Tae Sun Park

Aim: This study aimed to evaluate the prevalence, clinical characteristics, and factors associated with cardiovascular autonomic neuropathy (CAN) in Korean individuals with long‐standing type 2 diabetes mellitus (T2DM). Methods: A total of 876 participants with long‐standing T2DM were enrolled in this multicenter cross‐sectional study. CAN was evaluated using standard cardiovascular autonomic reflex tests (CARTs) and corrected QT interval (QTc), with additional heart rate variability (HRV) analysis. CAN severity was classified as early, definite, or severe. Multivariable logistic regression analysis was performed to identify factors independently associated with CAN. Results: CAN was detected in 88.4% of participants. Individuals with CAN showed reduced HRV indices and prolonged QTc intervals. Multivariable analysis revealed advanced age (OR = 1.062; 95% CI: 1.035–1.091; p < 0.0001) and higher systolic blood pressure (OR = 1.036; 95% CI: 1.022–1.051; p < 0.0001) as factors independently associated with CAN. Conclusion: CAN is highly prevalent among Korean individuals with long‐standing T2DM. Older age and elevated systolic blood pressure were independently associated with CAN, highlighting the importance of routine CAN screening and careful blood pressure management.

Baikhwan Cho, Soowan Chae, Tae Sun Park, In Deok Kong, Byung-Il Yeh. JLM 2026;16:1-5. https://doi.org/10.15280/jlm.2026.16.1.1

Background/Objectives: Diabetic kidney disease (DKD) is a major cause of end-stage kidney disease and a leading contributor to morbidity and mortality in patients with type 2 diabetes mellitus (T2DM). However, predictive models for DKD onset in Korean patients with T2DM remain underexplored. This study aimed to develop and validate a machine learning (ML)-based DKD prediction model for this population. Methods: This retrospective study utilized electronic health records from six secondary or tertiary hospitals in Korea. The Jeonbuk National University Hospital cohort was used for model development (ratio training: test data, 8:2), whereas datasets from five other hospitals supported external validation. We employed multiple ML algorithms, including lasso, ridge, and elastic net regression; random forest; XGBoost; support vector machines; and neural networks. The model incorporated demographic variables, comorbidities, medications, and laboratory test results. Results: Among 5120 patients with T2DM, 1361 (26.6%) developed DKD. In the development cohort, XGBoost achieved the highest predictive performance (AUC: 0.8099), followed by random forest and logistic regression models (AUCs: 0.7977–0.8019). External validation confirmed the model’s robustness with high AUCs (XGBoost: 0.8113, logistic regression models: 0.8228–0.8271). Key predictive factors included age; baseline estimated glomerular filtration rate; and creatinine, hemoglobin, and hemoglobin A1c levels. Conclusions: Our findings highlight the potential of ML-based approaches in predicting DKD in patients with T2DM. The superior performance of XGBoost and logistic regression models underscores their clinical utility. External validation supports the model’s generalizability. This model is a valuable tool for the early DKD risk assessment of Korean patients with T2DM.

Lee SJ, et al. J Korean Med Sci. 2025 Apr;40:e154. https://doi.org/10.3346/jkms.2025.40.e154

Background: Several machine learning (ML) prediction models for neurodegenerative diseases (NDs) in type 2 diabetes mellitus (T2DM) have recently been developed. However, the predictive power of these models is limited by the lack of multiple risk factors. Objective: This study aimed to assess the validity and use of an ML model for predicting the 3-year incidence of ND in patients with T2DM. Methods: We used data from 2 independent cohorts—the discovery cohort (1 hospital; n=22,311) and the validation cohort (2 hospitals; n=2915)—to predict ND. The outcome of interest was the presence or absence of ND at 3 years. We selected different ML-based models with hyperparameter tuning in the discovery cohort and conducted an area under the receiver operating characteristic curve (AUROC) analysis in the validation cohort. Results: The study dataset included 22,311 (discovery) and 2915 (validation) patients with T2DM recruited between 2008 and 2022. ND was observed in 133 (0.6%) and 15 patients (0.5%) in the discovery and validation cohorts, respectively. The AdaBoost model had a mean AUROC of 0.82 (95% CI 0.79-0.85) in the discovery dataset. When this result was applied to the validation dataset, the AdaBoost model exhibited the best performance among the models, with an AUROC of 0.83 (accuracy of 78.6%, sensitivity of 78.6%, specificity of 78.6%, and balanced accuracy of 78.6%). The most influential factors in the AdaBoost model were age and cardiovascular disease. Conclusions: This study shows the use and feasibility of ML for assessing the incidence of ND in patients with T2DM and suggests its potential for use in screening patients. Further international studies are required to validate these findings.

