The Danish Lymphoid Cancer Research (DALY-CARE) Data Resource: The Basis for Developing Data-Driven Hematology

Area of Science:

• Hematology
• Oncology
• Medical Artificial Intelligence (mAI)

Background:

• Lymphoid-lineage cancers (LC) share epidemiological and clinical features, making them suitable for meta-learning in medical AI.
• Limited access to large, shared datasets hinders medical AI research in LC.

Purpose of the Study:

• To create a large-scale data repository for patients with LC to facilitate data-driven hematology research.
• To develop a comprehensive data resource for Danish LC Research (DALY-CARE).

Main Methods:

• Gathered electronic health data from 10 nationwide registers, EHR, and laboratory data for Danish adults diagnosed with LC since 2002.
• Developed open-source processing pipelines and a secure cloud-based research environment for DALY-CARE.
• Included extensive data on treatments, diagnoses, procedures, and survival for 65,774 LC patients.

Main Results:

• The DALY-CARE resource integrates diverse data types, including treatments, comorbidities, pathology, and survival data for a large LC cohort.
• Demonstrated the utility of DALY-CARE for molecular studies, real-world evidence evaluation, and mAI development.
• Established a secure research environment on a high-powered cloud computer.

Conclusions:

• The DALY-CARE data resource supports the development of real-time decision-support tools for LC patient care.
• Facilitates extrapolation of clinical trial results to clinical practice, improving LC patient outcomes.
• Streamlines health data infrastructure across different cohorts and medical specialties.