Machine Learning and Clinical Text. Supporting Health Information Flow

Fluent health information flow is critical for clinical decision-making. However, a considerable part of this information is free-form text and inabilities to utilize it create risks to patient safety and cost-­effective hospital administration. Methods for automated processing of clinical text are emerging. The aim in this doctoral dissertation is to study machine learning and clinical text in order to support health information flow.First, by analyzing the content of authentic patient records, the aim is to specify clinical needs in order to guide the development of machine learning applications.The contributions are a model of the ideal information flow,a model of the problems and challenges in reality, and a road map for the technology development. Second, by developing applications for practical cases,the aim is to concretize ways to support health information flow. Altogether five machine learning applications for three practical cases are described: The first two applications are binary classification and regression related to the practical case of topic labeling and relevance ranking.The third and fourth application are supervised and unsupervised multi-class classification for the practical case of topic segmentation and labeling.These four applications are tested with Finnish intensive care patient records.The fifth application is multi-label classification for the practical task of diagnosis coding. It is tested with English radiology reports.The performance of all these applications is promising. Third, the aim is to study how the quality of machine learning applications can be reliably evaluated.The associations between performance evaluation measures and methods are addressed,and a new hold-out method is introduced.This method contributes not only to processing time but also to the evaluation diversity and quality. The main conclusion is that developing machine learning applications for text requires interdisciplinary, international collaboration. Practical cases are very different, and hence the development must begin from genuine user needs and domain expertise. The technological expertise must cover linguistics,machine learning, and information systems. Finally, the methods must be evaluated both statistically and through authentic user-feedback.

A cross-border VMI to Russia and cultural impacts to the implementation

VMI (Vendor managed inventory) is a collaboration model between a supplier and a customer, where a supplier has the responsibility of the inventory replenishments. The tightened competition forces companies to collaborate, and VMI is a simple method to cooperate. The aim of this study was to create a cross-border VMI model from Finland to Russia in the case company. However, the cultural differences between the countries produce problems and therefore the cultural impacts to the model and implementation were taken into account. This study includes two parts: the first framework consists of operational principles, benefits, risks, criteria and success factors of VMI and the second concentrates on cultural aspects of the process change. As a result, an operating model for case company’s supply chain was created. In addition, the suggestions for avoiding the cultural impacts in the implementation were given.

Combined electromagnetic and thermal design platform for totally enclosed induction machines

The aim of the thesis is to design a suitable thermal model that can be used as a tool for constructing the TEFC squirrel cage induction machine in addition to the electromagnetic model. A lumped-parameter thermal model is developed. The related problems and aspects of implementation are discussed in details. Losses are calculated analytically and the loss values are used in the thermal model. The sensitivity analysis is introduced to determine the most critical parameters of the model.

Financial and Environmental Impacts of a Dry Port to Facilitate Competitiveness of Two Major Transit Seaports of Finland

Environmental problems and issues have received more and more attention during the last decades. Reasons for this are different increased external costs such as congestion, CO2 emission, noise and accident costs. Transportation sector is the only sector with increasing external costs. The EU will increase its attention in decreasing the external costs of transport. Aim of this research was to find out if a dry port solution could decrease costs of transport, especially external costs. Dry port concept is an intermodal transport system, where inland transport between port and dry port is performed by rail transport instead of traditional road transport. In addition, dry ports offer similar services as ports. Research is conducted by performing a literature review about dry port concept and costs of transport, especially external costs of transport. Financial and environmental impacts of the dry port concept are studied by comparing costs of road and rail transport by cost accounting and with a simulation model. Location of dry port is researched with gravitational models. Results of the literature review are that rail transport is environmentally friendlier mode of transport than road transport. Cost model and simulation model show that if only costs of freight movement are considered, rail transport is more inexpensive transport mode than road transport in terms of internal and external costs. Because of that dry port concept could decrease costs of transport, especially external costs. Results of gravitational models are that city of Kouvola is in a good position to be a dry port. Russian transit traffic through Finland improves location of Kouvola to be a dry port.

