Artefact detection and removal algorithms for EEG diagnostic systems

The electroencephalogram (EEG) is a medical technology that is used in the monitoring of the brain and in the diagnosis of many neurological illnesses. Although coarse in its precision, the EEG is a non-invasive tool that requires minimal set-up times, and is suitably unobtrusive and mobile to allow continuous monitoring of the patient, either in clinical or domestic environments. Consequently, the EEG is the current tool-of-choice with which to continuously monitor the brain where temporal resolution, ease-of- use and mobility are important. Traditionally, EEG data are examined by a trained clinician who identifies neurological events of interest. However, recent advances in signal processing and machine learning techniques have allowed the automated detection of neurological events for many medical applications. In doing so, the burden of work on the clinician has been significantly reduced, improving the response time to illness, and allowing the relevant medical treatment to be administered within minutes rather than hours. However, as typical EEG signals are of the order of microvolts (μV ), contamination by signals arising from sources other than the brain is frequent. These extra-cerebral sources, known as artefacts, can significantly distort the EEG signal, making its interpretation difficult, and can dramatically disimprove automatic neurological event detection classification performance. This thesis therefore, contributes to the further improvement of auto- mated neurological event detection systems, by identifying some of the major obstacles in deploying these EEG systems in ambulatory and clinical environments so that the EEG technologies can emerge from the laboratory towards real-world settings, where they can have a real-impact on the lives of patients. In this context, the thesis tackles three major problems in EEG monitoring, namely: (i) the problem of head-movement artefacts in ambulatory EEG, (ii) the high numbers of false detections in state-of-the-art, automated, epileptiform activity detection systems and (iii) false detections in state-of-the-art, automated neonatal seizure detection systems. To accomplish this, the thesis employs a wide range of statistical, signal processing and machine learning techniques drawn from mathematics, engineering and computer science. The first body of work outlined in this thesis proposes a system to automatically detect head-movement artefacts in ambulatory EEG and utilises supervised machine learning classifiers to do so. The resulting head-movement artefact detection system is the first of its kind and offers accurate detection of head-movement artefacts in ambulatory EEG. Subsequently, addtional physiological signals, in the form of gyroscopes, are used to detect head-movements and in doing so, bring additional information to the head- movement artefact detection task. A framework for combining EEG and gyroscope signals is then developed, offering improved head-movement arte- fact detection. The artefact detection methods developed for ambulatory EEG are subsequently adapted for use in an automated epileptiform activity detection system. Information from support vector machines classifiers used to detect epileptiform activity is fused with information from artefact-specific detection classifiers in order to significantly reduce the number of false detections in the epileptiform activity detection system. By this means, epileptiform activity detection which compares favourably with other state-of-the-art systems is achieved. Finally, the problem of false detections in automated neonatal seizure detection is approached in an alternative manner; blind source separation techniques, complimented with information from additional physiological signals are used to remove respiration artefact from the EEG. In utilising these methods, some encouraging advances have been made in detecting and removing respiration artefacts from the neonatal EEG, and in doing so, the performance of the underlying diagnostic technology is improved, bringing its deployment in the real-world, clinical domain one step closer.

Context-aware real-time assistant architecture for pervasive healthcare

The aging population in many countries brings into focus rising healthcare costs and pressure on conventional healthcare services. Pervasive healthcare has emerged as a viable solution capable of providing a technology-driven approach to alleviate such problems by allowing healthcare to move from the hospital-centred care to self-care, mobile care, and at-home care. The state-of-the-art studies in this field, however, lack a systematic approach for providing comprehensive pervasive healthcare solutions from data collection to data interpretation and from data analysis to data delivery. In this thesis we introduce a Context-aware Real-time Assistant (CARA) architecture that integrates novel approaches with state-of-the-art technology solutions to provide a full-scale pervasive healthcare solution with the emphasis on context awareness to help maintaining the well-being of elderly people. CARA collects information about and around the individual in a home environment, and enables accurately recognition and continuously monitoring activities of daily living. It employs an innovative reasoning engine to provide accurate real-time interpretation of the context and current situation assessment. Being mindful of the use of the system for sensitive personal applications, CARA includes several mechanisms to make the sophisticated intelligent components as transparent and accountable as possible, it also includes a novel cloud-based component for more effective data analysis. To deliver the automated real-time services, CARA supports interactive video and medical sensor based remote consultation. Our proposal has been validated in three application domains that are rich in pervasive contexts and real-time scenarios: (i) Mobile-based Activity Recognition, (ii) Intelligent Healthcare Decision Support Systems and (iii) Home-based Remote Monitoring Systems.

