> For the complete documentation index, see [llms.txt](https://docs.nested-knowledge.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.nested-knowledge.com/get-started/demo-nests/rapid-tlr-treatment-landscape-for-platinum-resistant-ovarian-cancer.md). # Rapid TLR: Treatment Landscape for platinum-resistant ovarian cancer A walkthrough of the rapid targeted literature review demo nest on treatment landscape for platinum-resistant ovarian cancer. ### About This Review Platinum-resistant ovarian cancer has a fragmented treatment landscape — multiple chemotherapies, targeted therapies, and emerging immunotherapies, each with modest efficacy gains and no clear consensus on sequencing. This nest supports HEOR planning for an early-stage asset in that space, including a MUC16-positive biomarker subgroup that may respond differently than the broader population. This is a demo of a **targeted rapid review** to inform strategic planning, not an exhaustive synthesis. That's a deliberate tradeoff, not a shortcut. If your team needs a fast, defensible read on a competitive landscape, this is the nest that shows how Nested Knowledge supports that case. Want to move straight to a Q\&A with the evidence? Jump to Synthesis Chat ### Search **Smart Search** generated AI-assisted queries for PubMed and ClinicalTrials.gov, both searched via API integration. Building precise search queries by hand is one of the slower parts of any review — Smart Search compresses that step so the team can move to screening faster, which matters most when the deliverable is a landscape assessment on a planning timeline rather than a multi-month systematic review. Restricting to two sources (rather than the three-plus a full SLR might use) is itself part of the rapid-review tradeoff: PubMed and ClinicalTrials.gov cover published trials and the registry of ongoing ones, at the cost of missing some regional or non-indexed literature. **Try it yourself:** Run Smart Search against a related biomarker or line of therapy, and compare the queries it generates to the ones already in this nest.

Smart Search queries for platinum-resistant ovarian cancer. — Smart Search queries for the treatment landscape review.

**See also:** [Smart Search](/review-workflow/literature-search/ai-tools-in-search/smart-search.md), [Literature Search](/review-workflow/literature-search.md) ### Screening On **Configure Screening** page, screening criteria was generated. Then **Smart Screener** evaluated every record against the review's full set of PICOS criteria — population, interventions/comparators, outcomes, and study design — answering yes or no on each. A record needed to meet every criterion to be included.

Configure Screening page showing generated PICOS criteria. — Generated PICOS criteria in Configure Screening.

The review modes were set as Single Reviewer and Standard (one-pass) screening. Running every criterion as a discrete yes/no question, rather than a single inclusion judgment, keeps the screening decision auditable — if a reviewer later asks why a record was excluded, the answer is which specific criterion it failed. That structure is what makes a fast, AI-assisted screening pass still defensible for strategic decision-making. **Try it yourself:** Open a record in Screening to view how Smart Screener answered the PICOS criteria and apply a screening decision yourself.

Smart Screener decisions for a screening record. — Smart Screener answers the review's PICOS criteria.

**See also:** [Smart Screener](/review-workflow/screening/criteria-based-screening/smart-screener.md), [Configure Screening](/review-workflow/screening/configure-screening.md) ### Tagging and Extraction 74 full texts were bulk imported. On **Configure Tagging** page, Core Smart Tags was run early, giving an immediate PICO-level read across the whole corpus — useful for prioritizing which records to screen first, well before screening finished. Smart Config: Tagging was run based on the review's research question. Then, **Adaptive Smart Tags** extracted data on preliminary study characteristics.

Configure Tagging page showing the generated tag hierarchy. — Generated tag hierarchy for the treatment landscape review.

A competitive landscape review needs to be able to compare trials side by side — trial design, endpoints, and biomarker reporting all vary study to study, and Adaptive Smart Tags applies the same tag hierarchy consistently across all of them so the resulting data is actually comparable, rather than a pile of differently-shaped notes. This matters especially for the MUC16-positive subgroup: extraction only surfaces that population where it's reported, which itself is one of the landscape's findings. **Try it yourself:** Examine applied tags using the icon or open a study in Tagging to view extracted data.

Tagging view showing extracted trial data. — Extracted trial data in Tagging.

Tagging view showing applied tags for an included study. — Applied tags for an included trial.

**See also:** [Configure Tagging](/review-workflow/tagging/configure-tagging.md), [Core Smart Tags](/review-workflow/tagging/ai-tools-in-tagging/core-smart-tags.md), [Smart Config: Tagging](/review-workflow/tagging/ai-tools-in-tagging/smart-config-tagging.md), and [Adaptive Smart Tags](/review-workflow/tagging/ai-tools-in-tagging/adaptive-smart-tags.md) ### Study Inspector **Study Inspector** lets a reviewer check the whole set of included studies at once, rather than one at a time — for a rapid review built to support a planning decision quickly, that's often the fastest way to sanity-check the landscape before it goes into a deck or memo. An HEOR or Medical Affairs reviewer would use Study Inspector here to, for example: filter to only the studies reporting MUC16 status, since that's the review's key subgroup and not every trial reports it; check which included studies are single-arm versus comparator trials, since the protocol treats single-arm data as context rather than primary evidence; or export a defined subset — say, only Phase 3 trials — through Download from Inspector for a quick competitive summary. **Try it yourself:** Filter to studies published in the past two years, or to trials still listed as recruiting on ClinicalTrials.gov, and see how quickly the landscape narrows.

