Dr. Enrique Grande discusses how better use of clinical data can improve cancer care, support scientific progress, and strengthen evidence-based decision-making in oncology.
In Spain, as in many healthcare systems, oncology is becoming increasingly data-rich, yet much of this information remains fragmented, unstructured, and underutilized. As cancer care evolves toward more personalized and biomarker-driven approaches, the need for better data integration and standardization is becoming critical to both clinical practice and research.
In this interview, Dr. Enrique Grande shares his perspective on the current state of oncology data in Spain, the challenges clinicians face in documentation and data usability, and the opportunities to bridge clinical care with real-world evidence generation. He also explores how artificial intelligence, and smarter digital infrastructures can help transform routine data into meaningful insights, supporting more informed decisions and a more connected oncology ecosystem.
The Evolving Oncology Data Landscape
Oncology has become one of the most data-intensive medical specialties. How would you describe the current state of oncology data collection in routine clinical practice in Spain?
I believe this is a challenge that goes far beyond Spain, it is a global reality. Oncology generates an extraordinary amount of data every single day, but much of it is still fragmented, unstructured, and difficult to reuse. In routine clinical practice, physicians prioritize what matters most: taking care of the patient in front of them. However, this often comes at the cost of data consistency and structure. As a result, we are sitting on an immense volume of valuable information that is not yet fully leveraged. The opportunity ahead is enormous. If we can transform routine clinical data into structured, high-quality datasets, we will not only improve research but also enhance clinical decision-making in real time. That is where I believe the true revolution lies.
What are the biggest differences between data collected for clinical care and data required for research and real-world evidence generation?
Clinical care data is primarily narrative and focused on immediate decision-making, it tells the story of the patient. Research data, on the other hand, requires precision, consistency, and reproducibility. The challenge is that these two worlds have traditionally evolved in parallel rather than together. What we need is not to replace one with the other, but to bridge them. The future lies in systems that allow clinicians to document naturally while simultaneously generating structured, research-ready data in the background. This is where artificial intelligence can play a transformative role.
Why is structured and standardized data increasingly critical in modern oncology?
Because oncology is becoming increasingly complex and personalized. We are no longer treating diseases; we are treating molecularly defined subgroups of patients. Without structured data, it becomes almost impossible to identify patterns, measure outcomes, or learn at scale. Standardization is not about limiting clinical freedom, it is about enabling collective intelligence. It allows us to move from isolated decisions to data-driven, evidence-informed care across institutions and even countries.
Documentation Practices and Data Quality
How does variability in documentation styles between physicians’ impact data usability for research purposes?
It has a major impact. Every physician develops their own way of documenting clinical information, which is completely natural. However, from a data perspective, this variability creates noise and limits comparability. Two clinicians may describe the same clinical situation in completely different ways, making it very difficult to extract reliable insights retrospectively. This is not a criticism; it reflects the human side of medicine. But it also highlights why we need supportive tools that help harmonize data without interfering with the physician–patient interaction.
What are the most common gaps you observe in oncology records when data are later analysed retrospectively?
The most frequent gaps are not necessarily about missing data, but about incomplete structure. Key elements such as performance status, treatment sequencing, toxicity grading, or reasons for treatment decisions are often documented in free text rather than in a standardized format. Another important gap is longitudinal consistency in the sense that data may be captured at one time point but not systematically followed over time. These limitations make retrospective analysis challenging and sometimes introduce bias. Addressing them is essential if we want real-world data to reach its full potential.
Biomarkers, Molecular Testing, and Integration
Biomarker-driven treatment decisions are now central to oncology. How well integrated is biomarker information into routine clinical documentation?
We have made significant progress, but integration is still far from optimal. Biomarker data often resides in separate systems or parts of the electronic medical records like pathology reports, molecular platforms, or external laboratories, and is not always seamlessly incorporated into the clinical record. Yet, biomarkers are now at the core of decision-making. The next step is true integration: ensuring that molecular data is not only available, but also structured, longitudinally tracked, and clinically actionable. This is an area where digital transformation and AI can truly make a difference.
Clinical Trials and Real-World Data
Do you believe real-world evidence can meaningfully complement randomized clinical trials in oncology? In what situations?
Absolutely. Randomized clinical trials remain the gold standard since they provide the highest level of evidence under controlled conditions. However, they do not always reflect the complexity of real-life patients. Real-world evidence helps us understand how treatments perform in broader, more heterogeneous populations, including those often underrepresented in trials like elderly or frail patient populations, relevant comorbidities like cardiovascular concomitant diseases, patients with HIV, etc. It is particularly valuable in areas such as treatment sequencing, long-term outcomes, and safety in daily practice. The key message is not “trials versus real-world data,” but rather how both can work together to provide a more complete picture.
Standardization and Digital Infrastructure
How important is the implementation of unified templates or standardized documentation frameworks in oncology?
It is essential but it needs to be done thoughtfully. If standardization becomes a burden, it will fail. I think that if it becomes an enabler, it will transform practice. The goal is to design systems that integrate naturally into clinical workflows, reducing administrative burden while improving data quality. At One Oncology Madrid Program, we are actively working on this balance, combining standardized pathways with flexibility, always keeping the patient at the centre.
Cultural and Institutional Change
What incentives or structural changes could encourage physicians to adopt more structured documentation practices?
The most powerful incentive is to show value. If clinicians see that better documentation leads to better care, more efficient workflows, or access to innovation, adoption will follow. We also need institutional support, investment in digital infrastructure, training, and a cultural shift that recognizes data as a key asset in healthcare. Importantly, this transformation should not be imposed but it should be co-created with clinicians.
The Future of Oncology Data
Looking ahead five to ten years, how do you envision the oncology data ecosystem evolving?
I envision a more connected, intelligent, and patient-centred ecosystem. Data will flow seamlessly across platforms, enriched by AI to support clinical decisions in real time. Physicians will spend less time documenting and more time with patients. We will move towards truly learning healthcare systems, where every patient contributes to knowledge, and every new insight rapidly translates into better care. At the same time, we must ensure that this transformation is built on trust, respecting data privacy, ethical standards, and the human dimension of medicine. Ultimately, technology should not replace the physician moreover it should empower us to be better for our patients. That is the future I strongly believe in.
Dr. Enrique Grande, MD, PhD, Msc, is an internationally recognized medical oncologist with 20 years of experience. Currently he serves as the Director of ONE ONCOLOGY MADRID Cancer Program at QuirónSalud, the largest private hospital network in Spain.
His clinical research focuses on genitourinary oncology. He has authored more than 300 publications as well as contributed to international guidelines, scientific committees and educational programs at ESMO & ASCO. Also, he is the adjunct professor at the university of Texas MD Anderson Cancer center, and he wants to search for innovation ways to reinvent the oncology in Spain.
A major pillar of his recent work is AI applied to oncology being the key investigator of DIPCAN, a large-scale AI driven precision oncology project funded in the European Commission. This reflects his strong commitment to AI as transformative tools to improve clinical decision making, research efficiency and healthcare systems.
