Development and Evaluation of an AI-Assisted Answer Assessment (4A) for Cognitive Assessments in Nursing Education DOI Creative Commons
Piyanut Xuto, Piyaporn Prasitwattanaseree, Tareewan Chaiboonruang

и другие.

Nursing Reports, Год журнала: 2025, Номер 15(3), С. 80 - 80

Опубликована: Фев. 26, 2025

Artificial intelligence (AI) can potentially enhance cognitive assessment practices in maternal and child health nursing education. Objectives: To evaluate the reliability, accuracy precision, external validity of an AI-assisted answer (4A) program for assessments Methods: This study is a validation study. Initially, 170 students from northern Thailand participated, with 52 randomly selected detailed testing. Agreement testing between 4A human experts was conducted using intraclass correlation coefficient (ICC). Accuracy precision compared scores expert via McNemar test. External involved 138 participants to compare program’s against national examination outcomes logistic regression. Results: Results indicated high level consistency (ICC = 0.886). With 0.808 0.913, expert’s 0.923 1.000. The test (χ2 0.4, p 0.527) showed no significant difference evaluation performance AI experts. Higher on significantly predicted success (OR: 1.124, 0.031). Conclusions: demonstrates potential reliably assessing students’ abilities predicting exam success. advocates continued integration educational importance refining systems better align traditional methods.

Язык: Английский

Development and Evaluation of an AI-Assisted Answer Assessment (4A) for Cognitive Assessments in Nursing Education DOI Creative Commons
Piyanut Xuto, Piyaporn Prasitwattanaseree, Tareewan Chaiboonruang

и другие.

Nursing Reports, Год журнала: 2025, Номер 15(3), С. 80 - 80

Опубликована: Фев. 26, 2025

Artificial intelligence (AI) can potentially enhance cognitive assessment practices in maternal and child health nursing education. Objectives: To evaluate the reliability, accuracy precision, external validity of an AI-assisted answer (4A) program for assessments Methods: This study is a validation study. Initially, 170 students from northern Thailand participated, with 52 randomly selected detailed testing. Agreement testing between 4A human experts was conducted using intraclass correlation coefficient (ICC). Accuracy precision compared scores expert via McNemar test. External involved 138 participants to compare program’s against national examination outcomes logistic regression. Results: Results indicated high level consistency (ICC = 0.886). With 0.808 0.913, expert’s 0.923 1.000. The test (χ2 0.4, p 0.527) showed no significant difference evaluation performance AI experts. Higher on significantly predicted success (OR: 1.124, 0.031). Conclusions: demonstrates potential reliably assessing students’ abilities predicting exam success. advocates continued integration educational importance refining systems better align traditional methods.

Язык: Английский

Процитировано

0