Healthcare professionals' perceptions and needs for a Home-based Artificial Intelligence Pain Management System for cancer pain: A qualitative study.

Authors

Mengmeng Chen, Xin Chen, Jiajun Yuan, Meiling Yang, Jiachun Lu, Wing Chi Lam, Cheuk Yan Ng, Thomas K S Wong

Published in

International journal of nursing sciences. Volume 13. Issue 5. Pages 512-519. Epub Aug 09, 2026.

Abstract

This study aimed to explore healthcare professionals' (HCPs') perceptions of and needs for a Home-based Artificial Intelligence Pain Management System (HAIPMS) for cancer pain in Hong Kong, China.
A qualitative study was conducted using semi-structured interviews with 14 HCPs from Jockey Club Home for Hospice (JCHH) in Hong Kong, China between March and June 2025. Data were analyzed using thematic analysis.
Their professional experience ranged from 3 to 33 years. Thematic analysis generated three themes and ten subthemes. The themes were: 1) valued but under-supported home-based cancer pain management, including family-dependent and intermittent professional support; comfort, affordability, and system relief in home-based care; and subjective assessment, medication non-adherence, and delayed support; 2) cautious optimism toward AI integration, including expectations for visible, measurable, and continuous pain monitoring; concern of risks resulted from AI implementation; and heterogeneous attitudes shaped by professional and generational divides; and 3) practical requirements for HAIPMS implementation, including essential functional modules; user-centered design and adaptability; safety and ethical assurance requirements; and training and sustained support.
HCPs viewed HAIPMS as a potentially useful supportive tool for home-based cancer pain management, provided that it preserves professional autonomy, fits local care contexts, and incorporates ethical safeguards, user-friendly design, and sustained support. These findings offer practical guidance for developing AI-assisted pain management systems in home-based cancer pain.

PMID:
42805738
Bibliographic data and abstract were imported from PubMed on 29 Sep 2026.

Read full publication at:
Please sign in to see all details.

Stats

1-terrible, 9-excellent. How would you rate this publication? Sign in in to submit your rating.

Post a comment

You need to be signed in to post comments. You can sign in here.

Comments

There are no comments yet.