Review of Large Language Models for Patient and Caregiver Support in Cancer Care Delivery
Bibliographic record
Abstract
This narrative review examines the current landscape and evidence regarding large language model (LLM) applications designed to support patients with cancer and caregivers. We analyzed peer-reviewed literature, conference proceedings, and implementation studies exploring LLM use in oncology patient support. Applications cluster in four primary domains: education and information delivery, symptom checking and triage, telehealth integration, and clinical trial participation. Studies demonstrate promising accuracy for basic cancer information delivery, although performance varies for complex clinical scenarios. Early research shows preclinical feasibility and acceptability of LLM-enhanced tools for patients, but effectiveness data remain limited. Implementation barriers include scalable monitoring, equitable access, maintaining privacy standards, and validating accuracy across diverse populations. We also examine potential future applications across the cancer care continuum, from prevention through end-of-life care, and propose strategies for development and implementation. Additionally, we present a framework to guide physician-patient discussions regarding LLM use in oncology, addressing privacy concerns, setting appropriate expectations, and ensuring safe integration into care delivery. Future research should use robust evaluation frameworks focused on safety and patient-centered outcomes while carefully considering health equity implications. As these technologies evolve, maintaining focus on evidence-based validation will be crucial for realizing their potential to enhance cancer care delivery, engagement, and patient satisfaction.
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 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.003 | 0.001 |
| 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 | 0.001 |
| 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".