Ahmed J. Aljaaf

Predicting the likelihood of heart failure with a multi level risk assessment using decision tree

Heart failure comes in the top causes of death worldwide. The number of deaths from heart failure exceeds the number of deaths resulting from any other causes. Recent studies have focused on the use of machine learning techniques to develop predictive models that are able to predict the incidence of heart failure. The majority of these studies have used a binary output class, in which the prediction would be either the presence or absence of heart failure. In this study, a multi-level risk assessment of developing heart failure has been proposed, in which a five risk levels of heart failure can be predicted using C4.5 decision tree classifier. On the other hand, we are boosting the early prediction of heart failure through involving three main risk factors with the heart failure data set. Our predictive model shows an improvement on existing studies with 86.5% sensitivity, 95.5% specificity, and 86.53% accuracy.

Toward an optimal use of artificial intelligence techniques within a clinical decision support system

Intelligent clinical decision support systems have been increasingly used in health care organisations. These systems are intended to help physicians in their diagnosis procedures; making decisions more accurate and effective, minimising medical errors, improving patient safety and reducing costs. However, the effectiveness and accuracy of these systems largely depend on the underlying AI technique that has been used, where same clinical-related problem can be solved using more than one AI technique which may provide different outcomes. Consequently, it is crucial to figure out the ideal utilisation of AI techniques in the clinical decision support systems. Our research study reviews various researches which utilised Artificial Intelligence techniques in clinical decision support systems with the aim of identifying basic criterion for adequate use of intelligent techniques within such systems. This paper presents a yes/no inquiry approach based on observations of previous research studies. The objective of this inquiry is to facilitate the selection of the most beneficial and effective AI technique that can be applied in the medical decision support system to provide the best outcomes.

A Study of Data Classification and Selection Techniques for Medical Decision Support Systems

Artificial Intelligence techniques have been increasingly used in medical decision support systems to aid physicians in their diagnosis procedures; making decisions more accurate and effective, minimizing medical errors, improving patient safety and reducing costs. Our research study indicates that it is difficult to compare different artificial intelligence techniques which are utilised to solve various medical decision-making problems using different data models. This makes it difficult to find out the most useful artificial intelligence technique among them. This paper proposes a classification approach that would facilitate the selection of an appropriate artificial intelligence technique to solve a particular medical decision making problem. This classification is based on observations of previous research studies.

Gamification in e-Governance: Development of an Online Gamified System to Enhance Government Entities Services Delivery and Promote Public's Awareness

Electronic Governance (e-Governance) is the application of the Information and Communication Technology (ICT) with the aim to simplify and support the governance across different parties including public government organizations, business and citizens. Through the adoption and use of Information and Communication technology which will connect all of these three together to support the overall governments processes and operations. Its anticipated that e-Governance shall bring boundless improvements towards strategic planning, proper monitoring of government programs, investments, projects and activities. The e-Governance will provide easy access and delivery of government services to the citizens and reduce associated costs of transactions that occur across government entities. In the recent years, some of the new technological advancement concepts that include Gamification becomes one of the solutions that can be attached with the e-Governance implementation to sustain the effective adoption of government services delivery. Gamification is an evolution that supports people interactions with implemented government electronic services. It can be widely used within public organizations for training of new hires at workplaces, help employees to perform certain tasks and carry their day-to-day activities more efficiently by using Gamification tools which government entities has to offer in order to facilitate e-Governance implementation and services adoption by publics. The developed mobile application is based on a Gamification platform for employees at public government organizations for the purpose of training and learning. In this research, different variables were measured including productivity, motivational engagement, performance, training, support and services, collaboration, innovation, skills development, personal development and behavior changes.

A Systematic Comparison and Evaluation of Supervised Machine Learning Classifiers Using Headache Dataset

The massive growth of data volume within the healthcare sector pushes the current classical systems that were adapted to the limit. Recent studies have focused on the use of machine learning methods to develop healthcare systems to extract knowledge from data by means of analysing, mining, pattern recognition, classification and prediction. Our research study reviews and examines different supervised machine learning classifiers using headache dataset. Different statistical measures have been used to evaluate the performance of seven well-known classifiers. The experimental study indicated that Decision Tree classifier achieved a better overall performance, followed by Artificial Neural Network, Support Vector Machine and k-Nearest Neighbor. This would determine the most suitable classifier for developing a particular classification system that is capable of identifying primary headache disorders.

Applied machine learning classifiers for medical applications: Clarifying the behavioural patterns using a variety of datasets

Machine-learning (ML) techniques have grown to be among the leading research topics within the health care systems and particularly for clinical decision support systems (CDSS), which are commonly used in helping physicians to make more accurate diagnosis. However, applying these techniques for CDSS is most likely would face a lack of criteria for adequate use. Therefore, a range of recent studies have focused on evaluating different machine learning classifiers with the aim of identifying the most appropriate classifier to be used for particular decision making problem-domain. The majority of these studies have used a single dataset within a certain medical-related classification domain. Nevertheless, evaluating machine-learning classifiers with one sample of data appears to be unsatisfying, perhaps it is not reflecting the classifiers capabilities or their behavioral patterns under different circumstances. In this study, five well-known supervised machine-learning classifiers were examined using five different real-world datasets with a range of attributes. The main aim was to illustrate not only the impact of the datasets volume and attributes on the evaluation, but also and more importantly, present the classifiers capabilities and shortcomings under certain conditions, which potentially provide a guidance or instructions to help health analysts and researchers to determine the most suitable classifier to address a particular medical-related decision making problem.