BACKGROUND Several machine learning (ML) prediction models for neurodegenerative diseases (NDs) in type 2 diabetes mellitus (T2DM) have recently been developed. However, the predictive power of these models is limited by the lack of multiple risk factors. OBJECTIVE This study aimed to assess the validity and use of an ML model for predicting the 3-year incidence of ND in patients with T2DM. METHODS We used data from 2 independent cohorts—the discovery cohort (1 hospital; n=22,311) and the validation cohort (2 hospitals; n=2915)—to predict ND. The outcome of interest was the presence or absence of ND at 3 years. We selected different ML-based models with hyperparameter tuning in the discovery cohort and conducted an area under the receiver operating characteristic curve (AUROC) analysis in the validation cohort. RESULTS The study dataset included 22,311 (discovery) and 2915 (validation) patients with T2DM recruited between 2008 and 2022. ND was observed in 133 (0.6%) and 15 patients (0.5%) in the discovery and validation cohorts, respectively. The AdaBoost model had a mean AUROC of 0.82 (95% CI 0.79-0.85) in the discovery dataset. When this result was applied to the validation dataset, the AdaBoost model exhibited the best performance among the models, with an AUROC of 0.83 (accuracy of 78.6%, sensitivity of 78.6%, specificity of 78.6%, and balanced accuracy of 78.6%). The most influential factors in the AdaBoost model were age and cardiovascular disease. CONCLUSIONS This study shows the use and feasibility of ML for assessing the incidence of ND in patients with T2DM and suggests its potential for use in screening patients. Further international studies are required to validate these findings.

Disclosure: T. Park: None. I. Goak: None. H. Jin: None. K. Lee: None. Y. Kim: None. Backgrounds: Thyrotoxic periodic paralysis (TPP) is a life-threatening complication characterized recurrent episodes of hypokalemia and muscle weakness in the setting of thyrotoxicosis. The present study aimed to describe clinical manifestation and outcome of patients admitted for TPP in emergency department (ED). Methods: This retrospective study analyzed 42 patients with TPP who were admitted ED from January 2000 through December 2020 in a single tertiary referral hospital. Their clinical characteristics were reviewed retrospectively. Results: 42 patients with TPP were identified. The mean age of the patients was 35.0±12.4 years; all were males. The month in which the most patients occurred paralysis symptoms was February (16.7%), followed by October (14.3%). 5 patients had a history of severe exertion, 7 patients had ingested a heavy carbohydrate meal, one patient had an infection, 5 patients had ingested alcohol, but more than half of the patients (57.1%) were without a precipitating cause. TPP was the first presentation of thyrotoxicosis in 85.7% of patients. The most common cause of thyrotoxicosis in TPP patients was Graves' disease (88.1%). At the time of admission, the mean potassium level was 2.77±0.93 mmol/L (reference, 3.5-5.5), mean ionized calcium level was 1.17±0.15 mmol/L (1.13-1.32), mean Free T4 level was 43.36±16.92 pmol/L (11.5-22.7). About half of the patients (47.6%) suffered at least one further attack of TPP. 28 patients (66.7%) diagnosed with Graves’ disease had anti-thyroid drugs alone and 5 patients (11.9%) with thyrotoxic relapses eventually underwent radioactive iodine therapy. None of the patients underwent surgery. Conclusions: TPP can be the presenting feature of previously undiagnosed thyrotoxicosis and should be considered in the differential diagnosis in patients presenting with acute onset of motor paralysis. At the time of the TPP attack, a detailed interview and inquiry with a thorough physical examination usually provide clues to the diagnosis. Presentation: Saturday, June 17, 2023

BACKGROUND Various machine learning (ML) prediction models have recently been developed for cardiovascular disease (CVD) in type 2 diabetes mellitus (T2DM); however, the lack of multiple risk factors limits their predictive power. OBJECTIVE This study aimed to evaluate the validity and usefulness of an ML model for predicting the 3-year incidence of CVD in patients with T2DM. METHODS We used data from two independent cohorts, the discovery cohort (one hospital; n=12,809) and the validation cohort (two hospitals; n=2019), to predict CVD. The outcome of interest was the presence/absence of CVD at 3 years. We selected various ML-based models with hyperparameter tuning in the discovery cohort and performed an area under the receiver operating characteristic curve (AUROC) analysis in the validation cohort. RESULTS The study dataset included 12,809 (discovery) and 2,019 (validation) patients with T2DM recruited between 2008–2022. CVD was observed in 1,238 (10.2%) patients in the discovery cohort. The random forest (RF) model had a mean AUROC of 0.830 (95% confidence interval 0.816–0.845) in the discovery dataset. Applying this result to the extra-validation dataset revealed the best performance among the models, with an AUROC of 0.72 (accuracy of 65.4%, sensitivity of 66.0%, specificity of 65.4%, and balanced accuracy of 65.7%). Creatinine and glycated hemoglobin levels were the most influential factors in the RF model. CONCLUSIONS This study demonstrates the usefulness and feasibility of ML for assessing CVD incidence in patients with T2DM and suggests its potential for use in patient screening. Further international studies are required to validate our findings.