AI-GF-GNW on Prolonged Grief Reactions

AI-Assisted Grief-Focused Guided Narrative Writing for Subclinical Prolonged Grief Disorder in Bereaved Chinese Adolescents: A Three-Arm Parallel Randomized Controlled Trial.

Prolonged Grief Disorder (PGD) is a severe, disabling condition characterized by intense yearning and difficulty accepting the reality of loss, which significantly impairs the academic and psychosocial functioning of bereaved adolescents. While Grief-Focused Cognitive Behavioral Therapy (GF-CBT) is effective, its high cost and resource-intensive nature limit its accessibility for adolescents in mainland China. Grief-Focused Guided Narrative Writing (GF-GNW) offers a scalable, low-cost alternative that facilitates memory integration.

Furthermore, integrating Artificial Intelligence (AI) to provide personalized, structured feedback has the potential to simulate therapist functions and enhance intervention efficacy. However, the specific efficacy of AI-assisted feedback in this context remains empirically unvalidated.

This parallel randomized controlled trial aims to examine the effectiveness of AI-assisted GF-GNW (AI-GF-GNW) in treating Chinese adolescents (aged 10-19) with subclinical PGD, compared to a no-feedback NF-GF-GNW group and a free writing group. Primary outcomes include PGD symptom severity, while secondary outcomes assess depression, anxiety, and daily functioning. We hypothesize that both active intervention arms will significantly alleviate PGD and related symptoms compared to the free writing group, and that the AI-GF-GNW group will demonstrate a significantly greater reduction in symptoms and functional impairment than the NF-GF-GNW group.

Study Overview

• Status: Not yet recruiting
• Conditions: Anxiety; Depression - Major Depressive Disorder; Prolonged Grief Symptoms; Disabilities; Artificial Intelligence (AI)
• Intervention / Treatment: Behavioral: AI-Assisted Grief-Focused Guided Narrative Writing; Behavioral: No-Feedback Guided Narrative Writing; Behavioral: Free Writing

• Study Type: Interventional
• Enrollment (Estimated): 126
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Yinyin Zang, PhD; Phone Number: +86-010-62756953; Email: yinyin.zang@pku.edu.cn

Study Locations

• China
  • Beijing Municipality
    • Beijing, Beijing Municipality, China
      • Peking University

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Child; Adult
• Accepts Healthy Volunteers: Yes

Description

Inclusion Criteria:

• Junior and senior high school students currently studying in Chinese Mainland, aged 10-19;
• Between 6 and 60 months prior to the experimental period, experienced the death of a significant family member or close friend or close friend;
• The total symptom score of PG-13-R is between 20-29 points;
• Ability to write and understand written guidelines, to use the mobile phone to interact with AI;
• Consent to participate in the study.

Exclusion Criteria:

• Diagnosed or previously diagnosed with mental illness
• The bereavement time does not meet the time window
• PG-13-R score is not within the range
• At present, there is suicidal ideation or recent severe self harm behavior (Reynolds' Suicidal Ideation Questionnaire, SIQ-JR-4>0), and a crisis intervention hotline is provided when necessary.
• Has received other grief counseling or is currently taking psychiatric medication within the past month

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Treatment
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: Triple

Number of Arms

3

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: AI-GF-GNW	Behavioral: AI-Assisted Grief-Focused Guided Narrative Writing; Participants will independently complete the intervention writing tasks via the H5 platform. Participants were required to complete a 6-day, 3-session narrative writing task. Each session requires more than 20 minutes of uninterrupted writing. Session 1 requires describing the specific details and feelings of the bereavement event; Session 2 requires describing the negative impact of the event and one's own negative feelings; Session 3 requires a description of the positive impact of the event and one's own positive feelings, with a one-day interval between each session, synchronized with the NF-GF-GNW group. When participants complete and submit their writing, they will immediately receive a response generated by the AI large language model. Participants are not allowed to engage in any additional interaction with the AI large language model other than submitting writing content and receiving feedback.
Experimental: NF-GF-GNW	Behavioral: No-Feedback Guided Narrative Writing; All processes are the same as the AI-GF-GNW group, except that when participants complete their writing and submit, the platform will only display a "submission successful" prompt and will not provide any feedback on the writing content.
Active Comparator: FWG	Behavioral: Free Writing; Participants in the FWG will not receive structured guidance, and are only required to write freely about their loss experiences. The writing sessions will follow the same schedule and duration as the other groups.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Prolonged Grief Disorder-13-Revision (PG-13-R)	PG-13-R is a standardized diagnostic tool designed to assess the severity of prolonged grief disorder symptoms over the past month. The instrument consists of 10 questions scored on a 5-point Likert scale, alongside 2 true/false questions and 1 open-ended question assessing functional impairment and duration.Who gets 30 points or higher will be considered as clinical prolonged grief reactions.	Baseline (0 Day), post-treatment assessment (5 Day), follow-up assessment (35 Day)
Patient Health Questionnaire (PHQ-9)	PHQ-9 is a brief, validated screening tool used to measure the severity of depression symptoms in adolescents over the past two weeks. 9 questions are scored on a Likert scale of 0-3 with 0 being not at all and 3 being nearly every day.	Baseline (0 Day), post-treatment assessment (5 Day), follow-up assessment (35 Day)

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Generalized Anxiety Disorder (GAD-7)	GAD-7 is an easy-to-perform initial screening tool for generalized anxiety disorder. Questions are scored on a Likert scale of 0-3 with 0 being not at all and 3 being nearly every day.	Baseline (0 Day), post-treatment assessment (5 Day), follow-up assessment (35 Day)
WHO Disability Assessment Schedule-short version(WHODAS 2.0)	WHODAS 2.0 is a comprehensive instrument developed by the World Health Organization to measure health status and functional disability across six core domains over the past 30 days. 12 questions are scored on a Likert scale of 1-5 with 1 being no difficulty and 5 being extreme difficulty.	Baseline (0 Day), post-treatment assessment (5 Day), follow-up assessment (35 Day)

Collaborators and Investigators

• Sponsor: Peking University

Study record dates

Study Major Dates

• Study Start (Estimated): May 25, 2026
• Primary Completion (Estimated): May 1, 2027
• Study Completion (Estimated): May 1, 2027

Study Registration Dates

• First Submitted: May 9, 2026
• First Submitted That Met QC Criteria: May 9, 2026
• First Posted (Actual): May 15, 2026

Study Record Updates

• Last Update Posted (Actual): May 15, 2026
• Last Update Submitted That Met QC Criteria: May 9, 2026
• Last Verified: May 1, 2026

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Mental Disorders; Anxiety Disorders
• Other Study ID Numbers: AI-assisted Grief-Focused GNW

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No