The DOI matches its Crossref record; 77 of the 77 references it cites were found in a registry or an index; 30 of the 40 sources its claims cite were checked for support.
Artificial Intelligence in Oncology: Practical Applications Across Clinical Care, Scholarship, and Translation.
Open accessAbstract
Artificial intelligence (AI) is increasingly integrated into oncology across clinical care, research workflows, and translational implementation. This chapter provides a practical overview of these domains, emphasizing opportunities and limitations relevant to real-world oncology practice. In clinical care, AI applications include ambient documentation systems, decision support tools, and remote monitoring platforms. These technologies may reduce administrative burden, assist with evidence synthesis and guideline navigation, and enable longitudinal assessment of symptoms and functional status through wearable and patient-reported data. Emerging tools such as large language models also support patient communication through education, translation, and symptom triage. However, across these applications, performance remains dependent on data quality, validation, and appropriate clinical oversight. In research and scholarship, AI is increasingly used to support grant development, study design, literature review, and manuscript preparation. These tools may improve efficiency, enhance clarity, and assist in identifying research gaps or methodological approaches. At the same time, concerns regarding accuracy, hallucinated content, data privacy, and ethical responsibility require careful oversight. The responsibility for hypothesis generation, methodological rigor, and scientific integrity remains with the investigator. From a translational perspective, a persistent gap exists between model development and clinical deployment. Differences in data quality, infrastructure, and patient populations may limit generalizability, while workflow integration, clinician readiness, and bias mitigation remain critical challenges. Collectively, AI has the potential to enhance oncology care and research, but its impact depends on rigorous validation, equitable implementation, and sustained human oversight.
Overview
CoChat Summary
TL;DR
This ASCO Educational Book chapter provides a practical overview of AI in oncology across clinical care, research and scholarship, and translation, emphasizing opportunities and limitations for real-world practice. It argues that AI may improve workflow efficiency, evidence synthesis, monitoring, and patient communication, but its impact depends on rigorous validation, equitable implementation, and sustained human oversight.
Key findings
- In clinical care, AI applications include ambient documentation, decision support, remote monitoring, wearables, and large language models for patient education, translation, and symptom triage; these may reduce administrative burden and enable earlier detection of treatment-related toxicities, with wearable monitoring demonstrating earlier detection of cytokine release syndrome in CAR T-cell therapy compared with standard clinical assessment.
- In research and scholarship, generative AI may assist with grant development, study design, literature synthesis, manuscript preparation, and IRB applications, but risks include inaccuracy, hallucinated content, data privacy concerns, and ethical responsibility; in summer 2025, NIH grant review administrators reported receiving hundreds of proposals prepared with GenAI assistance, some containing fabricated or inaccurate references.
- A persistent translational gap exists between model development and clinical deployment: curated academic datasets often differ from real-world data, leading to dataset shift, technical/infrastructural mismatches, data quality problems, demographic/clinical/biological differences, workflow integration challenges, and clinician readiness issues.
- Responsible disclosure of AI use is framed as mandatory, optional, or unnecessary depending on whether use is intentional and substantial; mandatory examples include formulating questions or hypotheses, drafting or substantially revising text, translating, analyzing or interpreting data, extracting data for literature review, and generating synthetic data or images.
Methods
- Design: narrative educational chapter/practical overview, not a primary study or systematic review.
- Data or sample: no primary cohort or dataset is analyzed; the chapter draws on cited literature and examples across oncology AI.
- Main analysis: thematic synthesis across clinical care, research and scholarship, and translation, including a table on disclosing AI use in research and writing adapted from Resnik and Hosseini 2025.
Limitations
- The paper states that AI performance depends on data quality, validation, and clinical oversight; it also notes risks of hallucinations, bias, limited generalizability, workflow disruption, variable patient engagement, and heterogeneous or limited evidence for several applications.
