Jaewook Yu

Mr. Jaewook Yu

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
11 December 2024 in Journal of Medical Internet Research
Verified
Journal Article
Open access
SCSeungbeom Cho
Seungbeom Cho
MLMangyeong Lee
Mangyeong Lee
JYJaewook Yu
Jaewook Yu
JYJunghee Yoon
Junghee Yoon
JCJae-Boong Choi
Jae-Boong Choi
JCJuhee Cho
Juhee Cho
Background: Hospital call centers play a critical role in providing support and information to patients with cancer, making it crucial to effectively identify and understand patient intent during consultations. However, operational efficiency and standardization of telephone consultations, particularly when categorizing diverse patient inquiries, remain significant challenges. While traditional deep learning models like long short-term memory (LSTM) and bidirectional encoder representations from transformers (BERT) have been used to address these issues, they heavily depend on annotated datasets, which are labor-intensive and time-consuming to generate. Large language models (LLMs) like GPT-4, with their in-context learning capabilities, offer a promising alternative for classifying patient intent without requiring extensive retraining. Objective: This study evaluates the performance of GPT-4 in classifying the purpose of telephone consultations of patients with cancer. In addition, it compares the performance of GPT-4 to that of discriminative models, such as LSTM and BERT, with a particular focus on their ability to manage ambiguous and complex queries. Methods: We used a dataset of 430,355 sentences from telephone consultations with patients with cancer between 2016 and 2020. LSTM and BERT models were trained on 300,000 sentences using supervised learning, while GPT-4 was applied using zero-shot and few-shot approaches without explicit retraining. The accuracy of each model was compared using 1,000 randomly selected sentences from 2020 onward, with special attention paid to how each model handled ambiguous or uncertain queries. Results: GPT-4, which uses only a few examples (a few shots), attained a remarkable accuracy of 85.2%, considerably outperforming the LSTM and BERT models, which achieved accuracies of 73.7% and 71.3%, respectively. Notably, categories such as “Treatment,” “Rescheduling,” and “Symptoms” involve multiple contexts and exhibit significant complexity. GPT-4 demonstrated more than 15% superior performance in handling ambiguous queries in these categories. In addition, GPT-4 excelled in categories like “Records” and “Routine,” where contextual clues were clear, outperforming the discriminative models. These findings emphasize the potential of LLMs, particularly GPT-4, for interpreting complicated patient interactions during cancer-related telephone consultations. Conclusions: This study shows the potential of GPT-4 to significantly improve the classification of patient intent in cancer-related telephone oncological consultations. GPT-4’s ability to handle complex and ambiguous queries without extensive retraining provides a substantial advantage over discriminative models like LSTM and BERT. While GPT-4 demonstrates strong performance in various areas, further refinement of prompt design and category definitions is necessary to fully leverage its capabilities in practical health care applications. Future research will explore the integration of LLMs like GPT-4 into hybrid systems that combine human oversight with artificial intelligence–driven technologies.

11 August 2026 in Journal of Medical Internet Research
Verified
Journal Article
Open access
MLMangyeong Lee
Mangyeong Lee
SCSeung-Beom Cho
Seung-Beom Cho
JYJaewook Yu
Jaewook Yu
JYJunghee Yoon
Junghee Yoon
JCJae-Boong Choi
Jae-Boong Choi
JCJuhee Cho
Juhee Cho
Background: Patients with cancer undergoing long-term or vesicant chemotherapy frequently require peripherally inserted central catheters (PICCs). Due to the nature of ambulatory treatment administration, self-PICC management is essential for the continuation and completion of the planned treatment. Large language models offer potential for continuous patient support, but hallucinations and insufficient adherence to clinical protocols remain concerns. Fine-tuning (FT) and retrieval-augmented generation (RAG) improve factual grounding but cannot enforce the structured decision logic of expert-led PICC consultations, leaving the value of dialogue-control mechanisms unclear. Objective: This study is an expert-panel evaluation designed to exploratorily verify whether a finite state machine (FSM)–guided RAG architecture yields incremental gains in clinical acceptability when added on top of FT and RAG compared with simpler architectures (fine-tuned model alone; fine-tuned model with RAG). Methods: We conducted a blinded ablation comparison of three chatbot architectures sharing an identical fine-tuned GPT-4o-mini base: model 1 (fine-tuning only; FT), model 2 (FT + RAG), and model 3 (FT + RAG + FSM). Three nurses specializing in PICC management (≥10 y experience) independently evaluated responses to 43 PICC-related queries. The two-stage evaluation comprised query-level forced-choice preference and global Likert ratings across 8 predefined dimensions. Interrater agreement was quantified with Gwet AC1. Preference rates were compared with Cochran Q and pairwise McNemar tests with Bonferroni correction. Global Likert ratings were summarized descriptively across 8 predefined dimensions. Results: The FSM-guided model (model 3) was preferred in 34 of 43 scenarios (79.1%). Interrater agreement was moderate (Gwet AC1=0.58, 95% CI 0.42‐0.75; P <.001). Differences in model preference were significant (Cochran Q=48.2; P <.001). Pairwise McNemar tests showed model 3 was preferred significantly more often than model 1 and model 2 (both P <.001), while model 1 versus model 2 did not differ after Bonferroni correction. For the global ratings, descriptive statistics indicated that model 3 received higher ratings than models 1 and 2 across most criteria, although it tended to receive lower ratings for efficiency, possibly reflecting its multiturn structure. In qualitative debriefing, the nurses noted occasional unnecessary conversational turns under FSM guidance. Conclusions: In this expert-panel content-validation study, the FSM-guided fine-tuned RAG model received higher expert-rated acceptability than the simpler architectures, with FSM-based dialogue control more closely aligning chatbot outputs with expert-led PICC consultation patterns. Patient-facing usability testing and multicenter validation are required before claims regarding patient safety or clinical deployment can be made.

