A global research team sought rapid, structured insights across multiple emerging oncological therapeutic areas (some in rare disease). The goal was to build early-stage evidence assets covering clinical, epidemiologic, and economic evidence available on the research team’s therapies and all comparators in each of four therapeutic areas, ensuring preparedness for stakeholder engagement and future data needs. In effect, these reviews serve multiple purposes, including evidence generation planning and preparing for later health technology assessment.
For comparison, traditional reviews in these areas often take months and require significant resources, which would be too slow and expensive for this global team’s needs. The team also wanted to ensure that ‘living’ evidence was available on an ongoing basis for these therapeutic areas starting well before HTA submission activities.
Therefore, recognizing that AI-assisted Rapid Reviews can be performed in as little as 3 hours, their team partnered with Nested Knowledge to conduct AI-enabled Rapid Reviews, generating dashboard deliverables that synthesized evidence across 13 distinct reviews in four critical therapeutic areas.
Nested Knowledge’s AI-assisted systematic review workflow was applied across the 13 reviews. Each review proceeded through the following core steps:
These methods use the fully published, validated AI tools in the Nested Knowledge review workflow, with expert curation on the highest-value endpoints and screening studies that are borderline, but depend on the AI for the majority of Search, Screening, and Extraction.
The rapid review project achieved both scale and efficiency, demonstrating how AI can transform the evidence synthesis process. Across the 13 reviews, the Nested Knowledge platform streamlined every step, from searching and screening to extraction and synthesis.
Each review was delivered as an interactive dashboard and expert-written abstract, giving the team immediate access to structured insights across clinical, epidemiologic, and economic domains. Instead of static tables, they received living dashboards that could be explored, filtered, and shared across teams—ensuring that evidence was not only gathered, but also made usable.
Key project metrics:
In these reviews, the AI tools extracted hundreds of qualitative elements and quantitative data, ranging from clinical safety and efficacy outcomes to epidemiologic trends and economic measures. Importantly, timelines to completion were compressed dramatically, allowing the project to move from initiation to delivery far faster than would have been possible with conventional methods. Vitally, these reviews are all delivered directly within the Nested Knowledge software, and the team can make updates directly to the evidence within each ‘nest’ as living evidence repositories/libraries.
This project illustrates the transformative potential of AI-assisted Rapid Reviews in oncology. By combining automation with expert oversight, the team completed 13 full reviews in a fraction of the time required by traditional approaches. Each step was fully transparent and traceable, ensuring methodological rigor without sacrificing speed. The deliverables went beyond static reports: interactive dashboards provided immediate visualization and drill-down capability, while abstracts distilled complex findings into concise insights.
Perhaps most importantly, the use of AI brought costs down significantly, allowing the commissioning team to achieve scale and depth that would typically be out of reach with conventional review methods.
The global team emerged from the project with a portfolio of structured, actionable evidence across four oncology focus areas, delivered faster and at lower cost than expected. Instead of waiting months, they gained rapid access to living dashboards and expert summaries that could immediately inform strategy, internal alignment, and external engagement. This also demonstrated the effectiveness of AI Rapid Reviews in Nested Knowledge in the execution of evidence generation planning, HTA readiness, and flexible answers to strategically important questions.
These outputs didn’t just summarize data, they empowered teams. Interactive dashboards allowed stakeholders to explore the evidence dynamically, while abstracts offered polished narratives that could be directly applied in communications and planning. By completing 13 reviews with the majority of time spent on interpretation and presentation rather than the typically work-intensive screening or extraction steps, the project demonstrated how AI can accelerate and support the delivery of enterprise-level insights at a fraction of traditional cost and time.
Benefit to Customer:
This case study demonstrates that Nested Knowledge’s AI-enabled workflows can deliver multi-domain, multi-indication evidence synthesis at scale. With 13 rapid reviews completed efficiently and cost-effectively, the project established a proactive evidence base for clinical, epidemiologic, and economic outcomes ready to inform strategy, regulatory readiness, and stakeholder engagement.
Yep, you read that right. We started making software for conducting systematic reviews because we like doing systematic reviews. And we bet you do too.
If you do, check out this featured post and come back often! We post all the time about best practices, new software features, and upcoming collaborations (that you can join!).
Better yet, subscribe to our blog, and get each new post straight to your inbox.
One of the features of Core Smart Tags is Smart Study Type – this refers to our AI system that automatically categorises the study type
