Globally, there is an alarming increase in the incidence of Type II diabetes mellitus (T2DM). It is well recognized that women who develop gestational diabetes (GDM) in their pregnancies are at increased risk of T2DM in later life. In addition, poor glycaemic control in pregnancy impacts adversely on the neonatal outcome, as well as the long term disease risks of that child. The risk of these outcomes increases continuously as maternal fasting plasma glucose levels increases. Several adverse outcomes have been associated with DM during pregnancy. These include pre-eclampsia, polyhydramnios, fetal macrosomia, fetal hepatomegaly and cardiomegaly, birth trauma, operative delivery, perinatal mortality and neonatal respiratory problems and metabolic complications such as hypoglycaemia, hyperbilirubinaemia, hypocalcaemia and polycythaemia. Despite five decades of research there is little consensus regarding the optimal approach to screening for GDM. Recently most international organisations have recommended that all women should be screened for GDM. South Africa is a diverse multi-racial society with an increasing burden of non-communicable diseases. The health system is already overburdened, and the optimal approach to screening for GDM remains unclear. A prospective cohort observational study was conducted at the Eyethu Yarona clinic (Lion Park Clinic), in Johannesburg, South Africa (SA). One thousand (1000) consecutive non-diabetic women who were less than 26 weeks pregnant were recruited. At recruitment the women completed a demographic questionnaire, and had a random glucose and glycated haemoglobin (HbA1c) drawn. A fasting blood glucose was assessed within 2 weeks, and a serum specimen was frozen at -40°C for further testing at a later stage. Patients had a 75 g 2-hour oral glucose tolerance test (OGTT) and HbA1c between 24 – 28 weeks gestation. All glucose measurements were done at the laboratory using standardized tests (venous blood) and on a Roche Accuchek Active® glucometer (Roche Diagnostics, Mannheim, Germany) (capillary blood). GDM was diagnosed according to the International Federation of Gynecology and Obstetrics (FIGO) criteria, i.e. any one abnormal reading was diagnostic of GDM: 0-hour ≥5.1 mmol/l, 1-hour ≥10 mmol/l, or 2-hour ≥8.5 mmol/l. Thereafter a nested cohort study of HIV negative patients was conducted to investigate the association between the concentrations of biomarkers associated with glucose homeostasis and GDM in a South African population. C-reactive protein (CRP), adiponectin, and fasting insulin were measured on the stored serum samples. The Insulin Sensitivity Index (HOMA-IR = fasting insulin (microU/L) x fasting glucose (mmol/L) / 22.5), and Quantitative Insulin Sensitivity Check Index (QUICKI = 1 / [log (I0) + log (G0)]) were calculated for further evaluation of markers of insulin sensitivity. The significance of this research was to assess the burden of disease of GDM in a South African population. The different diagnostic criteria were also compared, as well as the universal versus the traditional risk-factor based screening approach to GDM. Screening methods were compared so as to propose a simple, effective, cost efficient screening and diagnostic tool that may be implemented at primary health care level, which will in turn identify those pregnant women who warrant referral to a high care obstetric unit, thus improving both maternal and neonatal outcomes in our population. / Thesis (PhD) - University of Pretoria, 2017. / SEMDSA / SASA / Roche / Obstetrics and Gynaecology / PhD / Unrestricted

This study develops a bankruptcy prediction model for South African companies listed on the Johannesburg Stock Exchange. The model is of considerable efficiency and the findings reported extend bankruptcy literature to developing countries. 64 financial ratios for 28 companies, grouped into failed and non-failed companies, were tested using multiple discriminant analysis after conducting normality tests. Three variables were found to be significant which are: Times Interest Earned, Cash to Debt and Working Capital to Turnover. The model correctly classified about 75% of failed and non-failed in the original and cross validation procedures. This study went on to conduct an external validation of the model superiority by introducing a sample of failed companies, which showed that the model predictive accuracy is more than chance. Despite the popularity of the topic among researchers this study highlighted the importance and relevance of the topic to corporate managers, policy makers and to investors especially in a developing market perspective, thereby contributing significantly towards understanding the factors that lead to corporate bankruptcy.

