Artificial intelligence in cancer survivorship: evaluating ChatGPT's performance in rehabilitation-related queries
Clinical Snapshot
PICO Framework
| P — Population | Cancer survivors seeking rehabilitation information |
| I — Intervention | ChatGPT-4 responses to rehabilitation queries |
| C — Comparator | Established clinical practice guidelines and expert consensus |
| O — Outcomes | Accuracy, completeness, and global quality scores of responses |
Bottom Line
This evaluation study assessed ChatGPT-4's ability to answer cancer rehabilitation questions across eight clinical domains. While responses demonstrated reasonable accuracy (79%) and quality, significant gaps in completeness (71%) and safety information were identified. The study's small sample size and lack of statistical testing limit confidence in findings. ChatGPT showed potential as a supplementary educational tool but cannot replace professional consultation. Key concerns include incomplete exercise dosing information and safety precautions. For Australian practice, this technology might support patient education in underserved areas but requires integration with established clinical pathways and professional oversight. Healthcare providers should view such tools as adjuncts to, not replacements for, evidence-based rehabilitation care. Further research with larger samples and validated assessment tools is needed before clinical implementation.
Key Findings
P Value: Not reported
Effect Size: Mean accuracy 3.93/5.0, completeness 2.13/3.0, global quality 3.60/5.0
Primary Outcome: ChatGPT performance across three domains: accuracy, completeness, and global quality
Nnt Or Sensitivity: Accuracy rate approximately 79%, completeness rate approximately 71%
Confidence Interval: Not reported
Clinical Application
High feasibility given widespread access to ChatGPT, but requires professional oversight for safety Relevant to Australian cancer survivors, particularly in rural/remote areas with limited access to cancer rehabilitation services. Could complement existing Cancer Council resources and telehealth initiatives under Medicare Cancer survivors seeking rehabilitation guidance, particularly those with limited access to specialist care
Abstract
PURPOSE: This study aimed to evaluate the performance of ChatGPT in responding to patient-centered queries related to cancer rehabilitation. It examined the accuracy, completeness, and overall quality of ChatGPT's responses across major domains of cancer rehabilitation from a physical therapy perspective. METHODS: Fifteen representative patient queries covering eight domains of cancer rehabilitation-including general exercise, fatigue, bone metastasis, neuropathy, balance and falls, breast cancer, women's health, and pediatric cancer-were developed by two licensed physical therapists. Each query was input into ChatGPT-4, and responses were independently evaluated for accuracy, completeness, and global quality based on established clinical practice guidelines and expert consensus. RESULTS: ChatGPT demonstrated a mean accuracy score of 3.93 (SD = 1.10) on a 5-point scale, a mean completeness score of 2.13 (SD = 0.83) on a 3-point scale, and a mean global quality score of 3.60 (SD = 1.12) on a 5-point scale. Responses were generally accurate and clinically relevant but often lacked details regarding exercise dosage, safety precautions, and guideline-concordant recommendations. CONCLUSION: ChatGPT shows potential as an accessible tool for general cancer rehabilitation education but requires refinement to ensure accuracy, contextual relevance, and safety. IMPLICATIONS FOR CANCER SURVIVORS: AI-driven conversational models may improve patient access to rehabilitation information and self-management support when used under professional oversight and guided by evidence-based frameworks.
References
- 1.Hao, J., Yao, Z., Fan, P., Remis, A., & Wu, K. (2026). Artificial intelligence in cancer survivorship: evaluating ChatGPT's performance in rehabilitation-related queries. Supportive Care in Cancer. https://doi.org/10.5014/ajot.2017.023572
Related Research
The American journal of pathology
An Integrated Machine Learning and Genomic Framework for Precise Detection of Gastric Cancer
3 Aug 2026
Current opinion in chemical biology
Prediction of protein-protein interactions and co-complex models with deep learning
3 Aug 2026
European journal of radiology
A CT-based deep learning model to differentiate between benign and malignant adrenal lesions
3 Aug 2026
This content is for educational purposes for healthcare professionals only and does not constitute clinical advice. Clinical decisions should be based on individual patient assessment, current guidelines, and appropriate specialist consultation. Editorial Standards · Privacy Policy · Terms of Service