Artificial intelligence (AI) and predictive modeling are tools used to diagnose a disease, determine how much a home is worth, estimate insurance risks, and detect fraud. AI and predictive modeling are so ubiquitous that they can be why one gets spam and why spam is automatically deleted. Information science integrates interdisciplinary elements of data-driven, behavioral, design, interpretive, and analytical research methodologies to design and understand interactions between digital media, information systems, and humans. This research focuses on the interaction between humans, AI, and predictive models. This research proposes a theoretical framework and a conceptual research model to understand the antecedents to reliance on AI and predictive modeling. The dissertation follows a traditional format that includes three studies. Study 1 employed a deductive quantitative research approach as a survey to model the relationship between trust in science and reliance on formal news sources. Study 2 employed a deductive quantitative research approach as a survey to understand the impact of framing questions and consider an alternative method of measuring society's reliance on science using predictive models. Study 3 employed a deductive quantitative research approach in the form of a survey to posit a new model based on the first two studies. This study benefited from a Toulouse Graduate School grant to fund research using the crowdsourcing platform https://lucidtheorem.com/ to generate a stratified sample of the U.S. population.

Background: Predictive models allow clinicians to more accurately identify higher- and lower-risk patients and make more targeted treatment decisions, which can help improve efficiency in health systems. Microalbuminuria (MA) is a condition characterized by the presence of albumin in the urine below the threshold detectable by a standard dipstick. Its presence is understood to be an early marker for cardiovascular disease. Therefore, identifying patients at risk for MA and intervening to treat or prevent conditions associated with MA, such as high blood pressure or high blood glucose, may support cost-effective treatment. Methods: The National Health and Nutrition Examination Survey (NHANES) was utilized to create predictive models for MA. This database includes clinical, medical and laboratory data. The dataset was split into thirds; one-third was used to develop the model, while the other two-thirds were utilized to validate the model. Univariate logistic regression was performed to identify variables related with MA. Stepwise multivariate logistic regression was performed to create the models. Model performance was evaluated using three criteria: 1) receiver operator characteristic (ROC) curves; 2) pseudo R-squared; and 3) goodness of fit (Hosmer-Lemeshow). The predictive models were then used to develop risk-scores. Results: Two models were developed using variables that had significant correlations in the univariate analysis (p-value<0.05). For Model A, variables included in the final model were: systolic blood pressure (SBP); fasting glucose; C-reactive protein; blood urea nitrogen (BUN); and alcohol consumption. For Model B, the variables were: SBP; glycohemoglobin; BUN; smoking status; and alcohol consumption. Both models performed well in the creation dataset and no significant difference between the models was found when they were evaluated in the validation set. A 0-18 risk score was developed utilizing Model A, and the predictive probability of developing MA was calculated. Conclusion: The predictive models developed provide new evidence about which variables are related with MA and may be used by clinicians to identify at-risk patients and to tailor treatment. Furthermore, the risk score developed using Model A may allow clinicians to more easily measure patient risk. Both predictive models will require external validation before they can be applied to other populations.