Unemployment Insurance serves as a vital economic stabiliser, offering financial assistance and promoting workforce reintegration. In Sweden, occupation-specific unemployment funds, known as "Arbetslöshetskassan" (A-KASSAN), manage these claims. New complex challenges pertaining to A-KASSAN's decision-making process and unemployment insurance claims necessitate a holistic data analytics framework, innovative modelling approaches, and effective implementation strategies.  This study aims to establish a comprehensive approach to data analytics for unemployment insurance claims to provide a more accurate prediction model to aid A-KASSAN's decision-making. It accomplishes this through three main objectives: the development of a thorough framework employing management data analytics for claim analysis; advancement in modelling approaches to predict unemployment trends; and deliberation on effective strategies to visualise the developed solutions.  Drawing on Data Science, Computer Science, and Economics and Management Science, this study has crafted a four-tiered comprehensive framework encompassing descriptive, diagnostic, predictive, and prescriptive analytics. It has explored novel methodologies, formulated a model library, devised rules for result integration, and validated these through case studies. The model library showcases diverse models from Economic modelling, Statistical modelling, Big Data analytics with Machine Learning and Deep Learning, alongside hybrid modelling strategies. This study primarily concentrates on developing visualisation tools as an implementation strategy. In a summary, this study provides A-KASSAN with an approach to overcome two central issues: the lack of a comprehensive data analytics approach for unemployment insurance claims, including a framework and predictive modelling, and a dearth of visualisation solutions for management data analytics pertinent to these claims.

Alzheimer’s disease (AD) is among the top 10 causes of global mortality, and dementia imposes a yearly $1 trillion USD economic burden. Of particular importance, women and minoritized groups are disproportionately affected by AD, with females having higher risk of developing AD compared to male cohorts. Differentiating mild cognitive impairment (MCIstable) from early stage Alzheimer’s disease (MCIAD) is vital worldwide. Despite genetic markers, such as apo-lipoprotein-E (APOE), identification of patients before they develop early stages of MCIAD, a critical period for possible pharmaceutical intervention, is not yet possible. Based on review of the literature three key limitations in existing AD-specific prediction models are apparent: 1) models developed by traditional statistics which overlook nonlinear relationships and complex interactions between features, 2) machine learning models are based on difficult to acquire, occasionally invasive, manually selected, and costly data, and 3) machine learning models often lack interpretability. Rapid, accurate, low-cost, easily accessible, non-invasive, interpretable and early clinical evaluation of AD is critical if an intervention is to have any hope at success. To support healthcare decision making and planning, and potentially reduce the burden of AD, this research leverages the Alzheimer’s Disease Neuroimaging Initiative (ADNI1/GO/2/3) database and a mathematical modelling approach based on supervised machine learning to identify 1) predictive markers of AD, and 2) patients at the highest risk of AD. Specifically we implemented a supervised XGBoost classifier with diagnostic (Exp 1) and prognostic (Exp 2) objectives. In experiment 1 (n=441) classification of AD (n=72) was performed in comparison to healthy controls (n= 369), while experiment 2 (n=738) involved classification of MCIstable (n = 444) compared to MCIAD(n = 294). In Experiment 1, machine learning tools identified three features (i.e., Everyday Cognition Questionnaire (Study partner) - Total, Alzheimer’s Disease Assessment Scale (13 items) and Delayed Total Recall) with ROC AUC scores consistently above 97%. Low performance on delayed recall alone appears to distinguish most AD patients. This finding is consistent with the pathophysiology of AD with individuals having problems storing new information into long-term memory. In experiment 2, the algorithm identified the major indicators of MCI-to-AD progression by integrating genetic, cognitive assessment, demographic and brain imaging to achieve ROC AUC scores consistently above 87%. This speaks to the multi-faceted nature of MCI progression and the utility of comprehensive feature selection. These features are important because they are non-invasive and easily collected. As an important focus of this research, the interpretability of the ML models and their predictions were investigated. The interpretable model for both experiments maintained performance with their complex counterparts while improving their interpretability. The interpretable models provide an intuitive explanation of the decision process which are vital steps towards the clinical adoption of machine learning tools for AD evaluation. The models can reliably predict patient diagnosis (Exp 1) and prognosis (Exp 2). In summary, our work extends beyond the identification of high-risk factors for developing AD. We identified accessible clinical features, together with clinically operable decision routes, to reliably and rapidly predict patients at the highest risk of developing Alzheimer’s disease. We addressed the aforementioned limitations by providing an intuitive explanation of the decision process among the high-risk non-invasive and accessible clinical features that lead to the patient’s risk. / Thesis / Master of Science in Biomedical Engineering / Early identification of patients at the highest risk of Alzheimer’s disease (AD) is crucial for possible pharmaceutical intervention. Existing prediction models have limitations, including inaccessible data and lack of interpretability. This research used a machine learning approach to identify patients at the highest risk of Alzheimer’s disease and found that certain clinical features, such as specific executive function- related cognitive testing (i.e., task switching), combined with genetic predisposition, brain imaging, and demographics, were important contributors to AD risk. The models were able to reliably predict patient diagnosis and prognosis and were designed to be low-cost, non-invasive, clinically operable and easily accessible. The interpretable models provided an intuitive explanation of the decision process, making it a valuable tool for healthcare decision-making and planning.

