Isaac Sung Him Ng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Isaac Sung Him Ng has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Oscar Sing Him Ho
King’s College London GKT School of Medical Education, London, UK
3 shared publications Abirami Muthukumar
2 shared publicationsAnatoliy Markiv
2 shared publications- Anatoliy Markiv
Faculty of Life Sciences and Medicine, King’s College London, London WC2R 2LS, UK
2 shared publications - Anthony Siu
Faculty of Life Sciences and Medicine, King’s College London, London WC2R 2LS, UK
2 shared publications Chantelle Gasa
2 shared publications
Latest Publications
- Open Access
- 19 September 2025
- Published by MDPI AG in Behavioral Sciences
- Vol. 15 (9) , 1284
Evaluating a Custom Chatbot in Undergraduate Medical Education: Randomised Crossover Mixed-Methods Evaluation of Performance, Utility, and Perceptions
Background: While LLM chatbots are gaining popularity in medical education, their pedagogical impact remains under-evaluated. This study examined the effects of a domain-specific chatbot on performance, perception, and cognitive engagement among medical students. Methods: Twenty first-year medical students completed two academic tasks using either a custom-built educational chatbot (Lenny AI by qVault) or conventional study methods in a randomised, crossover design. Performance was assessed through Single Best Answer (SBA) questions, while post-task surveys (Likert scales) and focus groups were employed to explore user perceptions. Statistical tests compared performance and perception metrics; qualitative data underwent thematic analysis with independent coding (κ = 0.403–0.633). Results: Participants rated the chatbot significantly higher than conventional resources for ease of use, satisfaction, engagement, perceived quality, and clarity (p < 0.05). Lenny AI use was positively correlated with perceived efficiency and confidence, but showed no significant performance gains. Thematic analysis revealed accelerated factual retrieval but limited support for higher-level cognitive reasoning. Students expressed high functional trust but raised concerns about transparency. Conclusions: The custom chatbot improved usability; effects on deeper learning were not detected within the tasks studied. Future designs should support adaptive scaffolding, transparent sourcing, and critical engagement to improve educational value.
- 19 September 2025
- Published by MDPI AG in Behavioral Sciences
- Vol. 15 (9) , 1284
Open AccessEvaluating a Custom Chatbot in Undergraduate Medical Education: Randomised Crossover Mixed-Methods Evaluation of Performance, Utility, and Perceptions
Background: While LLM chatbots are gaining popularity in medical education, their pedagogical impact remains under-evaluated. This study examined the effects of a domain-specific chatbot on performance, perception, and cognitive engagement among medical students. Methods: Twenty first-year medical students completed two academic tasks using either a custom-built educational chatbot (Lenny AI by qVault) or conventional study methods in a randomised, crossover design. Performance was assessed through Single Best Answer (SBA) questions, while post-task surveys (Likert scales) and focus groups were employed to explore user perceptions. Statistical tests compared performance and perception metrics; qualitative data underwent thematic analysis with independent coding (κ = 0.403–0.633). Results: Participants rated the chatbot significantly higher than conventional resources for ease of use, satisfaction, engagement, perceived quality, and clarity (p < 0.05). Lenny AI use was positively correlated with perceived efficiency and confidence, but showed no significant performance gains. Thematic analysis revealed accelerated factual retrieval but limited support for higher-level cognitive reasoning. Students expressed high functional trust but raised concerns about transparency. Conclusions: The custom chatbot improved usability; effects on deeper learning were not detected within the tasks studied. Future designs should support adaptive scaffolding, transparent sourcing, and critical engagement to improve educational value.
