Endocr Connect
Department of Clinical Nutrition, Xin Hua Hospital Affiliated to School of Medicine, Shanghai Jiao Tong University, Shanghai, China.
Published: December 2024
Introduction: Gestational diabetes mellitus (GDM) significantly affects pregnancy outcomes. Therefore, it is crucial to develop prediction models since they can guide timely interventions to reduce the incidence of GDM and its associated adverse effects.
Methods: A total of 554 pregnant women were selected and their sociodemographic characteristics, clinical data and dietary data were collected. Dietary data were investigated by a validated semi-quantitative food frequency questionnaire (FFQ). We applied random forest mean decrease impurity for feature selection and the models are built using logistic regression, XGBoost, and LightGBM algorithms. The prediction performance of different models was compared by accuracy, sensitivity, specificity, area under curve (AUC) and Hosmer-Lemeshow test.
Results: Blood glucose, age, pre-pregnancy body mass index (BMI), triglycerides and high-density lipoprotein cholesterol (HDL) were the top five features according to the feature selection. Among the three algorithms, XGBoost performed best with an AUC of 0.788, LightGBM came second (AUC = 0.749), and logistic regression performed the worst (AUC = 0.712). In addition, XGBoost and LightGBM both achieved a fairly good performance when dietary information was included, surpassing their performance on the non-dietary dataset (0.788 vs 0.718 in XGBoost; 0.749 vs 0.726 in LightGBM).
Conclusion: XGBoost and LightGBM algorithms outperform logistic regression in predicting GDM among Chinese pregnant women. In addition, dietary data may have a positive effect on improving model performance, which deserves more in-depth investigation with larger sample size.
Download full-text PDF |
Source |
---|---|
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11623027 | PMC |
http://dx.doi.org/10.1530/EC-24-0169 | DOI Listing |
BioData Min
January 2025
Department of Applied Mathematics and Statistics, The State University of New York, Korea, Incheon, South Korea.
Background: The treatment effects are heterogenous across patients due to the differences in their microbiomes, which in turn implies that we can enhance the treatment effect by manipulating the patient's microbiome profile. Then, the coadministration of microbiome-based dietary supplements/therapeutics along with the primary treatment has been the subject of intensive investigation. However, for this, we first need to comprehend which microbes help (or prevent) the treatment to cure the patient's disease.
View Article and Find Full Text PDFBMC Public Health
January 2025
Unit of Social Pediatrics, Department of Pediatrics, Faculty of Medicine, Hacettepe University, Ankara, Turkey.
Background: Age-appropriate breastfeeding and adequate complementary feeding play a crucial role in reducing under-5 mortality rates, malnutrition, and mortality worldwide. Given the high prevalence of adolescent pregnancy in Uganda, we aimed to assess the competence of adolescent mothers in infant and young child feeding (IYCF) using data from the 2016 Uganda Demographic Health Survey.
Method: Our sample comprised the last children aged 6-23 months of mothers aged 15-29 years, totaling 2594 mother-infant pairs; 402 were aged 15-19 years, 1,388 were aged 20-29 years with their first delivery before the age of 20, and 804 were aged 20-29 years with their first delivery at 20 years or older.
BMC Public Health
January 2025
Faculty of Health Sciences, Department of Internal Medicine Nursing, Sakarya University, Sakarya, 54050, Turkey.
Background: Adults with diabetes encounter various challenges related to managing their condition. In this study, we explored the experiences of adults with type 2 diabetes mellitus with low socioeconomic status in Türkiye.
Methods: This study was conducted as a phenomenological qualitative research.
Sci Rep
January 2025
Department of Epidemiology and Health Statistics, Xiangya School of Public Health, Central South University, NO. 172 Tong Zi Po Road, Yuelu District, Changsha, 410006, Hunan, China.
Osteoporotic fractures are a major public health concern, particularly among the aging population, as they significantly contribute to morbidity, mortality, and reduced quality of life. While cardiovascular health (CVH) has traditionally been linked to cardiovascular disease outcomes, emerging evidence suggests it may also influence bone health. This study investigates the association between CVH, as measured by the Life's Essential 8 (LE8) score, and the prevalence of osteoporotic fractures in U.
View Article and Find Full Text PDFEur J Pediatr
January 2025
Department of Emergency and Critical Care Nursing, School of Nursing, College of Medicine and Health Sciences, University of Gondar, Gondar, Ethiopia.
Unlabelled: Poor consumption of fruits and vegetables is associated with an increased risk of non-communicable diseases, micronutrient deficiency, and undernutrition. Fruit and vegetable consumption is generally low worldwide, particularly in rural regions of many low- and middle-income countries. This study aimed to determine the prevalence and determinants of zero vegetable or fruit consumption among children aged 6 to 23 months in Kenya using the most recent Kenya Demographic and Health Survey.
View Article and Find Full Text PDFEnter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!
© LitMetric 2025. All rights reserved.