http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
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.
Njideka U. Okubadejo,Obianuju B. Ozoh,Oluwadamilola O. Ojo,Ayesha O. Akinkugbe,Ifedayo A. Odeniyi,Oluseyi Adegoke,Babawale T. Bello,Osigwe P. Agabi 대한고혈압학회 2019 Clinical Hypertension Vol.25 No.3
Background: Hypertension is the major risk factor for cardiovascular diseases and prevalence rates are critical to understanding the burden and envisaging health service requirements and resource allocation. We aimed to provide an update of the current prevalence of hypertension and blood pressure profiles of adults in urban Nigeria. Methods: Cross sectional population-based survey in Lagos, Nigeria. Participants were selected using stratified multistage sampling. Relevant sections of the World Health Organization STEPwise approach to chronic disease risk factor surveillance were utilized for data collection. Blood pressures were categorized based on both the current American College of Cardiology/American Heart Association (ACC/AHA) 2017 guidelines and the pre-existing Joint National Committee on Hypertension 7 (JNC7) (2003) categories. Results: There were 5365 participants (51.8% female), age range of 16–92 years, and mean age ± SD 37.6 ± 13.1. The mean ± SD systolic and diastolic blood pressures were 126.8 ± 18.6 and 80.6 ± 13.2 respectively. There was significant correlation between both systolic and diastolic blood pressures and age (Pearson correlation 0.372 and 0.357 respectively and p = 0.000 in both instances). The prevalence of hypertension was 55.0% (3003) and 27.5% (1473) based on the ACC/AHA 2017 guideline and the JNC7 2003 guidelines respectively. Body mass index was positively correlated with systolic and diastolic BP (p = 0.000). Conclusions: Over half of the adult population in this major Nigerian city are classified to have hypertension by the recent guideline. There is an urgent need to develop and implement strategies for primordial prevention of hypertension (and obesity) and to restructure our healthcare delivery systems to adequately cater for the current and emerging hypertensive population.