Meniere's disease is a common inner ear disorder that affects balance and hearing. Electrovestibulography (EVestG) is a relatively new vestibular driven test that measures spontaneous and driven field potential activity recorded in the external ear canal in response to various vestibular stimuli. The main objectives of this thesis were to record and analyze EVestG signals in order to 1) testify whether the EVestG technology is capable of classifying individuals with Meniere’s from healthy ones, and if it is, then 2) identify the EVestG tilt stimulus providing the most informative response in relation to identifying Meniere’s symptoms; thus, optimizing the EVestG experimental protocol as a Meniere’s disease diagnostic aid. EVestG signals of two groups of Meniere’s and control individuals during seven different EVestG tilt stimuli were recorded and analyzed by linear and nonlinear signal processing techniques. Data of 14 with Meniere’s disease and 16 healthy individuals were used as the training set, while additional data of 21 individuals with vertiginous disorders (and suspected of Meniere’s disease) and 10 controls were used as the test set. An ad-hoc voting classifier built upon single-feature linear classifiers was designed, and used for classification of the two groups of both training and test datasets. The results showed an overall accuracy of 87% and 84% for training and test datasets, respectively. Among the seven different tilts that each evokes a specific part of the inner ear organ, the side tilt which stimulates most of the labyrinth and particularly the utricle, was found to generate the best characteristic features for identifying Meniere’s disease from controls. Thus, one may simplify the EVestG protocol to only the side tilt stimulus for a quick screening of Meniere’s disease. The proposed method encourages the use of EVestG technology as a non-invasive and potentially reliable diagnostic/screening tool to aid clinical diagnosis of Meniere’s diseases. / October 2016

Carta al editor / Revisión por pares

Damage to the crops occurs due to insects eating the leaves, environmental changes, irregular fertilization, and improper use of pesticides decreasing yield. It is important to identify the percentage of damages in crop that will help in selecting the quantity of pesticide used to treat the damage, and in predicting the change in the yield of the crop. So far, the research efforts handled this problem by collecting datasets from near-field and far-field images of damaged crops and then training Deep Learning Model to differentiate healthy leaf and Unhealthy leaf. To the best of our knowledge, there is no deep learning model has been trained to predict and classify the level of damage in the soybean leaves. Therefore, the main aim of this thesis is to propose a deep learning model that predicts the classes of damage from scale of one to five and also identifies healthy leaf from unhealthy leaf. The proposed model analyses dataset containing non-healthy leaves and healthy leaves and estimates the performance of classification methods. This analysis allows the model to predict different damage caused by insects and natural calamities to leaves, therefore aiding the agricultural professional to corrective actions based on specific class of damage.

Psoriatic arthritis is an inflammatory arthritis affecting a fifth of patients with skin psoriasis. Inflammation of the joints and tendons causes pain, stiffness, reduced function and disability. Work disability is increasingly recognised as an important, patient centred, functional measure of disease yet little is known about work disability in psoriatic arthritis. The overall aim of my thesis is to examine patient reported work disability in psoriatic arthritis by undertaking the following; • A systematic review of the relevant literature • Classification of a cohort of patients to study • Validation of a commonly used work outcome measure used in other rheumatic diseases • Selection of a suitable measure of structural damage to inflamed joints for investigating the associations of work disability in longitudinal observational studies. The results of the systematic review identified limited data reporting high levels of work disability associated with a wide variety of disease and non-disease related factors. The review also identified the lack of a validated outcome measure for use in psoriatic arthritis. I report the classification of a large single centre longitudinal cohort of patients with psoriatic arthritis and evidence supporting the retrospective application of a psoriatic arthritis classification criterion. Subsequently I report a preliminary validation study of the work productivity and activity impairment questionnaire to measure work disability in psoriatic arthritis and a further study comparing the existing measures of structural damage in psoriatic arthritis. Finally I developed and supervised a multicentre observational study to examine the associations of work disability in psoriatic arthritis. The study identified reduced work effectiveness to be associated with measures of disease activity, whereas unemployment was associated with recent disease onset, greater age and worse physical function. The study will provide a valuable cohort for prospective study of work disability and the effect of medical treatment and will form part of my planned post-doctoral studies.

Context- Vision is one of the five elementary physiologial senses. Vision is enabled via the eye, a very delicate sense organ which is highly susceptible to damage which results in loss of vision. The damage comes in the form of injuries or diseases such as diabetic retinopathy and glaucoma. While it is not possible to predict accidents, predicting the onset of disease in the earliest stages is highly attainable. Owing to the leaps in imaging technology,it is also possible to provide near instant diagnosis by utilizing computer vision and image processing capabilities. Objectives- In this thesis, an algorithm is proposed and implemented to classify images of the retina into healthy or two classes of unhealthy images, i.e, diabetic retinopathy, and glaucoma thus aiding diagnosis. Additionally the algorithm is studied to investigate which image transformation is more feasible in implementation within the scope of this algorithm and which region of retina helps in accurate diagnosis. Methods- An experiment has been designed to facilitate the development of the algorithm. The algorithm is developed in such a way that it can accept all the values of a dataset concurrently and perform both the domain transforms independent of each other. Results- It is found that blood vessels help best in predicting disease associations, with the classifier giving an accuracy of 0.93 and a Cohen’s kappa score of 0.90. Frequency transformed images also presented a accuracy in prediction with 0.93 on blood vessel images and 0.87 on optic disk images. Conclusions- It is concluded that blood vessels from the fundus images after frequency transformation gives the highest accuracy for the algorithm developed when the algorithm is using a bag of visual words and an image category classifier model. Keywords-Image Processing, Machine Learning, Medical Imaging

