• Contact us
  • E-Submission
ABOUT
BROWSE ARTICLES
JOURNAL POLICIES
FOR CONTRIBUTORS

Page Path

10
results for

"Diabetes mellitus"

Filter

Article category

Keywords

Publication year

Authors

"Diabetes mellitus"

Original articles

[English]
Feature-based ensemble modeling for addressing diabetes data imbalance using the SMOTE, RUS, and random forest methods: a prediction study
Younseo Jang
Received March 31, 2025  Accepted April 10, 2025  Published online April 15, 2025  
DOI: https://doi.org/10.12771/emj.2025.00353    [Epub ahead of print]
Purpose
This study developed and evaluated a feature-based ensemble model integrating the synthetic minority oversampling technique (SMOTE) and random undersampling (RUS) methods with a random forest approach to address class imbalance in machine learning for early diabetes detection, aiming to improve predictive performance.
Methods
Using the Scikit-learn diabetes dataset (442 samples, 10 features), we binarized the target variable (diabetes progression) at the 75th percentile and split it 80:20 using stratified sampling. The training set was balanced to a 1:2 minority-to-majority ratio via SMOTE (0.6) and RUS (0.66). A feature-based ensemble model was constructed by training random forest classifiers on 10 two-feature subsets, selected based on feature importance, and combining their outputs using soft voting. Performance was compared against 13 baseline models, using accuracy and area under the curve (AUC) as metrics on the imbalanced test set.
Results
The feature-based ensemble model and balanced random forest both achieved the highest accuracy (0.8764), followed by the fully connected neural network (0.8700). The ensemble model had an excellent AUC (0.9227), while k-nearest neighbors had the lowest accuracy (0.8427). Visualizations confirmed its superior discriminative ability, especially for the minority (high-risk) class, which is a critical factor in medical contexts.
Conclusion
Integrating SMOTE, RUS, and feature-based ensemble learning improved classification performance in imbalanced diabetes datasets by delivering robust accuracy and high recall for the minority class. This approach outperforms traditional resampling techniques and deep learning models, offering a scalable and interpretable solution for early diabetes prediction and potentially other medical applications.
  • 151 View
  • 9 Download
[English]
Cyclic dual latent discovery for improved blood glucose prediction through patient–provider interaction modeling: a prediction study
Suyeon Park, Seoyoung Kim, Dohyoung Rim
Received March 30, 2025  Accepted April 7, 2025  Published online April 15, 2025  
DOI: https://doi.org/10.12771/emj.2025.00332    [Epub ahead of print]
Purpose
Accurate prediction of blood glucose variability is crucial for effective diabetes management, as both hypoglycemia and hyperglycemia are associated with increased morbidity and mortality. However, conventional predictive models rely primarily on patient-specific biometric data, often neglecting the influence of patient–provider interactions, which can significantly impact outcomes. This study introduces Cyclic Dual Latent Discovery (CDLD), a deep learning framework that explicitly models patient–provider interactions to improve prediction of blood glucose levels. By leveraging a real-world intensive care unit (ICU) dataset, the model captures latent attributes of both patients and providers, thus improving forecasting accuracy.
Methods
ICU patient records were obtained from the MIMIC-IV v3.0 critical care database, including approximately 5,014 instances of patient–provider interaction. The CDLD model uses a cyclic training mechanism that alternately updates patient and provider latent representations to optimize predictive performance. During preprocessing, all numeric features were normalized, and extreme glucose values were capped at 500 mg/dL to mitigate the effect of outliers.
Results
CDLD outperformed conventional models, achieving a root mean square error of 0.0852 on the validation set and 0.0899 on the test set, which indicates improved generalization. The model effectively captured latent patient–provider interaction patterns, yielding more accurate glucose variability predictions than baseline approaches.
Conclusion
Integrating patient–provider interaction modeling into predictive frameworks can increase blood glucose prediction accuracy. The CDLD model offers a novel approach to diabetes management, potentially paving the way for artificial intelligence-driven personalized treatment strategies.
  • 157 View
  • 7 Download

