Abstract B060: DIGIONE: From Fragmentation to Federation: Enabling Scalable Oncology RWE (Real World Evidence) through an international hospital based Cancer OMOP (Observational Medical Outcomes Partnership) Network
Bibliographic record
Abstract
Abstract Real-world evidence in oncology today is largely “one question, one dataset” — and as a highly bespoke, slow, and fragmented. Pharma and academic teams have to stitch together disparate sources (such as registries or research cohorts) for each new regulatory, HTA (Health Technology Assessment) submission or AI development, with little scope for automation or reuse. This is because clinical registries and cohorts today remain siloed and driven by manual retype, and so lack alignment on common data models and paths to automation. This is strongly hampering the wide spread application of AI-driven RWE models at the international level. DIGICORE (Digital Institute for Cancer Outcome Research) is changing this by operationalising a pan-European hospital network with high quality real-world cancer data mapped to the Cancer OMOP model. A core enabler of this work is the development of MEDOC – a Minimal European Description of Caner agreed by international consensus as essential to the delivery of good cancer care. Over 20 hospitals have already mapped their EHR (Electronic Health Record) data to deliver MEDOC—covering demographics, clinical phenotype, biomarker, treatment activity, and pragmatic outcomes —enabling multi-country cohort assembly using shared protocols, with high data completeness from local NLP. Advanced analytics take OMOP tools from meta-analysis to patient level equivalence. We call this technology network DigiONE – the Digital Oncology Network for Europe. Disease Natural History and care quality assessment studies in Lung, Breast, and Colorectal cancer are already underway on large cohorts, with hospital readiness assessed through real study execution. To date, three projects have been completed, with additional 10 projects underway. Project 1: Analysis of the number of new primary cancers diagnosed and 12-month survival changes during COVID-19 lockdowns (124.682 patients). Primary Objectives: To Investigate the impact of COVID19 lockdowns on new cancer diagnoses. To estimate 12-month survivals. Project 2: A disease natural history and outcomes study with care quality assessment in metastatic non-small cell lung cancer (1294 patients). Primary Objectives: To investigate the survival of patients according to the location of the metastases. To describe treatment patterns by line of therapy prescribed to patients: All the cohort, Subgroups by locations of the metastases (oligometastatic cohort). To benchmark care quality between centers based on ESMO (European Society of Medical Oncology) recommendation. Project 3: A disease natural history and outcomes study with care quality assessment in HR+/HER2- metastatic breast cancer (5k-10k patients). Primary Objectives: To Describe the demographic, clinical, molecular phenotypes, and next-generation sequencing (NGS) results for patients with HR+/HER2− metastatic breast cancer (mBC). Citation Format: Alberto Traverso, Piers , Xose' Fernandez, Golbahar Pahlavan, Giovanni Tonon. From Fragmentation to Federation: Enabling Scalable Oncology RWE (Real World Evidence) through an international hospital based Cancer OMOP (Observational Medical Outcomes Partnership) Network [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Artificial Intelligence and Machine Learning; 2025 Jul 10-12; Montreal, QC, Canada. Philadelphia (PA): AACR; Clin Cancer Res 2025;31(13_Suppl):Abstract nr B060.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.033 | 0.066 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.004 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.008 | 0.010 |
| Open science | 0.003 | 0.017 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.024 | 0.012 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".