Mohammed Al-Jumaily

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.

Medical Diagnosis: Are Artificial Intelligence Systems Able to Diagnose the Underlying Causes of Specific Headaches?

Artificial intelligence is the capability of computing machines to perform at par with humans in some cognitive tasks. Since its conception in the 1940s, AI has ambitiously evolved to naturally and comfortably immerse in extraordinary and multidisciplinary fields including computer science, education, engineering and medicine. This survey aims to provide and highlight the importance of AI work in the field of medical informatics and biomedicine. We have reviewed latest AI research in this immense field of medical science with special attention given to medical diagnosis. Various intelligent computing tools from rule-based expert systems and fuzzy logic to neural networks and genetic algorithms used in medical diagnosis were considered. We have explored hydrocephalus, a medical condition causing headaches. We also analysed a prototype of what is known as NeuroDiary Web application that is currently being tested as a software mobile application for collecting data of patients with hydrocephalus. We finally propose the development of an expert mobile application system to assist clinicians in the diagnosis, analysis and treatment of hydrocephalus.

A Framework on a Computer Assisted and Systematic Methodology for Detection of Chronic Lower Back Pain Using Artificial Intelligence and Computer Graphics Technologies

Back pain is one of the major musculoskeletal pain problems that can affect many people and is considered as one of the main causes of disability all over the world. Lower back pain, which is the most common type of back pain, is estimated to affect at least 60 % to 80 % of the adult population in the United Kingdom at some time in their lives. Some of those patients develop a more serious condition namely Chronic Lower Back Pain in which physicians must carry out a more involved diagnostic procedure to determine its cause. In most cases, this procedure involves a long and laborious task by the physicians to visually identify abnormalities from the patient’s Magnetic Resonance Images. Limited technological advances have been made in the past decades to support this process. This paper presents a comprehensive literature review on these technological advances and presents a framework of a methodology for diagnosing and predicting Chronic Lower Back Pain. This framework will combine current state-of-the-art computing technologies including those in the area of artificial intelligence, physics modelling, and computer graphics, and is argued to be able to improve the diagnosis process.

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.

Lumbar Spine Discs Labeling Using Axial View MRI Based on the Pixels Coordinate and Gray Level Features

Disc herniation is a major reason for lower back pain (LBP), a health issue that affects a very high proportion of the UK population and is costing the UK government over £1.3 million per day in health care cost. Currently, the process to diagnose the cause of LBP involves examining a large number of Magnetic Resonance Images (MRI) but this process is both expensive in terms time and effort. Automatic labeling of lumbar disc pixels in the MRI to detect the herniation area will reduce the time to diagnose and detect the cause of LBP by the physicians. In this paper, we present a method for automatic labeling of the lumbar spine disc pixels in axial view MRI using pixels locations and gray level as features. Clinical MRIs are used for the training and testing of the method. The pixel classification accuracy and the quality of the reconstructed disc images are used as the main performance indicators for our method. Our experiments show that high level of classification accuracy of 91.1% and 98.9% can be achieved using Weighted KNN and Fine Gaussian SVM classifiers 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.