Study Inspector showing included ovarian cancer studies. — Study Inspector for the treatment landscape.

**See also:** [Study Inspector](/review-workflow/study-inspector.md), [Filters Available in Study Inspector](/review-workflow/study-inspector/filter-studies/filters-available-in-study-inspector.md), [Download from Inspector](/review-workflow/study-inspector/download-from-inspector.md) ### Synthesis However a nest is built, opening **Synthesis** surfaces the same set of views automatically, drawing on whatever's already been completed elsewhere in the nest — none of it needs to be built from scratch. **Qualitative Synthesis** generates on its own from applied tags, giving a synthesis-ready view of how those tags translate into findings. The **PRISMA** chart auto-populates the same way from screening decisions, producing a live, auditable count of records at each stage without anyone building it by hand. **Quantitative Synthesis** and **Critical Appraisal** visuals appear alongside these two, but only where that stage was actually completed in the nest — a review that skipped Meta-Analytical Extraction, for instance, simply won't have a Quantitative Synthesis view to show. **Synthesis Chat** is available immediately regardless of how much of the nest is populated — it's a conversational way to query whatever data exists so far, not a view that waits on a specific stage finishing. **Dashboard** is the one exception: it has to be built rather than generated, so it only appears if someone has configured one in this nest. **Smart Insights** are built here– they are generated AI-written text summaries from the extracted data, drawn together into a competitive landscape narrative. **See also:** [Synthesis](/review-workflow/synthesis.md), [Qualitative Synthesis](/review-workflow/synthesis/navigate-synthesis-outputs/qualitative-synthesis.md), [PRISMA Chart](/review-workflow/synthesis/navigate-synthesis-outputs/prisma-chart.md), [Meta-Analytical Extraction](/review-workflow/meta-analytical-extraction.md), [Quantitative Synthesis](/review-workflow/synthesis/navigate-synthesis-outputs/quantitative-synthesis.md), [Critical Appraisal](/review-workflow/critical-appraisal.md), [Critical Appraisal Outputs](/review-workflow/synthesis/navigate-synthesis-outputs/critical-appraisal-outputs.md), [Synthesis Chat](/review-workflow/synthesis/navigate-synthesis-outputs/synthesis-chat.md), [Dashboard Editor](/review-workflow/synthesis/set-up-synthesis-outputs/dashboard-editor.md), and [Smart Insights](/review-workflow/synthesis/set-up-synthesis-outputs/smart-insights.md) #### Dashboard All included study extracted data — trial design, endpoints, biomarker status, results — is organized in **Dashboard** into summary tables built for side-by-side comparison across the competitive set. As with every nest, Dashboard is a synthesis-side tool, not a data-collection one: it aggregates and displays what Search, Screening, and Tagging have already captured, rather than gathering anything new. If a value in a Dashboard table looks off, the fix is in the Adaptive Smart Tags extraction behind it, not in Dashboard itself. It is also where **Smart Insights** are generated. **Try it yourself:** Maximise the study insight cards to interact with the data, or download table cards to view data in Excel.

Dashboard summarizing the treatment landscape. — Dashboard summary of extracted treatment landscape data.

**See also:** [Dashboard in Synthesis](/review-workflow/synthesis/navigate-synthesis-outputs/dashboard-in-synthesis.md), [Smart Insights](/review-workflow/synthesis/set-up-synthesis-outputs/smart-insights.md) #### Synthesis Chat For a landscape review built on a planning timeline, **Synthesis Chat** is arguably the fastest way to use this nest at all — rather than reading through Dashboard tables or the Smart Insights narrative section by section, ask it a direct question: which included trials report an objective response rate above a given threshold, or which studies include a MUC16-positive subgroup. **Try it yourself:** Ask Synthesis Chat to compare this asset's likely competitive set against a specific comparator, and see how it grounds its answer in the trials actually extracted into this nest.

Synthesis Chat answering a treatment landscape question. — Synthesis Chat response based on extracted trial data.

**See also:** [Synthesis Chat](/review-workflow/synthesis/navigate-synthesis-outputs/synthesis-chat.md) ### Next Steps


Start A Pilot Trial	Set up a pilot trial of Nested Knowledge.	Start a Pilot Trial
Core Concepts	Understand the objects and terminology used in Nested Knowledge.	Core Concepts
Nest Setup	Learn how to set up your review in Nested Knowledge.	Nest Setup
Quickstart	Start building your first nest.	Quickstart

--- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.nested-knowledge.com/get-started/demo-nests/rapid-tlr-treatment-landscape-for-platinum-resistant-ovarian-cancer.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.