COVID-19 has led to a surge in the adoption of digital transformation in almost every sector. Digital health and well-being are no exception. For instance, now people get checkupsvia apps or websites instead of visiting a physician. The pandemic has pushed the health-care sector worldwide to advance the adoption of artificial intelligence (AI) capabilities.Considering the demand for AI in supporting the well-being of an individual, we presentthe real-life diagnosis as a digital twin(DT) diagnosis using machine learning. The MachineLearning (ML) technology enables DT to offer a prediction. Although several attemptsexist for predicting disease using ML and a few attempts through ML of DT frameworks,those do not deal with disease risk prediction. In addition, most of them deal with singledisease prediction after the occurrence and rely only on clinical test data like- ECG report,MRI scan, etc.To predict multiple disease/disease risks, we propose a dynamic machine learning algo-rithm (MLA) selection framework and a dynamic testing method. The proposed frameworkaccepts heterogeneous electronic health records (EHRs) or digital health status as datasetsand selects suitable MLA upon the highest similarity. Then it trains specific classifiers forpredicting a specific disease/disease risk. The dynamic testing method for prediction isused for predicting several diseases.We described three use cases: non-communicable disease(NCD) risk prediction, mentalwell-being prediction, and COVID-19 prediction. We selected diabetes, risk of diabetes,liver disease, thyroid, risk of stroke as NCDs, mental stress as a mental health issue, andCOVID-19. We employed seven datasets, including public and private datasets, with adiverse range of attributes, sizes, types, and formats to evaluate whether the proposedframework is suitable to data heterogeneity. Our experiment found that the proposed methods of dynamic MLA selection could select MLA for each dataset at cosine similarityscores ranging between 0.82-0.89. In addition, we predicted target disease/disease risks atan accuracy ranging from 94.5% to 98%.To verify the performance of the framework-selected predictor, we compared the accuracy measures individually for each of the three cases. We compared them with traditionalML disease prediction work in the literature. We found that the framework-selected algorithms performed with good accuracy compared to existing literature.

published_or_final_version / abstract / Electrical and Electronic Engineering / Doctoral / Doctor of Philosophy

The purpose of the present study was to compare 42 community-dwelling spouse and child Alzheimer's Disease caregivers with 38 community-dwelling potential caregivers on salience of illness symptoms, and accuracy of judging symptoms of illnesses.

Doctor of Philosophy / Department of Statistics / Wei-Wen Hsu / The classification methods based on a linear combination of multiple biomarkers have been widely used to improve the accuracy in disease screening and diagnosis. However, it is seldom to include covariates such as gender and age at diagnosis into these classification procedures. It is known that biomarkers or patient outcomes are often associated with some covariates in practice, therefore the inclusion of covariates may further improve the power of prediction as well as the classification accuracy. In this study, we focus on the classification methods for multiple biomarkers adjusting for covariates. First, we proposed a covariate-adjusted classification model for multiple cross-sectional biomarkers. Technically, it is a two-stage method with a parametric or non-parametric approach to combine biomarkers first, and then incorporating covariates with the use of the maximum rank correlation estimators. Specifically, these parameter coefficients associated with covariates can be estimated by maximizing the area under the receiver operating characteristic (ROC) curve. The asymptotic properties of these estimators in the model are also discussed. An intensive simulation study is conducted to evaluate the performance of this proposed method in finite sample sizes. The data of colorectal cancer and pancreatic cancer are used to illustrate the proposed methodology for multiple cross-sectional biomarkers. We further extend our classification method to longitudinal biomarkers. With the use of a natural cubic spline basis, each subject's longitudinal biomarker profile can be characterized by spline coefficients with a significant reduction in the dimension of data. Specifically, the maximum reduction can be achieved by controlling the number of knots or degrees of freedom in the spline approach, and its coefficients can be obtained by the ordinary least squares method. We consider each spline coefficient as ``biomarker'' in our previous method, then the optimal linear combination of those spline coefficients can be acquired using Stepwise method without any distributional assumption. Afterward, covariates are included by maximizing the corresponding AUC as the second stage. The proposed method is applied to the longitudinal data of Alzheimer's disease and the primary biliary cirrhosis data for illustration. We conduct a simulation study to assess the finite-sample performance of the proposed method for longitudinal biomarkers.

