Search

Premature birth (PTB) is the most common public health issue in gynecology and obstetrics. It has a variety of consequences, ranging from increased infant mortality to chronic disease and disability throughout one's life. Many PTB prediction studies have been published in recent years to improve the accuracy of PTB prediction. However, no single study has addressed the issue of premature birth using a data set from the Iraqi community. There are many research from different countries that have been collected regarding premature birth, where the pregnant woman differs from one region to another in terms of lifestyle as well as the diagnostic methods used, where in Iraq only manual methods are adopted in the diagnosis. The aim of this paper is to provide and improve the prediction accuracy of premature births using real data from Iraqi hospitals. Additionally, provide a validation of the results in terms of reliability and accuracy. The novel approach is used to identify the best maternal characteristics (those associated with PTB) from an obstetric dataset. The following classifiers (Decision Tree, Random Forest, Logistic Regression, K-Neighbor Nearest, Naive Bayes Classifier, Neural Networks, Support Vector Machine) were used in this study to classify all birth cases into term normal birth and preterm birth. As a result, the Random Forest classifier outperformed all other classifiers with a 98% percent accuracy. Its worth noting that the classifiers' performance is quantified in terms of accuracy, sensitivity, Specificity, Precision, Recall and F1 score. [ABSTRACT FROM AUTHOR]

The crime was the number one problem in terms of the highest priority concerned with both the individual, society, and government. With the increasing growth in crime rates all over the world, an urgent need to analyze crime data to reduce it, it has become necessary to create a database of crimes and criminals and develop a good tool to analyze crime and identify crime patterns quickly and efficiently. Data mining techniques work on analyzing data from different sources and changing it into an organized structure for additional use. The major aim of this paper is to find out certain prevalent patterns in the actual data of the Criminal Statistics Directorate / Police Affairs Agency / Iraqi Ministry of Interior for the period from 2010 to 2020 The basic stages to create a system include raw data processing, data visualization, and models building. using the Random Forest algorithm and the Gradient Boosting algorithm to classify governorates according to crimes occurred. The Random Forest classifier gave accuracy 82.2% better than the Gradient Boosting algorithm that gave accuracy 71.6%. [ABSTRACT FROM AUTHOR]

Since the emerging coronavirus pandemic spreads worldwide, countries continue to find new ways to combat and control the spread of "Covid-19." As part of the virus-fighting efforts, information on diagnostic procedures, infection and symptoms, and the most recent therapy and vaccine research have been updated. The main objective of this paper is to reduce the enormous load on the healthcare system by providing the best way to diagnose patients and predict the infection of COV-19 effectively. As a result of the scientific development in computers and their applications, this science has treated many medical problems. However, clinical trials and human skills are still required despite the undeniable contributions of artificial intelligence (AI) and data research responsible for fighting the pandemic. They are a global and open-source tool capable of assisting in this health emergency. However, due to the severity of the threat of this virus to global health and its rapid development, these solutions remain insufficient to combat it. This research paper uses data mining based on algorithms of AI and machine learning (ML) to detect and diagnose COVID-19 infection based on clinical diagnostic tests prepared previously in the Iraqi Ministry of Health. The model was provided with a dataset of the COVID-19 virus using the Python programming language. To create the model where the model predicts whether this person is infected or not infected with the virus, and if it is proven that he is in the danger zone (reaching death), can he bypass the virus and be cured. The current study results showed that the model was developed using the Random Forest Classifier algorithm more efficiently to predict infection with the Coronavirus. This represents the best model developed among other models that used various algorithms, such as Gaussian Naive Bayes, k-nearest neighbors, Support vector machine, Logistic Regression, Random Forest, Gradient boosting, Multi-layer Perceptron. [ABSTRACT FROM AUTHOR]