RESUMO
BACKGROUND: Dyslipidemia, characterized by variations in plasma lipid profiles, poses a global health threat linked to millions of deaths annually. OBJECTIVES: This study focuses on predicting dyslipidemia incidence using machine learning methods, addressing the crucial need for early identification and intervention. METHODS: The dataset, derived from the Lifestyle Promotion Project (LPP) in East Azerbaijan Province, Iran, undergoes a comprehensive preprocessing, merging, and null handling process. Target selection involves five distinct dyslipidemia-related variables. Normalization techniques and three feature selection algorithms are applied to enhance predictive modeling. RESULT: The study results underscore the potential of different machine learning algorithms, specifically multi-layer perceptron neural network (MLP), in reaching higher performance metrics such as accuracy, F1 score, sensitivity and specificity, among other machine learning methods. Among other algorithms, Random Forest also showed remarkable accuracies and outperformed K-Nearest Neighbors (KNN) in metrics like precision, recall, and F1 score. The study's emphasis on feature selection detected meaningful patterns among five target variables related to dyslipidemia, indicating fundamental shared unities among dyslipidemia-related factors. Features such as waist circumference, serum vitamin D, blood pressure, sex, age, diabetes, and physical activity related to dyslipidemia. CONCLUSION: These results cooperatively highlight the complex nature of dyslipidemia and its connections with numerous factors, strengthening the importance of applying machine learning methods to understand and predict its incidence precisely.
Assuntos
Dislipidemias , Aprendizado de Máquina , Humanos , Dislipidemias/epidemiologia , Incidência , Irã (Geográfico)/epidemiologia , Masculino , Feminino , Estilo de Vida , Algoritmos , Promoção da Saúde/métodos , Pessoa de Meia-Idade , AdultoRESUMO
This study aimed to assess the levels of heavy metals in the breast milk of women residing in the mining and agricultural areas of East Azerbaijan province in Iran. This cross-sectional study analyzed 68 lactating mothers from mining (n = 28) and agricultural (n = 40) areas of East Azerbaijan province in Iran between June 2022 and March 2023. The study used an Inductively Coupled Plasma Optical Emission Spectroscopy (ICP-OES) to measure the concentrations of heavy metals, including arsenic (As), chromium (Cr), copper (Cu), and iron (Fe). A semi-quantitative food frequency questionnaire (SQ-FFQ) was used to collect data on the dietary and sociodemographic characteristics of the mothers. Although the concentration of arsenic (As) was below the limit of detection (LOD), the mean concentrations of chromium (Cr), copper (Cu), and iron (Fe) were 1.11, 0.87, and 13.25 mg/L in agricultural areas and 0.83, 0.93, and 11.35 mg/L in mining areas, respectively. The concentrations of Cr (p < 0.001) and Fe (p = 0.019) were significantly higher in the breast milk of women residing in agricultural areas. However, the concentration of Cu was significantly higher (p = 0.085) in the breast milk of women living in mining areas. Additionally, lactation age had a significant effect on Cu levels (p = 0.015), with a negative coefficient of -0.011. The study indicates that the levels of heavy metals in breast milk can be influenced by the exposure to pesticides, fertilizers, volcanic soil, and disparities in access to post-natal care and iron supplements.
RESUMO
Background: Asthma is one of the most common chronic respiratory diseases. It is estimated that more than 400 million people will suffer from it by 2025. This study aims to determine the prevalence of asthma in East Azerbaijan and investigate the association between asthma and some environmental and demographic factors. Materials and Methods: This is a cross-sectional study based on a major Lifestyle Promotion Project (LPP) conducted in the districts of East Azerbaijan, including 2641 participants aged 15 to 65 years of the general population selected through probability proportional to size (PPS) multistage stratified cluster sampling. We used the World Health Survey questionnaire about doctor-diagnosed asthma to determine the prevalence of asthma. Age, smoking status, physical activity level, socioeconomic variables such as job and education level, and body mass index (BMI) were used as covariates in regression models. A questionnaire was used to obtain socio-demographic information and smoking status. The short form of the International Physical Activity Questionnaire was used to estimate the level of physical activity (IPAQ). Results: The mean age of participants was 40.9 ± 12.05 years including 1242 (47 %) males and 1399 (53 %) females. The prevalence of asthma was 3.3 %. The frequency of smokers was significantly higher in the asthmatic group compared with the non-asthmatic group (OR=2.33 [1.76-3.31]; p=0.03). There was no significant association between asthma and other demographic and lifestyle characteristics. Obesity has also played a significant role in the development of asthma. Conclusion: According to the results of this study, obesity and smoking have played a significant role in the development of asthma but there is no statistically significant relationship between socioeconomic and demographic factors.
RESUMO
Introduction: Metabolic syndrome (MetS) is a prevalent metabolic disorder with increasing prevalence attributed to extended life expectancy. This study aims to investigate MetS prevalence and its determinants in the East-Azerbaijan population. Methods: Conducted as a cross-sectional study within the East Azerbaijan region, this research is based on a major Lifestyle Promotion Project. The study encompasses 700 participants aged 15 to 65 years, representing the general population and selected using probability proportional to size multistage stratified cluster sampling. MetS diagnoses were conducted using the adult Panel III criteria. Data on socio-demographics, smoking status, and physical activity levels were collected through questionnaires. Results: Among participants, the mean age was 42.4±12.38 years, and the mean body mass index was 27.69±4.94 kg/m2. The MetS group exhibited higher mean age and body mass index compared to the non-MetS group (P<0.001). The prevalence of MetS in the population was 34.2%, with higher rates in females (37.1%) compared to males (30.5%), though this difference wasn't statistically significant (P=0.11). Notably, a substantial distinction was observed between the two groups regarding education levels (P<0.001). Conclusion: The study reveals a significant association between increasing age and higher prevalence of MetS. Furthermore, lower educational levels were linked to an elevated prevalence of MetS. While other socio-demographic factors didn't demonstrate statistically significant relationships, these findings emphasize the importance of targeted interventions and education in mitigating MetS risks.