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

N/AEnrolling By InvitationNCT07141420

The Affiliated Hospital Of Guizhou Medical University90 enrolled

Overview

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.

Study Type

INTERVENTIONAL

Allocation

RANDOMIZED

Purpose

SUPPORTIVE_CARE

Masking

QUADRUPLE

Enrollment

Conditions

Post-Intensive Care Syndrome

Interventions

Routine CareBEHAVIORAL

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 ProgramBEHAVIORAL

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 ProgramBEHAVIORAL

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 .

Eligibility

Sex: ALLMin age: 18 YearsMax age: 100 Years

Medical Language ↔ Plain English

Inclusion Criteria: * ICU hospitalization duration \> 24 hours. * Age ≥ 18 years. * Conscious at ICU discharge, able to communicate without barriers. * Provide informed consent to participate. * Regular access to and usage of smart electronic devices. Exclusion Criteria: * Previous ICU admission (≥24h) within 3 months before the current hospitalization. * Transferred to another ICU during the current hospitalization. * Pre-existing cognitive impairment (Blessed Dementia Rating Scale \[BDRS\] score \>4 before ICU admission). * Severe communication barriers: Hearing impairment Dysarthria Other conditions preventing follow-up assessments. * Critically unstable condition preventing questionnaire completion. * Infrequent/no experience using smart electronic devices (e.g., smartphones, tablets).

Outcomes

Primary Outcomes

Change in Post-Intensive Care Syndrome (PICS) Symptom Severity

\- 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).

Time frame: Measured at baseline (pre-discharge), 1 month, 3 months, and 6 months post-discharge.

Secondary Outcomes

Self-Management Ability

\- Total score of the Adults Health Self-Management Ability Rating Scale (AHSMSRS). Scoring: 38 items × 1-3 points = 38-114 total; higher scores = poorer self-management.

Time frame: 1m, 3m, 6m post-discharge.

Patient Experience with LLMs

Qualitative insights from semi-structured interviews based on the Technology Acceptance Model (TAM).

Time frame: 3 months and 6 months post-discharge (Group C only).