Personalized absolute benefit of statin treatment for primary or secondary prevention of vascular disease in individual elderly patients

Objective: To estimate the absolute treatment effect of statin therapy on major adverse cardiovascular events (MACE; myocardial infarction, stroke and vascular death) for the individual patient aged C70 years. Methods: Prediction models for MACE were derived in patients aged C70 years with (n = 2550) and without (n = 3253) vascular disease from the ‘‘PROspective Study of Pravastatin in Elderly at Risk’’ (PROSPER) trial and validated in the ‘‘Secondary Manifestations of ARTerial disease’’ (SMART) cohort study (n = 1442) and the ‘‘Anglo-Scandinavian Cardiac Outcomes Trial-Lipid Lowering Arm’’ (ASCOT-LLA) trial (n = 1893), respectively, using competing risk analysis. Prespecified predictors were various clinical characteristics including statin treatment. Individual absolute risk reductions (ARRs) for MACE in 5 and 10 years were estimated by subtracting ontreatment from off-treatment risk. Results: Individual ARRs were higher in elderly patients with vascular disease [5-year ARRs: median 5.1 %, interquartile range (IQR) 4.0–6.2 %, 10-year ARRs: median 7.8 %, IQR 6.8–8.6 %] than in patients without vascular disease (5-year ARRs: median 1.7 %, IQR 1.3–2.1 %, 10-year ARRs: 2.9 %, IQR 2.3–3.6 %). Ninetyeight percent of patients with vascular disease had a 5-year ARR C2.0 %, compared to 31 % of patients without vascular disease. Conclusions: With a multivariable prediction model the absolute treatment effect of a statin on MACE for individual elderly patients with and without vascular disease can be quantified. Because of high ARRs, treating all patients is more beneficial than prediction-based treatment for secondary prevention of MACE. For primary prevention of MACE, the prediction model can be used to identify those patients who benefit meaningfully from statin therapy.

Finding optimal alternatives based on efficient comparative preference inference

Choosing the right or the best option is often a demanding and challenging task for the user (e.g., a customer in an online retailer) when there are many available alternatives. In fact, the user rarely knows which offering will provide the highest value. To reduce the complexity of the choice process, automated recommender systems generate personalized recommendations. These recommendations take into account the preferences collected from the user in an explicit (e.g., letting users express their opinion about items) or implicit (e.g., studying some behavioral features) way. Such systems are widespread; research indicates that they increase the customers' satisfaction and lead to higher sales. Preference handling is one of the core issues in the design of every recommender system. This kind of system often aims at guiding users in a personalized way to interesting or useful options in a large space of possible options. Therefore, it is important for them to catch and model the user's preferences as accurately as possible. In this thesis, we develop a comparative preference-based user model to represent the user's preferences in conversational recommender systems. This type of user model allows the recommender system to capture several preference nuances from the user's feedback. We show that, when applied to conversational recommender systems, the comparative preference-based model is able to guide the user towards the best option while the system is interacting with her. We empirically test and validate the suitability and the practical computational aspects of the comparative preference-based user model and the related preference relations by comparing them to a sum of weights-based user model and the related preference relations. Product configuration, scheduling a meeting and the construction of autonomous agents are among several artificial intelligence tasks that involve a process of constrained optimization, that is, optimization of behavior or options subject to given constraints with regards to a set of preferences. When solving a constrained optimization problem, pruning techniques, such as the branch and bound technique, point at directing the search towards the best assignments, thus allowing the bounding functions to prune more branches in the search tree. Several constrained optimization problems may exhibit dominance relations. These dominance relations can be particularly useful in constrained optimization problems as they can instigate new ways (rules) of pruning non optimal solutions. Such pruning methods can achieve dramatic reductions in the search space while looking for optimal solutions. A number of constrained optimization problems can model the user's preferences using the comparative preferences. In this thesis, we develop a set of pruning rules used in the branch and bound technique to efficiently solve this kind of optimization problem. More specifically, we show how to generate newly defined pruning rules from a dominance algorithm that refers to a set of comparative preferences. These rules include pruning approaches (and combinations of them) which can drastically prune the search space. They mainly reduce the number of (expensive) pairwise comparisons performed during the search while guiding constrained optimization algorithms to find optimal solutions. Our experimental results show that the pruning rules that we have developed and their different combinations have varying impact on the performance of the branch and bound technique.

A next application prediction service using the BaranC framework

Predicting user behaviour enables user assistant services provide personalized services to the users. This requires a comprehensive user model that can be created by monitoring user interactions and activities. BaranC is a framework that performs user interface (UI) monitoring (and collects all associated context data), builds a user model, and supports services that make use of the user model. A prediction service, Next-App, is built to demonstrate the use of the framework and to evaluate the usefulness of such a prediction service. Next-App analyses a user's data, learns patterns, makes a model for a user, and finally predicts, based on the user model and current context, what application(s) the user is likely to want to use. The prediction is pro-active and dynamic, reflecting the current context, and is also dynamic in that it responds to changes in the user model, as might occur over time as a user's habits change. Initial evaluation of Next-App indicates a high-level of satisfaction with the service.

Metabolically healthy obesity across the life course: epidemiology, determinants and implications

In recent years, different subphenotypes of obesity have been described, including metabolically healthy obesity (MHO), in which a proportion of obese individuals, despite excess body fat, remain free of metabolic abnormalities and increased cardiometabolic risk. In the absence of a universally accepted set of criteria to classify MHO, the reported prevalence estimates vary widely. Our understanding of the determinants and stability of MHO over time and the associated cardiometabolic and mortality risks is improving, but many questions remain. For example, whether MHO is truly benign is debatable, and whether risk stratification of obese individuals on the basis of their metabolic health status may offer new opportunities for more personalized approaches in diagnosis, intervention, and treatment of diabetes remains speculative. Furthermore, as most of the research to date has focused on MHO in adults, little is known about childhood MHO. In this review, we focus on the epidemiology, determinants, stability, and health implications of MHO across the life course.