Large language models in oncology: a review
Bibliographic record
Abstract
Large language models (LLMs) have demonstrated emergent human-like capabilities in natural language processing, leading to enthusiasm about their integration in healthcare environments. In oncology, where synthesising complex, multimodal data is essential, LLMs offer a promising avenue for supporting clinical decision-making, enhancing patient care, and accelerating research. This narrative review aims to highlight the current state of LLMs in medicine; applications of LLMs in oncology for clinicians, patients, and translational research; and future research directions. Clinician-facing LLMs enable clinical decision support and enable automated data extraction from electronic health records and literature to inform decision-making. Patient-facing LLMs offer the potential for disseminating accessible cancer information and psychosocial support. However, LLMs face limitations that must be addressed before clinical adoption, including risks of hallucinations, poor generalisation, ethical concerns, and scope integration. We propose the incorporation of LLMs within compound artificial intelligence systems to facilitate adoption and efficiency in oncology. This narrative review serves as a non-technical primer for clinicians to understand, evaluate, and participate as active users who can inform the design and iterative improvement of LLM technologies deployed in oncology settings. While LLMs are not intended to replace oncologists, they can serve as powerful tools to augment clinical expertise and patient-centred care, reinforcing their role as a valuable adjunct in the evolving landscape of oncology.
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 | 0.002 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.003 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| 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".