1.AI-driven Medical Care: Evaluation of Large Language Models in Generating Personalized Stroke Education Materials
Surim YOON ; Woo-Keun SEO ; Kyungseo KIM ; Seongvin JU ; Hyun Kyung KIM ; Hyung Jun KIM ; Jong-Won CHUNG ; Oh Young BANG ; Gyeong-Moon KIM ; Eun Young LEE ; Youngrak CHOI ; Soyoung YOO
Healthcare Informatics Research 2026;32(2):179-189
Objectives:
Large language models (LLMs) demonstrate remarkable potential in healthcare communication. However, whether they can process complex, high-volume medical information, such as stroke-related content, remains insufficiently validated. This study aimed to evaluate the natural language processing capabilities of LLMs in handling such content and to develop an evaluation instrument.
Methods:
A survey compared educational materials generated by two LLMs (ChatGPT 4.0 and Claude 3) with neurologist-authored content on stroke. The materials were based on two clinical scenarios representing distinct stroke etiologies: cardioembolism and large-artery atherosclerosis. They were evaluated in terms of accuracy, legality, ethics, comprehensiveness, and information delivery. Scores for comprehensiveness and information delivery were compared according to participants’ agreement with the use of LLMs in healthcare.
Results:
ChatGPT received the highest scores across all domains, except for legality in Scenario 2. In Scenario 1, the ranking for accuracy and summarization of clinical information was, from highest to lowest, ChatGPT, Claude, and the neurologist (η2 = 0.140, p < 0.001; η2 = 0.175, p < 0.001). The same hierarchy was observed in Scenario 2 for accuracy (η2 = 0.077, p < 0.001) and summarization (η2 = 0.194, p < 0.001). Participants who agreed with the use of LLMs in healthcare assigned higher scores for the comprehensiveness (Scenario 1, p = 0.005; Scenario 2, p = 0.007) and information delivery (Scenario 1, p = 0.003; Scenario 2, p = 0.026) of ChatGPT-generated materials than participants who did not agree.
Conclusions
LLMs demonstrated adequate capability to convey complex content, such as stroke-related information, in an accessible and understandable manner for non-experts.
2.The First Korean Case of MAN1B1-Congenital Disorder of Glycosylation Diagnosed Using Whole-Exome Sequencing and Matrix-Assisted Laser Desorption Ionization Time-of-Flight Mass Spectrometry
Kyoung Bo KIM ; Gi Su LEE ; Soyoung SHIN ; Dong-Chan KIM ; Donggun SEO ; Hyeongjin KWEON ; Hyein KANG ; Sunggyun PARK ; Do-Hoon KIM ; Namhee RYOO ; Soyoung LEE ; Jung Sook HA
Annals of Laboratory Medicine 2025;45(1):112-115
6.Establishing Three-Dimensional Explant Culture of Human Dental Pulp Tissue
Eun Jin SEO ; Soyoung PARK ; Eungyung LEE ; Yang Hoon HUH ; Ye Eun HA ; Gabor J. TIGYI ; Taesung JEONG ; Il Ho JANG ; Jonghyun SHIN
International Journal of Stem Cells 2024;17(3):330-336
Mesenchymal stem cells in the dental tissue indicate a disposition for differentiation into diverse dental lineages and contain enormous potential as the important means for regenerative medicine in dentistry. Among various dental tissues, the dental pulp contains stem cells, progenitor cells and odontoblasts for maintaining dentin homeostasis. The conventional culture of stem cells holds a limit as the living tissue constitutes the three-dimensional (3D) structure. Recent development in the organoid cultures have successfully recapitulated 3D structure and advanced to the assembling of different types. In the current study, the protocol for 3D explant culture of the human dental pulp tissue has been established by adopting the organoid culture. After isolating dental pulp from human tooth, the intact tissue was placed between two layers for Matrigel with addition of the culture medium. The reticular outgrowth of pre-odontoblast layer continued for a month and the random accumulation of dentin was observed near the end. Electron microscopy showed the cellular organization and in situ development of dentin, and immunohistochemistry exhibited the expression of odontoblast and stem cell markers in the outgrowth area. Three-dimensional explant culture of human dental pulp will provide a novel platform for understanding stem cell biology inside the tooth and developing the regenerative medicine.
