Data-driven trial feasibility with a knowledge graph

Feasibility is one of the most critical steps in drug development. Before a clinical trial even begins, pharmaceutical companies must evaluate whether their study is realistically achievable: Can the right patients be recruited? Are the necessary sites available and qualified? Will timelines and budgets hold up under real-world conditions?

Traditionally, feasibility assessments have been slowed down by fragmented, siloed data. Patient demographics might be in one system, investigator experience in another, and regulatory considerations in yet another. Teams often spend weeks or months trying to piece together insights from scattered spreadsheets, reports, and databases—only to discover gaps or conflicting information. This leads to longer timelines, higher costs, and the risk of underperforming sites. What’s missing isn’t data, but the ability to connect data in context to drive better decisions.

In this blog post, we’ll explore why traditional feasibility methods struggle to keep pace with today’s complex trials, and how knowledge graph technology offers a smarter path forward. By connecting siloed datasets into a unified, contextual view, knowledge graphs enable feasibility teams to shift from conducting manual data gathering to insight-driven analyses and processes. We’ll also look at how ONTOFORCE’s DISQOVER platform empowers pharmaceutical companies to scale this capability across feasibility and beyond—helping teams ask better questions of their data, make smarter decisions faster, and ultimately increase the likelihood of trial success.

Feasibility data silos, knowledge gaps, and manual efforts

Pharma companies already have a wealth of data relevant to feasibility: internal performance records, trial registries, investigator profiles, electronic health records, patient registries, and country-level intelligence. The problem is that these data live in disconnected silos, such as spreadsheets, databases, and reports that don’t talk to each other.

As a result, feasibility teams spend far more time collecting and reconciling information than analyzing or acting on it. By the time datasets are merged, cleaned, and formatted for use, the insights may already be outdated. And, even when the data is accessible, it might be incomplete, inconsistent, or outdated, making it hard to form a trustworthy, holistic view.

Moreover, feasibility isn’t just about compiling data and making reports. It’s about enabling decisions that result in success:

• Can the right patients be recruited in the right geographies?
• Do the available sites have the necessary staff, infrastructure, and investigator expertise?
• Will regulatory and country-level conditions support the trial’s requirements?
• Can timelines and budgets hold up under real-world conditions?

Without actionable insights to answer these questions, feasibility risks becoming a checkbox exercise. What’s needed is a way to turn disparate data into connected knowledge that directly informs action.

Knowledge graphs connecting data for trial feasibility insights

Knowledge graph technology offers a way forward. Instead of storing data in isolated silos, knowledge graphs connect datasets into a single, navigable web of relationships. This allows feasibility leaders to explore how patients, sites, investigators, and operational factors relate to each other in context.

Consider a few real-world examples:

• Patient recruitment potential
  Instead of only looking at disease prevalence statistics, a knowledge graph can link patient demographics from real-world data with eligibility criteria from past protocols, showing where the right patients are likely to be found—and where eligibility might become a barrier.
• Investigator and site capabilities
  Beyond basic trial participation history, knowledge graphs reveal how investigator expertise, site performance, and available infrastructure. For example, a site may have high enrollment rates but limited staff capacity for a more complex protocol. That insight is only visible when the data is connected.
• Country-level readiness
  Feasibility often hinges on country-specific factors: regulatory timelines, technology availability, and even standards of care. By linking regulatory intelligence with site and patient data, knowledge graphs can shed light on which geographies are most aligned with trial requirements.

The result is a shift from feasibility as a manual, report-driven process to feasibility as an insight-driven exploration. Instead of asking, “What data do we have?” teams can ask, “What decisions can we make with this connected knowledge?”

Powering trial feasibility with DISQOVER

DISQOVER is ONTOFORCE’s flagship product operating on knowledge graph and semantic search technology, built exclusively for the life sciences industry. DISQOVER integrates diverse data sources and makes them accessible through an intuitive user interface. Users can search, explore, and filter data with intuitive query building and visual filtering tools, seamlessly connecting different semantic types and data sources in a single view.

DISQOVER gives feasibility teams what traditional systems cannot: a connected, dynamic view of trial feasibility that spans patients, sites, investigators, and countries. Rather than functioning as a static “site feasibility tool,” DISQOVER is a knowledge graph platform where feasibility analyses can be run with speed, precision, and scalability.

Here’s how:

All data in one place
Imagine a feasibility lead preparing to evaluate an oncology trial. Instead of juggling spreadsheets, clinical trial registries, internal performance reports, and external databases, DISQOVER brings them together in a single interface. Patient prevalence, investigator track records, site enrollment histories, and regulatory considerations are all accessible in one platform, so time isn’t wasted switching between systems.

Complex questions answered in real time
A feasibility strategist might need to confirm: “Do we have enough eligible patients in Germany, given the protocol’s biomarker requirements, and which investigators there have the right expertise?” With DISQOVER, the answer isn’t buried in multiple databases. Through intuitive querying in the DSIQOVER interface, the strategist can instantly combine patient-level insights with investigator and site performance data to arrive at a clear, contextualized answer in minutes.

Here are some real example queries that are answerable in DISQOVER:

“Which clinical sites were involved in studies recruiting patient population​ with JAK2 V617F mutation and for myeloproliferative diseases?”

“What recruitment rates do historical studies have with my eligibility criteria and which alternative criteria do they suggest for better population coverage?”​

"Which sites participated in phase 3 Clinical Studies on Cystic Fibrosis that have proven recruitment for patients with CFTR mutations?"

Continuous refinement through live data
Trial feasibility isn’t static. As questionnaire responses come in from sites, or as trial registries update with new studies, the feasibility picture evolves. DISQOVER allows for seamless data updates that can be made available to users in near real-time.

Trusted, compliant intelligence
ONTOFORCE experts curate and update 82 relevant public datasets weekly, ensuring feasibility assessments are always based on the latest information. At the same time, DISQOVER maintains data provenance and applies advanced security standards, so teams can explore sensitive internal and external data confidently and compliantly.

In practice, this means feasibility leaders can stop drowning in fragmented reports and start making smarter, faster decisions about:

• Which patients can realistically be recruited, and where.
• Which investigators and sites are best aligned to the protocol.
• Which countries provide the most operationally viable path forward.
• How to reduce risks and improve the likelihood of successful execution.

A scalable, future-proof approach to feasibility and beyond

As trials become more complex with targeted therapies, rare disease indications, adaptive designs, and more, the feasibility challenge only intensifies. Manual spreadsheets and disconnected reports can’t keep pace with the demands of modern R&D.

Knowledge graphs provide the scalable, future-proof foundation feasibility leaders need. By connecting data at scale, they make it possible to handle increasing complexity without sacrificing accuracy or speed.

With DISQOVER, pharma companies gain more than just a platform—they gain an enterprise-wide capability to run feasibility assessments and other critical analyses and applications at scale. This foundation enables teams to ask smarter questions, make faster decisions, and improve the likelihood of research and trial success.