Artificial intelligence for symptom assessment and patient-reported outcomes in neuro-oncology.
15 affiliations
- 1Department of Neurology & Rehabilitation Medicine, University of Cincinnati, Stetson Building 260 Stetson Street, Suite 2300, Cincinnati, OH, 45267-0525, USA. [email protected].
- 2Department of Neurology & Rehabilitation Medicine, University of Cincinnati, Stetson Building 260 Stetson Street, Suite 2300, Cincinnati, OH, 45267-0525, USA.
- 3Department of Neurology, Icahn School of Medicine at Mount Sinai, New York City, NY, USA.
- 4Brookdale Department of Geriatrics and Palliative Medicine, Icahn School of Medicine at Mount Sinai, New York City, NY, USA.
- 5Department of Neurology and Neurosurgery, Montreal Neurological Institute-Hospital, McGill University, Montreal, QC, Canada.
- 6Departments of Medicine and Neurology, University of California, Los Angeles, CA, USA.
- 7University of Virginia Comprehensive Cancer Center, Charlottesville, VA, USA.
- 8Center for Neuro-Oncology, Department of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA, USA.
- 9Division of Adult Palliative Care, Department of Supportive Oncology, Dana-Farber Cancer Institute, Boston, MA, USA.
- 10Department of Neurology, Harvard Medical School, Boston, MA, USA.
- 11Ember Health Inc., Greensboro, NC, USA.
- 12Department of Neurosurgery, Duke University Hospital, Durham, NC, USA.
- 13Division of Medical Oncology, Duke Cancer Institute, Durham, NC, USA.
- 14Department of Neurology, University of California Davis, Davis, CA, USA.
- 15Department of Neurology, Sutter Health/CPMC, San Francisco, CA, USA.
Abstract
Purpose
Patient-reported outcomes (PROs) are critical tools for measuring how patients experience their illness and treatment. Neuropsychiatric symptoms, headaches, seizures, and neurological deficits evolve over time and impact quality of life. In this narrative review, we summarize current literature on PROs in neuro-oncology, extant artificial intelligence (AI) tools for PRO analysis, considerations for real-world application, and ethical implications.Methods
We searched PubMed/MEDLINE, Embase, and Google Scholar for English-language articles published from January 2015 through April 2026, supplemented by reference-list reviews. Four themes were agreed upon, and authors were assigned to each theme. Authors conducted a literature review, selected articles, and synthesized the information under each of these themes. An initial 78 articles were narrowed down to 53 confirming eligibility if they reported PRO or symptom data in people with brain tumors or computational/AI methods were applied to PRO or symptom monitoring in oncology. Article selection was verified by two senior authors (L.V.Y, A.S.). Older, foundational studies were retained where they remain the primary evidence.Results
The growing volume and complexity of PRO data present challenges for traditional analysis methods. Integrating AI, including machine learning (ML) and large language models (LLMs), may help model longitudinal symptom trajectories to predict deterioration, extract symptoms from free-text clinical notes, and embed outputs in clinical decision support tools. Autonomy, informed consent, data security, bias, access, transparency and accountability should be considered.Conclusion
Successful translation will require interpretable, electronic health record-integrated, bias-mitigating tools that allow for actionable insights and preserve patient consent, privacy, and autonomy in this highly vulnerable population.Clinical trial number
Not applicable.
Related
- Artificial intelligence–enabled nursing surveillance for pediatric cancer immunotherapy: integrating biomarkers, patient-reported outcomes, and long-term toxicity management
- The role of radiographic knee alignment in total knee replacement outcomes and opportunities for artificial intelligence-driven assessment
- Editorial: Artificial intelligence and anti-cancer drugs: advancing discovery, personalization, and precision oncology
- The promise and limits of patient-reported outcomes in molecular tumor board-guided care: toward a framework for patient-centered precision oncology.
- Reference Standards in Artificial Intelligence Detection of Apical Periodontitis: A Narrative Review of What Reported Accuracy Measures
BibTeX
@article{yogendran2026artificial,
title = {{Artificial intelligence for symptom assessment and patient-reported outcomes in neuro-oncology.}},
author = {Lalanthica V Yogendran and Chace Avery and Rita C Crooms and Ahmad Ozair and Cara Siegel and Irene Guterman and John Y Rhee and Jason Binder and Maria Minor and Laura Alder and Joshua Davis and Akanksha Sharma},
journal = {Journal of neuro-oncology},
year = {2026},
month = oct,
doi = {10.1007/s11060-026-05832-9},
url = {https://europepmc.org/article/MED/42905223},
note = {CC BY},
}
RIS
TY - JOUR
TI - Artificial intelligence for symptom assessment and patient-reported outcomes in neuro-oncology.
AU - Lalanthica V Yogendran
AU - Chace Avery
AU - Rita C Crooms
AU - Ahmad Ozair
AU - Cara Siegel
AU - Irene Guterman
AU - John Y Rhee
AU - Jason Binder
AU - Maria Minor
AU - Laura Alder
AU - Joshua Davis
AU - Akanksha Sharma
PY - 2026
DA - 2026/10/21
JO - Journal of neuro-oncology
DO - 10.1007/s11060-026-05832-9
UR - https://europepmc.org/article/MED/42905223
AB - Purpose Patient-reported outcomes (PROs) are critical tools for measuring how patients experience their illness and treatment. Neuropsychiatric symptoms, headaches, seizures, and neurological deficits evolve over time and impact quality of life. In this narrative review, we summarize current literature on PROs in neuro-oncology, extant artificial intelligence (AI) tools for PRO analysis, considerations for real-world application, and ethical implications.Methods We searched PubMed/MEDLINE, Embase, and Google Scholar for English-language articles published from January 2015 through April 2026, supplemented by reference-list reviews. Four themes were agreed upon, and authors were assigned to each theme. Authors conducted a literature review, selected articles, and synthesized the information under each of these themes. An initial 78 articles were narrowed down to 53 confirming eligibility if they reported PRO or symptom data in people with brain tumors or computational/AI methods were applied to PRO or symptom monitoring in oncology. Article selection was verified by two senior authors (L.V.Y, A.S.). Older, foundational studies were retained where they remain the primary evidence.Results The growing volume and complexity of PRO data present challenges for traditional analysis methods. Integrating AI, including machine learning (ML) and large language models (LLMs), may help model longitudinal symptom trajectories to predict deterioration, extract symptoms from free-text clinical notes, and embed outputs in clinical decision support tools. Autonomy, informed consent, data security, bias, access, transparency and accountability should be considered.Conclusion Successful translation will require interpretable, electronic health record-integrated, bias-mitigating tools that allow for actionable insights and preserve patient consent, privacy, and autonomy in this highly vulnerable population.Clinical trial number Not applicable.
SN - 0167-594X
SN - 1573-7373
ER -