An ensemble is a composite model, combining the predictions from several other models. Ensembles are known to be more accurate than single models. Diversity has been identified as an important factor in explaining the success of ensembles. In the context of classification, diversity has not been well defined, and several heuristic diversity measures have been proposed. The focus of this thesis is on how to create effective ensembles in the context of classification. Even though several effective ensemble algorithms have been proposed, there are still several open questions regarding the role diversity plays when creating an effective ensemble. Open questions relating to creating effective ensembles that are addressed include: what to optimize when trying to find an ensemble using a subset of models used by the original ensemble that is more effective than the original ensemble; how effective is it to search for such a sub-ensemble; how should the neural networks used in an ensemble be trained for the ensemble to be effective? The contributions of the thesis include several studies evaluating different ways to optimize which sub-ensemble would be most effective, including a novel approach using combinations of performance and diversity measures. The contributions of the initial studies presented in the thesis eventually resulted in an investigation of the underlying assumption motivating the search for more effective sub-ensembles. The evaluation concluded that even if several more effective sub-ensembles exist, it may not be possible to identify which sub-ensembles would be the most effective using any of the evaluated optimization measures. An investigation of the most effective ways to train neural networks to be used in ensembles was also performed. The conclusions are that effective ensembles can be obtained by training neural networks in a number of different ways but that high average individual accuracy or much diversity both would generate effective ensembles. Several findings regarding diversity and effective ensembles presented in the literature in recent years are also discussed and related to the results of the included studies. When creating confidence based predictors using conformal prediction, there are several open questions regarding how data should be utilized effectively when using ensembles. Open questions related to predicting with confidence that are addressed include: how can data be utilized effectively to achieve more efficient confidence based predictions using ensembles; how do problems with class imbalance affect the confidence based predictions when using conformal prediction? Contributions include two studies where it is shown in the first that the use of out-of-bag estimates when using bagging ensembles results in more effective conformal predictors and it is shown in the second that a conformal predictor conditioned on the class labels to avoid a strong bias towards the majority class is more effective on problems with class imbalance. The research method used is mainly inspired by the design science paradigm, which is manifested by the development and evaluation of artifacts. / En ensemble är en sammansatt modell som kombinerar prediktionerna från flera olika modeller. Det är välkänt att ensembler är mer träffsäkra än enskilda modeller. Diversitet har identifierats som en viktig faktor för att förklara varför ensembler är så framgångsrika. Diversitet hade fram tills nyligen inte definierats entydigt för klassificering vilket resulterade i att många heuristiska diverstitetsmått har föreslagits. Den här avhandlingen fokuserar på hur klassificeringsensembler kan skapas på ett ändamålsenligt (eng. effective) sätt. Den vetenskapliga metoden är huvudsakligen inspirerad av design science-paradigmet vilket lämpar sig väl för utveckling och evaluering av IT-artefakter. Det finns sedan tidigare många framgångsrika ensembleralgoritmer men trots det så finns det fortfarande vissa frågetecken kring vilken roll diversitet spelar vid skapande av välpresterande (eng. effective) ensemblemodeller. Några av de frågor som berör diversitet som behandlas i avhandlingen inkluderar: Vad skall optimeras när man söker efter en delmängd av de tillgängliga modellerna för att försöka skapa en ensemble som är bättre än ensemblen bestående av samtliga modeller; Hur väl fungerar strategin att söka efter sådana delensembler; Hur skall neurala nätverk tränas för att fungera så bra som möjligt i en ensemble? Bidraget i avhandlingen inkluderar flera studier som utvärderar flera olika sätt att finna delensembler som är bättre än att använda hela ensemblen, inklusive ett nytt tillvägagångssätt som utnyttjar en kombination av både diversitets- och prestandamått. Resultaten i de första studierna ledde fram till att det underliggande antagandet som motiverar att söka efter delensembler undersöktes. Slutsatsen blev, trots att det fanns flera delensembler som var bättre än hela ensemblen, att det inte fanns något sätt att identifiera med tillgänglig data vilka de bättre delensemblerna var. Vidare undersöktes hur neurala nätverk bör tränas för att tillsammans samverka så väl som möjligt när de används i en ensemble. Slutsatserna från den undersökningen är att det är möjligt att skapa välpresterande ensembler både genom att ha många modeller som är antingen bra i genomsnitt eller olika varandra (dvs diversa). Insikter som har presenterats i litteraturen under de senaste åren diskuteras och relateras till resultaten i de inkluderade studierna. När man skapar konfidensbaserade modeller med hjälp av ett ramverk som kallas för conformal prediction så finns det flera frågor kring hur data bör utnyttjas på bästa sätt när man använder ensembler som behöver belysas. De frågor som relaterar till konfidensbaserad predicering inkluderar: Hur kan data utnyttjas på bästa sätt för att åstadkomma mer effektiva konfidensbaserade prediktioner med ensembler; Hur påverkar obalanserad datade konfidensbaserade prediktionerna när man använder conformal perdiction? Bidragen inkluderar två studier där resultaten i den första visar att det mest effektiva sättet att använda data när man har en baggingensemble är att använda sk out-of-bag estimeringar. Resultaten i den andra studien visar att obalanserad data behöver hanteras med hjälp av en klassvillkorad konfidensbaserad modell för att undvika en stark tendens att favorisera majoritetsklassen. / <p>At the time of the doctoral defense, the following paper was unpublished and had a status as follows: Paper 8: In press.</p> / Dataanalys för detektion av läkemedelseffekter (DADEL)

