+ SCIENCE Stochastic gradient descent (SGD), one of the most fundamental optimization algorithms in machine learning (M…+ LIFESTYLE With the increasing interest in glamping, the demand for more functional camping cookware has grown, driving…− MEDIA & ARTS Ai Weiwei is talking me through the decision-making process before his first visit to China in over a decade.…+ EDUCATION Anil Seth is right to point out that to overestimate artificial intelligence is to underestimate ourselves (O…− POLICY Content generated by artificial intelligence models can ‘defy basic physics, design principles or operational…+ MEDIA & ARTS Hook users can remix, mash up and share their content using fully licensed and cleared songs from UMG, Downto…− POLICY Pulitzer prize-winning US historian Jill Lepore’s new book addresses the threat posed to liberal democracy by…± EDUCATION Since its maiden release into the public domain on November 30, 2022, ChatGPT garnered more than one million…
TruaceTracing the truth around AIFriday, August 21, 2026
Subscribe
Health·G Space·Evidence-backed gain·Published 2026-08-18

An AI-Supported Virtual Patient Application Using a Structured Prompting Framework to Develop Mental Status Examination Skills in Psychiatric Nursing Internship Students: An Interventional Mixed-Methods Study

Abstract: The aim of this study is to evaluate the effect of an artificial intelligence (AI)-powered virtual patient application (ChatGPT) on the development of Mental Status Examination (MSE) skills in psychiatric nursing internship students and to explore how this process is reflected in their experiences. This study employed a sequential explanatory mixed-method design, consisting of a quantitative pre/post-test phase followed by a qualitative phase. In the quantitative phase, the MSE Competency Assessment scores of 27…

TRV-2026-0820Peer-reviewedPermanent record — cite & verify
An AI-Supported Virtual Patient Application Using a Structured Prompting Framework to Develop Mental Status Examination Skills in Psychiatric Nursing Internship Students: An Interventional Mixed-Methods Study

US Navy 060608-N-3714J-085 Navy Lt. Tara Collins, of Le Grange, Ky., gives a group of nursing students from the Jolo Norte Dame Nursing School a tour of the U.S. Military Sealift Command (MSC) Hospital ship USNS Mercy (T-AH 19) by U.S. Navy photo. Public domain

The quick read

Researchers tested an AI-powered virtual patient application built on ChatGPT to teach Mental Status Examination skills to 27 psychiatric nursing internship students. Using a sequential explanatory mixed-methods design, they measured competency before and after the structured prompting intervention and then interviewed 18 students about their experience.

By the publication date of August 17, 2026, the study reported a measured increase in competency scores and positive student reports of skill development, suggesting a potential training benefit for psychiatric nursing education. It remains uncertain how this small, single-group, internship-student sample would generalize to other programs, whether gains persist in real clinical encounters, and what specific limitations students identified under the Limitations theme.

Main points
  • Study used sequential explanatory mixed-method design with quantitative pre/post-test followed by qualitative interviews.
  • Quantitative phase included 27 undergraduate psychiatric nursing internship students assessed with MSE Competency Assessment.
  • Qualitative phase included in-depth individual interviews with 18 volunteer students.
  • Intervention was named "AI-Supported Virtual Patient Intervention: Structured Prompting Framework" using ChatGPT.
Gain

Psychiatric nursing internship students who used the ChatGPT-based virtual patient with a structured prompting framework showed higher MSE competency after the intervention.

The rundown

The intervention was delivered as the "AI-Supported Virtual Patient Intervention: Structured Prompting Framework" using ChatGPT. Quantitative assessment used the MSE Competency Assessment in a pre-test/post-test model with 27 students, showing a statistically significant increase reported as Z = -6.266, p < 0.001.

Qualitative thematic analysis produced five main themes: Skill Development, Learning Experience, Impact of AI, Debriefing, and Limitations. Students described enhanced examination and communication skills and highlighted the importance of guided support during the AI-based learning experience.

Sources

Reader signal

How should this claim be treated?

The debate