The past decade has witnessed rapid advances at the intersection of machine learning and medicine. Owing to the tremendous amount of digitized hospital data, machine learning is poised to bring innovation to the traditional healthcare workflow. Though machine learning models have strong predictive power, it is challenging to translate a research project into a clinical tool partly due to the lack of a rigorous validation framework. In this dissertation, I presented a range of machine learning models that were trained to classify Alzheimer’s disease - a condition with an insidious onset - using routinely collected clinical data. In addition to reporting the model performance, I discussed several considerations, including feature selection, data harmonization, effect of confounding variables, diagnostic scope, model interpretability and validation, which are critical to the design, development, and validation of machine learning models. From the methodological standpoint, I presented a multidisciplinary collaboration in which medical domain knowledge which was obtained from experts and tissue examinations was tightly integrated with the interpretable outcomes derived from our machine learning frameworks. I demonstrated that the model, which generalized well on multiple independent cohorts, achieved diagnostic performance on par with a group of medical professionals. The interpretable analysis of our model showed that its underlying decision logic corresponds with expert ratings and neuropathological findings. Taken together, this work presented a machine learning system for classification of Alzheimer’s disease, marking an important milestone towards a translatable clinical application in the future.

<p> Clinical diagnosis, classification of injury and the reliable and detailed description of a patient's neurological status are key factors in determining intervention, rehabilitation programs and predicting recovery. The American Spinal Injury Association (ASIA) impairment scale (AIS) is a standardized method for spinal cord injury (SCI) classification and neurologic status examination. Studies have revealed the AIS classification to be a general assessment tool that fails to explain the varying degrees and patterns of neurological damage, especially in individuals with incomplete injuries. In addition, intragroup variability can be attributed to inaccuracies in examinations and improper assessment tools that have limited research findings. Transcranial Magnetic Stimulation (TMS) has been used as a non-invasive method of evaluating the integrity of the motor nervous system. The primary purpose of this study was to evaluate TMS as an assessment tool to describe motor impairment of SCI individuals. A second purpose of this study was to assess AIS accuracy and sensitivity to muscle activation by using surface electromyographic (sEMG) techniques during clinical examinations. Six incomplete SCI participants were clinically assessed to obtain their individual motor scores from key muscles following AIS assessment criteria. TMS was then used to stimulate the motor cortex to elicit motor evoked potentials (MEPs) in 4 key muscles. MEPs correlated with motor scores, where significantly higher and lower MEPs corresponded to the highest and lowest motor scores, respectively. Of the 48 muscles analyzed, 18 received a motor score of zero; however MEPs were obtained in 7 of these 18 muscles. In general, MEPs paralleled motor function as assessed by the AIS. Results suggest that TMS may provide information on the relationship between corticospinal integrity and the quality of motor function. In addition, TMS demonstrated adequate validity and sensitivity to SCI individual differences. MEPs provided additional information regarding the existence of spared neuronal pathways not identified by standard clinical evaluations. The therapeutic potential of these motor pathways has yet to be explored. EMG activity was significantly correlated to motor scores and MEPs however; EMG analysis revealed some inaccuracies in muscle examinations and supported MEP data. Results suggest that the implementation of electrophysiological assessment tools may be more sensitive to detect motor damage, adaptive movement patterns and overall muscle activation that may be misinterpreted during clinical examinations.</p> / Thesis / Master of Science (MSc)

Made available in DSpace on 2015-03-05T17:05:26Z (GMT). No. of bitstreams: 0 Previous issue date: 8 / Nenhuma / Este estudo tem como objetivo propor um instrumento de diagnóstico de ecoeficiência. Trata-se de um mecanismo para obtenção de dados para a análise qualitativa da performance ambiental. A pesquisa é motivada pelo fato de que as preocupações atuais se sobrepõem às inquietações relativas aos impactos ecológicos e aos danos causados à natureza, e evidenciam o anseio da sociedade à melhoria da qualidade e preservação da vida humana. Considerando que a melhor solução para os impactos ambientais será sempre a prevenção, oportunizou-se este estudo focado no desenvolvimento de um instrumento para o diagnóstico do uso da ecoeficiência. A partir da revisão bibliográfica estabeleceram-se as características da ecoeficiência, as quais compuseram o instrumento proposto. Foram feitas duas aplicações piloto em empresas produtoras de móveis estofados, produtos que têm gerado, ao longo e no final de suas vidas, uma considerável parcela de resíduos a serem descartados no meio-ambiente, grandes desperdícios com a produção inefic

