Seung Wook Lee
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
Seung Wook Lee has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Edric Tam
Department of Biomedical Data Science, Stanford University , 300 Pasteur Drive , Palo Alto, California 94304
2 shared publications - Hong Seo Lim
Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology and Emory University, Atlanta, Georgia, United States of America
2 shared publications - Hyoungwon Jeon
Department of Otorhinolaryngology‐Head and Neck Surgery Seoul National University Bundang Hospital Seongnam Republic of Korea
2 shared publications - Inez Lam
Clinical Pharmacology, Pharmacometrics, & Translational Sciences MapLight Therapeutics, Inc. Redwood City California USA
2 shared publications - Ja-Won Koo
Department of Otorhinolaryngology-Head and Neck Surgery, Seoul National University Bundang Hospital, Seoul National University College of Medicine
2 shared publications - Joanne Song
Center for Imaging Science and Institute for Computational Medicine, Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, United States
2 shared publications
Latest Publications
- Top Cited PapersOpen Access
- 15 September 2025
- Published by Korean Pediatric Society in Clinical and Experimental Pediatrics
- Vol. 68 (9) , 641-651
Artificial intelligence in pediatric healthcare: current applications, potential, and implementation considerations
Artificial intelligence (AI) has transformed pediatric healthcare by supporting diagnostics, personalized treatment strategies, and prognosis predictions. Although it offers significant promise in these areas, its application in pediatric settings poses distinct challenges compared with that in adults due to variable developmental status, the limited availability of pediatric data, and ethical concerns regarding bias and transparency. This narrative review summarizes the key concepts of AI and its clinical applications across clinical fields in the treatment of children and adolescents. Here we highlight the emerging role of large language models in performing administrative tasks and clinical documentation and supporting decision-making. We also address the evolving impact of AI integration in surgical care as an example while exploring ongoing concerns regarding reliability and diagnostic safety. Furthermore, we survey AI-enabled medical devices and discuss the current regulatory frameworks relevant to pediatric care. This review provides a balanced overview of opportunities and challenges from a pediatrician's standpoint and aims to facilitate effective alignment and collaboration with key stakeholders in pediatric healthcare. Pediatricians must implement AI solutions cautiously and accountably to avoid unintended harm and realize their potential.
- 15 September 2025
- Published by Korean Pediatric Society in Clinical and Experimental Pediatrics
- Vol. 68 (9) , 641-651
Top Cited PapersOpen AccessArtificial intelligence in pediatric healthcare: current applications, potential, and implementation considerations
Artificial intelligence (AI) has transformed pediatric healthcare by supporting diagnostics, personalized treatment strategies, and prognosis predictions. Although it offers significant promise in these areas, its application in pediatric settings poses distinct challenges compared with that in adults due to variable developmental status, the limited availability of pediatric data, and ethical concerns regarding bias and transparency. This narrative review summarizes the key concepts of AI and its clinical applications across clinical fields in the treatment of children and adolescents. Here we highlight the emerging role of large language models in performing administrative tasks and clinical documentation and supporting decision-making. We also address the evolving impact of AI integration in surgical care as an example while exploring ongoing concerns regarding reliability and diagnostic safety. Furthermore, we survey AI-enabled medical devices and discuss the current regulatory frameworks relevant to pediatric care. This review provides a balanced overview of opportunities and challenges from a pediatrician's standpoint and aims to facilitate effective alignment and collaboration with key stakeholders in pediatric healthcare. Pediatricians must implement AI solutions cautiously and accountably to avoid unintended harm and realize their potential.
- Open Access
- 12 July 2022
- Published by Springer Nature in npj Digital Medicine
Multi-center validation of machine learning model for preoperative prediction of postoperative mortality
Accurate prediction of postoperative mortality is important for not only successful postoperative patient care but also for information-based shared decision-making with patients and ef fi cient allocation of medical resources. This study aimed to create a machine-learning prediction model for 30-day mortality after a non-cardiac surgery that adapts to the manageable amount of clinical information as input features and is validated against multi-centered rather than single-centered data. Data were collected from 454,404 patients over 18 years of age who underwent non-cardiac surgeries from four independent institutions. We performed a retrospective analysis of the retrieved data. Only 12 – 18 clinical variables were used for model training. Logistic regression, random forest classi fi er, extreme gradient boosting (XGBoost), and deep neural network methods were applied to compare the prediction performances. To reduce over fi tting and create a robust model, bootstrapping and grid search with tenfold cross-validation were performed. The XGBoost method in Seoul National University Hospital (SNUH) data delivers the best performance in terms of the area under receiver operating characteristic curve (AUROC) (0.9376) and the area under the precision- recall curve (0.1593). The predictive performance was the best when the SNUH model was validated with Ewha Womans University Medical Center data (AUROC, 0.941). Preoperative albumin, prothrombin time, and age were the most important features in the model for each hospital. It is possible to create a robust arti fi cial intelligence prediction model applicable to multiple institutions through a light predictive model using only minimal preoperative information that can be automatically extracted from each hospital.