7.Late-onset drug resistant epilepsy in an adolescent with Allan-Herndon-Dudley syndrome
Soyoung PARK ; Young-Lim SHIN ; Go Hun SEO ; Yong Hee HONG
Journal of Genetic Medicine 2024;21(1):31-35
Allan-Herndon-Dudley syndrome (AHDS) is a rare X-linked neurodevelopmental disorder with abnormal thyroid function caused by mutation in the solute carrier family 16 member 2 (SLC16A2) gene. Clinical manifestations of AHDS are global or axial hypotonia, a variety of movement disorders, severe intellectual disability, quadriplegia or spastic diplegia, growth failure, and seizures. A 10-year-old boy visited our hospital with the chief complaint of newly onset generalized tonic seizures with vocalization of weekly to daily frequency. He showed early infantile hypotonia, severe intellectual disability, and frequent respiratory infections. He could not walk independently and was non-verbal. Electroencephalogram revealed generalized slow spike and waves with multifocal spikes and slow background rhythms. His tonic seizures were controlled with more than two anti-seizure medications (ASMs). At 11 years of age, he was evaluated for thyroid function as part of regular screening for ASM maintenance and was found to have abnormal thyroid function. We performed whole exome sequencing for severe global developmental delay, drug-resistant epilepsy, and abnormal thyroid function. The hemizygous c.940C>T (p.Arg314Ter) variant in the SLC16A2 gene (NM_006517.5) was identified and confirmed based on Sanger sequencing. Herein, we describe a case of an AHDS patient with late-onset drug-resistant epilepsy combined with congenital hypotonia, global developmental delay, and abnormal thyroid function results. To the best of our knowledge, this is the oldest adolescent among AHDS cases reported in Korea. In this report, clinical characteristics of a mid-adolescence patient with AHDS were presented.
8.Phosphate level predicts mortality in acute kidney injury patients undergoing continuous kidney replacement therapy and has a U-shaped association with mortality in patients with high disease severity: a multicenter retrospective study
Young Hwan LEE ; Soyoung LEE ; Yu Jin SEO ; Jiyun JUNG ; Jangwook LEE ; Jae Yoon PARK ; Tae Hyun BAN ; Woo Yeong PARK ; Sung Woo LEE ; Kipyo KIM ; Kyeong Min KIM ; Hyosang KIM ; Ji-Young CHOI ; Jang-Hee CHO ; Yong Chul KIM ; Jeong-Hoon LIM
Kidney Research and Clinical Practice 2024;43(4):492-504
This study investigated the association between serum phosphate level and mortality in acute kidney injury (AKI) patients undergoing continuous kidney replacement therapy (CKRT) and evaluated whether this association differed according to disease severity. Methods: Data from eight tertiary hospitals in Korea were retrospectively analyzed. The patients were classified into four groups (low, normal, high, and very high) based on their serum phosphate level at baseline. The association between serum phosphate level and mortality was then analyzed, with further subgroup analysis being conducted according to disease severity. Results: Among the 3,290 patients identified, 166, 955, 1,307, and 862 were in the low, normal, high, and very high phosphate groups, respectively. The 90-day mortality rate was 63.9% and was highest in the very high group (76.3%). Both the high and very high groups showed a significantly higher 90-day mortality rate than did the normal phosphate group (high: hazard ratio [HR], 1.35, 95% confidence interval [CI], 1.21–1.51, p < 0.001; very high: HR, 2.01, 95% CI, 1.78–2.27, p < 0.001). The low group also exhibited a higher 90-day mortality rate than did the normal group among those with high disease severity (HR, 1.47; 95% CI, 1.09–1.99; p = 0.01) but not among those with low disease severity. Conclusion: High serum phosphate level predicted increased mortality in AKI patients undergoing CKRT, and low phosphate level was associated with increased mortality in patients with high disease severity. Therefore, serum phosphate levels should be carefully considered in critically ill patients with AKI.
10.Clinical Manifestation of Alopecia Areata After COVID-19 Infection or Vaccination
Seungjin SON ; Soyoung JIN ; Ji Yeon HONG ; Jung-Min SHIN ; Kyung Eun JUNG ; Young-Joon SEO ; Chang-Deok KIM ; Dongkyun HONG ; Young LEE
Annals of Dermatology 2024;36(6):361-366
Background:
Alopecia areata (AA) is characterized by an autoimmune inflammatory response to hair follicles. Several studies have suggested that infection and vaccination can trigger an autoimmune process around hair follicles. Moreover, reports of AA and various other autoimmune diseases have increased since the coronavirus disease 2019 (COVID-19) pandemic became established.
Objective:
We assessed the clinical characteristics and treatment response in patients who developed AA following COVID-19 infection or vaccination.
Methods:
This retrospective study involved patients who had developed COVID-19 or received a COVID-19 vaccination within 3 months before the onset or aggravation of AA from January 2020 to December 2022.
Results:
Fifty patients met the inclusion criteria. Eighteen patients had a history of COVID-19 infection, and 32 had a history of COVID-19 vaccination. The mean onset of AA after COVID-19 infection and vaccination was 5.22±3.35 and 4.13±2.73 weeks, respectively. The most common COVID-19-associated symptoms before AA were fever (88.9%) in the infection group and myalgia (50.0%) in the vaccination group. In the vaccination group, AA most commonly occurred after receiving the Pfizer-BioNTech vaccine (BNT162b2, 46.9%) or Moderna vaccine (mRNA-1273, 34.4%). The vaccination group showed more rapid improvement than the infection group;however, both showed significant improvement after 6 months of treatment of AA.
Conclusion
We examined the clinical characteristics and treatment responses of patients who developed AA after COVID-19 infection or vaccination. Further research is needed to evaluate the detailed pathogenesis and association between COVID-19 and AA.

Result Analysis
Print
Save
E-mail