Key Takeaways
- Most oncology data remains unstructured and underutilized, limiting its impact on precision oncology and clinical research.
- Structured real-world data (RWD) is essential for clinical decision-making, reimbursement, and regulatory alignment.
- AI in oncology is already enabling regulatory-grade real-world evidence (RWE) at national scale.
- Spain has the expertise to lead in healthcare AI and oncology data structuring.
- At Sqilline Health, we see healthcare AI as a structured maturity journey from Raw Clinical Documents to Curated Real-World Data and Validated Real-World Evidence
ECO DEBATES 2026: A Strategic Forum for AI in Oncology
ECO DEBATES 2026 in Madrid brought together leading oncologists to debate advances in cancer diagnosis, treatment sequencing, biomarkers, and immunotherapy. The workshop addressed major oncology indications including breast cancer, lung cancer, tumours of the digestive system, and genitourinary malignancies.
As oncology becomes increasingly driven by molecular profiling and targeted therapies, the importance of structured clinical data and real-world evidence continues to grow. Clinical decisions today require not only randomized trial results but also high-quality real-world data analytics.
Sqilline Health participated in the special session:
“Inteligencia Artificial en Oncología: Herramientas para transformar la práctica clínica, la investigación y la comunicación científica.”
The session focused on how healthcare AI can transform fragmented oncology data into structured, regulatory-grade evidence.
The Structural Challenge: Why Oncology Data Remains Underused
Despite rapid advances in precision oncology, up to 90% of healthcare data remains unused for advanced analytics.
Key structural challenges include:
- Unstructured electronic health records (EHRs)
- Free-text clinical documentation
- Fragmented hospital systems
- Missing variables across datasets
- Limited interoperability
This lack of oncology data structuring creates bottlenecks in:
- Real-world evidence generation
- Clinical trial recruitment
- Clinical outcomes observation tracking
- Regulatory submissions
- Health technology assessment (HTA)
The issue is not data scarcity. It is lack of structured, harmonized data.
From Unstructured Records to Regulatory-Grade Real- World Evidence
At ECO DEBATES, Sqilline Health presented its structured approach to AI-powered oncology data transformation.
The Data Maturity Journey in Oncology
Unstructured → Processed → Validated → Actionable
Through proprietary AI models, Sqilline Health:
- Ingests oncology data in any format (clinical text, scanned reports, PDFs).
- Automatically anonymizes and de-identifies data in full GDPR compliance.
- Structures data using harmonized standards such as the OMOP Common Data Model.
- Enables advanced clinical data analytics, including survival analysis and multicentre benchmarking.
The result is regulatory-grade real-world evidence suitable for research publications, reimbursement discussions, and policy decision-making. Sqilline Health’s Danny Platform has been recognized by the European Medicines Agency and is included in the EMA RWD Catalogues.
This approach positions AI in oncology not as an experimental add-on, but as core infrastructure.
Real-World Data at National Scale: Evidence in Practice
Sqilline Health demonstrated how structured oncology data can generate validated real-world evidence through nationwide studies.
Examples include better to provide the links to the publications, not to add additional information
Breast Cancer Real-World Evidence
- Nationwide HR+/HER2- advanced breast cancer cohort
- Real-world progression-free survival comparable to pivotal clinical trials
- Structured EHR data across 57 hospitals
Melanoma Real-World Analytics
- National BRAF-positive melanoma study
- Comparable or favourable outcomes versus RCT benchmarks
Validation of targeted therapies in routine practice
Lung Cancer Pathway Optimization
- Nationwide study across multiple regions
- Analysis of stage at diagnosis and time-to-treatment
- Identification of regional disparities in care delivery
These studies demonstrate the power of AI-driven oncology data structuring to support precision oncology and health system optimization.
Discussion: Impact of Healthcare AI Across the Oncology Ecosystem
AI in Clinical Research and RWE Generation
- Automated cohort creation
- Sponsor-ready datasets
- Accelerated publication workflows
- Survival and outcomes analytics
AI in Clinical Practice
- Guideline adherence benchmarking
- Optimization of treatment sequencing
- Reduction of diagnostic delays
- Quality improvement programs
AI in Clinical Trials
- Data-driven site selection
- Faster patient identification
- Reduced recruitment timelines
- Digital enrolment workflows
Structured oncology intelligence improves both patient outcomes and research efficiency.
Strategic Vision: Structured Oncology Data as National Infrastructure
Spain has the clinical expertise and scientific credibility to lead in AI-powered oncology.
Sqilline Health and Fundación ECO share a strategic commitment to:
- Promote structured oncology data as a national priority
- Establish governance frameworks and measurable KPIs
- Define quality and validation standards for real-world evidence
- Foster trusted public–private collaboration in healthcare AI
Sqilline is not offering a standalone software solution.
It is enabling infrastructure-level transformation for oncology data analytics.
The Future of AI in Oncology: From Debate to Execution
The discussions at ECO DEBATES confirmed a structural reality:
- Precision oncology requires structured data.
- Regulators increasingly demand real-world evidence.
- Healthcare systems need harmonized oncology intelligence.
The technology is ready.
The evidence is proven.
The need is structural.
Sqilline Health invites oncology institutions, researchers, policymakers, and life sciences partners to collaborate in building regulator-grade oncology data infrastructure in Spain and across Europe.