Review

[English]
Relationship between periodontitis and systemic health conditions: a narrative review
Min-Young Kim, Eun-Kyoung Pang
Received March 4, 2025  Accepted April 8, 2025  Published online April 14, 2025  
DOI: https://doi.org/10.12771/emj.2025.00101    [Epub ahead of print]
This review examines the bidirectional relationship between periodontitis and systemic health conditions, offering an integrated perspective based on current evidence. It synthesizes epidemiological data, biological mechanisms, and clinical implications to support collaborative care strategies recognizing oral health as a key component of overall wellness. Periodontitis affects 7.4% to 11.2% of adults worldwide, and its prevalence increases with age. Beyond its local effects, including gingival inflammation, periodontal pocket formation, and alveolar bone loss, periodontitis is associated with various systemic conditions. Emerging evidence has established links with obesity, diabetes mellitus, cardiovascular disease, chronic kidney disease, inflammatory bowel disease, rheumatoid arthritis, respiratory diseases, adverse pregnancy outcomes, certain malignancies, neurodegenerative diseases, psychological disorders, and autoimmune conditions. These associations are mediated by 3 primary mechanisms: dysbiotic oral biofilms, chronic low-grade systemic inflammation, and the dissemination of periodontal pathogens throughout the body. The pathophysiology involves elevated levels of pro-inflammatory cytokines (including interleukin 6, tumor necrosis factor alpha, and C-reactive protein), impaired immune function, oxidative stress, and molecular mimicry. Periodontal pathogens, particularly Porphyromonas gingivalis, are crucial in initiating and sustaining systemic inflammatory responses. Treatment of periodontitis has demonstrated measurable improvements in numerous systemic conditions, emphasizing the clinical significance of these interconnections. Periodontitis should be understood as more than just a localized oral disease; it significantly contributes to the overall systemic inflammatory burden, with implications for general health. An integrated, multidisciplinary approach to prevention, early detection, and comprehensive treatment is vital for optimal patient outcomes. Healthcare providers should acknowledge oral health as an essential element of systemic well-being.
  • 140 View
  • 9 Download

Case Report

[English]
Determining the timing and extent of amputation in symmetrical peripheral gangrene: a report of three cases from Korea
Maria Florencia Deslivia, Hyun-Joo Lee, In-Ho Jeon, Hemanshu Kochhar, Hyo-Jin Kim, Poong-Taek Kim
Ewha Med J 2025;48(1):e77.   Published online January 31, 2025
DOI: https://doi.org/10.12771/emj.2024.e77

Symmetrical peripheral gangrene is a severe condition marked by symmetric acral necrosis without obstruction of the major blood vessels. This case report examines the critical decisions involved in choosing between early and delayed amputation, as well as determining the extent of the necessary amputation. We present three cases: one involving antiphospholipid syndrome, another with disseminated intravascular coagulation, and a third associated with diabetes mellitus. All three cases ultimately required amputation due to symmetrical peripheral gangrene. In the first two cases, amputation was delayed, which is typically advantageous as it allows for the clear demarcation of necrotic tissue. However, in the third case, where infection was evident, immediate amputation was necessary despite the patient's overall poor health.

  • 161 View
  • 17 Download

Review Articles

[English]
Diagnostic and Therapeutic Strategies of Type 2 Diabetes Mellitus in Youth
Hwa Young Kim, Jae Hyun Kim
Ewha Med J 2022;45(3):e3.   Published online July 31, 2022
DOI: https://doi.org/10.12771/emj.2022.e3
ABSTRACT

The incidence of type 2 diabetes mellitus (T2DM) is increasing in youth, largely in correlation with an increase in childhood overweight and obesity. Youth-onset T2DM is a major public health concern worldwide, and tends to show more aggressive features than adult-onset T2DM. Early diagnosis and treatment are important to prevent the occurrence of complications and comorbidities. However, current treatment options are limited and only modestly successful in youth-onset T2DM. Over the last few decades, significant progress has been made in the understanding of youth-onset T2DM. This review summarizes the current understanding of the pathogenesis, diagnosis, and treatment of T2DM in youth. (Ewha Med J 2022;45(3):e3)

  • 109 View
  • 0 Download
[Korean]

