aceApplication of Artificial Intelligence (AI) in cancer symptom management for adult cancer survivors: a scoping review
Abstract: Artificial Intelligence (AI) has been increasingly used in cancer survivorship to support symptom management. This scoping review aimed to map existing evidence on AI applications in cancer symptom management for adult cancer survivors, including AI model development, AI-enabled intervention delivery and adoption, symptom targets, key features of the AI approaches used, reported outcomes, influencing factors, and research gaps to inform future priorities. This scoping review was conducted in accordance with the…
Characterization of autonomic symptom burden in long COVID- A global survey of 2,314 adults by Nicholas W. Larsen, Lauren E. Stiles, Ruba Shaik, Logan Schneider, Srikanth Muppidi, Cheuk To Tsui, Linda N. Geng, Hector Bonilla, Mitchell G. Miglis. CC BY 4.0 · https://creativecommons.org/licenses/by/4.0
This scoping review examined 41 empirical studies published from 2015 to March 2026 on AI for cancer symptom management in adult survivors. Twenty-one studies focused on model development using mainly unstructured electronic health record data, 18 on AI-enabled delivery using patient-reported inputs, and 2 on both, employing natural language processing, machine learning, and conversational AI for detection, monitoring, triage, decision support, personalised management, education and counselling.
The findings matter because nearly half addressed general or multiple symptoms while others targeted pain and psychological distress, with delivery studies reporting clinical and psychosocial improvements. What remains uncertain is whether these moderate-to-high performing models translate into safe, equitable, and effective real-world care, given heterogeneous designs, limited symptom coverage, and gaps in validation, co-design, and workflow integration noted by the authors.
- Scoping review included 41 studies: 21 on AI model development, 18 on AI-enabled intervention delivery, and 2 on both, searched across eight databases through March 2026.
- Common techniques were natural language processing, machine learning, and conversational AI, using unstructured electronic health record data for development and patient-reported inputs for delivery.
- AI applications supported symptom detection (n=15), monitoring (n=5), triage (n=2), clinical decision support (n=3), personalised management (n=5), patient education (n=9) and counselling (n=2), with pain and psychological distress most frequent specific targets.
AI-enabled intervention delivery for adult cancer survivors was associated with reported improvements in clinical and psychosocial outcomes, with model performance generally moderate to high across symptom tasks.
The rundown
The review followed Joanna Briggs Institute methodology, including empirical studies from 2015 onward focused on development and/or implementation of AI models for cancer-related symptom care among adult survivors.
Synthesis used descriptive statistics and narrative analysis, with inductive content analysis identifying six influencing factor categories: technical performance; data quality, documentation, and generalisability; clinical workflow integration; usability, access, and equity; human-centred communication; and ethics and safety.
Sources
- Peer-reviewedInternational Journal of Medical Informatics2026-08-15
How should this claim be treated?
The debate