Cheng-Heng Liu

Cheng-Heng Liu

Auto-generated profile, based on publicly available information

Cheng-Heng Liu

Department of Medical Education, National Taiwan University Hospital

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
28 October 2024 in Journal of Dental Sciences
Verified
Journal Article
Open access
PLPing-Yi Lin
Ping-Yi Lin
YTYi-Hsuan Tsai
Yi-Hsuan Tsai
TCTing-Chen Chen
Ting-Chen Chen
CHChing-Yao Hsieh
Ching-Yao Hsieh
SOShiu-Fong Ou
Shiu-Fong Ou
CWChen-Ying Wang
Chen-Ying Wang
The shift towards virtual assessment in dental education represents a significant advancement over traditional evaluation methods, offering new opportunities for assessing both theoretical knowledge and practical skills. This review examines the use of virtual assessment tools within the context of dental education. A narrative literature review was conducted, analyzing studies published between 2000 and 2024, sourced from PubMed, the Cochrane Library, and Embase. From the initial search, 13 studies were selected for qualitative synthesis. The results indicate that virtual assessments, facilitated by technologies such as computer-based simulations and remote objective structured clinical examinations (OSCEs), have enhanced the accuracy and comprehensiveness of dental student evaluations. These methods allow for more consistent and objective assessments of competencies, addressing some limitations of traditional practical exams. However, the integration of virtual assessments presents challenges, including the need for significant investment in technology, infrastructure, and training for faculty and students. Despite these challenges, the review concludes that virtual assessment has the potential to become a cornerstone of modern dental education, offering a scalable and adaptable solution for evaluating dental competencies in diverse learning environments.

13 August 2026 in JMIR Medical Education
Verified
Journal Article
Open access
CLCheng-Heng Liu
Cheng-Heng Liu
YCYu-Ting Chen
Yu-Ting Chen
CHChih-Hung Hsu
Chih-Hung Hsu
HCHuey-Ling Chen
Huey-Ling Chen
CYChih-Wei Yang
Chih-Wei Yang
Background: Generative AI (GenAI) is increasingly integrated into clinical learning and practice. However, medical students often lack the competencies required for safe and critical use, including prompt design, output verification, and recognition of limitations. Educational interventions that integrate GenAI with clinical reasoning frameworks remain limited. Objective: This study evaluated a structured, theory-informed workshop integrating GenAI, prompt engineering, and clinical reasoning education to enhance medical students’ self-perceived AI literacy and collaborative learning attitudes, and to assess whether patient-centered orientation changed following intensive AI exposure. Methods: We conducted a single-group, pre-post, explanatory sequential mixed methods study with fifth-year medical students enrolled at an academic medical center between April 2024 and May 2025. The 3-hour workshop comprised 6 modules integrating clinical reasoning, cognitive-bias awareness, verification-oriented GenAI use, and hands-on prompt engineering and centered on ChatGPT (OpenAI). Quantitative outcomes were self-reported measures from a 20-item self-report AI-literacy questionnaire adapted from the Meta AI Literacy Scale and were examined with exploratory and confirmatory factor analysis, the 6-item Patient-Practitioner Orientation Scale-Short, and a modified Collaborative Learning Attitude Scale (CLAS). Pre-post change was assessed using 2-tailed paired t tests with Benjamini-Hochberg correction and Cohen d ; the Patient-Practitioner Orientation Scale-Short and CLAS were available for a subsample (n=46). Qualitative data from 6 interviews and 17 reflective narratives were analyzed using reflexive thematic analysis and integrated with the quantitative findings. Results: Among 150 eligible students, 139 (92.7%) completed paired AI-literacy assessments. Self-perceived AI literacy improved across all domains (Cohen d =0.69‐0.93, all P <.001; all remaining significant after false discovery rate correction), and collaborative learning attitudes increased substantially ( d =0.94, P <.001). Patient-centered orientation showed no significant change ( d =0.03); however, baseline scores were concentrated at the favorable end of the scale (a floor/restricted-range effect), and the subsample analysis was underpowered (minimum detectable dz =0.42), so this null result is inconclusive rather than evidence of unchanged orientation. Gains did not differ by sex or across the sequential cohorts. Reflexive thematic analysis (interviews: n=6; reflections: n=17) identified five themes and one emergent theme describing a shift toward verification-oriented GenAI use: (1) understanding GenAI capabilities and limitations, (2) prompt-engineering skill development, (3) calibrated trust through verification, (4) GenAI-supported communication and collaboration, and (5) ethical considerations, with emerging reconceptualization of professional identity. Conclusions: A brief, theory-informed educational intervention integrating GenAI with clinical reasoning was associated with medium-to-large improvements in self-perceived AI literacy and collaborative attitudes. No detectable change in patient-centered orientation was observed; however, this finding should be interpreted as inconclusive, given measurement and power constraints. Embedding verification practices within clinical reasoning frameworks may offer a scalable approach for preparing physicians for responsible human-AI collaboration. Future studies should incorporate comparative designs, performance-based assessments, and longitudinal follow-up.