- 12 July 2022
- Published by Springer Nature in npj Digital Medicine
Open AccessMulti-center validation of machine learning model for preoperative prediction of postoperative mortality
Accurate prediction of postoperative mortality is important for not only successful postoperative patient care but also for information-based shared decision-making with patients and ef fi cient allocation of medical resources. This study aimed to create a machine-learning prediction model for 30-day mortality after a non-cardiac surgery that adapts to the manageable amount of clinical information as input features and is validated against multi-centered rather than single-centered data. Data were collected from 454,404 patients over 18 years of age who underwent non-cardiac surgeries from four independent institutions. We performed a retrospective analysis of the retrieved data. Only 12 – 18 clinical variables were used for model training. Logistic regression, random forest classi fi er, extreme gradient boosting (XGBoost), and deep neural network methods were applied to compare the prediction performances. To reduce over fi tting and create a robust model, bootstrapping and grid search with tenfold cross-validation were performed. The XGBoost method in Seoul National University Hospital (SNUH) data delivers the best performance in terms of the area under receiver operating characteristic curve (AUROC) (0.9376) and the area under the precision- recall curve (0.1593). The predictive performance was the best when the SNUH model was validated with Ewha Womans University Medical Center data (AUROC, 0.941). Preoperative albumin, prothrombin time, and age were the most important features in the model for each hospital. It is possible to create a robust arti fi cial intelligence prediction model applicable to multiple institutions through a light predictive model using only minimal preoperative information that can be automatically extracted from each hospital.
- Open Access
- 15 March 2021
- Published by JMIR Publications Inc. in JMIR mHealth and uHealth
- Vol. 9 (3) , e20890
An mHealth App (Speech Banana) for Auditory Training: App Design and Development Study
Background: With the growing adult population using electronic hearing devices such as cochlear implants or hearing aids, there is an increasing worldwide need for auditory training (AT) to promote optimal device use. However, financial resources and scheduling conflicts make clinical AT infeasible. Objective: To address this gap between need and accessibility, we primarily aimed to develop a mobile health (mHealth) app called Speech Banana for AT. The app would be substantially more affordable and portable than clinical AT; would deliver a validated training model that is reflective of modern techniques; and would track users’ progress in speech comprehension, providing greater continuity between periodic in-person visits. To improve international availability, our secondary aim was to implement the English language training model into Korean as a proof of concept for worldwide usability. Methods: A problem- and objective-centered Design Science Research Methodology approach was adopted to develop the Speech Banana app. A review of previous literature and computer-based learning programs outlined current AT gaps, whereas interviews with speech pathologists and users clarified the features that were addressed in the app. Past and present users were invited to evaluate the app via community forums and the System Usability Scale. Results: Speech Banana has been implemented in English and Korean languages for iPad and web use. The app comprises 38 lessons, which include analytic exercises pairing visual and auditory stimuli, and synthetic quizzes presenting auditory stimuli only. During quizzes, users type the sentence heard, and the app provides visual feedback on performance. Users may select a male or female speaker and the volume of background noise, allowing for training with a range of frequencies and signal-to-noise ratios. There were more than 3200 downloads of the English iPad app and almost 100 downloads of the Korean app; more than 100 users registered for the web apps. The English app received a System Usability Scale rating of “good” from 6 users, and the Korean app received a rating of “OK” from 16 users. Conclusions: Speech Banana offers AT accessibility with a validated curriculum, allowing users to develop speech comprehension skills with the aid of a mobile device. This mHealth app holds potential as a supplement to clinical AT, particularly in this era of global telemedicine.
- 15 March 2021
- Published by JMIR Publications Inc. in JMIR mHealth and uHealth
- Vol. 9 (3) , e20890
Open AccessAn mHealth App (Speech Banana) for Auditory Training: App Design and Development Study
Background: With the growing adult population using electronic hearing devices such as cochlear implants or hearing aids, there is an increasing worldwide need for auditory training (AT) to promote optimal device use. However, financial resources and scheduling conflicts make clinical AT infeasible. Objective: To address this gap between need and accessibility, we primarily aimed to develop a mobile health (mHealth) app called Speech Banana for AT. The app would be substantially more affordable and portable than clinical AT; would deliver a validated training model that is reflective of modern techniques; and would track users’ progress in speech comprehension, providing greater continuity between periodic in-person visits. To improve international availability, our secondary aim was to implement the English language training model into Korean as a proof of concept for worldwide usability. Methods: A problem- and objective-centered Design Science Research Methodology approach was adopted to develop the Speech Banana app. A review of previous literature and computer-based learning programs outlined current AT gaps, whereas interviews with speech pathologists and users clarified the features that were addressed in the app. Past and present users were invited to evaluate the app via community forums and the System Usability Scale. Results: Speech Banana has been implemented in English and Korean languages for iPad and web use. The app comprises 38 lessons, which include analytic exercises pairing visual and auditory stimuli, and synthetic quizzes presenting auditory stimuli only. During quizzes, users type the sentence heard, and the app provides visual feedback on performance. Users may select a male or female speaker and the volume of background noise, allowing for training with a range of frequencies and signal-to-noise ratios. There were more than 3200 downloads of the English iPad app and almost 100 downloads of the Korean app; more than 100 users registered for the web apps. The English app received a System Usability Scale rating of “good” from 6 users, and the Korean app received a rating of “OK” from 16 users. Conclusions: Speech Banana offers AT accessibility with a validated curriculum, allowing users to develop speech comprehension skills with the aid of a mobile device. This mHealth app holds potential as a supplement to clinical AT, particularly in this era of global telemedicine.
