http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Odukoya, Oluwakemi Ololade,Odeyemi, Kofoworola Abimbola,Oyeyemi, Abisoye Sunday,Upadhyay, Ravi Prakash Asian Pacific Journal of Cancer Prevention 2013 Asian Pacific journal of cancer prevention Vol.14 No.3
Background: It is projected that low and middle-income countries will bear a major burden of tobacco related morbidity and mortality, yet, only limited information is available on the determinants of smoking initiation among youth in Africa. This study aimed to assess the determinants of smoking initiation and susceptibility to future smoking among a population of high school school students in Lagos, Nigeria. Materials and Methods: Baseline data from an intervention study designed to assess the effect of an anti-smoking awareness program on the knowledge, attitudes and practices of adolescents was analyzed. The survey was carried out in six randomly selected public and private secondary schools in local government areas in Lagos state, Nigeria. A total of 973 students completed self-administered questionnaires on smoking initiation, health related knowledge and attitudes towards smoking, susceptibility to future smoking and other factors associated with smoking. Results: Of the respondents, 9.7% had initiated smoking tobacco products with the predominant form being cigarettes (7.3%). Males (OR: 2.77, 95%CI: 1.65-4.66) and those with more pro-smoking attitudes (OR: 1.44, 95%CI: 1.34-1.54) were more likely to have initiated smoking. Those with parents and friends who are smokers were 3.47 (95%CI: 1.50-8.05) and 2.26 (95%CI: 1.27-4.01) times more likely to have initiated smoking. Non-smoking students, in privately owned schools (OR: 5.08), with friends who smoke (5.09), with lower knowledge (OR: 0.87) and more pro-smoking attitudes (OR 1.13) were more susceptible to future smoking. In addition, respondents who had been sent to purchase cigarettes by an older adult (OR: 3.68) were also more susceptible to future smoking. Conclusions: Being male and having parents who smoke are predictors of smoking initiation among these students. Consistent with findings in other countries, peers not only influence smoking initiation but also influence smoking susceptibility among youth in this African setting. Prevention programs designed to reduce tobacco use among in-school youth should take these factors into consideration. In line with the recommendations of article 16 of the WHO FCTC, efforts to enforce the ban on the sales of cigarettes to minors should be also emphasised.
Oluwakemi Odukoya,Solomon Nwaneri,Ifedayo Odeniyi,Babatunde Akodu,Esther Oluwole,Gbenga Olorunfemi,Oluwatoyin Popoola,Akinniyi Osuntoki 대한의료정보학회 2022 Healthcare Informatics Research Vol.28 No.1
Objectives: This study developed and compared the performance of three widely used predictive models—logistic regression(LR), artificial neural network (ANN), and decision tree (DT)—to predict diabetes mellitus using the socio-demographic,lifestyle, and physical attributes of a population of Nigerians. Methods: We developed three predictive models using 10 inputvariables. Data preprocessing steps included the removal of missing values and outliers, min-max normalization, and featureextraction using principal component analysis. Data training and validation were accomplished using 10-fold cross-validation. Accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and area under thereceiver operating characteristic curve (AUROC) were used as performance evaluation metrics. Analysis and model developmentwere performed in R version 3.6.1. Results: The mean age of the participants was 50.52 ± 16.14 years. The classificationaccuracy, sensitivity, specificity, PPV, and NPV for LR were, respectively, 81.31%, 84.32%, 77.24%, 72.75%, and 82.49%. Those for ANN were 98.64%, 98.37%, 99.00%, 98.61%, and 98.83%, and those for DT were 99.05%, 99.76%, 98.08%, 98.77%,and 99.82%, respectively. The best-performing and poorest-performing classifiers were DT and LR, with 99.05% and 81.31%accuracy, respectively. Similarly, the DT algorithm achieved the best AUC value (0.992) compared to ANN (0.976) and LR(0.892). Conclusions: Our study demonstrated that DT, LR, and ANN models can be used effectively for the prediction ofdiabetes mellitus in the Nigerian population based on certain risk factors. An overall comparative analysis of the modelsshowed that the DT model performed better than LR and ANN.