<p>Den här rapporten beskriver ett examensarbete för högskoleingenjörsexamen i datorteknik vid Växjö universitet. Vid företaget BSR i Växjö pågår utvecklingen av ett diagnosverktyg benämt BSR Diagnostic Tool. Syftet med projektet är att kunna använda en hårdvaruklass som kommunikationsdel istället för diagnosverktyg från de olika biltillverkarna. Inom objektorienterad programmering är en klass ett avsnitt programkod som samlar en mängd relaterade attributer och funktioner för ett objekt. I rapporten beskrivs implementeringen av hårdvaruklassen samt tillhörande teori för kommunikationsbussen som används, nämligen CAN. BSR har redovisat vilka funktioner som bör finnas med i klassen genom att göra ett diagram med dessa. Målet i första hand var att få en fungerande kommunikation med styrenheter i en Saab. Testning har skett genom ett enkelt testprogram som ger möjlighet att skicka en fråga och få tillbaka ett svar från en styrenhet i fordonet genom hårdvaruklassen. Utvecklingen av systemet har skett med hjälp av programspråket C# och utvecklingsmiljön .NET. Företagets representanter var nöjda med resultatet då det utgör en bra grund för vidareutvecklingen av BSR Diagnostic Tool.</p> / <p>This abstract describes the bachelor degree thesis in computer technology at Växjö University. At the company BSR in Växjö, Sweden there is a new project under development called BSR Diagnostic Tool. The main idea is to use a hardware class for communication instead of the diagnostic tools that are provided by the car manufactures. In object-oriented programming, a class is a programming language construct that is used as a blueprint to create objects. The task was to implement this hardware class which will handle the communication between a computer and the control units in the vehicles. The report also includes a big theoretical part about the communication bus that is used, CAN. The objective was to create the class and make it communicate successfully with a Saab. The testing of the class was done with a simple program. The program can send a question to the vehicle and retrieve an answer with help of the hardware class. BSR provided a diagram with functions that should be present. The development of the system was done using C# and .NET Environment. The company was satisfied with the results since they provided a good basis to further development of BSR Diagnostic Tool.</p>

Den här rapporten beskriver ett examensarbete för högskoleingenjörsexamen i datorteknik vid Växjö universitet. Vid företaget BSR i Växjö pågår utvecklingen av ett diagnosverktyg benämt BSR Diagnostic Tool. Syftet med projektet är att kunna använda en hårdvaruklass som kommunikationsdel istället för diagnosverktyg från de olika biltillverkarna. Inom objektorienterad programmering är en klass ett avsnitt programkod som samlar en mängd relaterade attributer och funktioner för ett objekt. I rapporten beskrivs implementeringen av hårdvaruklassen samt tillhörande teori för kommunikationsbussen som används, nämligen CAN. BSR har redovisat vilka funktioner som bör finnas med i klassen genom att göra ett diagram med dessa. Målet i första hand var att få en fungerande kommunikation med styrenheter i en Saab. Testning har skett genom ett enkelt testprogram som ger möjlighet att skicka en fråga och få tillbaka ett svar från en styrenhet i fordonet genom hårdvaruklassen. Utvecklingen av systemet har skett med hjälp av programspråket C# och utvecklingsmiljön .NET. Företagets representanter var nöjda med resultatet då det utgör en bra grund för vidareutvecklingen av BSR Diagnostic Tool. / This abstract describes the bachelor degree thesis in computer technology at Växjö University. At the company BSR in Växjö, Sweden there is a new project under development called BSR Diagnostic Tool. The main idea is to use a hardware class for communication instead of the diagnostic tools that are provided by the car manufactures. In object-oriented programming, a class is a programming language construct that is used as a blueprint to create objects. The task was to implement this hardware class which will handle the communication between a computer and the control units in the vehicles. The report also includes a big theoretical part about the communication bus that is used, CAN. The objective was to create the class and make it communicate successfully with a Saab. The testing of the class was done with a simple program. The program can send a question to the vehicle and retrieve an answer with help of the hardware class. BSR provided a diagram with functions that should be present. The development of the system was done using C# and .NET Environment. The company was satisfied with the results since they provided a good basis to further development of BSR Diagnostic Tool.

