Prevalence of Pre-diabetes, Diabetes and Associated Risk Factors among Staff and Students of Federal Polytechnic, Kaura-Namoda DOI Creative Commons

Uthman Kabiru Samaila,

Idris Aliyu Kankara

International Journal of Science for Global Sustainability, Journal Year: 2023, Volume and Issue: 9(4), P. 90 - 94

Published: Dec. 31, 2023

Obesity and overweight are major public health issues worldwide. This study was aimed at assessing the prevalence of diabetes its associated risk factors among staff students Federal Polytechnic Kaura-Namoda. A total 159 participants took part in study, consisting 60 99 students. Anthropometric measurement World Health Organization’s (WHO) cut-offs were used to classify body weight into underweight, normal weight, obesity. Fasting blood glucose (FBG) level determined using glucometer. Blood pressure measured an electronic monitor. The overall 2.5%, with 2.0% being known cases 0.5% newly diagnosed individuals. higher (2%) than (0.5%). pre-diabetes 5.7%, 4.4% occurring 1.3% While prevalent obesity 51% 23.9% respectively, participants, more affected staff. Hypertension found males (1.9%) none females. Also, pre-hypertension (32%) (0%). Pre-diabetes overweight, obese, hypertensive, 40 years or above participants. There a correlation between age, obesity, hypertension. In conclusion, low hypertension, Kaura Namoda. adoption regular physical exercise, healthy eating habits, lifestyle is therefore recommended for improved status.

Language: Английский

Explainable Machine Learning-Based Prediction Model for Diabetic Nephropathy DOI Creative Commons

Jing-Mei Yin,

Yang Li,

Jun-Tang Xue

et al.

Journal of Diabetes Research, Journal Year: 2024, Volume and Issue: 2024, P. 1 - 13

Published: Jan. 20, 2024

The aim of this study is to analyze the effect serum metabolites on diabetic nephropathy (DN) and predict prevalence DN through a machine learning approach. dataset consists 548 patients from April 2018 2019 in Second Affiliated Hospital Dalian Medical University (SAHDMU). We select optimal 38 features least absolute shrinkage selection operator (LASSO) regression model 10-fold cross-validation. compare four algorithms, including extreme gradient boosting (XGB), random forest, decision tree, logistic regression, by AUC-ROC curves, calibration curves. quantify feature importance interaction effects predictive Shapley additive explanation (SHAP) method. XGB has best performance screen for with highest AUC value 0.966. also gains more clinical net benefits than others, fitting degree better. In addition, there are significant interactions between duration diabetes. develop algorithm DN. C2, C5DC, Tyr, Ser, Met, C24, C4DC, Cys have great contribution can possibly be biomarkers

Language: Английский

Citations

10
Artificial intelligence applied to diabetes complications: a bibliometric analysis DOI Creative Commons
Yu-Han Tao,

Jinzheng Hou,

Guangxin Zhou

et al.

Frontiers in Artificial Intelligence, Journal Year: 2025, Volume and Issue: 8

Published: Jan. 31, 2025

Artificial intelligence (AI)-driven medical assistive technology has been widely used in the diagnosis, treatment and prognosis of diabetes complications. Here we conduct a bibliometric analysis scientific articles field AI complications to explore current research trends cutting-edge hotspots. On April 20, 2024, collected screened relevant published from 1988 2024 PubMed. Based on tools such as CiteSpace, Vosviewer bibliometix, construct knowledge maps visualize literature information, including annual production, authors, countries, institutions, journals, keywords A total 935 meeting criteria were analyzed. The number publications showed an upward trend. Raman, Rajiv most articles, Webster, Dale R had highest collaboration frequency. United States, China, India productive countries. Scientific Reports was journal with publications. three frequent diabetic retinopathy, nephropathy, foot. Machine learning, screening, deep foot are still being researched 2024. Global is expected increase further. investigation retinopathy will be focus future.

Language: Английский

Citations

1
Development and validation of predictive models for diabetic retinopathy using machine learning DOI Creative Commons

Peigang Yang,

Bin Yang

PLoS ONE, Journal Year: 2025, Volume and Issue: 20(2), P. e0318226 - e0318226

Published: Feb. 24, 2025

Objective This study aimed to develop and compare machine learning models for predicting diabetic retinopathy (DR) using clinical biochemical data, specifically logistic regression, random forest, XGBoost, neural networks. Methods A dataset of 3,000 patients, including 1,500 with DR, was obtained from the National Population Health Science Data Center. Significant predictors were identified, four predictive developed. Model performance assessed accuracy, precision, recall, F1-score, area under curve (AUC). Results Random forest XGBoost demonstrated superior performance, achieving accuracies 95.67% 94.67%, respectively, AUC values 0.991 0.989. Logistic regression yielded an accuracy 76.50% (AUC: 0.828), while networks achieved 82.67% 0.927). Key included 24-hour urinary microalbumin, HbA1c, serum creatinine. Conclusion The highlights as effective tools early DR detection, emphasizing importance renal glycemic markers in risk assessment. These findings support integration into decision-making improved patient outcomes diabetes management.

Language: Английский

Citations

1
Machine learning-based risk predictive models for diabetic kidney disease in type 2 diabetes mellitus patients: a systematic review and meta-analysis DOI Creative Commons
Yihan Li, Nan Jin, Qimin Zhan

et al.