- Open Access
- 21 June 2020
- Published by JMIR Publications Inc. in JMIR Preprints
An mHealth App (Speech Banana) for Auditory Training: App Design and Development Study (Preprint)
BACKGROUND With the growing adult population using electronic hearing devices such as cochlear implants or hearing aids, there is an increasing worldwide need for auditory training (AT) to promote optimal device use. However, financial resources and scheduling conflicts make clinical AT infeasible. OBJECTIVE To address this gap between need and accessibility, we primarily aimed to develop a mobile health (mHealth) app called Speech Banana for AT. The app would be substantially more affordable and portable than clinical AT; would deliver a validated training model that is reflective of modern techniques; and would track users’ progress in speech comprehension, providing greater continuity between periodic in-person visits. To improve international availability, our secondary aim was to implement the English language training model into Korean as a proof of concept for worldwide usability. METHODS A problem- and objective-centered Design Science Research Methodology approach was adopted to develop the Speech Banana app. A review of previous literature and computer-based learning programs outlined current AT gaps, whereas interviews with speech pathologists and users clarified the features that were addressed in the app. Past and present users were invited to evaluate the app via community forums and the System Usability Scale. RESULTS Speech Banana has been implemented in English and Korean languages for iPad and web use. The app comprises 38 lessons, which include analytic exercises pairing visual and auditory stimuli, and synthetic quizzes presenting auditory stimuli only. During quizzes, users type the sentence heard, and the app provides visual feedback on performance. Users may select a male or female speaker and the volume of background noise, allowing for training with a range of frequencies and signal-to-noise ratios. There were more than 3200 downloads of the English iPad app and almost 100 downloads of the Korean app; more than 100 users registered for the web apps. The English app received a System Usability Scale rating of “good” from 6 users, and the Korean app received a rating of “OK” from 16 users. CONCLUSIONS Speech Banana offers AT accessibility with a validated curriculum, allowing users to develop speech comprehension skills with the aid of a mobile device. This mHealth app holds potential as a supplement to clinical AT, particularly in this era of global telemedicine.
- 21 June 2020
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessAn mHealth App (Speech Banana) for Auditory Training: App Design and Development Study (Preprint)
BACKGROUND With the growing adult population using electronic hearing devices such as cochlear implants or hearing aids, there is an increasing worldwide need for auditory training (AT) to promote optimal device use. However, financial resources and scheduling conflicts make clinical AT infeasible. OBJECTIVE To address this gap between need and accessibility, we primarily aimed to develop a mobile health (mHealth) app called Speech Banana for AT. The app would be substantially more affordable and portable than clinical AT; would deliver a validated training model that is reflective of modern techniques; and would track users’ progress in speech comprehension, providing greater continuity between periodic in-person visits. To improve international availability, our secondary aim was to implement the English language training model into Korean as a proof of concept for worldwide usability. METHODS A problem- and objective-centered Design Science Research Methodology approach was adopted to develop the Speech Banana app. A review of previous literature and computer-based learning programs outlined current AT gaps, whereas interviews with speech pathologists and users clarified the features that were addressed in the app. Past and present users were invited to evaluate the app via community forums and the System Usability Scale. RESULTS Speech Banana has been implemented in English and Korean languages for iPad and web use. The app comprises 38 lessons, which include analytic exercises pairing visual and auditory stimuli, and synthetic quizzes presenting auditory stimuli only. During quizzes, users type the sentence heard, and the app provides visual feedback on performance. Users may select a male or female speaker and the volume of background noise, allowing for training with a range of frequencies and signal-to-noise ratios. There were more than 3200 downloads of the English iPad app and almost 100 downloads of the Korean app; more than 100 users registered for the web apps. The English app received a System Usability Scale rating of “good” from 6 users, and the Korean app received a rating of “OK” from 16 users. CONCLUSIONS Speech Banana offers AT accessibility with a validated curriculum, allowing users to develop speech comprehension skills with the aid of a mobile device. This mHealth app holds potential as a supplement to clinical AT, particularly in this era of global telemedicine.