Background and objectives: Prediction models are useful tools in clinical practise by providing predictive estimates of outcome probabilities to aid in decision making. As biomedical research advances, concerns have been raised regarding combined effectiveness (benefit) and safety (harm) outcomes in a prediction model, while typically different prediction models only focus on predictions of separate outcomes. A second issue is that, evidence also reveals poor predictive accuracy in different populations and settings for some prediction models, requiring model calibration or redevelopment. A third issue in data analyses is whether the treatment effect estimates could be influenced by competing risk bias. If other events preclude the outcomes of interest, these events would compete with the outcomes and thus fundamentally change the probability of the outcomes of interest. Failure to recognize the existence of competing risk or to account for it may result in misleading conclusions in health research. Therefore in this thesis, we explored three methodological issues in prediction models and data analyses by: (1) developing and externally validating a prediction model for patients’ individual combined benefit and harm outcomes (stroke with no major bleeding, major bleeding with no stroke, neither event, or both stroke and major bleeding) with and without warfarin therapy for atrial fibrillation; (2) constructing a prediction model for hospital mortality in medical-surgical critically ill patients; and (3) performing a competing risk analysis to assess the efficacy of the low molecular weight heparin dalteparin versus unfractionated heparin in venous thromboembolism in medical-surgical critically ill patients. Methods: Project 1: Using the Kaiser Permanente Colorado (KPCO) anticoagulation management cohort in the Denver-Boulder metropolitan area of Colorado in the United States to include patients with AF who were and were not prescribed warfarin therapy, we used a new approach to build a prediction model of individual combined benefit and harm outcomes related to warfarin therapy (stroke with no major bleeding, major bleeding with no stroke, neither event, or both stroke and major bleeding) in patients with AF. We utilized a polytomous logistic regression (PLR) model to identify risk factors and then construct the new prediction model. Model performances and validation were evaluated systematically in the study. Project 2: We used data from a multicenter randomized controlled trial named Prophylaxis for Thromboembolism in Critical Care Trial (PROTECT) to develop a new prediction model for hospital mortality in critically ill medical-surgical patients receiving heparin thromboprophylaxis. We first identified risk factors independent of APACHE (Acute Physiology and Chronic Health Evaluation) II score for hospital mortality, and then combined the identified risk factors and APACHE II score to build the new prediction model. Model performances were compared between the new prediction model and the APACHE II score. Project 3: We re-analyzed the data from PROTECT to perform a sensitivity analysis based on a competing risk analysis to investigate the efficacy of dalteparin versus unfractionated heparin in preventing venous thromboembolism in medical-surgical critically ill patients, taking all-cause death as a competing risk for venous thromboembolism. Results from the competing risk analysis were compared with findings from the cause-specific analysis. Results and Conclusions: Project 1: The PLR model could simultaneously predict risk of individual combined benefit and harm outcomes in patients with and without warfarin therapy for AF. The prediction model was a good fit, had acceptable discrimination and calibration, and was internally and externally validated. Should this approach be validated in other patient populations, it has potential advantages over existing risk stratification approaches. Project 2: The new model combining other risk factors and APACHE II score was a good fit, well calibrated and internally validated. However, the discriminative ability of the prediction model was not satisfactory. Compared with the APACHE II score alone, the new prediction model increased data collection, was more complex but did not substantially improve discriminative ability. Project 3: The competing risk analysis yielded no significant effect of dalteparin compared with unfractionated heparin on proximal leg deep vein thromboses, but a lower risk of pulmonary embolism in critically ill medical-surgical patients. Findings from the competing risk analysis were similar to results from the cause-specific analysis. / Thesis / Doctor of Philosophy (PhD)

