Your new experience awaits. Try the new design now and help us make it even better

STUDY PROTOCOL article

Front. Psychiatry

Sec. Public Mental Health

This article is part of the Research TopicAdvances in Artificial Intelligence Applications that Support Psychosocial HealthView all 15 articles

The Effect of Artificial Intelligence-Empowered Mobile Health on Psychological Distress in Women Following Abortion: protocol for a mixed-methods study

Provisionally accepted
Wei  ZhangWei Zhang1Yuqi  YangYuqi Yang2Meimei  LiuMeimei Liu1Lirong  WangLirong Wang1Qing  LeiQing Lei1Qiumei  ZhangQiumei Zhang1Jing  WangJing Wang3Hui  LiHui Li4*Gumula  WuriGumula Wuri1*
  • 1Department of Gynaecology, Inner Mongolia Maternity and Child Health Care Hospital, Hohhot, China
  • 2School of Nursing, Henan University of Science and Technology, Luoyang, China
  • 3School of Public Health, Peking University, Beijing, China
  • 4Nursing Department, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, China

The final, formatted version of the article will be published soon.

Background: The number of abortions worldwide continues to rise, and abortion can have adverse physical and psychological effects. At present, there is little attention paid to the psychological distress experienced by women after abortion, such as anxiety and depression. Current interventions rely heavily on specific personnel, time, and location, which can be costly. Artificial Intelligence-Empowered Mobile Health can compensate for the shortcomings of current interventions, and these interventions are guided by Swanson's Theory of Caring. Methods: This study is a mixed-methods research protocol to be implemented at the Inner Mongolia Maternity and Child Health Care Hospital. A total of 100 women after abortion will be included and randomly assigned to either the intervention group or the standard care group. The intervention group will receive two weeks of Artificial Intelligence-Empowered Mobile Health intervention guided by Swanson's Theory of Caring, including medical knowledge about abortion, post-operative diet, and exercise guidance. The standard care group will receive standard prenatal care. The primary outcome is the change in depression levels, while secondary outcomes include anxiety, perceived stress, perceived social support, and other factors. This study uses IBM SPSS Statistics 27.0 and NVivo 12.0 for data analysis, employing descriptive statistics, normality tests, Mann–Whitney U, Wilcoxon, and chi-square tests. Discussion:This study pioneers an Artificial Intelligence-Empowered Mobile Health guided by Swanson's Theory of Caring, providing continuous post-abortion support to reduce psychological distress. It applies Large Language Models to Artificial Intelligence-Empowered Mobile Health for women experienced abortion, delivering timely, specialized care. This approach overcomes traditional barriers: offering real-time interaction, breaking spatiotemporal limits, lowering costs, and integrating expert knowledge to mitigate regional resource disparities, and also promoting health equity.

Keywords: artificial intelligence, mobile health, Swanson's theory of caring, Large Language Model, Abortion, psychological distress, mixed-methods

Received: 14 Jul 2025; Accepted: 29 Oct 2025.

Copyright: © 2025 Zhang, Yang, Liu, Wang, Lei, Zhang, Wang, Li and Wuri. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

* Correspondence:
Hui Li, 1977meigui@163.com
Gumula Wuri, wuri2000@sohu.com

Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.