2 July 2024 in JMIR Preprints
Verified
Preprint
Open access
SCSeungbeom Cho
Seungbeom Cho
MLMangyeong Lee
Mangyeong Lee
JYJaewook Yu
Jaewook Yu
JYJunghee Yoon
Junghee Yoon
JCJae-Boong Choi
Jae-Boong Choi
JCJuhee Cho
Juhee Cho
BACKGROUND Hospital call centers play a critical role in providing support and information to patients with cancer, making it crucial to effectively identify and understand patient intent during consultations. However, operational efficiency and standardization of telephone consultations, particularly when categorizing diverse patient inquiries, remain significant challenges. While traditional deep learning models like long short-term memory (LSTM) and bidirectional encoder representations from transformers (BERT) have been used to address these issues, they heavily depend on annotated datasets, which are labor-intensive and time-consuming to generate. Large language models (LLMs) like GPT-4, with their in-context learning capabilities, offer a promising alternative for classifying patient intent without requiring extensive retraining. OBJECTIVE This study evaluates the performance of GPT-4 in classifying the purpose of telephone consultations of patients with cancer. In addition, it compares the performance of GPT-4 to that of discriminative models, such as LSTM and BERT, with a particular focus on their ability to manage ambiguous and complex queries. METHODS We used a dataset of 430,355 sentences from telephone consultations with patients with cancer between 2016 and 2020. LSTM and BERT models were trained on 300,000 sentences using supervised learning, while GPT-4 was applied using zero-shot and few-shot approaches without explicit retraining. The accuracy of each model was compared using 1,000 randomly selected sentences from 2020 onward, with special attention paid to how each model handled ambiguous or uncertain queries. RESULTS GPT-4, which uses only a few examples (a few shots), attained a remarkable accuracy of 85.2%, considerably outperforming the LSTM and BERT models, which achieved accuracies of 73.7% and 71.3%, respectively. Notably, categories such as “Treatment,” “Rescheduling,” and “Symptoms” involve multiple contexts and exhibit significant complexity. GPT-4 demonstrated more than 15% superior performance in handling ambiguous queries in these categories. In addition, GPT-4 excelled in categories like “Records” and “Routine,” where contextual clues were clear, outperforming the discriminative models. These findings emphasize the potential of LLMs, particularly GPT-4, for interpreting complicated patient interactions during cancer-related telephone consultations. CONCLUSIONS This study shows the potential of GPT-4 to significantly improve the classification of patient intent in cancer-related telephone oncological consultations. GPT-4’s ability to handle complex and ambiguous queries without extensive retraining provides a substantial advantage over discriminative models like LSTM and BERT. While GPT-4 demonstrates strong performance in various areas, further refinement of prompt design and category definitions is necessary to fully leverage its capabilities in practical health care applications. Future research will explore the integration of LLMs like GPT-4 into hybrid systems that combine human oversight with artificial intelligence–driven technologies.

9 June 2026 in Applied Sciences
Verified
Journal Article
Open access
PDF file
JYJaewook Yu
Jaewook Yu
SYSangmo Yang
Sangmo Yang
JCJae-Boong Choi
Jae-Boong Choi
Reactive Ion Etching (RIE) equipment widely employs showerhead-type structures to ensure plasma and etching uniformity; however, geometric degradation of the showerhead nozzle exit during prolonged operation may alter the internal chamber environment and thereby affect process performance. In this study, the effects of showerhead nozzle exit geometric degradation on process characteristics were evaluated for a 300 mm wafer-scale RIE system using a multiphysics numerical approach. A total of 16 analysis cases were constructed according to nozzle position and nozzle exit diameter, and Computational Fluid Dynamics (CFD), electrostatic analysis, and particle tracing analysis were performed sequentially using COMSOL Multiphysics. The results showed that increasing the showerhead nozzle exit diameter decreased both the pressure and velocity at the nozzle exit, while increasing the electric potential near the nozzle exit. These changes led to different wafer-level distributions of neutral and charged species. Neutral species were mainly affected by drag-based transport under the flow field, whereas charged species were influenced by both the flow field and the electric potential distribution. Cases with below-range neutral-species distributions occurred more frequently than cases with above-range distributions, and below-range charged-species distributions were concentrated in cases with larger diameter combinations. These findings indicate that geometric degradation of the showerhead nozzle exit can influence wafer-level reactive-species distributions through coupled fluidic and electrical pathways and may contribute to process non-uniformity.