A Study of Data Classification and Selection Techniques to Diagnose Headache Patients.

Primary headache disorders are the most common complaint worldwide. The socioeconomic and personal impact of headache disorders is enormous, as it is the leading cause of workplace absenteeism. The development of diagnostic models to aid in the diagnosis of primary headaches has become an interesting research topic, particularly after the launch of the International Headache Society IHS criteria. In this chapter, we review the literature to investigate recent expert systems with respect to the diagnosis of primary headache disorders. The main aim of this chapter is to analyze the core concept of these diagnostic models to explore their advantages and drawbacks, which enable us to initialize a new pathway toward robust diagnostic model that overcomes current challenges.

An Intelligent Systems Approach to Primary Headache Diagnosis

In this study, the problem of primary headache diagnosis is considered, referring to multiple frames of reference, including the complexity characteristics of living systems, the limitation of human information processing, the enduring nature of headache throughout history, and the potential for intelligent systems paradigms to both broaden and deepen the scope of such diagnostic solutions. In particular, the use of machine learning is recruited for this study, for which a dataset of 836 primary headache cases is evaluated, originating from two medical centres located in Turkey. Five primary headache classes were derived from the data obtained, namely Tension Type Headache (TTH), Chronic Tension Type Headache (CTTH), Migraine with Aura (MwA), Migraine without Aura (MwoA), followed by Trigeminal Autonomic Cephalalgia (TAC). A total of 9 machine learning based classifiers, ranging from linear to non-linear ensembles, in addition to 1 random baseline procedure, were evaluated within a supervised learning setting, yielding highest performance outcomes of AUC 0.985, sensitivity 1, and specificity 0.966. The study concludes that modern computing platforms represent a promising setting through which to realise intelligent solutions, enabling the space of analytical operations needed to drive forward diagnostic capability in the primary headache domain and beyond.

Evaluation of Machine Learning Methods to Predict Knee Loading from the Movement of Body Segments

Abnormal joint moments during gait are validated predictors of knee pain in osteoarthritis. Calculation of moments necessitates measurement of forces and moment arms about joints during walking. Dynamically changing moment arms can be calculated from motion trackers either optically or with wireless inertia sensing units, but the measurement of forces is more problematic. Either the patient has to walk over a force platform or a force sensing device has to be built into the sole of the shoes. One possible means of registering abnormal joint moments without the restrictions due to force measurements is to predict moments from the movement of body segments using advanced machine learning techniques. To test the viability of this approach, we aimed to predict the frontal plane internal knee abduction moment form 3D Euler angles of the ankle, knee, hip and pelvis during a single gait cycle of 31 patients with alkaptonuria. Four machine-learning algorithms were used in our experiment to predict moments namely: Decision Tree, Random Forest, Linear Regression and Multilayer Perceptron neural network. Based on performance measures of prediction (R2, root mean squared error and area under the recall curve), the random forest algorithm performed best but this was also the slowest by a factor of 10. Considering both performance and speed, the Multilayer Perceptron neural network method was superior with R2, root mean square of error, area under the recall curve and required training time of 0.8616, 0.0743, 0.874 and 730 ms, respectively.

Partially Synthesised Dataset to Improve Prediction Accuracy

The real world data sources, such as statistical agencies, library databanks and research institutes are the major data sources for researchers. Using this type of data involves several advantages including, the improvement of credibility and validity of the experiment and more importantly, it is related to a real world problems and typically unbiased. However, this type of data is most likely unavailable or inaccessible for everyone due to the following reasons. First, privacy and confidentiality concerns, since the data must to be protected on legal and ethical basis. Second, collecting real world data is costly and time consuming. Third, the data may be unavailable, particularly in the newly arises research subjects. Therefore, many studies have attributed the use of fully and/or partially synthesised data instead of real world data due to simplicity of creation, requires a relatively small amount of time and sufficient quantity can be generated to fit the requirements. In this context, this study introduces the use of partially synthesised data to improve the prediction of heart diseases from risk factors. We are proposing the generation of partially synthetic data from agreed principles using rule-based method, in which an extra risk factor will be added to the real-world data. In the conducted experiment, more than 85 % of the data was derived from observed values (i.e., real-world data), while the remaining data has been synthetically generated using a rule-based method and in accordance with the World Health Organisation criteria. The analysis revealed an improvement of the variance in the data using the first two principal components of partially synthesised data. A further evaluation has been conducted using five popular supervised machine-learning classifiers. In which, partially synthesised data considerably improves the prediction of heart diseases. Where the majority of classifiers have approximately doubled their predictive performance using an extra risk factor.