Role of artificial intelligence in imaging and endoscopy for the diagnosis, monitoring and prognostication of inflammatory bowel disease: a scoping review protocol
Bibliographic record
Abstract
INTRODUCTION: Inflammatory bowel diseases (IBD) are immune-mediated conditions that are increasing in incidence and prevalence worldwide. Their assessment and monitoring are becoming increasingly important, though complex. The best disease control is achieved through tight monitoring of objective inflammatory parameters (such as serum and stool inflammatory markers), cross-sectional imaging and endoscopic assessment. Considering the complexity of the information obtained throughout a patient's journey, artificial intelligence (AI) provides an ideal adjunct to existing tools to help diagnose, monitor and predict the course of disease of patients with IBD. Therefore, we propose a scoping review assessing AI's role in diagnosis, monitoring and prognostication tools in patients with IBD. We aim to detect gaps in the literature and address them in future research endeavours. METHODS AND ANALYSIS: We will search electronic databases, including Medline, Embase, Cochrane CENTRAL, CINAHL Complete, Web of Science and IEEE Xplore. Two reviewers will independently screen the abstracts and titles first and then perform the full-text review. A third reviewer will resolve any conflict. We will include both observational studies and clinical trials. Study characteristics will be extracted using a data extraction form. The extracted data will be summarised in a tabular format, following the imaging modality theme and the study outcome assessed. The results will have an accompanying narrative review. ETHICS AND DISSEMINATION: Considering the nature of the project, ethical review by an institutional review board is not required. The data will be presented at academic conferences, and the final product will be published in a peer-reviewed journal.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".