Classifying individuals into binary disease categories can be challenging due to complex relationships across different exposures of interest. In this thesis, we investigate three different approaches for disease classification using multiple biomarkers. First, we consider combining information from literature reviews and INTERHEART data set to identify the threshold of ApoB, ApoA1 and the ratio of these two biomarkers to classify individuals at risk of developing myocardial infarction. We develop a Bayesian estimation procedure for this purpose that utilizes the conditional probability distribution of these biomarkers. This method is flexible compared to standard logistic regression approach and allows us to identify a precise threshold of these biomarkers. Second, we consider the problem of disease classification using two dependent biomarkers. An independently identified threshold for this purpose usually leads to a conflicting classification for some individuals. We develop and describe a method of determining the joint threshold of two dependent biomarkers for a disease classification, based on the joint probability distribution function constructed through copulas. This method will allow researchers uniquely classify individuals at risk of developing the disease. Third, we consider the problem of classifying an outcome using a gene and miRNA expression data sets. Linear principal component analysis (PCA) is a widely used approach to reduce the dimension of such data sets and subsequently use it for classification, but many authors suggest using kernel PCA for this purpose. Using real and simulated data sets, we compare these two approaches and assess the performance of components towards genetic data integration for an outcome classification. We conclude that reducing dimensions using linear PCA followed by a logistic regression model for classification seems to be acceptable for this purpose. We also observe that integrating information from multiple data sets using either of these approaches leads to a better performance of an outcome classification. / Thesis / Doctor of Philosophy (PhD)

Thesis (Ph. D.)--University of California, San Diego, 2002. / Vita. Includes bibliographical references.

[Tuncated abstract] This research thesis consists of five sections. Section one provides the background information (chapter 1) and a description of characteristics of the cohort and the methods of analysis (chapter 2). The Acute Physiology and Chronic Health Evaluation (APACHE) II scoring system is one of commonly used severity of illness scoring systems in many intensive care units (ICUs). Section two of this thesis includes an assessment of the performance of the APACHE II scoring system in an Australian context. First, the performance of the APACHE II scoring system in predicting hospital mortality of critically ill patients in an ICU of a tertiary university teaching hospital in Western Australia was assessed (Chapter 3). Second, a simple modification of the traditional APACHE II scoring system, the 'admission APACHE II scoring system', generated by replacing the worst first 24-hour data by the ICU admission physiological and laboratory data was assessed (Chapter 3). Indigenous and Aboriginal Australians constitute a significant proportion of the population in Western Australia (3.2%) and have marked social disadvantage when compared to other Australians. The difference in the pattern of critical illness between indigenous and non-indigenous Australians and also whether the performance of the APACHE II scoring system was comparable between these two groups of critically ill patients in Western Australia was assessed (Chapter 4). Both discrimination and calibration are important indicators of the performance of a prognostic scoring system. ... The use of the APACHE II scoring system in patients readmitted to ICU during the same hospitalisation was evaluated and also whether incorporating events prior to the ICU readmission to the APACHE II scoring system would improve its ability to predict hospital mortality of ICU readmission was assessed in chapter 10. Whilst there have been a number of studies investigating predictors of post-ICU in-hospital mortality none have investigated whether unresolved or latent inflammation and sepsis may be an important predictor. Section four examines the role of inflammatory markers measured at ICU discharge on predicting ICU re- 4 admission (Chapter 11) and in-hospital mortality during the same hospitalisation (Chapter 12) and whether some of these inflammatory markers were more important than organ failure score and the APACHE II scoring system in predicting these outcomes. Section five describes the development of a new prognostic scoring system that can estimate median survival time and long term survival probabilities for critically ill patients (Chapter 13). An assessment of the effects of other factors such as socioeconomic status and Aboriginality on the long term survival of critically ill patients in an Australian ICU was assessed (Chapter 14). Section six provides the conclusions. Chapter 15 includes a summary and discussion of the findings of this thesis and outlines possible future directions for further research in this important aspect of intensive care medicine.

Cartas al editor

This work deals with designing and testing of new acoustic features for analysis of dysprosodic speech occurring in hypokinetic dysarthria patients. 41 new features for dysprosody quantification (describing melody, loudness, rhythm and pace) are presented and tested in this work. New features can be divided into 7 groups. Inside the groups, features vary by the used statistical values. First four groups are based on absolute differences and cumulative sums of fundamental frequency and short-time energy of the signal. Fifth group contains features based on multiples of this fundamental frequency and short-time energy combined into one global intonation feature. Sixth group contains global time features, which are made of divisions between conventional rhythm and pace features. Last group contains global features for quantification of whole dysprosody, made of divisions between global intonation and global time features. All features were tested on Czech Parkinsonian speech database PARCZ. First, kernel density estimation was made and plotted for all features. Then correlation analysis with medicinal metadata was made, first for all the features, then for global features only. Next classification and regression analysis were made, using classification and regression trees algorithm (CART). This analysis was first made for all the features separately, then for all the data at once and eventually a sequential floating feature selection was made, to find out the best fitting combination of features for the current matter. Even though none of the features emerged as a universal best, there were a few features, that were appearing as one of the best repeatedly and also there was a trend that there was a bigger drop between the best and the second best feature, marking it as a much better feature for the given matter, than the rest of the tested. Results are included in the conclusion together with the discussion.