This longitudinal study tracks how 5- to 7-year-olds perform with early number skills. The aim of this study is to diagnose at-risk mathematics students by distinguishing the skills that, if not mastered by the end of Kindergarten, lead to greater difficulty in mathematics in 1st grade. This study’s methodology is mixed as it follows an exploratory and inductive path in light of its use of a hypothesis, an interpretive path in light of its interest in the individual student, and a positivist path in light of its focus on developing rules from analyzed data. An oral diagnostic test based on a comprehensive collection of early number skills was used to test students as Kindergarteners and again as 1st graders. The test results created benchmarks, revealing how the majority of the students performed with early number skills. The test results also revealed that each early number skill is highly, moderately, or minimally predictive in terms of student placement by the end of 1st grade. When comparing the individual skill scores of each Kindergarten student to his/her total test results of 1st grade, the predictive power of each skill emerged. Performing poorly with skills that are minimally predictive did not seem to have an impact on how the Kindergarten student finished in 1st grade; performing poorly with moderately predictive skills had a greater impact on 1st grade placement; performing poorly with highly predictive skills in Kindergarten increased the likelihood that the student would finish in the lower attaining group in 1st grade. A third result of the test showed that certain skills serve as preconditions for other skills; success with certain skills usually meant success with other skills. These connections between skills point to a learning model called in this study “simultaneous pathways,” indicating that there are connections between certain skills, and that students can be learning on several pathways simultaneously. The impact of the predictive power of early number skills is that diagnosis becomes more effective. Early diagnosis means early remediation which may prevent at-risk students from falling further behind their peers. The benchmarks developed by this research will help teachers assess their students because they will know the general skill level of Kindergarteners and 1st graders. This oral diagnostic test informs curriculum development. If test results show that students are missing the skills that are highly predictive, teachers can address those gaps in order to insure mastery.

This diploma thesis introduces the options for motor skills assessment of preschool children in the pedagogical and health care setting. This thesis is divided into two parts - theoretical and practical part. In the theoretical part, the author describes the psychomotor development of a child with a focus on the preschool period. The following chapter provides an overview of pedagogical and healthcare professions that mostly focus on the psychomotor development matters. The following chapters analyse the options for motor skills diagnostics in preschool children, including an overview of the most commonly used tests. In the practical part, a set of diagnostic tasks was created for the purpose of rough estimation of motor skills levels of preschool children. The suggested task set was then put to a clinical trial in five kindergartens in two cities in the Czech Republic. The practical part consists of a description of individual tasks in the task set, their evaluation, description of the used sample of children, administration of the task set and collection of data in accordance with stated ethical principles of research. There data is then presented, analysed and the resolving power of the task set is evaluated. The addendum of the practical part contains suggested modifications of the diagnostic...

