Abstract

Problem: Nurses need to develop specialized knowledge and competence to optimize the use of artificial intelligence (AI) technology. This study evaluates the use of AI in a Nursing Informatics graduate-level course assignment focused on designing an EHR alert. The evaluation focuses on both students and faculty. Students conducted a literature search with AI tools and compared them to other databases. AI was also used to create an alert design and workflow analysis. Faculty used AI to grade the assignment utilizing a rubric.

Methods: An IRB-exempt retrospective descriptive design was used with a convenience sample of 103 Doctor of Nurse Practitioner students taking an online informatics course. The assignment objective was to design an electronic alert for clinical decisions on intimate partner violence. The individual portion of the assignment aimed to identify high-risk individuals by searching relevant literature in bibliographic databases and using AI tools, reviewing, and selecting articles. The group portion of the assignment involved identifying alert triggers, designing an EHR alert and intervention screen, and workflow analysis, and writing a proposal to the nursing informatics team. Students’ scores were assigned a value of 1 (Mastered), 2 (Competent), or 3 (Did not Master). Descriptive analyses were performed. Students’ comparisons of the AI tools versus the databases and faculty reflections on grading both assignment components are summarized.

Results: The individual portion of the assignment revealed that 91.4% of the students mastered the assignment, 1.9% were competent, and 6.7% did not master. A summary of students’ comparisons of the use of AI tools versus other databases for a literature search revealed mixed results, as some students found AI inaccurate and incomplete. In contrast, others found AI time efficient and that it provided a template that could be expanded.

The group portion of the assignment revealed that 25 groups (69.4%) mastered the assignment, 7 groups (19.4%) were competent, and 4 groups (11.1%) did not master.

Grading revealed that AI inaccurately determined whether citations were APA formatted. For example, AI tools did not recognize hanging indents and double spacing 100% of the time. When grading the group assignments, AI summarized strong and weak points and provided areas for improvement. Comparing faculty grading to AI, there was agreement 14% of the time, 60% of faculty grades were lower, 26% of faculty grades were higher.

Notes

Reference list included in attached slide deck.

Description

Implications: AI is revolutionizing healthcare technology and can be harnessed to transform healthcare. Thus, nurses must be proficient in the use of AI. Using AI to search the literature and develop an alert, students learn the efficiency of AI while experiencing the limitations. AI may produce inaccurate information, and references must be checked. Use of AI for grading has shown that the process can be more efficient, but faculty will need to evaluate both the efficiency and reliability of AI.

Author Details

Barbara Kupferschmid, PhD, RN; Rhonda R. Schoville, PhD, RN; and Jeff Drake, PHD

Sigma Membership

Pi Delta, Rho

Type

Presentation

Format Type

Text-based Document

Study Design/Type

Descriptive/Correlational

Research Approach

Mixed/Multi Method Research

Keywords:

Competence, Teaching and Learning Strategies, Nursing Informatics, Nursing Education, Emerging Technologies, Artificial Intelligence, Electronic Health Records

Conference Name

48th Biennial Convention

Conference Host

Sigma Theta Tau International

Conference Location

Indianapolis, Indiana, USA

Conference Year

2025

Rights Holder

All rights reserved by the author(s) and/or publisher(s) listed in this item record unless relinquished in whole or part by a rights notation or a Creative Commons License present in this item record. All permission requests should be directed accordingly and not to the Sigma Repository. All submitting authors or publishers have affirmed that when using material in their work where they do not own copyright, they have obtained permission of the copyright holder prior to submission and the rights holder has been acknowledged as necessary.

Review Type

Abstract Review Only: Reviewed by Event Host

Acquisition

Proxy-submission

Date of Issue

2025-12-04

Click on the above link to access the slide deck.

Share

COinS
 

Revolutionizing Nursing Informatics: Using AI for Students to Develop EHR Alerts and Faculty Grading

Indianapolis, Indiana, USA

Problem: Nurses need to develop specialized knowledge and competence to optimize the use of artificial intelligence (AI) technology. This study evaluates the use of AI in a Nursing Informatics graduate-level course assignment focused on designing an EHR alert. The evaluation focuses on both students and faculty. Students conducted a literature search with AI tools and compared them to other databases. AI was also used to create an alert design and workflow analysis. Faculty used AI to grade the assignment utilizing a rubric.

Methods: An IRB-exempt retrospective descriptive design was used with a convenience sample of 103 Doctor of Nurse Practitioner students taking an online informatics course. The assignment objective was to design an electronic alert for clinical decisions on intimate partner violence. The individual portion of the assignment aimed to identify high-risk individuals by searching relevant literature in bibliographic databases and using AI tools, reviewing, and selecting articles. The group portion of the assignment involved identifying alert triggers, designing an EHR alert and intervention screen, and workflow analysis, and writing a proposal to the nursing informatics team. Students’ scores were assigned a value of 1 (Mastered), 2 (Competent), or 3 (Did not Master). Descriptive analyses were performed. Students’ comparisons of the AI tools versus the databases and faculty reflections on grading both assignment components are summarized.

Results: The individual portion of the assignment revealed that 91.4% of the students mastered the assignment, 1.9% were competent, and 6.7% did not master. A summary of students’ comparisons of the use of AI tools versus other databases for a literature search revealed mixed results, as some students found AI inaccurate and incomplete. In contrast, others found AI time efficient and that it provided a template that could be expanded.

The group portion of the assignment revealed that 25 groups (69.4%) mastered the assignment, 7 groups (19.4%) were competent, and 4 groups (11.1%) did not master.

Grading revealed that AI inaccurately determined whether citations were APA formatted. For example, AI tools did not recognize hanging indents and double spacing 100% of the time. When grading the group assignments, AI summarized strong and weak points and provided areas for improvement. Comparing faculty grading to AI, there was agreement 14% of the time, 60% of faculty grades were lower, 26% of faculty grades were higher.