Type 1 diabetes requires lifelong insulin therapy because insulin-secretion capability is diminished. Glycemic control and glucose monitoring are important to prevent type 1 diabetes complications. Diabetes technologies have developed rapidly; continuous glucose monitoring (CGM) and continuous subcutaneous insulin infusion (CSII) are now common and greatly aid glycemic control, especially in children and adolescents. The National Health Insurance Service has provided partial reimbursements for both CGM and CSII devices since 2019 and 2020, respectively; the devices are thus expected to become more popular. CGM reduces the frequency of hypoglycemia and the level of glycated hemoglobin. CSII affords more precise glycemic control than multi-dose insulin therapy. CSII showed reduced frequency of hypoglycemia and improved metabolic outcome without an increase in the body mass index z-score. Technological advancement of combined CGM and CSII will eventually serve as an artificial pancreas. The National Health Insurance Service should fund not only the devices but also education of patients and caregivers. In addition, healthcare providers must be continuously updated on new diabetes technologies.

Citations

Citations to this article as recorded by  
  • Tailored Meal-Type Food Provision for Diabetes Patients Can Improve Routine Blood Glucose Management in Patients with Type 2 Diabetes: A Crossover Study
    Dong Hoon Jung, Jae Won Han, Hyeri Shin, Hee-Sook Lim
    Nutrients.2024; 16(8): 1190.     CrossRef
  • 222 View
  • 6 Download
  • 1 Web of Science
  • 1 Crossref

Case Reports

[English]
Paroxetine-induced Hypoglycemia in Type 2 Diabetic Patient
Seunghee Han, Hye-Sun Park, Yong-ho Lee, Byung-Wan Lee, Eun Seok Kang, Bong-Soo Cha
Ewha Med J 2016;39(1):14-16.   Published online January 29, 2016
DOI: https://doi.org/10.12771/emj.2016.39.1.14

Selective serotonin reuptake inhibitors are commonly prescribed drugs for the treatment of depression in the patients with diabetes. Here, we report a case of paroxetineinduced severe recurrent hypoglycemia that developed in a 35-year-old woman with poorly controlled type 2 diabetes complicated by diabetic nephropathy and neuropathy. She discontinued her daily insulin therapy 2 months after the introduction of paroxetine, but hypoglycemic events were sustained. After discontinuation of paroxetine, no more hypoglycemic events occurred.

Citations

Citations to this article as recorded by  
  • Pharmacological treatment for mental health illnesses in adults receiving dialysis: A scoping review
    Jenny Wichart, Peter Yoeun, Tracy Chin, Christopher Evernden, Charlotte Berendonk, Jodi Kerr, Alexandra Birchall, Belinda Boschee, Kimberly Defoe, Jasleen Dhaliwal, Tasia KarisAllen, Megan Kennedy, Alexis McDonald, Monika K. Mierzejewski, Kara Schick‐Maka
    Fundamental & Clinical Pharmacology.2024; 38(5): 862.     CrossRef
  • Paroxetine

    Reactions Weekly.2016; 1597(1): 166.     CrossRef
  • 119 View
  • 4 Download
  • 2 Crossref
[English]
Cutaneous Mucormycosis in a Patient with Diabetes Mellitus
Ji Hwan Park, Seo Hwa Park, Eun Gyu Kang, Gyu Cheon Kyung, Hyo Dong An, So-Yeon An
Ewha Med J 2016;39(1):10-13.   Published online January 29, 2016
DOI: https://doi.org/10.12771/emj.2016.39.1.10

Mucormycosis is a rare disease caused by fungi. Most commonly involved sites of mucormycosis infection are sinuses, lungs, skin and soft tissues. Systemic risk factors for mucormycosis are diabetes mellitus, neutropenia, corticosteroid use, hematological malignancies, organ transplantation, metabolic acidosis, deferoxamine use and advanced age. Local risk factors are history of trauma, burns, surgery and motor vehicle accidents. We present a case of cutaneous mucormycosis in a patient with diabetes mellitus. A 66-year-old female with uncontrolled diabetes mellitus, admitted with necrotizing lesion after minor abrasions on leg. We took a culture of the lesion and it is diagnosed with mucormycosis. Disease progressed despite administration of systemic amphotericin B. We performed above-knee amputation and changed antifungal agents into liposomal amphotericin B. A tissue biopsy showed nonseptate, irregularly wide fungal hyphae with frequent right-angle branching. Our case report suggests that patients with risk factors should be observed carefully.

