Junseok Kang

Junseok Kang

Auto-generated profile, based on publicly available information

Junseok Kang

Harvard John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
31 October 2025 in Ewha Medical Journal
Verified
Journal Article
Open access
JKJunseok Kang
Junseok Kang
JAJihyun Ahn
Jihyun Ahn
Generative artificial intelligence (GenAI), including large language models such as GPT-4 and image-generation tools like DALL-E, is rapidly transforming the landscape of medical education. These technologies present promising opportunities for advancing personalized learning, clinical simulation, assessment, curriculum development, and academic writing. Medical schools have begun incorporating GenAI tools to support students’ self-directed study, design virtual patient encounters, automate formative feedback, and streamline content creation. Preliminary evidence suggests improvements in engagement, efficiency, and scalability. However, GenAI integration also introduces substantial challenges. Key concerns include hallucinated or inaccurate content, bias and inequity in artificial intelligence (AI)-generated materials, ethical issues related to plagiarism and authorship, risks to academic integrity, and the potential erosion of empathy and humanistic values in training. Furthermore, most institutions currently lack formal policies, structured training, and clear guidelines for responsible GenAI use. To realize the full potential of GenAI in medical education, educators must adopt a balanced approach that prioritizes accuracy, equity, transparency, and human oversight. Faculty development, AI literacy among learners, ethical frameworks, and investment in infrastructure are essential for sustainable adoption. As the role of AI in medicine expands, medical education must evolve in parallel to prepare future physicians who are not only skilled users of advanced technologies but also compassionate, reflective practitioners.

31 January 2026 in The Asian Journal of Kinesiology
Verified
Journal Article
Open access
PDF file
BKBokyoung Kim
Bokyoung Kim
JKJunseok Kang
Junseok Kang
YJYun Jae Jung
Yun Jae Jung
JAJihyun Ahn
Jihyun Ahn
Generative artificial intelligence (AI), particularly large language models (LLMs) such as ChatGPT, has rapidly advanced in capability and accessibility, creating novel paradigms for personalized healthcare. In exercise and sports medicine, where clinical decision-making necessitates the integration of complex physiological data, individualized programming, and patient-centered communication, generative AI offers transformative potential for workflow augmentation. This narrative review synthesizes current applications, strengths, and limitations across seven core domains: (1) personalized exercise prescription, (2) performance enhancement and training support, (3) clinical rehabilitation and disease management, (4) lifestyle modification, (5) education and communication, (6) injury prevention, and (7) data analytics. LLMs demonstrated the ability to generate structured exercise prescriptions and rehabilitation protocols with moderate to high guideline compliance across cardiac and musculoskeletal rehabilitation contexts, while patient education content achieved favorable readability and clinical relevance ratings. Furthermore, methodological advancements such as prompt engineering and wearable-integrated closed-loop systems have enhanced personalization and real-time adaptability. In the domain of patient communication, generative AI tools produced readable educational materials with high factual consistency, although challenges persist regarding comorbidity screening, individualized safety verification, and cultural-linguistic contextualization. Ultimately, generative AI is poised to function as a first-draft accelerator and productivity amplifier within exercise and sports medicine. However, mandatory expert oversight, rigorous clinical validation, and robust governance frameworks remain essential prerequisites for the safe and effective integration of this approach into frontline clinical practice.

27 October 2025 in Journal of Educational Evaluation for Health Professions
Verified
Journal Article
Open access
PDF file
BKBokyoung Kim
Bokyoung Kim
JKJunseok Kang
Junseok Kang
MKMin-Young Kim
Min-Young Kim
JAJihyun Ahn
Jihyun Ahn
The emergence of large language models (LLMs) has generated growing interest in their potential applications for medical assessment and item development. This practice-oriented narrative review examines the potential of LLMs, particularly ChatGPT, for generating and validating single-best-answer multiple-choice questions in health professions licensing examinations, using a Korean Medical Licensing Examination (KMLE)-focused case perspective. We frame LLMs as human-in-the-loop tools rather than replacements for high-stakes testing. Recent applications of LLMs in assessment were reviewed, including prompting strategies such as few-shot, multi-stage, and chain-of-thought methods, as well as retrieval-augmented generation (RAG) to align outputs with exam blueprints. Approaches to enforcing formatting rules, checklist-based self-validation, and iterative refinement were analyzed for their role in supporting item development. Findings indicate that LLMs can perform near passing thresholds on high-stakes exams and assist with grading and feedback tasks. Prompt engineering enhances structural fidelity and clinical plausibility, while human oversight remains critical for accuracy, cultural appropriateness, and psychometric defensibility. The emerging multimodal generation of images, audio, and video suggests the feasibility of new item formats, provided robust validation safeguards are implemented. The most effective approach is a human-in-the-loop workflow that leverages artificial intelligence efficiency while embedding expert judgment, psychometric evaluation, and ethical governance. This practice-oriented roadmap—integrating strategic prompt selection, RAG-based blueprint alignment, rigorous validation gates, and KMLE-specific formatting—offers an implementable and methodologically defensible approach for licensing examinations.

30 November 2025 in International Journal of Thyroidology
Verified
Journal Article
Open access
PDF file
BKBokyoung Kim
Bokyoung Kim
JAJihyun Ahn
Jihyun Ahn
JKJunseok Kang
Junseok Kang
JHJeong Hun Hah
Jeong Hun Hah
Bokyoung Kim, Jihyun Ahn, Junseok Kang and Jeong Hun Hah. Int J Thyroidol 2025;18:124-33. https://doi.org/10.11106/ijt.2025.18.2.124

1 January 2026 in Journal of Periodontal & Implant Science
Verified
Journal Article
Open access
KKKeun-Suh Kim
Keun-Suh Kim
Chunui LeeChunui Lee
Chunui Lee
JKJun-Seok Kang
Jun-Seok Kang
WKWoo-Joo Kim
Woo-Joo Kim
HLHyo-Jung Lee
Hyo-Jung Lee
JLJae-Hong Lee
Jae-Hong Lee
Kim KS, et al. J Periodontal Implant Sci. 2026 ;56:e21. https://doi.org/10.5051/jpis.2504860243

1 January 2026 in Journal of Periodontal & Implant Science
Verified
Journal Article
Open access
PDF file
JKJun-Seok Kang
Jun-Seok Kang
YKYeon-Tae Kim
Yeon-Tae Kim
Akhilanand ChaurasiaAkhilanand Chaurasia
Akhilanand Chaurasia
JLJae-Hong Lee
Jae-Hong Lee
Kang JS, et al. J Periodontal Implant Sci. 2026 ;56:e34. https://doi.org/10.5051/jpis.2601900095