FHIR Standard–Based Oncology Data Model for Cancer Screening: Design and Implementation Study
Bibliographic record
Abstract
BACKGROUND: Cancer is a leading cause of death worldwide. Early detection through screening, diagnosis, and effective management can reduce cancer mortality. Risk assessment is crucial for improving outcomes by identifying high-risk individuals based on family history, genetics, lifestyle, and environment. Such targeted screening enhances accuracy and resource efficiency. However, the complex nature of oncology data-which includes clinical observations, lab results, radiology images, treatment regimens, and genetic information-presents significant challenges for data interoperability and exchange. OBJECTIVE: This study proposes an oncology data model (ODM) based on the Fast Healthcare Interoperability Resources (FHIR) standard to facilitate the capturing, sharing, and processing of oncology data across various cancer care stages. We particularly focused on screening and risk assessment for 5 cancers: breast, cervical, esophageal, lung, and oral, within the Meghalaya Fourth Industrial Revolution for Sustainable Transformation Cancer Care pilot project in India. METHODS: The ODM incorporates data elements from a cancer patient's journey across 5 phases: encounter, risk assessment, clinical investigation, treatment, and outcome. Essential oncology data elements were modeled using the Health Level 7 FHIR Revision 4 standard. Custom FHIR profiles were developed for cancer-specific use cases, with terminology mapped to Systematized Nomenclature of Medicine-Clinical Terms, Logical Observation Identifiers Names and Codes, and the International Classification of Diseases, 10th Revision. The implementation guide (IG) was created using FHIR Shorthand, SUSHI Unshortens Short Hand Inputs, and the Health Level 7 IG Publisher. Technical and clinical validation and a stakeholder usability assessment were conducted using a demonstration tool designed for implementer training and adoption. RESULTS: The data model enhances interoperability across the cancer care continuum, from screening to treatment. The resulting IG includes 25 oncology-specific resource profiles and 50 standardized terminology value sets that support both semantic and syntactic interoperability. Central to the model are the FHIR Questionnaire and QuestionnaireResponse resources, customized for structured data collection in clinical and community settings, supporting cancer screening workflows. Technical validation yielded FHIR conformance and terminology binding, while clinical validation by oncologists and public health experts confirmed the usability and relevance of 5 screening questionnaires. The demonstration tool promoted stakeholder engagement and practical evaluation of the FHIR profiles. CONCLUSIONS: The FHIR-based ODM offers a unified framework for structured, interoperable cancer data exchange from screening to after treatment. This study marks the first comprehensive Indian initiative to apply FHIR standards for oncology screening and risk assessment. Integrating with national digital health systems, like the Ayushman Bharat Digital Mission, can ensure consistent data sharing across screening programs, hospitals, and registries. Future work will focus on real-world model deployment, evaluation in multiple districts, expanding to treatment and survivorship data, and promoting national adoption to inform cancer policy, research, and precision oncology efforts.
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 | 0.019 | 0.025 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 0.001 |
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".