京都大学 / 新制・課程博士 / 博士(社会健康医学) / 甲第24844号 / 社医博第133号 / 新制||社医||13(附属図書館) / 京都大学大学院医学研究科社会健康医学系専攻 / (主査)教授 近藤, 尚己, 教授 川上, 浩司, 教授 平井, 豊博 / 学位規則第4条第1項該当 / Doctor of Public Health / Kyoto University / DFAM

No description available.

Defined as a platelet count <100x109/L with no known cause, immune thrombocytopenia (ITP) is a diagnosis of exclusion, meaning other thrombocytopenic conditions must be ruled out before establishing the ITP diagnosis. This can lead to errors, unnecessary exposures to expensive and harmful treatments, and increased patient anxiety and distress. In the absence of a standardized diagnostic test, a clinical prediction model, called the Predict-ITP tool, was developed to aid hematologists in establishing the ITP diagnosis among patients who present with thrombocytopenia. Based on a cohort of 839 patients referred to an academic hematology clinic and using penalized logistic regression, the following predictor variables for the ITP diagnosis were identified: 1) high platelet variability index; 2) lowest platelet count; 3) highest mean platelet volume; and 4) history of a major bleed. Internal validation was completed using bootstrap resampling, and showed good discrimination and excellent calibration. Following internal validation and prior to implementation, the Predict-ITP Tool must undergo external validation by evaluating the tool’s performance in a different cohort. A study protocol was developed with the objective of externally validating the Predict-ITP Tool by collecting data from 960 patients from 11 clinics across Canada. The tool will compute the probability of ITP using information available at the time of the initial consultation, and results will be compared with either the local hematologist’s diagnosis at the end of follow-up or the adjudicated diagnosis. Discrimination (the ability to differentiate between patients with and without ITP) and calibration (the agreement between predicted and actual classifications) of the tool will be assessed. The Predict-ITP Tool must demonstrate good discrimination (c-statistic ≥ 0.8) and excellent calibration (calibration-in-the-large close to 0; calibration slope close to 1) to achieve external validation. If implemented, this tool will improve diagnostic accuracy and reduce delays in diagnosis and unnecessary treatments and investigations. / Thesis / Master of Science (MSc) / There lack of a standardized test to diagnose immune thrombocytopenia (ITP) leads to delays in care, use of incorrect treatments, and increased patient anxiety. The Predict-ITP Tool was developed to classify patients as ITP or non-ITP using the following data: 1) platelet counts in the recent past; 2) the highest mean platelet volume; and 3) major bleeding at any time in the past. The preliminary internal validation study showed promise. I developed a study protocol to externally validate the Predict-ITP Tool that will collect data from 960 patients from 11 clinics across Canada to see how accurately the tool would have performed to classify patients as ITP or non-ITP at the first hematology visit compared with the gold standard clinical diagnosis by the hematologist or an independent expert committee. A successful external validation that demonstrates the tool’s predictive accuracy in an external population must be completed before widespread use.