by Frankie Kar-Ming Wong. / Thesis (M.Phil.)--Chinese University of Hong Kong, 1997. / Includes bibliographical references (leaves 101-107). / Acknowledgements --- p.IV / Abstract --- p.V / Abbreviations --- p.VI / Chapter Chapter 1 --- Introduction to Lipoprotein and Apolipoprotein --- p.1 / Chapter 1.1 --- Lipoprotein structure and classification --- p.1 / Chapter 1.2 --- Apolipoprotein A-I and B100 --- p.1 / Chapter 1.2.1 --- Apolipoprotein A-I (apoA-I) --- p.1 / Chapter 1.2.2 --- Apolipoprotein B100 (apoB100) --- p.3 / Chapter 1.2.3 --- Biological functions of apolipoprotein --- p.4 / Chapter 1.3 --- Evidence linking apoA-I and B100 with atherosclerosis --- p.4 / Chapter 1.4 --- The roles of apoA-I and B100 in the development of atherosclerosis --- p.6 / Chapter 1.5 --- Measurement of human serum lipoproteins as an assessment of risk for coronary heart disease (CHD) --- p.8 / Chapter 1.6 --- Aims of this study --- p.10 / Chapter Chapter 2 --- Purification of ApoA-I and B100 and Production of Polyclonal Antibodies --- p.12 / Chapter 2.1 --- Introduction --- p.12 / Chapter 2.1.1 --- Purification of apoA-I and B100 from human serum --- p.12 / Chapter 2.1.2 --- Immunization for polyclonal antibodies production against apoA-I and B100 --- p.14 / Chapter 2.1.3 --- Antibody purification --- p.15 / Chapter 2.1.3.1 --- Ammonium sulfate precipitation --- p.17 / Chapter 2.1.3.2 --- DEAE and QEAE Sepharose --- p.17 / Chapter 2.1.3.3 --- Protein A and Protein G --- p.17 / Chapter 2.1.3.4 --- Affinity chromatography --- p.18 / Chapter 2.2 --- Methods --- p.20 / Chapter 2.2.1 --- Purification of HDL and LDL --- p.20 / Chapter 2.2.2 --- Purification of apolipoproteins --- p.22 / Chapter 2.2.3 --- Immunization of rabbit with apoA-I and B100 --- p.23 / Chapter 2.2.4 --- Enzyme-linked immunosorbent assay (ELISA) --- p.24 / Chapter 2.2.5 --- Purification of lipoprotein specific immunoglobulin from antisera --- p.25 / Chapter 2.2.5.1 --- Salt fractionation --- p.25 / Chapter 2.2.5.2 --- Purification of immunoglobulin by Protein A affinity chromatography --- p.25 / Chapter 2.2.5.3 --- Isolation of specific antibody by lipoprotein-coupled affinity chromatography --- p.26 / Chapter 2.3 --- Results --- p.27 / Chapter 2.3.1 --- Purification of apoA-I and B100 --- p.27 / Chapter 2.3.2 --- Purification of immunoglobulins from rabbit anti-apolipoprotein sera --- p.32 / Chapter 2.4 --- Discussion --- p.38 / Chapter Chapter 3 --- Production of monoclonal antibodies against apoA-I and B100 --- p.48 / Chapter 3.1 --- Introduction --- p.48 / Chapter 3.1.1 --- What is monoclonal antibody? --- p.48 / Chapter 3.1.2 --- The basic methodology --- p.49 / Chapter 3.1.2.1 --- Immunization of host --- p.49 / Chapter 3.1.2.2 --- Cell lines required for fusion --- p.49 / Chapter 3.1.2.3 --- Fusion --- p.51 / Chapter 3.1.2.4 --- Selection of hybrids --- p.52 / Chapter 3.1.2.5 --- Screening assay --- p.54 / Chapter 3.1.2.6 --- Cloning --- p.54 / Chapter 3.1.2.7 --- Bulk production of monoclonal antibody --- p.55 / Chapter 3.1.2.8 --- Monoclonal antibody purification --- p.55 / Chapter 3.2 --- Methods --- p.55 / Chapter 3.2.1 --- Immunization of mice with apoA-I and apoB100 --- p.55 / Chapter 3.2.2 --- Preparation before fusion --- p.58 / Chapter 3.2.2.1 --- Preparation of tissue culture working solutions --- p.58 / Chapter 3.2.2.2 --- Preparation of spleen cells --- p.59 / Chapter 3.2.2.3 --- Preparation of myeloma cells --- p.60 / Chapter 3.2.3 --- Fusion --- p.60 / Chapter 3.2.4 --- Screening assay for positive clones --- p.61 / Chapter 3.2.5 --- Limiting dilution cloning --- p.61 / Chapter 3.2.6 --- Determination of isotype --- p.62 / Chapter 3.2.7 --- Cryopreservation of myeloma and established hybridoma cell lines --- p.62 / Chapter 3.2.7.1 --- Freezing cells --- p.62 / Chapter 3.2.7.2 --- Thawing cells --- p.63 / Chapter 3.2.8 --- Bulk production of monoclonal antibodies from ascites --- p.63 / Chapter 3.2.9 --- Purification of monoclonal antibodies from ascites --- p.63 / Chapter 3.2.10 --- Western blot analyses of the monoclonal antibodies --- p.64 / Chapter 3.2.11 --- Iodination of apolipoproteins --- p.64 / Chapter 3.2.12 --- Binding of the monoclonal antibody to iodinated apolipoprotein --- p.65 / Chapter 3.2.13 --- Competitive displacement analyses --- p.65 / Chapter 3.3 --- Results --- p.66 / Chapter 3.3.1 --- Development of monoclonal antibodies --- p.66 / Chapter 3.3.2 --- Purification of monoclonal antibody from ascites --- p.69 / Chapter 3.3.3 --- Western blotting analyses of AB6 and BE8 --- p.69 / Chapter 3.3.4 --- Monoclonal antibody titration curve for apolipoproteins by radioimmunoassays --- p.75 / Chapter 3.3.5 --- Competitive displacement analysis of AB6 and BE8 --- p.75 / Chapter 3.4 --- Discussion --- p.79 / Chapter Chapter 4 --- Enzyme-linked immunosorbent assay (ELISA) for ApoA-I --- p.84 / Chapter 4.1 --- Introduction --- p.84 / Chapter 4.1.1 --- Alkaline phosphatase (ALP) --- p.84 / Chapter 4.1.2 --- Conjugation methods --- p.85 / Chapter 4.1.3 --- Design of the immunoassay format --- p.87 / Chapter 4.1.4 --- Modified solid-phase: Protein A antibody-capture ELISA (PACE) --- p.87 / Chapter 4.2 --- Materials and Methods --- p.90 / Chapter 4.2.1 --- Conjugation of AB6 with maleimide activated alkaline phosphatase --- p.90 / Chapter 4.2.2 --- Titration curve of AB6-ALP conjugate --- p.90 / Chapter 4.2.3 --- Calibration curve of apoA-I sandwich ELISA --- p.91 / Chapter 4.2.4 --- Measurement of apoA-I by Protein A antibody-capture ELISA --- p.91 / Chapter 4.3 --- Results --- p.92 / Chapter 4.3.1 --- Characterization of AB6-ALP conjugate --- p.92 / Chapter 4.3.2 --- Calibration curve for the measurement of apoA-I --- p.92 / Chapter 4.4 --- Discussion --- p.95 / Chapter Chapter 5 --- General Conclusions --- p.99 / References --- p.101