- Open Access
- 16 June 2025
- Published by MDPI AG in Preprints.org
AI Chatbots in Medical Education: Exploring Performance, Utility, and Learner Perceptions – A Mixed Methods Study
Background: While AI chatbots are gaining popularity in medical education, their pedagogical impact remains under-evaluated. This study examined the impact of a domain-specific chatbot on learning performance, perception, and cognitive engagement among medical students. Methods: Twenty first-year medical students completed two academic tasks using a custom-built educational chatbot (Lenny AI by qVault.ai) or conventional study methods in a randomised, crossover design. Learning was assessed through Single Best Answer (SBA) questions over two tasks with corresponding post-task perception surveys using Likert scales, and separate focus group discussions. Statistical analyses were performed to compare performance scores with perception measures, while qualitative data underwent thematic analysis with independent coding (κ = 0.403–0.633). Results: Participants rated the chatbot significantly higher than conventional resources in ease of use, satisfaction, engagement, perceived quality, and ease of understanding. (p < 0.05). Improvements in perceived efficiency and confidence were observed with mixed patterns. Lenny AI use did not result in significant performance gains; however, it was positively correlated with perceived efficiency, confidence in applying information, and perceived quality of information. Thematic analysis revealed accelerated factual retrieval but limited critical thinking and schema integration. Students expressed high functional trust but raised concerns about transparency. The chatbot was seen as a tool for rapid fact-checking, favouring learners who were goal-directed. Conclusion: AI chatbots can substantially enhance ease of use, satisfaction, and knowledge access in medical education. However, their capacity to foster deep learning remains limited. Future designs must prioritise adaptive scaffolding, traceable sourcing, and support for critical engagement to achieve sustained educational value.
- 16 June 2025
- Published by MDPI AG in Preprints.org
Open AccessAI Chatbots in Medical Education: Exploring Performance, Utility, and Learner Perceptions – A Mixed Methods Study
Background: While AI chatbots are gaining popularity in medical education, their pedagogical impact remains under-evaluated. This study examined the impact of a domain-specific chatbot on learning performance, perception, and cognitive engagement among medical students. Methods: Twenty first-year medical students completed two academic tasks using a custom-built educational chatbot (Lenny AI by qVault.ai) or conventional study methods in a randomised, crossover design. Learning was assessed through Single Best Answer (SBA) questions over two tasks with corresponding post-task perception surveys using Likert scales, and separate focus group discussions. Statistical analyses were performed to compare performance scores with perception measures, while qualitative data underwent thematic analysis with independent coding (κ = 0.403–0.633). Results: Participants rated the chatbot significantly higher than conventional resources in ease of use, satisfaction, engagement, perceived quality, and ease of understanding. (p < 0.05). Improvements in perceived efficiency and confidence were observed with mixed patterns. Lenny AI use did not result in significant performance gains; however, it was positively correlated with perceived efficiency, confidence in applying information, and perceived quality of information. Thematic analysis revealed accelerated factual retrieval but limited critical thinking and schema integration. Students expressed high functional trust but raised concerns about transparency. The chatbot was seen as a tool for rapid fact-checking, favouring learners who were goal-directed. Conclusion: AI chatbots can substantially enhance ease of use, satisfaction, and knowledge access in medical education. However, their capacity to foster deep learning remains limited. Future designs must prioritise adaptive scaffolding, traceable sourcing, and support for critical engagement to achieve sustained educational value.
- 1 November 2024
- Published by IATED Academy
- Vol. 1, 9761
ENHANCING AI-GENERATED SINGLE BEST ANSWER QUESTIONS IN MEDICAL EDUCATION: A STUDY ON THE EFFECTIVENESS OF PROMPT CHAINING
- 1 November 2024
- Published by IATED Academy
- Vol. 1, 9761
ENHANCING AI-GENERATED SINGLE BEST ANSWER QUESTIONS IN MEDICAL EDUCATION: A STUDY ON THE EFFECTIVENESS OF PROMPT CHAINING
- 1 October 2021
- Published by Elsevier in World Neurosurgery
- Vol. 154, e580-e589
Cannabis Use and Increased Nonaneurysmal Subarachnoid Hemorrhage in the Past Decade
- 1 October 2021
- Published by Elsevier in World Neurosurgery
- Vol. 154, e580-e589
Cannabis Use and Increased Nonaneurysmal Subarachnoid Hemorrhage in the Past Decade