An ensemble is a composite model, combining the predictions from several other models. Ensembles are known to be more accurate than single models. Diversity has been identified as an important factor in explaining the success of ensembles. In the context of classification, diversity has not been well defined, and several heuristic diversity measures have been proposed. The focus of this thesis is on how to create effective ensembles in the context of classification. Even though several effective ensemble algorithms have been proposed, there are still several open questions regarding the role diversity plays when creating an effective ensemble. Open questions relating to creating effective ensembles that are addressed include: what to optimize when trying to find an ensemble using a subset of models used by the original ensemble that is more effective than the original ensemble; how effective is it to search for such a sub-ensemble; how should the neural networks used in an ensemble be trained for the ensemble to be effective? The contributions of the thesis include several studies evaluating different ways to optimize which sub-ensemble would be most effective, including a novel approach using combinations of performance and diversity measures. The contributions of the initial studies presented in the thesis eventually resulted in an investigation of the underlying assumption motivating the search for more effective sub-ensembles. The evaluation concluded that even if several more effective sub-ensembles exist, it may not be possible to identify which sub-ensembles would be the most effective using any of the evaluated optimization measures. An investigation of the most effective ways to train neural networks to be used in ensembles was also performed. The conclusions are that effective ensembles can be obtained by training neural networks in a number of different ways but that high average individual accuracy or much diversity both would generate effective ensembles. Several findings regarding diversity and effective ensembles presented in the literature in recent years are also discussed and related to the results of the included studies. When creating confidence based predictors using conformal prediction, there are several open questions regarding how data should be utilized effectively when using ensembles. Open questions related to predicting with confidence that are addressed include: how can data be utilized effectively to achieve more efficient confidence based predictions using ensembles; how do problems with class imbalance affect the confidence based predictions when using conformal prediction? Contributions include two studies where it is shown in the first that the use of out-of-bag estimates when using bagging ensembles results in more effective conformal predictors and it is shown in the second that a conformal predictor conditioned on the class labels to avoid a strong bias towards the majority class is more effective on problems with class imbalance. The research method used is mainly inspired by the design science paradigm, which is manifested by the development and evaluation of artifacts. / En ensemble är en sammansatt modell som kombinerar prediktionerna från flera olika modeller. Det är välkänt att ensembler är mer träffsäkra än enskilda modeller. Diversitet har identifierats som en viktig faktor för att förklara varför ensembler är så framgångsrika. Diversitet hade fram tills nyligen inte definierats entydigt för klassificering vilket resulterade i att många heuristiska diverstitetsmått har föreslagits. Den här avhandlingen fokuserar på hur klassificeringsensembler kan skapas på ett ändamålsenligt (eng. effective) sätt. Den vetenskapliga metoden är huvudsakligen inspirerad av design science-paradigmet vilket lämpar sig väl för utveckling och evaluering av IT-artefakter. Det finns sedan tidigare många framgångsrika ensembleralgoritmer men trots det så finns det fortfarande vissa frågetecken kring vilken roll diversitet spelar vid skapande av välpresterande (eng. effective) ensemblemodeller. Några av de frågor som berör diversitet som behandlas i avhandlingen inkluderar: Vad skall optimeras när man söker efter en delmängd av de tillgängliga modellerna för att försöka skapa en ensemble som är bättre än ensemblen bestående av samtliga modeller; Hur väl fungerar strategin att söka efter sådana delensembler; Hur skall neurala nätverk tränas för att fungera så bra som möjligt i en ensemble? Bidraget i avhandlingen inkluderar flera studier som utvärderar flera olika sätt att finna delensembler som är bättre än att använda hela ensemblen, inklusive ett nytt tillvägagångssätt som utnyttjar en kombination av både diversitets- och prestandamått. Resultaten i de första studierna ledde fram till att det underliggande antagandet som motiverar att söka efter delensembler undersöktes. Slutsatsen blev, trots att det fanns flera delensembler som var bättre än hela ensemblen, att det inte fanns något sätt att identifiera med tillgänglig data vilka de bättre delensemblerna var. Vidare undersöktes hur neurala nätverk bör tränas för att tillsammans samverka så väl som möjligt när de används i en ensemble. Slutsatserna från den undersökningen är att det är möjligt att skapa välpresterande ensembler både genom att ha många modeller som är antingen bra i genomsnitt eller olika varandra (dvs diversa). Insikter som har presenterats i litteraturen under de senaste åren diskuteras och relateras till resultaten i de inkluderade studierna. När man skapar konfidensbaserade modeller med hjälp av ett ramverk som kallas för conformal prediction så finns det flera frågor kring hur data bör utnyttjas på bästa sätt när man använder ensembler som behöver belysas. De frågor som relaterar till konfidensbaserad predicering inkluderar: Hur kan data utnyttjas på bästa sätt för att åstadkomma mer effektiva konfidensbaserade prediktioner med ensembler; Hur påverkar obalanserad datade konfidensbaserade prediktionerna när man använder conformal perdiction? Bidragen inkluderar två studier där resultaten i den första visar att det mest effektiva sättet att använda data när man har en baggingensemble är att använda sk out-of-bag estimeringar. Resultaten i den andra studien visar att obalanserad data behöver hanteras med hjälp av en klassvillkorad konfidensbaserad modell för att undvika en stark tendens att favorisera majoritetsklassen. / <p>At the time of the doctoral defense, the following paper was unpublished and had a status as follows: Paper 8: In press.</p> / Dataanalys för detektion av läkemedelseffekter (DADEL)

