Artificial intelligence and chordoma: A scoping review of the current landscape and future directions
Bibliographic record
Abstract
Introduction: Chordomas are rare, locally aggressive tumours that present significant treatment challenges due to their proximity to critical neurovascular structures. Artificial intelligence (AI) methodologies have shown promise in enhancing diagnostic precision, surgical planning, and prognostication in various cancers. Research question: What is the current landscape of AI applications in chordoma management, and what are the key limitations and future directions for integrating AI into clinical practice for this rare malignancy? Materials and methods: We conducted a scoping review following the PRISMA-ScR guidelines and the Arksey and O'Malley framework. A search of five databases with an end date of November 9, 2024, identified peer-reviewed studies assessing AI or machine learning applications in chordoma management. Data extraction focused on study characteristics, methodologies, clinical tasks, and performance metrics. Results: Twenty-one studies published between 2017 and 2024 were included, encompassing 5486 patients. The studies addressed diverse clinical tasks: 7 focused on differentiating chordomas from other tumours or classifying subtypes, 6 on survival prediction, 2 on tumour segmentation, 2 on outcome prediction, and 4 miscellaneous tasks. Common algorithms used included convolutional neural networks, support vector machines, random forests, and clustering algorithms. Limitations identified across studies included small sample sizes, single-center data, reliance on single data modalities, and issues with model interpretability. Discussion and conclusion: AI applications in chordoma management show potential in improving diagnostic accuracy, surgical planning, and prognostication. Future research should focus on collaborative efforts for larger, diverse datasets with external validation cohorts, interpretable multimodal models, and validation through prospective clinical trials.
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 | 0.082 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.004 | 0.005 |
| Bibliometrics | 0.024 | 0.023 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.006 | 0.005 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.004 | 0.003 |
| 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".