Includes a list of thesis related publications, reviews and thesis related abstracts, awards, book chapters and invited presentations (leaves vii-xii). / Includes bibliographical references (leaves 179-234). / xvii, 234 leaves : ill. (some col.) ; 30 cm. / Title page, contents and abstract only. The complete thesis in print form is available from the University Library. / A systematic evaluation of magnetic resonance imaging and its use in the ex vivo and in vivo setting, in the aorta and coronary arteries in rabbit and porcine models, leading to the potential for human coronary atherosclerotic imaging. / Thesis (Ph.D.)--Adelaide University, Dept. of Medicine, 2001

Classical Swine Fever (CSF) is a highly contagious viral disease of swine that causes major losses to pig production. CSF virus is a member of the genus Pestivirus of the family Flaviviridae and is closely related antigenically to other Pestiviruses, Bovine Viral Diarrhoea (BVD) virus and Border Disease (BD) virus. In the Lao People’s Democratic Republic (Laos), CSF has been recognised as a disease that causes significant loss to the smallholder pig sector. However, there exists in Laos a deficiency in fully understanding the epidemiology and impact of CSF, together with limitations in being able to reliably detect CSF outbreaks in a timely manner. (For complete abstract open document)

This study examined differences in scoring patterns among those diagnosed with Alzheimer's dementia and vascular dementia on the clock-drawing test. Archival clock drawing data was retrieved on 279 patients presenting at a county hospital-based memory clinic. Analysis of drawings was based on frequency of qualitative errors, as well as an overall quantitative score. Mean comparisons found those patients with Alzheimer's dementia to perform worse on both quantitative and qualitative scoring measures. However, Pearson's chi-squared test revealed a significantly higher rate of spacing errors among subjects with vascular dementia. Such lends support to my hypothesis that impaired executive functioning in vascular dementia patients would lead to poor qualitative performance. Logistic regression found significant predictive ability for the qualitative criteria in diagnosis (χ2 = 25.49, p < .001), particularly the rate of omission (z = 8.96, p = .003) and addition errors (z = 7.58, p = .006). Such findings hold important implications for the use of qualitative criteria in cognitive screening assessments.

No description available.

Parkinson's disease is a chronic neurological disorder affecting hundreds of thousands of Americans. The current best practice for assessment of this disease is a clinical examination and subjective rating using the Unified Parkinson's Disease Rating Scale. Such ratings are coarse scaled, subject to rater bias, and costly. Instruments which provide objective measurements of disease state can eliminate rater bias, provide repeatable data, and increase the frequency and responsiveness of subject assessments, expediting the validation of new therapies and treatments. This thesis describes the design and implementation of a battery of bio-mechanical devices suitable for clinical and in home use, including descriptions of the instruments and the functionality of the data acquisition software, as well as the overall system used for data collection. A data analysis algorithm is fully described, and descriptive statistics of pilot data from twenty two subjects are reported. These statistics show promising correlations of time duration metrics with the motor subsection of the UPDRS, as well as good responsiveness to dopaminergic intervention. Data also suggests that these devices have an advantage over previously described devices in the ability to record the full range of motion in standard assessment tasks, thereby providing additional metrics related to hesitations and halts in prescribed movements.