Frontiers in Endocrinology, Journal Year: 2025, Volume and Issue: 16

Published: March 3, 2025

Background Machine learning (ML) models are being increasingly employed to predict the risk of developing and progressing diabetic kidney disease (DKD) in patients with type 2 diabetes mellitus (T2DM). However, performance these still varies, which limits their widespread adoption practical application. Therefore, we conducted a systematic review meta-analysis summarize evaluate clinical applicability predictive identify key research gaps. Methods We compare ML models. searched PubMed, Embase, Cochrane Library, Web Science for English-language studies using algorithms DKD T2DM, covering period from database inception April 18, 2024. The primary metric was area under receiver operating characteristic curve (AUC) 95% confidence interval (CI). bias assessed Prediction Model Risk Bias Assessment Tool (PROBAST) checklist. Results 26 that met eligibility criteria were included into meta-analysis. 25 performed internal validation, but only 8 external validation. A total 94 developed, 81 evaluated validation sets 13 sets. pooled AUC 0.839 (95% CI 0.787-0.890) 0.830 0.784-0.877) Subgroup analysis based on showed traditional regression 0.797 0.777-0.816), 0.811 0.785-0.836), deep 0.863 0.825-0.900). included, AUCs used three or more times pooled. Among them, random forest (RF) demonstrated best 0.848 0.785-0.911). Conclusion This demonstrates exhibit high predicting T2DM patients. challenges related data during model development need be addressed. Future should focus enhancing transparency standardization, as well validating models’ generalizability through multicenter studies. Systematic Review Registration https://inplasy.com/inplasy-2024-9-0038/ , identifier INPLASY202490038.

Language: Английский

Citations

0
An interpreting machine learning models to predict amputation risk in patients with diabetic foot ulcers: a multi-center study DOI Creative Commons
Haoran Tao, Lili You, Yuhan Huang

et al.

Frontiers in Endocrinology, Journal Year: 2025, Volume and Issue: 16

Published: March 25, 2025

Background Diabetic foot ulcers (DFUs) constitute a significant complication among individuals with diabetes and serve as primary cause of nontraumatic lower-extremity amputation (LEA) within this population. We aimed to develop machine learning (ML) models predict the risk LEA in DFU patients used SHapley additive explanations (SHAPs) interpret model. Methods In retrospective study, data from 1,035 DFUs at Sun Yat-sen Memorial Hospital were utilized training cohort ML models. Data 297 across multiple tertiary centers for external validation. then least absolute shrinkage selection operator analysis identify predictors amputation. developed five [logistic regression (LR), support vector (SVM), random forest (RF), k-nearest neighbors (KNN) extreme gradient boosting (XGBoost)] patients. The performance these was evaluated using several metrics, including area under receiver operating characteristic curve (AUC), decision (DCA), precision, recall, accuracy, F1 score. Finally, SHAP method ascertain significance features Results final comprising 1332 individuals, 600 underwent Following hyperparameter optimization, XGBoost model achieved best prediction an accuracy 0.94, precision 0.96, score 0.94 AUC 0.93 internal validation set on basis 17 features. For set, attained 0.78, 0.93, 0.83. Through analysis, we identified white blood cell counts, lymphocyte urea nitrogen levels model’s main predictors. Conclusion algorithm-based can be dynamically estimate patients, making it valuable tool preventing progression

Language: Английский

Citations

0
The accuracy of Machine learning in the prediction and diagnosis of diabetic kidney Disease: A systematic review and Meta-Analysis DOI

Changmao Dai,

Sun Xiaolan,

Jia Xu

et al.

International Journal of Medical Informatics, Journal Year: 2025, Volume and Issue: unknown, P. 105975 - 105975

Published: May 1, 2025

Language: Английский

Citations

0
Integrated machine learning and deep learning for predicting diabetic nephropathy model construction, validation, and interpretability DOI
Junjie Ma,

Shaoguang An,

Mohan Cao

et al.

Endocrine, Journal Year: 2024, Volume and Issue: 85(2), P. 615 - 625

Published: Feb. 23, 2024

Language: Английский

Citations

1
Unveiling the utility of artificial intelligence for prediction, diagnosis, and progression of diabetic kidney disease: an evidence-based systematic review and meta-analysis DOI
Sagar Dholariya, Siddhartha Dutta, Amit Sonagra

et al.

Current Medical Research and Opinion, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 31

Published: Oct. 30, 2024

The purpose of this study was to conduct a systematic investigation the potential artificial intelligence (AI) models in prediction, detection diagnostic biomarkers, and progression diabetic kidney disease (DKD). In addition, we compared performance non-logistic regression (LR) machine learning (ML) conventional LR prediction models.

Language: Английский

Citations

1
Factors associated with acquiring exercise habits through health guidance for metabolic syndrome among middle-aged Japanese workers: A machine learning approach DOI Creative Commons

Jiawei Wan,

Kyohsuke Wakaba, Takeshi Onoue

et al.

Preventive Medicine Reports, Journal Year: 2024, Volume and Issue: 48, P. 102915 - 102915

Published: Oct. 19, 2024

Language: Английский

Citations

0
Development and validation of an interpretable machine learning model associated with erythrocyte fatty acids to identify coronary artery disease among Chinese adults DOI

Yongjin Wang,

Zhaocheng Zhuang,

Yandan Wang

et al.

Food Bioscience, Journal Year: 2024, Volume and Issue: unknown, P. 105368 - 105368

Published: Oct. 1, 2024

Language: Английский

Citations

0