Archana Chauhan

Archana Chauhan

Auto-generated profile, based on publicly available information

Archana Chauhan

Department of Physiology, Dr Yashwant Singh Parmar Government Medical College, Nahan 173001, Himachal Pradesh, India

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 April 2025 in International Journal of Artificial Intelligence in Education
Verified
Journal Article
Open access
PDF file
ACArchana Chauhan
Archana Chauhan
FKFarah Khaliq
Farah Khaliq
KNKirtana Raghurama Nayak
Kirtana Raghurama Nayak
The integration of Artificial Intelligence (AI), particularly Chatbot Generative Pre-Trained Transformer (ChatGPT), in medical education has introduced new possibilities for generating various educational resources for assessments. However, ensuring the quality of ChatGPT-generated assessments poses challenges, with limited research in the literature addressing this issue. Recognizing this gap, our study aims to investigate the quality of ChatGPT-based assessment. In this study among first-year medical students, a crossover design was employed to compare scenario-based multiple-choice questions (SBMCQs) crafted by both faculty members and ChatGPT through item analysis to determine the quality of assessment. The study comprised three main phases: development, implementation, and evaluation of SBMCQs. During the development phase, both faculty members and ChatGPT generated 60 SBMCQs each, covering topics related to cardiovascular, respiratory, and endocrinology. These questions underwent assessment by independent reviewers, after which 80 SBMCQs were selected for the tests. Subsequently, in the implementation phase, one hundred and twenty students, divided into two batches, were assigned to receive either faculty-generated or ChatGPT-generated questions across four test sessions. The collected data underwent rigorous item analysis and thematic analysis to evaluate the effectiveness and quality of the questions generated by both parties. Only 9 of ChatGPT’s SBMCQs met ideal criteria MCQ on Difficulty Index, Discrimination Index and Distractor Effectiveness contrasting with 19 from faculty. Moreover, ChatGPT’s questions exhibited a higher rate of nonfunctional distractors (33.75% vs. faculty’s 13.75%). During focus group discussion, faculty highlighted importance of educators in reviewing, refining, and validating ChatGPT-generated SBMCQs to ensure their appropriateness within the educational context.

16 April 2025 in The National Medical Journal of India
Verified
Journal Article
Open access
ACArchana Chauhan
Archana Chauhan
AMAnushi Mahajan
Anushi Mahajan
JBJarina Begum
Jarina Begum
AKAnil Kapoor
Anil Kapoor
DBDinesh Badyal
Dinesh Badyal
SKSupriya Kulkarni
Supriya Kulkarni

1 December 2023 in Advances in Physiology Education
Verified
Journal Article
Closed access
ACArchana Chauhan
Archana Chauhan
JBjarina Begum
jarina Begum
SSShaistha Saiyad
Shaistha Saiyad
This article presents a highly unique and novel approach by introducing a structured checklist for communication skill assessment in medical students. Its rigorous validation process ensures reliability and effectiveness, while its adaptation to sociocultural norms highlights its relevance and applicability. The user-friendly design with a single-page layout and dichotomous scale further enhances its practicality in objective structured clinical examinations. The developed checklist equips educators with a valuable resource to assess and improve students’ communication abilities.

1 October 2024 in International Journal of Applied & Basic Medical Research
Verified
Journal Article
Open access
ACArchana Chauhan
Archana Chauhan
JBJarina Begum
Jarina Begum
KLK. M Lavanya
K. M Lavanya
AGAnju Gupta
Anju Gupta
SGSujata Ghosh
Sujata Ghosh
SKSupriya Kulkarni
Supriya Kulkarni
Background: Active learning strategies (ALSs) in medical education are valued for their effectiveness but face adoption challenges among educators, underscoring the need for a deeper understanding of their implementation and impact. Aim: The aim of the study was to investigate the perceptions of medical educators regarding the effectiveness and challenges of ALS through mentor–learner (ML) web-based discussions. Settings and Design: The retrospective cross-sectional study analyzed data from 32 medical educators enrolled in the Foundation for Advancement of International Medical Education Research course at Christian Medical College, Ludhiana. It utilized a mixed-method approach, gathering both quantitative and qualitative data through ML web discussions. Materials and Methods: The study used a “dual-method” approach, combining traditional online discussions with a “role-reversal” method on an ML web platform, promoting experiential learning. Participant responses on ALS implementation tasks were collected and analyzed within these discussions. Results: Participants shared various ALS for collaborative learning (20), classroom engagement (26), assessing prior knowledge (12), and note-taking during lectures (10). Further, among the 11 ALS examined, the ease of implementation varied significantly among participants ( P < 0.0001). Challenges in ALS implementation included inadequate faculty training (91%), motivation (84%), resource constraints (81%), student (75%), and administrative resistance (69%). Four themes emerged as recommendations for effective ALS implementation: empowering educators, engaging students, streamlining support systems, and monitoring impact. Conclusion: The study highlights a mixed perspective of medical educators on ALS. Although ALS was perceived as effective in fostering critical thinking and developing collaborative learning among students, various challenges, such as a lack of skilled faculty and resources, necessitated robust faculty development initiatives.