Prediction of diabetes disease using an ensemble of machine learning multi-classifier models.

BACKGROUND AND OBJECTIVE: Diabetes is a life-threatening chronic disease with a growing global prevalence, necessitating early diagnosis and treatment to prevent severe complications. Machine learning has emerged as a promising approach for diabetes diagnosis, but challenges such as limited labeled data, frequent missing values, and dataset imbalance hinder the development of accurate prediction models. Therefore, a novel framework is required to address these challenges and improve performance. METHODS: In this study, we propose an innovative pipeline-based multi-classification framework to predict diabetes in three classes: diabetic, non-diabetic, and prediabetes, using the imbalanced Iraqi Patient Dataset of Diabetes. Our framework incorporates various pre-processing techniques, including duplicate sample removal, attribute conversion, missing value imputation, data normalization and standardization, feature selection, and k-fold cross-validation. Furthermore, we implement multiple machine learning models, such as k-NN, SVM, DT, RF, AdaBoost, and GNB, and introduce a weighted ensemble approach based on the Area Under the Receiver Operating Characteristic Curve (AUC) to address dataset imbalance. Performance optimization is achieved through grid search and Bayesian optimization for hyper-parameter tuning. RESULTS: Our proposed model outperforms other machine learning models, including k-NN, SVM, DT, RF, AdaBoost, and GNB, in predicting diabetes. The model achieves high average accuracy, precision, recall, F1-score, and AUC values of 0.9887, 0.9861, 0.9792, 0.9851, and 0.999, respectively. CONCLUSION: Our pipeline-based multi-classification framework demonstrates promising results in accurately predicting diabetes using an imbalanced dataset of Iraqi diabetic patients. The proposed framework addresses the challenges associated with limited labeled data, missing values, and dataset imbalance, leading to improved prediction performance. This study highlights the potential of machine learning techniques in diabetes diagnosis and management, and the proposed framework can serve as a valuable tool for accurate prediction and improved patient care. Further research can build upon our work to refine and optimize the framework and explore its applicability in diverse datasets and populations.

The effect of breastfeeding on children's growth indices up to 6 months: An application of multivariate t linear mixed model.

Background: This study aimed to determine the effect of breastfeeding on children's growth indices. Materials and Methods: Longitudinal data of children's growth (height, weight, and head circumference) were as a dependent variable and type of nutrition as an independent variable with using multivariate t linear mixed model. Results: The indicated that the height, weight, and head circumference of infants who were fed with breast milk showed a statistically significant difference (P < 0.05) with those of infants receiving formula. Conclusion: Exclusive feeding with breast milk, especially in the first 6 months of life, has a significant impact on the child's growth indicators compared to formula or, or a combination of both.

Developing a bi-objective resilience relief logistic considering operational and disruption risks: a post-earthquake case study in Iran.

Today, according to the occurrence of numerous disasters in allover over the world, designing the proper and comprehensive plan for relief logistics has received a lot of attention from crisis managers and people. Besides, considering resilience capability along with operational and disruption risks leads to the robustness of the humanitarian relief chain (HRC), and this comprehensive framework ensures the essential supplies delivery to the beneficiaries and is close to real-world problems. The resilience parameters used for the second objective are obtained by a strong Best Worst Method (BWM). Another supposition of the model is the consideration of uncertainty in all stages of the proposed problem. Moreover, the multiple disasters (sub-sequent minor post disasters) which can increase the initial demand are considered. Furthermore, the proposed model is solved using three well-known metaheuristic algorithms includes non-dominated sorting genetic algorithm (NSGA-II), network reconfiguration genetic algorithm (NRGA), and multi-objective particle swarm optimization (MOPSO), and their performance is compared by several standard multi-objective measure metrics. Finally, the obtained results show the robustness of the proposed approaches, and some directions for future researches are provided.

Occupational Exposure and Health Impairments of Formaldehyde on Employees of a Wood Industry.

BACKGROUND: Occupational exposure to formaldehyde may decrease white blood cell counts and change blood concentration. In this study, the influences of occupational exposure to formaldehyde on the number of white blood cells and blood concentrations were studied. METHODS: This case-control study was conducted in June of 2012 at North Wood Factory, Golestan Province, Iran. The US-NIOSH method No. 2541 was used to determine the occupational exposure of 30 workers of the production line (case group) and 30 administrative staffs (control group) to formalde-hyde. The number of white blood cells and blood concentration were determined using the normal blood count method and related indices. Demographic features as well as the symptoms of being exposed to formaldehyde were collected using a standard questionnaire. RESULTS: The occupational exposure of case group ranged from 0.50 ppm to 1.52 ppm. The prevalence of all studied symptoms from formaldehyde exposure in workers (2