Key Takeaways
- Most hospitals still lack structured oncology data, which limits their ability to apply AI, analytics, and real-world evidence in practice
- The core barrier is not AI. It is unstructured and fragmented clinical data, which prevents meaningful use of existing information
- There is clear consensus among experts that data structuring is essential for research, collaboration, and improving clinical outcomes
- Hospitals are prioritizing quality, benchmarking, and decision-making, rather than technology adoption alone
- The most effective path forward is pilot, validate, then scale, shifting data initiatives from perceived cost to strategic investment
- The challenge is no longer conceptual. It is execution
The uncomfortable truth: oncology is data-rich, but insight-poor
Across Europe, oncology generates vast amounts of clinical data every day, from electronic health records to registries, imaging, and treatment outcomes. Yet, despite this large quantity, most hospitals still struggle to translate data into actionable insights.
The recent ECO Advisory Board report on Big Data in Oncology highlights a critical gap: most hospitals still lack a structured oncology database, and most have very limited ability to extract usable data from clinical systems. This is not a technology gap. It is a data readiness gap.
The real bottleneck: unstructured clinical data
For years, the conversation around innovation in oncology has focused on artificial intelligence. But the report makes something clear: AI is not the problem. The data is.
Most oncology data today is:
- Fragmented across systems
- Locked in free-text clinical notes
- Not standardized or interoperable
Without structured, high-quality data, even the most advanced AI models cannot deliver meaningful outcomes. This is why the transformation of unstructured clinical data into usable Real-World Data (RWD) is emerging as the foundational step for any digital oncology strategy
The experts already agree on the solution
One of the most important findings from the report is the level of consensus across experts:
- AI-based data structuring would help maintain oncology registries
- Structured data is essential for research and collaboration
This is no longer a debate. The question is not whether to structure data. It is how fast healthcare systems can implement it.
Hospitals are not chasing AI. They are chasing control
While AI often dominates headlines, hospitals are driven by more immediate and practical needs. According to the report:
- They prioritize quality indicators and benchmarking as the primary objective
- They highlight the importance of interoperable national databases
This reflects a fundamental shift. Healthcare organizations are not investing in AI for innovation’s sake. They are investing in data to improve clinical quality, transparency, and decision-making.
Real-World Data: the bridge between care and research
Structured data unlocks the true potential of Real-World Data (RWD), which includes data collected routinely from clinical practice such as EHRs, registries, and administrative systems. When properly structured and standardized, RWD enables:
- Evidence generation beyond clinical trials
- Faster patient recruitment for studies
- Continuous outcome monitoring
- More personalized treatment strategies
Without structuring, this data remains inaccessible, limiting both clinical and research progress.
What actually works: from pilots to scale
The ECO report does not just describe the problem. It outlines a pragmatic path forward. Successful transformation follows a clear pattern:
- Start with controlled pilot projects
- Build through public-private collaboration
- Invest in clinical training and adoption
- Demonstrate early value through measurable outcomes
This approach changes perception. Technology stops being seen as a cost and becomes a strategic investment once impact is demonstrated.
Beyond efficiency: building data-driven oncology systems
The real impact of data transformation goes beyond operational improvements. According to the report, data-driven hospitals:
- Enable better clinical decision-making
- Strengthen research capabilities
- Participate more effectively in European initiatives
- Attract talent and investment
In this context, data maturity becomes a competitive advantage. Hospitals that fail to build data capabilities risk falling behind, not only technologically, but also clinically and strategically.
The roadmap is clear. Execution is the challenge
The ECO Advisory Board delivers a clear strategic direction:
- Establish strong data governance
- Adopt interoperability standards such as FHIR and OMOP
- Ensure data quality and traceability
- Deploy solutions progressively through pilots
- Continuously validate outcomes
The conclusion is undisputable. The challenge is no longer conceptual. It is executional.
Sqilline Health: enabling the data foundation for oncology
At Sqilline Health, we believe that the future of oncology does not start with AI. It starts with data readiness. Our approach focuses on:
- Transforming unstructured clinical data into structured, interoperable formats
- Enabling scalable Real-World Evidence generation
- Supporting hospitals in building sustainable data infrastructures
- Accelerating the transition from pilots to system-wide impact
By addressing the foundational layer, data structuring, we enable healthcare systems to unlock the full value of AI, research, and precision medicine.
Final thought: from data to decisions
Oncology does not lack data. It lacks the ability to use it effectively. The path forward is clear:
- Structure the data
- Connect the systems
- Generate real-world evidence
- Enable better decisions
Those who move first will not just adopt new technologies.
They will redefine how oncology care is delivered, measured, and improved.
Q&A: Big Data in Oncology
What is the biggest challenge in oncology data today?
The main challenge is not the lack of data, but the lack of structured and interoperable data. Most hospitals still rely on fragmented and unstructured clinical records.
Why do AI projects in hospitals often fail?
AI depends on high-quality, structured data. Without it, outputs are unreliable and adoption by clinicians is limited.
What is Real-World Data (RWD) in oncology?
RWD refers to data collected from routine clinical practice, such as EHRs, registries, and claims, which can be used for research and decision-making when properly structured.
How can hospitals start becoming data-driven?
The most effective approach is:
- Start with pilot projects
- Structure raw clinical data
- Implement governance models
- Scale based on validated results
Why is data structuring important for clinical trials?
Structured data enables faster identification of eligible patients, improves data quality, and accelerates trial recruitment and execution.
What role does interoperability play in oncology?
Interoperability allows different healthcare institutions to exchange and use data effectively, enabling collaboration, benchmarking, and large-scale research initiatives.
How does Sqilline Health support this transformation?
Sqilline Health enables hospitals to convert unstructured clinical data into structured, interoperable formats, unlocking real-world evidence and supporting data-driven oncology care.