4 January 2025 in Current Psychology
Verified
Journal Article
Closed access
PDF file
YJYuJeng Ju
YuJeng Ju
YWYi-Ching Wang
Yi-Ching Wang
SLShih-Chieh Lee
Shih-Chieh Lee
CLCheng-Heng Liu
Cheng-Heng Liu
JLJen-Hsuan Liu
Jen-Hsuan Liu
CHChing-Lin Hsieh
Ching-Lin Hsieh

27 October 2026 in JMIR Medical Education
Verified
Journal Article
Open access
CLCheng-Heng Liu
Cheng-Heng Liu
Ming-Ju HsiehMing-Ju Hsieh
Ming-Ju Hsieh
YCYu-Ting Chen
Yu-Ting Chen
CYChih-Wei Yang
Chih-Wei Yang
Background: Blended learning is common in health professions education, but aggregate comparisons may obscure differences among knowledge, procedural skill, and integrated performance. Whether these domains differ after program-level changes under a common assessment system remains uncertain. Objective: We aimed to compare knowledge, psychomotor performance, and integrated scenario competence between blended and traditional in-person emergency medical technician level 1 certification training, and, as an exploratory secondary aim, to describe digital engagement and technology acceptance among blended-cohort participants who completed the survey. Methods: We compared routinely collected certification records from traditional in-person (2020; n=603) and blended (2023; n=581) emergency medical technician level 1 cohorts. The primary outcome was psychomotor performance; secondary outcomes were knowledge, integrated scenario performance, and competency-threshold attainment. We estimated between-cohort differences with 95% CIs and adjusted linear regression. Equivalence was assessed using two 1-sided tests with expert-derived educational importance margins established through an instructor consensus exercise before the panel was provided with the between-cohort results (±5 points for knowledge, ±3 points for psychomotor performance, and ±4 points for integrated scenario performance). These margins represent educational consensus thresholds rather than externally validated clinical thresholds. Blended-cohort trainees were additionally offered a questionnaire on digital engagement and technology acceptance, analyzed by multiple linear regression on intention to use e-learning again. Results: Psychomotor performance was lower in the blended cohort (80.60, SD 9.70, vs 84.44, SD 10.80; mean difference 3.84, in-person minus blended, 95% CI 2.67-5.01; d=0.37; P<.001); the adjusted coefficient was −4.04 (95% CI −5.15 to −2.92; P<.001). Equivalence within the prespecified ±3-point margin was not demonstrated. Knowledge (difference −0.30, 95% CI −1.68 to 1.08) and integrated scenario performance (−0.94, 95% CI −1.89 to 0.00) fell within the prespecified ±5- and ±4-point margins, respectively. Psychomotor-threshold (521/581, 89.7%, vs 557/603, 92.4%; P=.10) and overall-certification rates (459/581, 79%, vs 474/603, 78.6%; P=.87) did not differ detectably. Knowledge-threshold attainment was higher in the blended cohort (516/581, 88.8%, vs 503/603, 83.4%; P=.007). Among the 236 blended-cohort participants who completed the survey, perceived benefits and positive attitudes toward digital learning were positively associated with intention to use e-learning again. Conclusions: The blended cohort had lower early psychomotor scores, whereas knowledge and integrated scenario differences fell within the prespecified margins. Programs adopting comparable models should assess psychomotor outcomes directly rather than infer them from knowledge or overall certification outcomes.

