly identify core papers from a large initial set. The ability to work from the mobile app allows them to screen articles during spare moments. They export a clean, deduplicated list of included studies directly into their reference manager for citation.
A government agency or NGO needs to synthesize existing evidence to inform a new public health policy. A large team uses Rayyan's Teams or Enterprise plan to collaborate across departments. Features like blinding, audit trails, and high-volume handling ensure the process is transparent and defensible. The final exported report provides a clear rationale for included studies, supporting evidence-based decision-making.
A university professor uses Rayyan to teach a graduate-level course on research methods. Students are assigned to small groups to conduct mini-reviews. The professor can create a class account, monitor each group's progress in real-time, and use the platform to demonstrate key concepts like blinding, conflict resolution, and the importance of a structured screening process.
A hospital committee needs to quickly assess the latest evidence on a treatment protocol. Using Rayyan, a small team performs a rapid review. The AI acceleration and pre-built screening templates allow them to compress a months-long process into weeks. The ability to upload and annotate full-text PDFs of guidelines and trials within the platform speeds up the extraction of key recommendations.
Sign in to leave a review
A Cloud Guru (ACG) is a comprehensive cloud skills development platform designed to help individuals and organizations build expertise in cloud computing technologies. Originally focused on Amazon Web Services (AWS) training, the platform has expanded to cover Microsoft Azure, Google Cloud Platform (GCP), and other cloud providers through its acquisition by Pluralsight. The platform serves IT professionals, developers, system administrators, and organizations seeking to upskill their workforce in cloud technologies. It addresses the growing skills gap in cloud computing by providing structured learning paths, hands-on labs, and certification preparation materials. Users can access video courses, interactive learning modules, practice exams, and sandbox environments to gain practical experience. The platform is particularly valuable for professionals preparing for cloud certification exams from AWS, Azure, and GCP, offering targeted content aligned with exam objectives. Organizations use ACG for team training, tracking progress, and ensuring their staff maintain current cloud skills in a rapidly evolving technology landscape.
Abstrackr is a web-based, AI-assisted tool designed to accelerate the systematic review process, particularly the labor-intensive screening phase. Developed by the Center for Evidence-Based Medicine at Brown University, it helps researchers, librarians, and students efficiently screen thousands of academic article titles and abstracts to identify relevant studies for inclusion in a review. The tool uses machine learning to prioritize citations based on user feedback, learning from your initial 'include' and 'exclude' decisions to predict the relevance of remaining records. This active learning approach significantly reduces the manual screening burden. It is positioned as a free, open-source solution for the academic and medical research communities, aiming to make rigorous evidence synthesis more accessible and less time-consuming. Users can collaborate on screening projects, track progress, and export results, streamlining a critical step in evidence-based research.
AdaptiveLearn AI is an innovative platform that harnesses artificial intelligence to deliver personalized and adaptive learning experiences. By utilizing machine learning algorithms, it dynamically adjusts educational content based on individual learner performance, preferences, and pace, ensuring optimal engagement and knowledge retention. The tool is designed for educators, trainers, and learners across various sectors, supporting subjects from academics to professional skills. It offers features such as real-time feedback, comprehensive progress tracking, and customizable learning paths. Integration with existing Learning Management Systems (LMS) allows for seamless implementation in schools, universities, and corporate environments. Through data-driven insights, AdaptiveLearn AI aims to enhance learning outcomes by providing tailored educational journeys that adapt to each user's unique needs and goals.