- Evident from the text: as a narrative overview, the chapter reports no systematic search strategy, inclusion criteria, formal quality appraisal, or primary data, so its conclusions are illustrative rather than systematically synthesized.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
26 Valid · 3 Not valid · 7 Not checked · 38 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“LLMs can simplify complex medical information, improving patient understanding of diagnoses, treatments, and adverse effects.38,39”
§ Artificial Intelligence in Oncology: Practical Applications Across Clinical Care, Scholarship, and Translation > PRACTICAL APPLICATIONS
What the sources say
- Partly supportedcites [38] sourceExperimental — accuracy not yet measured
The Introduction and Results describe ChatGPT translating radiology reports into patient-friendly language and explaining medical terms, supporting the claim about simplifying diagnostic information. The cited passages do not establish improved patient understanding of treatments or adverse effects; the study evaluates radiology-report translations rather than those topics. Page numbers were not supplied in our copy. (LLM, conf=0.86)
- Not checked — no full text of the sourcecites [39] source
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Pilot and randomized studies have demonstrated improvements in self-efficacy, quality of life, and patient activation.35,36”
§ Artificial Intelligence in Oncology: Practical Applications Across Clinical Care, Scholarship, and Translation > PRACTICAL APPLICATIONS
What the sources say
- Not checked — no full text of the sourcecites [35] source
- Partly supportedcites [36] sourceExperimental — accuracy not yet measured
The Discussion (Principal Findings; page not provided) reports improved self-efficacy and quality of life with AI-TA. It describes greater participation and initiative, but our copy does not report an improvement in patient activation as an outcome. It mentions a prior pilot study without establishing that the pilot demonstrated all three improvements. (LLM, conf=0.88)
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“AI tools may assist with cross-referencing increasingly complex oncology guidelines, particularly when multiple variables must be considered simultaneously.11”
§ Artificial Intelligence in Oncology: Practical Applications Across Clinical Care, Scholarship, and Translation > Abstract
What the sources say
- Partly supportedcites [11] sourceExperimental — accuracy not yet measured
In “Examples of ELCAP type 2 AI systems” (page not available), the paper says LLMs have shown promise in pointing clinicians to the correct guidelines; “Drafting documents” also describes tools that help identify relevant guidelines. It does not specifically say they cross-reference guidelines when multiple variables must be considered simultaneously, so that qualification is not established by our copy. (LLM, conf=0.82)
hedgedstates a possible cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“AI tools may enhance risk stratification by integrating clinical, molecular, and imaging data to generate individualized estimates of recurrence, treatment response, and survival.14”
§ Artificial Intelligence in Oncology: Practical Applications Across Clinical Care, Scholarship, and Translation > Abstract
What the sources say
- Partly supportedcites [14] sourceExperimental — accuracy not yet measured
The Discussion (page unavailable) says AI may analyze genomic, imaging, and clinical data to personalize oncology decisions. The Results describe cancer-risk classification, and the Methods table reports mortality prediction. Our copy does not establish that combining those data produces individualized estimates of recurrence, treatment response, and survival as claimed. (LLM, conf=0.86)
hedgedstates a possible cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“These measures may correlate with quality of life and recovery trajectories.28”
§ Artificial Intelligence in Oncology: Practical Applications Across Clinical Care, Scholarship, and Translation > PRACTICAL APPLICATIONS
What the sources say
- Supportedcites [28] source
The Discussion identifies both quality of life and functional recovery among outcomes associated with wearable-measured physical activity. It also describes associations between wearable data and physical or psychosocial outcomes across phases of cancer care, supporting the claim’s hedged wording. (LLM, conf=0.90)
hedgedstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
26 more claims · 11 with their cited sources checked
Create a free account to see all 74 claims and every source verdict.
- It may state two separate claims as one. 25
- Probably not a substantial claim. 28
Citations
Cites
Dissecting racial bias in an algorithm used to manage the health of populations
Obermeyer, Z., Powers, B., Vogeli, C., & Mullainathan, S. (2019) · Science · doi:10.1126/science.aax2342 · Cited by 7,137
Sensitivity analysis in observational research: Introducing the E-value
VanderWeele, T. J., & Ding, P. (2017) · Annals of Internal Medicine · doi:10.7326/m16-2607 · Cited by 6,350
Decision curve analysis: a novel method for evaluating prediction models
Vickers, A. J., & Elkin, E. B. (2006) · Medical Decision Making · doi:10.1177/0272989x06295361 · Cited by 6,341
Artificial intelligence in healthcare: past, present and future
Jiang, F., Jiang, Y., Zhi, H., Dong, Y., Li, H., Ma, S., Wang, Y., Dong, Q., Shen, H., & Wang, Y. (2017) · Stroke and Vascular Neurology · doi:10.1136/svn-2017-000101 · Cited by 4,837
Using Big Data to Emulate a Target Trial When a Randomized Trial Is Not Available: Table 1.
