Infant deaths in Pudong, Shanghai, China: A retrospective study of the police data and comparison with the centre for disease control data
مرگ و میر نوزادان در پودونگ ، شانگهای ، چین: یک مطالعه گذشته نگر از داده های پلیس و مقایسه آن با مرکز کنترل داده های بیماری-2019
In China, every year many infants (< 1 year) are abandoned, but abandonment related deaths are rarely reported. In this study, the police records of infant deaths in Pudong, Shanghai have been explored, then, the police data were compared with the corresponding Centre for Disease Control (“CDC”) data. During the period 2004–2017, a total of 297 infant deaths were recorded by the police, including 87 sudden natural deaths (occurred outside hospitals) and 210 unnatural deaths. The CDC data were retrieved from a Chinese article. Joinpoint Trend Analysis was used to evaluate the trend of the police records on infant deaths, and Poisson regression was used to calculate the mortality rate ratio (“RR”) by gender and places of origin (local, migrant, unknown identity). It is observed that infants born to migrant mothers were more vulnerable to sudden natural deaths than their local counterparts (RR: 4.6, 95% CI: 2.8 to 8.1). 8 abandonment deaths and 187 suspicious abandonment deaths were spotted. Births to unmarried mothers, severe illnesses, and deformities could be important risk factors resulting in abandonments. However, the female gender was not a reason that led to the abandonments. Infant deaths related to abandonments/suspicious abandonments rapidly declined during the period 2004–2017. The CDC data showed that 27 infants died of unnatural causes during the period 2002–2013, while the police data recorded 182 unnatural infant deaths during the period 2004–2013, a shorter period but more unnatural deaths. Thus, the CDC data could have underreported the infant deaths.
Keywords: Infant | Unnatural death | Abandonment | China
Dropout early warning systems for high school students using machine learning
ترک سیستم های هشدار اولیه برای دانش آموزان دبیرستانی که از یادگیری ماشین استفاده می کنند-2019
Students dropouts are a serious problem for students, society, and policy makers. Predictive modeling using machine learning has a great potential in developing early warning systems to identify students at risk of dropping out in advance and help them. In this study, we use the random forests in machine learning to predict students at risk of dropping out. The data used in this study are the samples of 165,715 high school students from the 2014 National Education Information System (NEIS), which is a national system for educational administration information connected through the Internet with around 12,000 elementary and secondary schools, 17 city/provincial offices of education, and the Ministry of Education in Korea. Our predictive model showed an excellent performance in predicting students dropouts in terms of various performance metrics for binary classification. The results of our study demonstrate the benefit of using machine learning with students big data in education. We briefly overview machine learning in general and the random forests model and present the various performance metrics to evaluate our predictive model.
Keywords: Dropout | Machine learning | Predictive model | Random forests model | Big data