Salim Amour Diwani

Bio: Salim Amour Diwani is an academic researcher from Nelson Mandela African Institute of Science and Technology. The author has contributed to research in topics: Human resources & Knowledge extraction. The author has an hindex of 3, co-authored 5 publications receiving 29 citations.

Diabetes Forecasting Using Supervised Learning Techniques

Abstract: Diabetes Mellitus is one of the most serious health challenges affecting children, adolescents and young adults in both developing and developed countries. To predict hidden patterns of diseases diagnostic in the healthcare sector, nowadays we use various data mining techniques. In this paper, we have applied supervised machine learning techniques like Naive Bayes and J48 decision tree to identify diabetic patients. We evaluated the proposed methods on Pima Indian diabetes data sets, which is a data mining data sets from UCI machine learning laboratory. It has been observed through analysis of the experimental results that Naive Bayes performs better than the decision tree method J48.

Overview Applications of Data Mining In Health Care: The Case Study of Arusha Region

Abstract: Data mining as one of many constituents of health care has been used intensively and extensively in many organizations around the globe as an efficient technique of finding correlations or patterns among dozens of fields in large relational databases to results into more useful health information. In healthcare, data mining is becoming increasingly popular and essential. Data mining applications can greatly benefits all parties involved in health care industry. The huge amounts of data generated by healthcare transactions are too complex and voluminous to be processed and analyzed by traditional methods. Data mining provides the methodology and technology to transform huge amount of data into useful information for decision making. This paper explores data mining applications in healthcare in Arusha region of Tanzania more particularly; it discusses data mining and its applications in major areas such as evaluation of treatment effectiveness, management of healthcare itself and lowering medical costs.

Data Mining Awareness and Readiness in Healthcare Sector: a case of Tanzania

Abstract: Globally the application of data mining in healthcare is great, because the healthcare sector is rich with tremendous amount of data and data mining becoming very essential. Healthcare sector collect huge amount of data in daily basis. Transferring data into secure electronic systems of medical health will saves lives and reduce the cost of healthcare services as well as early discovery of contiguous diseases with advanced collection of data. This study explore the awareness and readiness to implement data mining technology within healthcare in Tanzania public sector . This study is triangulated adopted online survey using Google doc and offline survey using presentation techniques through different hospital and distributed the questionnaires to the healthcare professionals. The issues explored in the questionnaire included the awareness of data mining technology, the level of understanding of, perception of and readiness to implement data mining technology within healthcare public sector. In this study we will analyze the data using SPSS statistical tool.

Framework for Data Mining In Healthcare Information System in Developing Countries: A Case of Tanzania

Abstract: Globally the healthcare sector is abundant with data and hence using data mining techniques in this area seems promising. Healthcare sector collects huge amounts of data on a daily basis. Transferring data into secure electronic system of medical health can save lives and reduce the cost of healthcare services as well as early discovery of contagious diseases with advanced collection of medical data. In this study we have proposed a best fit for data mining techniques in healthcare based on a case study. The proposed framework aims to provide self healthcare treatments where by several monitoring equipments using the cyberspace devices have been developed to help patients manage their medical conditions at home for example, diabetic patients can test their blood sugar level by using e-device, which ,with the click of a computer mouse, downloads the results to a healthcare practitioner, minimizes time to wait for medical treatments, and minimizes the delay time in providing medical treatments. Data mining is a new technology used in different types of sectors to improve the effectiveness and efficiency of business model as well as solving problems in business world.

Theoretical Factors underlying Data Mining Techniques in Developing Countries: a case of Tanzania

Abstract: Just as the mining of Tanzanite is the process of extracting large block of hard rock`s by using sophisticated hard rock mining techniques to find valuable tanzanite glamour, data mining is the process of extracting useful information or knowledge from large un-organized data to enable effective decision making. Although data mining technology is growing rapidly, many IT experts and business consultants may not have a clue about the term. The purpose of this paper is to introduce data mining techniques, tools, a survey of data mining applications, data mining ethics and data mining process.

A comparative study on machine learning based algorithms for prediction of motorcycle crash severity.

Abstract: Motorcycle crash severity is under-researched in Ghana. Thus, the probable risk factors and association between these factors and motorcycle crash severity outcomes is not known. Traditional statistical models have intrinsic assumptions and pre-defined correlations that, if flouted, can generate inaccurate results. In this study, machine learning based algorithms were employed to predict and classify motorcycle crash severity. Machine learning based techniques are non-parametric models without the presumption of relationships between endogenous and exogenous variables. The main aim of this research is to evaluate and compare different approaches to modeling motorcycle crash severity as well as investigating the effect of risk factors on the injury outcomes of motorcycle crashes. Motorcycle crash dataset between 2011 and 2015 was extracted from the National Road Traffic Crash Database at the Building and Road Research Institute (BRRI) in Ghana. The dataset was classified into four injury severity categories: fatal, hospitalized, injured, and damage-only. Three machine learning based models were developed: J48 Decision Tree Classifier, Random Forest (RF) and Instance-Based learning with parameter k (IBk) were employed to model the severity of injury in a motorcycle crash. These machine learning algorithms were validated using 10-fold cross-validation technique. The three machine learning based algorithms were compared with one another and the statistical model: multinomial logit model (MNLM). Also, the relative importance analysis of the attribute was conducted to determine the impact of these attributes on injury severity outcomes. The results of the study reveal that the predictions of machine learning algorithms are superior to the MNLM in accuracy and effectiveness, and the RF-based algorithms show the overall best agreement with the experimental data out of the three machine learning algorithms, for its global optimization and extrapolation ability. Location type, time of the crash, settlement type, collision partner, collision type, road separation, road surface type, the day of the week, and road shoulder condition were found as the critical determinants of motorcycle crash injury severity.

Effective Prediction of Type II Diabetes Mellitus Using Data Mining Classifiers and SMOTE

Abstract: Diabetes is a metabolic disorder and currently is one of the most appalling diseases that mankind is facing. In diabetic disease, the body does not properly respond to “insulin”, an important hormone that converts sugar into energy needed for the proper functioning of regular life. The disease comes with severe complications on our body as it increases the risk of developing kidney disease, heart disease, eye retinal disease, nerve damage, and blood vessel damage. As per the World Health Organization, about 8.8% of the world was diabetic in the year 2017 and they have projected it to reach nearly 10% by 2045. This study develops a model for diabetic prediction based on data mining classifications techniques. Classification of imbalanced data especially in medical informatics is challenging and was the motivational factor for developing a classifier using a rebalancing algorithm. A two-phase classification model is employed in which the first step is preprocessing the data by use of Synthetic Minority Oversampling Technique (SMOTE), and the second one is feeding five classifiers (Bagging, SVM (Support Vector Machine), MLP (Multi-Layer Perceptron), Simple Logistic and Decision Tree) with the preprocessed data in order to select the best classifier for balanced dataset to predict diabetes. We have achieved an accuracy of 94.7013%, and 0.953 receiver operator characteristics (ROC) curve with decision tree classifier. The validation was achieved via a 10-fold cross validation with an experiment that was conducted on clinical records of 734 patients.