Hernán, M. A., & Robins, J. M. (2016) · American Journal of Epidemiology · doi:10.1093/aje/kwv254 · Cited by 3,115
Calibration: the Achilles heel of predictive analytics
On behalf of Topic Group ‘Evaluating diagnostic tests and prediction models’ of the STRATOS initiative, Van Calster, B., McLernon, D. J., van Smeden, M., Wynants, L., & Steyerberg, E. W. (2019) · BMC Medicine · doi:10.1186/s12916-019-1466-7 · Cited by 2,650
Implementing Machine Learning in Health Care — Addressing Ethical Challenges
Char, D. S., Shah, N. H., & Magnus, D. (2018) · New England Journal of Medicine · doi:10.1056/nejmp1714229 · Cited by 1,857
Zech, J. R., Badgeley, M. A., Liu, M., Costa, A. B., Titano, J. J., & Oermann, E. K. (2018) · PLOS Medicine · doi:10.1371/journal.pmed.1002683 · Cited by 1,719
Artificial intelligence in digital pathology — new tools for diagnosis and precision oncology
Bera, K., Schalper, K. A., Rimm, D. L., Velcheti, V., & Madabhushi, A. (2019) · Nature Reviews Clinical Oncology · doi:10.1038/s41571-019-0252-y · Cited by 1,698
Shickel, B., Tighe, P. J., Bihorac, A., & Rashidi, P. (2018) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2017.2767063 · Cited by 1,688
Research works printed but not linked: 1
- Quinn R: NIH to Limit AI Use, Cap PI Grant Applications at 6 per Year. Insider Higher Ed. 2025. https://www.insidehighered.com/news/faculty-issues/research/2025/07/22/nih-limit-ai-use-cap-grant-applications-6-year
Cited by
Application of deep learning in prognostic prediction of non-small cell lung cancer
Lun, X. (2026) · Frontiers in Cell and Developmental Biology · doi:10.3389/fcell.2026.1878798
“AI decision support works best when it’s deeply embedded in the EHR, able to pull in both structured and unstructured data, spot missing information, and offer relevant guideline recommendations on the spot (Hundal et al., 2026).”
Metadata
- Authors
- Hundal, J., Veettil, A. A. V., Chung, C., & Hosseini, M.
- Affiliations
- Cleveland Clinic (US)
- The University of Texas MD Anderson Cancer Center (US)
- Northwestern University (US)
- Venue
- American Society of Clinical Oncology Educational Book
- Published
- 2026-06
- Volume
- 46
- Issue
- 3
- Pages
- e517280-e517280
- ISSN
- 1548-8748 (ISSN-L)
- 1548-8756
- OpenAlex
- W7164305352
- Cited by
- 1
- References
- 54
- Citations by year
- 2026: 1
- FWCI
- 1.95
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- American Society of Clinical Oncology Educational Book (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Keywords
- artificial intelligence in oncology, clinical decision support, remote patient monitoring, wearable devices, patient-reported outcomes, large language models, symptom triage, AI-assisted research, manuscript preparation, clinical implementation, model validation, generalizability, algorithmic bias, data privacy, human oversight, administrative burden
- MeSH terms
- Artificial Intelligence, Humans, Medical Oncology, Neoplasms, Translational Research, Biomedical
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Artificial Intelligence in Oncology: Practical Applications Across Clinical Care, Scholarship, and Translation. https://app.cochat.ai/papers/10.1200/edbk-26-517280
- The paper
- Hundal, J., Veettil, A. A. V., Chung, C., & Hosseini, M. (2026). Artificial Intelligence in Oncology: Practical Applications Across Clinical Care, Scholarship, and Translation. American Society of Clinical Oncology Educational Book. https://doi.org/10.1200/edbk-26-517280
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.