Application of Large Language Models Techniques to Post-ICU Syndrome Management in Critically Ill Patients: A Fully Longitudinal Mixed Study

Condition(s) studied

Investigational drug(s) / intervention(s)

Routine Care: Participants receive standard post-ICU follow-up care according to hospital protocols . This includes routine health assessments and general rehabilitation guidance at designated intervals (discharge, 1/3/6 months post-discharge). No structured PICS management program or AI technology is provided.

Health Promotion Model-Based Optimized Program: An evidence-based, multidisciplinary rehabilitation protocol for Post-Intensive Care Syndrome (PICS) management, developed using the Health Promotion Model (HPM). It includes: Personalized rehabilitation plans addressing physical, cognitive, and psychological recovery. Structured follow-up at discharge, 1/3/6 months post-discharge. Components: Physical function training, cognitive exercises, anxiety/depression coping strategies, and sleep hygiene education. Delivery: Clinician-guided (no AI/technology involved). Developed via literature review and validated by ICU physicians and nursing experts .

LLM-Enhanced Optimized Program: Combines the HPM-Based Optimized Program with Large Language Model (LLM) technology for dynamic personalization: AI-generated rehabilitation plans: ChatGPT-4 synthesizes patient data (baseline + follow-ups) to create/update monthly plans, reviewed by a multidisciplinary expert team. Patient-facing LLM tool: "Kimi Smart Assistant" installed for daily health queries under strict safety protocols (all outputs validated by nurses via WeChat). Phased implementation: Pre-discharge: LLM training + baseline plan generation. 1/3/6 months: Plan updates + outcome tracking. 3/6 months: Semi-structured interviews on LLM experience. Includes LLM usage guidelines and expert validation safeguards .

Study summary

The goal of this clinical trial is to evaluate whether Large Language Models (LLMs) combined with an optimized care program can effectively manage Post-Intensive Care Syndrome (PICS) in adult ICU survivors (aged ≥18 years) discharged from a tertiary hospital in China. The main questions it aims to answer are:

* Does the intervention (optimized program + LLMs) improve physical, psychological, cognitive, and social function recovery compared to standard care or the optimized program alone?
* How do patients experience and perceive the utility of LLMs in PICS self-management during recovery?

Researchers will compare three groups:

1. Group A (routine care)
2. Group B (optimized program without LLMs)
3. Group C (optimized program + LLMs) to see if adding LLMs significantly enhances PICS symptom management, patient self-efficacy, and quality of life over 6 months post-discharge.

Participants will:

* Install and use the Kimi Smart Assistant LLM (Group C only) for health queries under nurse supervision.
* Complete standardized questionnaires at discharge (baseline), 7 days, 1 month, 3 months, and 6 months post-discharge:

* PICS Symptom Questionnaire (PICSQ)
* Pittsburgh Sleep Quality Index (PSQI)
* Anxiety (GAD-7) and Depression (PHQ-9) scales
* Self-Management Ability Scale (AHSMSRS)
* Attend semi-structured interviews (Group C only) at 3 and 6 months to share experiences with LLM use.

Eligibility

Primary outcome measure(s)

• Change in Post-Intensive Care Syndrome (PICS) Symptom Severity — Measured at baseline (pre-discharge), 1 month, 3 months, and 6 months post-discharge.
  \- Total score of the Chinese Version of the Post-Intensive Care Syndrome Questionnaire (PICSQ). Domains: Physical function (6 items), cognitive impairment (6 items), psychological symptoms (6 items). Scoring: 18 items × 0-3 points = 0-54 total; higher scores = worse symptoms. * Total score of the Pittsburgh Sleep Quality Index (PSQI). Scoring: 7 components × 0-3 points = 0-21 total; higher scores = poorer sleep. * Recall experiences measured by the Chinese ICU Memory Tool (ICUMT). Format: 14-item mixed open/closed questions about ICU admission, treatment, and discharge memories. * Anxiety: GAD-7 score (0-21; higher = worse anxiety). Depression: PHQ-9 score (0-27; higher = worse depression).

Trial sites (1)

More The Affiliated Hospital Of Guizhou Medical University trials in China