Citations

Citations to this article as recorded by  
  • Epidemiology and Treatment Outcome of Mucormycosis in Khuzestan, Southwest of Iran
    Roohangiz Nashibi, Sara Afzalzadeh, Mohammad Javad Mohammadi, Ahmad Reza Yari, Farid Yousefi
    Archives of Clinical Infectious Diseases.2016;[Epub]     CrossRef
  • 106 View
  • 0 Download
  • 1 Crossref
Original Articles
[English]
Decreased Insulin Secretion in Women with Previous Gestational Diabetes Mellitus
Yoon Pyo Lee, Soo Kyung Lim, Ji young Chang, Eun kyo Jung, Youn-i Choi, Jee-Young Oh, Youngsun Hong, Yeon-Ah Sung, Hyejin Lee
Ewha Med J 2015;38(1):30-35.   Published online March 26, 2015
DOI: https://doi.org/10.12771/emj.2015.38.1.30
Objectives

Gestational diabetes mellitus (GDM) affects 2%-4% of the all pregnant women, and it is a major risk factor for development of type 2 DM. We performed this cross-sectional study to determine whether there were defects in insulin secretory capacity or insulin sensitivity in women with previous GDM.

Methods

On 6-8 weeks after delivery, 75 g oral glucose tolerance test was performed in 36 women with previous GDM and 19 non-pregnant control women matched with age and weight. Intravenous glucose tolerance test was performed on 10-14 weeks after delivery. Insulin secretory capacity measured as the acute insulin response to glucose (AIRg) and insulin sensitivity as minimal model derived sensitivity index (SI) were obtained. AIRg×SI (β-cell disposition index) was used as an index of β-cell function.

Results

Women with previous GDM were classified into normal glucose tolerance (postpartum-NGT, n=19) and impaired glucose tolerance (postpartum-IGT, n=17). Postpartum fasting glucose levels were significantly higher in postpartum-IGT compared to postpartum-NGT and control (P<0.05). AIRg×SI was significantly lower in postpartum-IGT compared to control (P<0.05). SI was lower in postpartum-NGT and postpartum-IGT compared to control, but the difference did not have the statistical significance. Frequency of parental history of type 2 diabetes was significantly greater in postpartum-IGT compared to postpartum-NGT (P<0.05).

Conclusion

Women with previous GDM showed impaired insulin secretion although their glucose tolerance states were restored to normal. It suggests impaired early insulin secretion may be a major pathophysiologic factor for development of type 2 DM, and this defect may be genetically determined.

  • 77 View
  • 0 Download
[English]
CT Findings of Tuberculous Pneumonia in Diabetic Patients: Comparison with Tuberculosis in Nondiabetics
Yookyung Kim, Sung Won Park, Sang Min Lee, Kyung Soo Cho
Ihwa Ŭidae chi 2001;24(3):109-114.   Published online September 30, 2001
DOI: https://doi.org/10.12771/emj.2001.24.3.109
Objective

To evaluate the CT findings of pulmonary tuberculosis in diabetic patients compared with patients without underlying disease.

Methods

The chest CT scans of pulmonary tuberculosis in 23 diabetic patients(M : F=21 : 2 ; mean age, 59 yrs.) and in 24 nondiabetic patients(M : F=12 : 12 ; mean age, 48 yrs.) were retrospectively analyzed by two radiologists ; decisions were reached by consensus.

Results

The frequencies of consolidation(100%, 42%), inhomogeneity of consolidation(70%, 21%), multiple small low-density areas(52%, 13%), cavitation(70%, 25%), multiple small cavity(35%, 4%), bizarre-shaped cavity(22%, 0%), air-bronchogram(95%, 54%) were significantly more common in pulmonary tuberculosis in diabetic patients than in nondiabetic patients(p<.05). There was no significant difference in localization of pulmonary lesions between diabetic and nondiabetic patients.

Conclusion

Diabetic patients have a high prevalence of inhomogeneous consolidation containing multiple small low densities and multiple or bizarre-shaped cavities than do patients without diabetics.

  • 56 View
  • 0 Download
TOP