12 April 2026 in JMIR Preprints
Verified
Preprint
Open access
CLCheng-Heng Liu
Cheng-Heng Liu
Ming-Ju HsiehMing-Ju Hsieh
Ming-Ju Hsieh
YCYu-Ting Chen
Yu-Ting Chen
CYChih-Wei Yang
Chih-Wei Yang
BACKGROUND Blended learning is common in health professions education, but aggregate comparisons may obscure differences among knowledge, procedural skill, and integrated performance. Whether these domains differ after program-level changes under a common assessment system remains uncertain. OBJECTIVE We aimed to compare knowledge, psychomotor performance, and integrated scenario competence between blended and traditional in-person emergency medical technician level 1 certification training, and, as an exploratory secondary aim, to describe digital engagement and technology acceptance among blended-cohort participants who completed the survey. METHODS We compared routinely collected certification records from traditional in-person (2020; n=603) and blended (2023; n=581) emergency medical technician level 1 cohorts. The primary outcome was psychomotor performance; secondary outcomes were knowledge, integrated scenario performance, and competency-threshold attainment. We estimated between-cohort differences with 95% CIs and adjusted linear regression. Equivalence was assessed using two 1-sided tests with expert-derived educational importance margins established through an instructor consensus exercise before the panel was provided with the between-cohort results (±5 points for knowledge, ±3 points for psychomotor performance, and ±4 points for integrated scenario performance). These margins represent educational consensus thresholds rather than externally validated clinical thresholds. Blended-cohort trainees were additionally offered a questionnaire on digital engagement and technology acceptance, analyzed by multiple linear regression on intention to use e-learning again. RESULTS Psychomotor performance was lower in the blended cohort (80.60, SD 9.70, vs 84.44, SD 10.80; mean difference 3.84, in-person minus blended, 95% CI 2.67-5.01; d=0.37; P<.001); the adjusted coefficient was −4.04 (95% CI −5.15 to −2.92; P<.001). Equivalence within the prespecified ±3-point margin was not demonstrated. Knowledge (difference −0.30, 95% CI −1.68 to 1.08) and integrated scenario performance (−0.94, 95% CI −1.89 to 0.00) fell within the prespecified ±5- and ±4-point margins, respectively. Psychomotor-threshold (521/581, 89.7%, vs 557/603, 92.4%; P=.10) and overall-certification rates (459/581, 79%, vs 474/603, 78.6%; P=.87) did not differ detectably. Knowledge-threshold attainment was higher in the blended cohort (516/581, 88.8%, vs 503/603, 83.4%; P=.007). Among the 236 blended-cohort participants who completed the survey, perceived benefits and positive attitudes toward digital learning were positively associated with intention to use e-learning again. CONCLUSIONS The blended cohort had lower early psychomotor scores, whereas knowledge and integrated scenario differences fell within the prespecified margins. Programs adopting comparable models should assess psychomotor outcomes directly rather than infer them from knowledge or overall certification outcomes. CLINICALTRIAL

15 May 2024 in JMIR Preprints
Verified
Preprint
Open access
KHKuan-Ju Huang
Kuan-Ju Huang
CLCheng-Heng Liu
Cheng-Heng Liu
CWChien-Chun Wu
Chien-Chun Wu
BSBor-Ching Sheu
Bor-Ching Sheu
CYChih-Wei Yang
Chih-Wei Yang
BACKGROUND Generative AI has garnered awareness in the medical field, yet its potential is constrained by inherent limitations. By responding to inputs through predicting the next word from its memory-based archive, we aim to explore some of these constraints from a medical education and psychological perspective, utilizing Bloom’s taxonomy. OBJECTIVE To assess AI's cognitive functions in the medical sector by examining its performance through medical licensing exams and applying Bloom's taxonomy. METHODS Questions from the Taiwan Medical Licensing Examination (TMLE) (August 2022) and the third step of the United States Medical Licensing Examination (USMLE) (August 2022) were classified based on Bloom's taxonomy levels. The ChatGPT versions were tasked through individual prompts, with questions entered separately into ChatGPT-3.5 and ChatGPT-4 using different accounts. After each response, the chat logs were erased and reset to ensure the independence of each answer. Responses from ChatGPT-3.5 and ChatGPT-4, collected between January and February 2024, were analyzed. The questions from both exams were available online during the study period. RESULTS Although the overall performance of ChatGPT-4 surpassed that of ChatGPT-3.5, the analysis of responses from both models across various cognitive levels revealed no significant correlation between their performance and the levels of Bloom's taxonomy. This lack of significance persisted even when considering the strength of ChatGPTs in their extensive databases classified under "remember," compared to other cognitive levels labeled as "non-remember." CONCLUSIONS In the medical field, ChatGPT models may utilize their "remember" function to answer all types of questions across all categories defined by Bloom's taxonomy. Further research is required focusing on different versions, medical specialties, and the level of difficulty assessed by individuals from various backgrounds.