In this thesis, a machine learning approach was used to develop a predictive model for residual methanol concentration in industrial formalin produced at the Akzo Nobel factory in Kristinehamn, Sweden. The MATLABTM computational environment supplemented with the Statistics and Machine LearningTM toolbox from the MathWorks were used to test various machine learning algorithms on the formalin production data from Akzo Nobel. As a result, the Gaussian Process Regression algorithm was found to provide the best results and was used to create the predictive model. The model was compiled to a stand-alone application with a graphical user interface using the MATLAB CompilerTM.

The identification of asthma patients most at risk of experiencing an emergency department event is an important step toward lessening public health burdens in the United States. In this report, the CDC BRFSS Asthma Call Back Survey Data from 2006 to 2009 is explored for potential factors for a predictive model. A metric for classifying the control level of asthma patients is constructed and applied. The data is then used to construct a predictive model for ED events with the rpart algorithm. / text

No description available.

No description available.

When an emergency department (ED) decides that it is not going to be able to serve any more newly arriving patients, it declares "diversion". When an ED is on diversion, it suspends arrivals that can be controlled by forcing some or all of the incoming emergency medical system (EMS) transport units to search for alternate treatment facilities for their patients. This search causes both patients and EMS crew to loose valuable time. Contrary to the general belief that suggests diversions are not very common, the results of the American Hospital Association survey present an example where one third of the studied hospitals were on diversion more than 20% of the three-day study period. Past research indicates that the lack of critical care beds in the hospital is the primary contributor to ambulance diversion. When patients need to be transferred from the ED to the hospital with no available beds in the hospital, they continue occupying their beds (i.e. the patient is boarding). While they are boarding in the ED, the associated staff is idle, and their bed cannot be used to treat other patients. Boarders in the ED lead to gridlock, which is defined as the situation when no new patient can be accepted to the ED until a hospital bed becomes available. In this research, we developed a predictive model to provide probabilities of entering gridlock within a time horizon, given the current state of the system. These real-time predictions are provided for a relatively short time horizon, and in order to be useful, they need to be used in conjunction with effective preventive measures that can be applied quickly. The predictive model is based on a queueing theoretic approach and encapsulated in a user-friendly Visual Basic program in order to calculate and provide gridlock probabilities. Two systems, one with low (24% - System 1), and one with high (81% - System 2) gridlock probability were simulated in conjunction with our predictive model and preventive measures. When a gridlock was found imminent, the number of ED beds was temporarily increased, attempting to prevent gridlock. With only 3 additional beds, the probability of gridlock decreased to 6% in System 1 and 58% in System 2. With 5 additional beds, gridlocks in System 1 were almost eliminated while System 2 entered gridlock only 34% of the time. Our results indicate that by temporarily increasing the number of ED beds in the event of an imminent gridlock, the proportion of time that system enters gridlock can be significantly reduced. / Master of Science

Heterogeneous computer systems are ubiquitous in all areas of computing, from mobile to high-performance computing. They promise to deliver increased performance at lower energy cost than purely homogeneous, CPU-based systems. In recent years GPU-based heterogeneous systems have become increasingly popular. They combine a programmable GPU with a multi-core CPU. GPUs have become flexible enough to not only handle graphics workloads but also various kinds of general-purpose algorithms. They are thus used as a coprocessor or accelerator alongside the CPU. Developing applications for GPU-based heterogeneous systems involves several challenges. Firstly, not all algorithms are equally suited for GPU computing. It is thus important to carefully map the tasks of an application to the most suitable processor in a system. Secondly, current frameworks for heterogeneous computing, such as OpenCL, are low-level, requiring a thorough understanding of the hardware by the programmer. This high barrier to entry could be lowered by automatically generating and tuning this code from a high-level and thus more user-friendly programming language. Both challenges are addressed in this thesis. For the task mapping problem a machine learning-based approach is presented in this thesis. It combines static features of the program code with runtime information on input sizes to predict the optimal mapping of OpenCL kernels. This approach is further extended to also take contention on the GPU into account. Both methods are able to outperform competing mapping approaches by a significant margin. Furthermore, this thesis develops a method for targeting GPU-based heterogeneous systems from OpenMP, a directive-based framework for parallel computing. OpenMP programs are translated to OpenCL and optimized for GPU performance. At runtime a predictive model decides whether to execute the original OpenMP code on the CPU or the generated OpenCL code on the GPU. This approach is shown to outperform both a competing approach as well as hand-tuned code.