Skip to content

ChatGPT-Driven Blended Teaching for Pain Management in Nursing Students: A Randomized Controlled Trial

Effect of a ChatGPT-Driven Blended Teaching Model for Pain Management on Knowledge, Attitudes, Competence, and Self-Efficacy Among Nursing Students: A Two-Arm Parallel-Group Randomized Controlled Trial

Status
Not yet recruiting
Phases
Unknown
Study type
Interventional
Source
ClinicalTrials.gov
Registry ID
NCT07552363
Enrollment
156
Registered
2026-04-27
Start date
2026-09-01
Completion date
2027-01-01
Last updated
2026-04-27

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Knowledge, Attitudes, Practice, Nursing Education, Pain Management

Keywords

ChatGPT, Artificial Intelligence, Blended Learning, Pain Management, Nursing Students, Clinical Competence, Randomized Controlled Trial

Brief summary

Pain management is a core competency in nursing practice, yet nursing students consistently demonstrate insufficient knowledge, unfavorable attitudes, limited competence, and low self-efficacy in this area. Artificial intelligence (AI)-based educational tools, particularly ChatGPT, have emerged as promising resources in nursing education; however, rigorous experimental evidence on their effectiveness remains scarce. This study is a two-arm, parallel-group randomized controlled trial (RCT) that aims to evaluate the effect of a ChatGPT-driven blended teaching model for pain management on nursing students' knowledge and attitudes toward pain, nursing competence, and learning self-efficacy. Eligible nursing students at Shahid Beheshti University of Medical Sciences (Tehran, Iran) will be randomly assigned in a 1:1 ratio to either: * Intervention group: ChatGPT-assisted blended clinical nursing rounds (8 sessions over 4 weeks, each 90 minutes, combining bedside rounds with AI-assisted pre- and post-round activities) * Control group: Traditional clinical nursing rounds (same number and duration of sessions, without any AI tools) Outcomes will be measured at baseline (1 week before intervention), immediate post-test (1 week after intervention), and 3-month follow-up using validated instruments: the Nurses' Knowledge and Attitudes Survey Regarding Pain (NKASRP), the Nursing Student Competence Scale (NSCS), and the Nursing Students' Learning Self-Efficacy instrument (NLSE). Findings will provide empirical evidence to guide educational policy and curriculum design in nursing programs, with the goal of improving pain management education and patient care outcomes.

Interventions

BEHAVIORALChatGPT-Driven Blended Teaching Model for Pain Management

A blended teaching model integrating ChatGPT with in-person clinical nursing rounds for pain management education. Delivered over 4 weeks (8 sessions × 90 minutes). Each session includes: (1) pre-round preparation using standardized ChatGPT prompts for case analysis and evidence retrieval; (2) bedside nursing rounds with pain assessment, patient education, and instructor feedback; and (3) post-round activities using ChatGPT to resolve clinical uncertainties and complete case reports. All ChatGPT outputs were reviewed by supervising faculty for accuracy. Students used pre-designed, standardized prompts based on the WHO analgesic ladder and national clinical protocols.

BEHAVIORALTraditional Clinical Nursing Rounds

Standard clinical nursing rounds without AI tools. The instructor directs all activities including case introduction, bedside assessment, nursing diagnosis, intervention planning, and outcome evaluation. Students primarily observe and respond to instructor questions. Sessions match the intervention group in number, duration, and clinical setting (8 sessions × 90 minutes over 4 weeks).

Sponsors

Shahid Beheshti University of Medical Sciences
Lead SponsorOTHER

Study design

Allocation
RANDOMIZED
Intervention model
PARALLEL
Primary purpose
OTHER
Masking
SINGLE (Outcomes Assessor)

Masking description

Due to the nature of the educational intervention, blinding of participants and instructors was not feasible. Outcome assessors responsible for administering and scoring questionnaires, and the data analyst, remained blinded to group allocation throughout the study. All questionnaires were distributed using participant identification codes rather than names.

Intervention model description

Two-arm parallel-group design with 1:1 allocation ratio. Participants are randomly assigned to either a ChatGPT-driven blended teaching group or a traditional clinical nursing rounds group. Both groups receive the same number and duration of sessions (8 sessions over 4 weeks, each approximately 90 minutes) in the same clinical departments.

Eligibility

Sex/Gender
ALL
Age
18 Years to No maximum
Healthy volunteers
Yes

Inclusion criteria

1. Undergraduate nursing students in their fourth semester or higher, or master's or doctoral nursing students engaged in clinical training involving direct patient care 2. Provision of electronic informed consent 3. Access to the internet and a personal device (computer, tablet, or smartphone) for the asynchronous components of the blended teaching model 4. No participation in a formal comprehensive pain management course within the previous 12 months

Exclusion criteria

1. Inability to attend at least one face-to-face session or to complete online activities (e.g., due to repeated absences) 2. Any self-reported or university-documented cognitive or mental health condition that prevented completion of questionnaires or participation in training 3. Voluntary withdrawal at any stage of the study

Design outcomes

Primary

MeasureTime frameDescription
Knowledge and Attitudes Toward PainBaseline (1 week before intervention), immediate post-test (1 week after intervention), and 3-month follow-upMeasured using the Nurses' Knowledge and Attitudes Survey Regarding Pain (NKASRP), a 39-item instrument comprising 22 true/false questions, 13 multiple-choice questions, and 2 case studies. Each correct answer scores 1 point (range: 0-39); results expressed as percentage of correct responses. Higher scores indicate better knowledge and attitudes toward pain management. A Persian forward-backward translation was performed, with face and content validity confirmed by a nursing faculty panel.

Secondary

MeasureTime frameDescription
Nursing CompetenceBaseline (1 week before intervention), immediate post-test (1 week after intervention), and 3-month follow-upMeasured using the Persian version of the Nursing Student Competence Scale (NSCS), a 28-item instrument across 6 subscales: medical-related knowledge, basic nursing skills, communication and cooperation, lifelong learning, global perspective, and critical thinking. Items rated on a 5-point Likert scale (range: 28-140). Higher scores indicate greater competence. The Persian version demonstrated Cronbach's α = 0.90 and ICC = 0.88.
Learning Self-EfficacyBaseline (1 week before intervention), immediate post-test (1 week after intervention), and 3-month follow-upMeasured using the Persian version of the Nursing Students' Learning Self-Efficacy instrument (NLSE), a 21-item instrument across 5 dimensions: conceptual understanding, higher-order cognitive skills, practical work, everyday application, and nursing communication. Items rated on a 5-point Likert scale (range: 21-105). Higher scores indicate greater self-efficacy. The Persian version demonstrated Cronbach's α = 0.93 and ICC = 0.89.

Countries

Iran

Contacts

CONTACTSogand Sarmadi
sogand.sarmadi@ymail.com+989198599908

Outcome results

None listed

Source: ClinicalTrials.gov · Data processed: Apr 28, 2026