Les personnes souffrant d’un syndrome de Down (SD), appelé aussi trisomie 21, ont vu leur espérance de vie augmenter bien au delà des 50 ans induisant l’apparition de démence de type Alzheimer (DTA). Les conséquences de cette augmentation de l'espérance sont multiples : difficulté à diagnostiquer une démence au sein d'une population présentant des déficientes intellectuelles, difficulté de prise en charge de cette population, etc. Ainsi, les établissements médicoOsociaux et les centres de consultation mémoire restent désarmés face à la prise en charge et au diagnostic de cette population. Notre travail de thèse a eu pour objectif d'aborder l'ensemble des difficultés lié à cette problématique.Nos travaux ont ainsi mis en exergue : 1/ cette problématique concerne aussi bien les structures pour personnes âgées que celles pour personnes handicapées 2/ il existe une véritable difficulté à diagnostiquer la présence d'une démence auprès de cette population. Pour répondre à cette difficulté nous avons élaboré et testé un outil d'aide au diagnostic 3/ la problématique de diagnostic, de formation des professionnels PA/PH et de prise en charge de cette population (activités, locaux non adaptés, taux d’encadrement insuffisant, médicalisation accrue..) via la modélisation organisationnelle des parcours de vie des personnes atteintes de SD et de DTA notamment. Cette modélisation montre l’impact sur l’évolution des organisations et des institutions d’accueil ainsi que le manque de lien entre le secteur sanitaire et médico social. Des pistes sont discutées. / People with Down syndrome (DS), also known as trisomy 21, have seen their life expectancy increase beyond 50 years inducing the onset of AlzheimerOtype dementia (DTA). The consequences of this increase in life expectancy are multiple: difficulty of diagnosing dementia in a population with intellectual disabilities, difficulty of care for this population, etc. Thus, specialised institution and memory clinics remain powerless against the management and diagnosis of this population. Our thesis has aimed to address all the challenges related to this issue.Our work thus highlighted: 1 / this problem concerns both for the elderly than for the disabled, 2 / there is a real difficulty in diagnosing the presence of dementia in this population. To meet this challenge we have developed and tested a diagnostic aid tool. 3 / diagnostic problematic, professional training and support for people in charge of this population (activities, unsuitable premises, insufficient teacher ratio, increasing medicalization, etc.) via organizational modelling the life course of individuals suffering from SD and DTA. This model shows the impact on the evolution of organizations and host institutions and the lack of connection between the health sector and medicoOsocial. Hypothesis and possible solutions are discussed.

La reproduction est un pilier majeur de la productivité des fermes laitières. Dans ce contexte, il est pertinent d’identifier à l’avance les animaux à risque d’avoir des performances en reproduction sous-optimales, surtout si un traitement efficace est disponible pour améliorer ces performances. Les endométrites clinique et subclinique sont des conditions définies selon leur impact sur les performances en reproduction subséquentes et donc, des outils très intéressants de surveillance de la santé utérine. Le premier objectif de cette étude était de déterminer simultanément des seuils diagnostiques pour les endométrites clinique (diagnostiquée par le Metricheck) et subclinique (diagnostiquée par la cytologie endométriale ou par l’estérase leucocytaire) selon leur impact sur les performances en reproduction à la première saillie. L’écoulement vaginal purulent a été identifié comme seuil pour l’endométrite clinique, alors que les seuils identifiés pour l’endométrite subclinique ont été un pourcentage de polymorphonucléaires de 6% à la cytologie et une « forte quantité de leucocytes » à l’estérase leucocytaire. Le second objectif de l’étude était d’évaluer l’effet d’un traitement intra-utérin de céphapirine sur les performances à la première saillie des animaux sains et atteints d’endométrite. Aucun effet du traitement n’a été observé chez les vaches saines ou atteintes d’endométrite clinique, alors qu’une tendance à l’amélioration des performances a été associée au traitement chez celles atteintes d’endométrite subclinique. L’anovulation post-partum prolongée pourrait altérer l’efficacité du traitement de céphapirine, surtout chez les vaches atteintes d’endométrite clinique. / Reproduction is a major concern in the dairy industry. In this context, it is relevant to have an early identification of cows at risk of altered subsequent reproductive performance, especially if a treatment is available and effective to improve this performance. Clinical and subclinical endometritis are defined based on their impact on reproductive performance and are interesting tools for reproductive tract health surveillance. The first objective of this research project was to determine simultaneously diagnostic criteria for clinical (diagnosed by Metricheck) and subclinical (diagnosed by endometrial cytology or leukocyte esterase testing) endometritis based on their impact on reproductive performance at first service. Clinical endometritis was defined as presence of purulent vaginal discharge whereas subclinical endometritis was defined as presence of ≥ 6% of polymorphonuclear cells using endometrial cytology or the presence of “large amount of leukocytes” using leukocyte esterase testing. The second objective of this research project was to determine the effect of an intrauterine infusion of cephapirin on the reproductive performance at first service in cows with clinical endometritis, subclinical endometritis, and in cows unaffected by endometritis. Cephapirin treatment had no effect on first service pregnancy risk in unaffected cows or in cows affected by clinical endometritis. However, there was a tendency of a positive effect of the treatment in cows affected by subclinical endometritis. Presence of prolonged postpartum anovulation in cows may reduce the efficacy of the cephapirin treatment, especially in cows affected by clinical endometritis.