The role of mitogen activated protein kinase phosphatase-1 in neurotoxic and inflammatory-induced changes in the development of midbrain dopaminergic neurons: relevance to Parkinson’s disease

Parkinson’s disease (PD) is a progressive neurodegenerative disorder characterised by the loss of midbrain dopaminergic neurons from the substantia nigra pars compacta(SNpc), which results in motor, cognitive and psychiatric symptoms. Evidence supports a role for the mitogen-activated protein kinase p38 in the demise of dopaminergic neurons, while mitogen-activated protein kinase phosphatase-1 (MKP-1), which negatively regulates p38 activity, has not yet been investigated in this context. Inflammation may also be associated with the neuropathology of PD due to evidence of increased levels of proinflammatory cytokines such as interleukin-1β (IL-1β) within the SNpc. Because of the specific loss of dopaminergic neurons in a discreet region of the brain, PD is considered a suitable candidate for cell replacement therapy but challenges remain to optimise dopaminergic cell survival and morphological development. The present thesis examined the role of MKP-1 in neurotoxic and inflammatory-induced changes in the development of midbrain dopaminergic neurons. We show that MKP-1 is expressed in dopaminergic neurons cultured from embryonic day (E) 14 rat ventral mesencephalon (VM). Inhibition of dopaminergic neurite growth induced by treatment of rat VM neurons with the dopaminergic neurotoxin 6- hydroxydopamine (6-OHDA) is mediated by p38, and is concomitant with a significant and selective decrease in MKP-1 expression in these neurons. Dopaminergic neurons transfected to overexpress MKP-1 displayed a more complex morphology and contributed to neuroprotection against the effects of 6-OHDA. Therefore, MKP-1 expression can promote the growth and elaboration of dopaminergic neuronal processes and can help protect them from the neurotoxic effects of 6-OHDA. Neural precursor cells (NPCs) have emerged as promising alternative candidates to fetal VM for cell replacement strategies in PD. Here we show that phosphorylated (and thus activated) p38 and MKP-1 are expressed at basal levels in untreated E14 rat VM NPCs (nestin, DCX, GFAP and DAT-positive cells) following proliferation as well as in their differentiated progeny (DCX, DAT, GFAP and βIII-tubulin) in vitro. Challenge with 6-OHDA or IL-1β changed the expression of endogenous phospho-p38 and MKP-1 in these cells in a time-dependent manner, and so the dynamic balance in expression may mediate the detrimental effects of neurotoxicity and inflammation in proliferating and differentiating NPCs. We demonstrate that there was an up-regulation in MKP-1 mRNA expression in adult rat midbrain tissue 4 days post lesion in two rat models of PD; the 6-OHDA medial forebrain bundle (MFB) model and the four-site 6-OHDA striatal lesion model. This was concomitant with a decrease in tyrosine hydroxylase (TH) mRNA expression at 4 and 10 days post-lesion in the MFB model and 10 and 28 days post-lesion in the striatal lesion model. There was no change in mRNA expression of the pro-apoptotic gene, bax and the anti-apoptotic gene, bcl-2 in the midbrain and striatum. These data suggest that the early and transient upregulation of MKP-1 mRNA in the midbrain at 4 days post-6-OHDA administration may be indicative of an attempt by dopaminergic neurons in the midbrain to protect against the neurotoxic effects of 6-OHDA at later time points. Collectively, these findings show that MKP-1 is expressed by developing and adult dopaminergic neurons in the midbrain, and can promote their morphological development. MKP-1 also exerts neuroprotective effects against dopaminergic neurotoxins in vitro, and its expression in dopaminergic neurons can be modulated by inflammatory and neurotoxic insults both in vitro and in vivo. Thus, these data contribute to the information needed to develop therapeutic strategies for protecting midbrain dopaminergic neurons in the context of PD.

The political and economic context of Keynes’s 1933 Finlay lecture: transforming a business practitioner’s ways of knowing

This thesis is structured in the format of a three part Portfolio of Exploration to facilitate transformation in my ways of knowing to enhance an experienced business practitioner’s capabilities and effectiveness. A key factor in my ways of knowing, as opposed to what I know, is my exploration of context and assumptions. By interacting with my cultural, intellectual, economic, and social history, I seek to become critically aware of the biographical, historical, and cultural context of my beliefs and feelings about myself. This Portfolio is not exclusively for historians of economics or historians of ideas but also for those interested in becoming more aware of how these culturally assimilated frames of reference and bundles of assumptions that influence the way they perceive, think, decide, feel and interpret their experiences in order to operate more effectively in their professional and organisational lives. In the first part of my Portfolio, I outline and reflect upon my Portfolio’s overarching theory of adult development; the writings of Harvard’s Robert Kegan and Columbia University’s Jack Mezirow. The second part delves further into how meaning-making, the activity of how one organises and makes sense of the world and how meaning-making evolves to different levels of complexity. I explore how past experience and our interpretations of history influences our understandings since all perception is inevitably tinged with bias and entrenched ‘theory-laden’ assumptions. In my third part, I explore the 1933 inaugural University College Dublin Finlay Lecture delivered by economist John Maynard Keynes. My findings provide a new perspective and understanding of Keynes’s 1933 lecture by not solely reading or relying upon the text of the three contextualised essay versions of his lecture. The purpose and context of Keynes’s original longer lecture version was quite different to the three shorter essay versions published for the American, British and German audiences.