Artificial intelligence in nuclear cardiology: Technical perspectives, strategic directions, and recommendations from an IAEA expert working group
Bibliographic record
Abstract
Artificial intelligence (AI) is increasingly permeating nuclear cardiology and offers the possibility to enhance diagnostic accuracy, prognostic stratification, and operational efficiency. AI is demonstrating applicability across the imaging workflow-from individualized patient selection and adaptive image reconstruction to denoising of low-dose datasets, automated attenuation and motion correction, calcium scoring, and the integration of imaging with clinical and functional variables for enhanced diagnosis and comprehensive risk assessment. But the translational trajectory of AI in nuclear cardiology is challenged by the lag in fundamental AI knowledge among researchers and clinicians, the quality of the target data regarding heterogeneity in acquisition protocols, scanner platforms, and patient populations, and by infrastructural disparities that constrain the generation of large, representative datasets needed for training and validation, particularly in low-resource settings. Additionally, necessary regulatory and legal frameworks remain in early stages of harmonization. This white paper, developed by an International Atomic Energy Agency (IAEA) working group, provides a succinct overview of the technical basis, areas of deployment, clinical value and unmet challenges of AI in nuclear cardiology. It makes punctual suggestions to aid maturation in this area while maintaining a sober interaction with the overwhelming nature of the field. These include promoting standardized acquisition and reporting practices, establishing globally representative reference datasets, promoting imaging multimodality frameworks and developing AI-proficient clinical and technical personnel. Under these conditions, AI may meaningfully enhance the diagnostic and prognostic value of nuclear cardiology while supporting equitable implementation and preserving clinical accountability.
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 | 0.087 | 0.035 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.004 |
| Science and technology studies | 0.002 | 0.004 |
| Scholarly communication | 0.013 | 0.010 |
| Open science | 0.004 | 0.005 |
| Research integrity | 0.014 | 0.015 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
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".