Digital signal processing and artificial intelligence for the automated classification of food allergy

As a by-product of the ‘information revolution’ which is currently unfolding, lifetimes of man (and indeed computer) hours are being allocated for the automated and intelligent interpretation of data. This is particularly true in medical and clinical settings, where research into machine-assisted diagnosis of physiological conditions gains momentum daily. Of the conditions which have been addressed, however, automated classification of allergy has not been investigated, even though the numbers of allergic persons are rising, and undiagnosed allergies are most likely to elicit fatal consequences. On the basis of the observations of allergists who conduct oral food challenges (OFCs), activity-based analyses of allergy tests were performed. Algorithms were investigated and validated by a pilot study which verified that accelerometer-based inquiry of human movements is particularly well-suited for objective appraisal of activity. However, when these analyses were applied to OFCs, accelerometer-based investigations were found to provide very poor separation between allergic and non-allergic persons, and it was concluded that the avenues explored in this thesis are inadequate for the classification of allergy. Heart rate variability (HRV) analysis is known to provide very significant diagnostic information for many conditions. Owing to this, electrocardiograms (ECGs) were recorded during OFCs for the purpose of assessing the effect that allergy induces on HRV features. It was found that with appropriate analysis, excellent separation between allergic and nonallergic subjects can be obtained. These results were, however, obtained with manual QRS annotations, and these are not a viable methodology for real-time diagnostic applications. Even so, this was the first work which has categorically correlated changes in HRV features to the onset of allergic events, and manual annotations yield undeniable affirmation of this. Fostered by the successful results which were obtained with manual classifications, automatic QRS detection algorithms were investigated to facilitate the fully automated classification of allergy. The results which were obtained by this process are very promising. Most importantly, the work that is presented in this thesis did not obtain any false positive classifications. This is a most desirable result for OFC classification, as it allows complete confidence to be attributed to classifications of allergy. Furthermore, these results could be particularly advantageous in clinical settings, as machine-based classification can detect the onset of allergy which can allow for early termination of OFCs. Consequently, machine-based monitoring of OFCs has in this work been shown to possess the capacity to significantly and safely advance the current state of clinical art of allergy diagnosis

Maltodextrin-incorporated-vacuum-dried honey powder: processing and stability

Honey is rich in sugar content and dominated by fructose and glucose that make honey prone to crystallize during storage. Due to honey composition, the anhydrous glass transition temperature of honey is very low that makes honey difficult to dry alone and drying aid or filler is needed to dry honey. Maltodextrin is a common drying aid material used in drying of sugar-rich food. The present study aims to study the processing of honey powder by vacuum drying method and the impact of drying process and formulation on the stability of honey powder. To achieve the objectives, the series of experiments were done: investigating of maltodextrin DE 10 properties, studying the effect of drying temperature, total solid concentration, DE value, maltodextrin concentration and anti-caking agent on honey powder processing and stability. Maltodextrin provide stable glass compared to lower molecular weight sugars. Dynamic Dew Point Isotherm (DDI) data could be used to determine amorphous content of a system. The area under the first derivative curve from DDI curve is equal to the amount of water needed by amorphous material to crystallize. The drying temperature affected the amorphous content of vacuum-dried honey powder. The higher temperature seemed to result in honey powder with more amorphous component. The ratio of maltodextrin affected more significantly the stability of honey powder compared to the treatments of total solids concentration, DE value and drying temperature. The critical water activity of honey powder was lower than water activity of the equilibrium water content corresponding to BET monolayer water content. Addition of anti-caking agent increased stability and flow-ability of honey powder. Addition of Calcium stearate could inhibit collapse of the honey powder during storage.

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.

Molecular and cellular aspects of the SREBP pathway

The SREBP (sterol response element binding proteins) transcription factors are central to regulating de novo biosynthesis of cholesterol and fatty acids. The SREBPs are regulated by retention or escape from the ER to the Golgi where they are proteolytically cleaved into active forms. The SREBP cleavage activating protein (SCAP) and the INSIG proteins are essential in this regulatory process. The aim of this thesis is to further characterise the molecular and cellular aspects surrounding regulation of SREBP processing. SREBP and SCAP are known to interact via their carboxy-terminal regulatory domains (CTDs) but this interaction is poorly characterised. Significant steps were achieved in this thesis towards specific mapping of the interaction site. These included cloning and over expression and partial purification of tagged SREBP1 and SREBP2 CTDs and probing of a SCAP peptide array with the CTDs. Results from the SREBP2 probing were difficult to interpret due to insolubility issues with the protein, however, probing with SREBP1 revealed five potential binding sites which were detected reproducibly. Further research is necessary to overcome SREBP2 insolubility issues and to confirm the identified SREBP1 interaction site(s) on SCAP. INSIG1 has a central role in regulating SREBP processing and in regulating stability of 3-hydroxy-3-methylglutaryl coenzyme A reductase (HMGCR), a rate limiting enzyme in cholesterol biosynthesis. There are two protein isoforms of human INSIG1 produced through the use of two in-frame alternative start sites. Bioinformatic analysis indicated that the presence of two in-frame start sites within the 5-prime region of INSIG1 mRNA is highly conserved and that production of two isoforms of INSIG1is likely a conserved event. Functional differences between these two isoforms were explored. No difference in either the regulation of SREBP processing or HMGCR degradation between the INSIG1 isoforms was observed and the functional significance of the two isoforms is as yet unclear. The final part of this thesis focused on enhancing the cytotoxicity of statins by targeted inhibition of SREBP processing by oxysterols. Statins have significant potential as anti-cancer agents as they inhibit the activity of HMGCR leading to a deficiency in mevalonate which is essential for cell survival. The levels of HMGCR fluctuate widely due to cholesterol feedback of SREBP processing. The relationship between sterol feedback and statin mediated cell death was investigated in depth in HeLa cells. Down regulation of SREBP processing by sterols significantly enhanced the efficacy of statin mediated cell death. Investigation of sterol feedback in additional cancer cell lines showed that sterol feedback was absent in cell lines A- 498, DU-145, MCF-7 and MeWo but was present in cell lines HT-29, HepG2 and KYSE-70. In the latter inhibition of SREBP processing using oxysterols significantly enhanced statin cytotoxicity. The results indicate that this approach is valid to enhance statin cytotoxicity in cancer cells, but may be limited by deregulation of SREBP processing and off target effects of statins, which were observed for some of the cancer cell lines screened.