La reproduction est un pilier majeur de la productivité des fermes laitières. Dans ce contexte, il est pertinent d’identifier à l’avance les animaux à risque d’avoir des performances en reproduction sous-optimales, surtout si un traitement efficace est disponible pour améliorer ces performances. Les endométrites clinique et subclinique sont des conditions définies selon leur impact sur les performances en reproduction subséquentes et donc, des outils très intéressants de surveillance de la santé utérine. Le premier objectif de cette étude était de déterminer simultanément des seuils diagnostiques pour les endométrites clinique (diagnostiquée par le Metricheck) et subclinique (diagnostiquée par la cytologie endométriale ou par l’estérase leucocytaire) selon leur impact sur les performances en reproduction à la première saillie. L’écoulement vaginal purulent a été identifié comme seuil pour l’endométrite clinique, alors que les seuils identifiés pour l’endométrite subclinique ont été un pourcentage de polymorphonucléaires de 6% à la cytologie et une « forte quantité de leucocytes » à l’estérase leucocytaire. Le second objectif de l’étude était d’évaluer l’effet d’un traitement intra-utérin de céphapirine sur les performances à la première saillie des animaux sains et atteints d’endométrite. Aucun effet du traitement n’a été observé chez les vaches saines ou atteintes d’endométrite clinique, alors qu’une tendance à l’amélioration des performances a été associée au traitement chez celles atteintes d’endométrite subclinique. L’anovulation post-partum prolongée pourrait altérer l’efficacité du traitement de céphapirine, surtout chez les vaches atteintes d’endométrite clinique. / Reproduction is a major concern in the dairy industry. In this context, it is relevant to have an early identification of cows at risk of altered subsequent reproductive performance, especially if a treatment is available and effective to improve this performance. Clinical and subclinical endometritis are defined based on their impact on reproductive performance and are interesting tools for reproductive tract health surveillance. The first objective of this research project was to determine simultaneously diagnostic criteria for clinical (diagnosed by Metricheck) and subclinical (diagnosed by endometrial cytology or leukocyte esterase testing) endometritis based on their impact on reproductive performance at first service. Clinical endometritis was defined as presence of purulent vaginal discharge whereas subclinical endometritis was defined as presence of ≥ 6% of polymorphonuclear cells using endometrial cytology or the presence of “large amount of leukocytes” using leukocyte esterase testing. The second objective of this research project was to determine the effect of an intrauterine infusion of cephapirin on the reproductive performance at first service in cows with clinical endometritis, subclinical endometritis, and in cows unaffected by endometritis. Cephapirin treatment had no effect on first service pregnancy risk in unaffected cows or in cows affected by clinical endometritis. However, there was a tendency of a positive effect of the treatment in cows affected by subclinical endometritis. Presence of prolonged postpartum anovulation in cows may reduce the efficacy of the cephapirin treatment, especially in cows affected by clinical endometritis.