Introduction Postoperative medical complications are often preceded by a period with hypotension. Postoperative hypotension is poorly described in the literature. Data are needed to determine the incidence and risk factors for the development of postoperative clinically important hypotension after noncardiac surgery. Methods The incidence of postoperative clinically important hypotension was examined in a cohort of 40,004 patients enrolled in the VISION (Vascular Events in Noncardiac Surgery Patients Cohort Evaluation) Study. Eligible patients were ≥45 years of age, underwent an in-patient noncardiac surgery procedure, and required a general or regional anesthetic. I undertook a multivariable logistic regression model to determine the predictors for postoperative clinically important hypotension. Model validation was performed using calibration and discrimination. Results Of the 40,004 patients included, 20,442 patients were selected for the derivation cohort, and 19,562 patients were selected for the validation cohort. The incidence of clinically important hypotension in the entire cohort was 12.4% (4,959 patients) [95% confidence interval 12.1-12.8]. Using 41 variables related to baseline characteristics, preoperative hemodynamics, laboratory characteristics, and type of surgery, I developed a model to predict the risk of clinically important postoperative hypotension (bias-corrected C-statistics: 0.73) The prediction model was slightly improved by adding intraoperative variables (bias-corrected C-statistics: 0.75). A simplified prediction model using the following variables: high-risk surgery, preoperative systolic blood pressure <130 mm Hg, preoperative heart rate >100 beats per minute, and open surgery, also predicted clinically important hypotension, albeit with less accuracy (bias-corrected C-statistics 0.68). Conclusion Our clinical prediction model can accurately predict patients’ risk of postoperative clinically important hypotension after noncardiac surgery. This model can help identify which patients should have enhanced monitoring after surgery and patients to include in clinical trials evaluating interventions to prevent postoperative clinically important hypotension. / Thesis / Master of Science (MSc) / In patients undergoing noncardiac surgery, numerous patients will develop postoperative clinically important hypotension. This may lead to complications including death, stroke, and myocardial infarction. I performed a large observational study to examine which risk factors would predict clinically important postoperative hypotension. Once we have identified these risk factors, we will use them to conduct randomized trials in patients at risk of clinically important hypotension to determine if we can prevent major postoperative complications.

Yes / Repeated hospital admissions are prevalent in older people. The role of medication in repeated hospital admissions has not been widely studied. The hypothesis that medication-related risk factors for initial hospital admissions were also associated with repeated hospital admissions was generated. To examine the association between medication-related risk factors and repeated hospital admissions in older people living with frailty. A retrospective case-control study was carried out with 200 patients aged ≥75 years with unplanned medical admissions into a large teaching hospital in England between January and December 2015. Demographic, clinical, and medication-related data were obtained from review of discharge summaries. Statistical comparisons were made between patients with 3 or more hospital admissions during the study period (cases) and those with 2 or fewer admissions (controls). Regressions were performed to establish independent predictors of repeated hospital admissions. Participants had a mean age of 83.8 years (SD 5.68) and 65.5% were female. There were 561 admission episodes across the sample, with the main reasons for admissions recorded as respiratory problems (25%) and falls (17%). Univariate logistic regression revealed five medication-related risks to be associated with repeated hospital admissions: Hyper-polypharmacy (defined as taking ≥10 medications) (OR 2.50, p < 0.005); prescription of potentially inappropriate medications (PIMs) (OR 1.89; p < 0.05); prescription of a diuretic (OR 1.87; p < 0.05); number of high risk medication (OR 1.29; p < 0.05) and the number of 'when required' medication (OR 1.20; p < 0.05). However, the effects of these risk factors became insignificant when comorbid disease was adjusted for in a multivariable model. Medication-related risk factors may play an important role in future repeated admission risk prediction models. The modifiable nature of medication-related risks factors highlights a real opportunity to improve health outcomes.