The Vulnerable Brain and Very Preterm Infants - Findings from the PIPARI-Study

Preterm birth is a risk for normal brain development. Brain maturation that normally happens in the uterus is in very preterm infants a developmental challenge during their stay in a neonatal intensive care unit (NICU). Typical brain injuries of preterm infants include ischemic injuries, brain haemorrhages, ventricular dilatation (VD), and reduced brain volumes. Brain injury is a serious complication of prematurity leading to possible long term consequences for the neurodevelopment of the very low birth weight (VLBW) infant, such as cerebral palsy (CP), hearing impairments, vision problems, and delay in cognitive development.There is a need for further studies to ascertain the potential risk factors and their causal relationships to brain vulnerability, growth and development in the increasing number of surviving VLBW infants. This thesis consists of four studies evaluating the definitions, causes and consequences of brain lesions in VLBW(<1500g) or very low gestationalage (VLGA) (gestational age <32 gestational weeks) infants. We showed that the redistribution of fetal blood flow is a risk factor for smaller brain volumes at term. In addition,we showed that brain lesions related to prematurity are not associated with increased spontaneous crying behaviour or circadian rhythm development in infancy. However, the preterm infants began to fuss more often and were held more than term infants at five months of age. Furthermore, we showed that VD is associated with brain lesions and smaller brain volumes. Therefore, brain magneticresonance imaging can be recommended for infants with VD. VD together with other brain pathology is a risk factor for the onset of developmental impairments in VLBW/VLGA infants at two years of age.

The application of cDNA and tissue microarray methods in the study of human carcinomas

Currently, numerous high-throughput technologies are available for the study of human carcinomas. In literature, many variations of these techniques have been described. The common denominator for these methodologies is the high amount of data obtained in a single experiment, in a short time period, and at a fairly low cost. However, these methods have also been described with several problems and limitations. The purpose of this study was to test the applicability of two selected high-throughput methods, cDNA and tissue microarrays (TMA), in cancer research. Two common human malignancies, breast and colorectal cancer, were used as examples. This thesis aims to present some practical considerations that need to be addressed when applying these techniques. cDNA microarrays were applied to screen aberrant gene expression in breast and colon cancers. Immunohistochemistry was used to validate the results and to evaluate the association of selected novel tumour markers with the outcome of the patients. The type of histological material used in immunohistochemistry was evaluated especially considering the applicability of whole tissue sections and different types of TMAs. Special attention was put on the methodological details in the cDNA microarray and TMA experiments. In conclusion, many potential tumour markers were identified in the cDNA microarray analyses. Immunohistochemistry could be applied to validate the observed gene expression changes of selected markers and to associate their expression change with patient outcome. In the current experiments, both TMAs and whole tissue sections could be used for this purpose. This study showed for the first time that securin and p120 catenin protein expression predict breast cancer outcome and the immunopositivity of carbonic anhydrase IX associates with the outcome of rectal cancer. The predictive value of these proteins was statistically evident also in multivariate analyses with up to a 13.1- fold risk for cancer specific death in a specific subgroup of patients.

Training system for conceptual design and evaluation for wastewater treatment

Rising population, rapid urbanisation and growing industrialisation have severely stressed water quality and its availability in Malawi. In addition, financial and institutional problems and the expanding agro industry have aggravated this problem. The situation is worsened by depleting water resources and pollution from untreated sewage and industrial effluent. The increasing scarcity of clean water calls for the need for appropriate management of available water resources. There is also demand for a training system for conceptual design and evaluation for wastewater treatment in order to build the capacity for technical service providers and environmental practitioners in the country. It is predicted that Malawi will face a water stress situation by 2025. In the city of Blantyre, this situation is aggravated by the serious pollution threat from the grossly inadequate sewage treatment capacity. This capacity is only 23.5% of the wastewater being generated presently. In addition, limited or non-existent industrial effluent treatment has contributed to the severe water quality degradation. This situation poses a threat to the ecologically fragile and sensitive receiving water courses within the city. This water is used for domestic purposes further downstream. This manuscript outlines the legal and policy framework for wastewater treatment in Malawi. The manuscript also evaluates the existing wastewater treatment systems in Blantyre. This evaluation aims at determining if the effluent levels at the municipal plants conform to existing standards and guidelines and other associated policy and regulatory frameworks. The raw material at all the three municipal plants is sewage. The typical wastewater parameters are Biochemical Oxygen Demand (BOD5), Chemical Oxygen Demand (COD), and Total Suspended Solids (TSS). The treatment target is BOD5, COD, and TSS reduction. Typical wastewater parameters at the wastewater treatment plant at MDW&S textile and garments factory are BOD5 and COD. The treatment target is to reduce BOD5 and COD. The manuscript further evaluates a design approach of the three municipal wastewater treatment plants in the city and the wastewater treatment plant at Mapeto David Whitehead & Sons (MDW&S) textile and garments factory. This evaluation utilises case-based design and case-based reasoning principles in the ED-WAVE tool to determine if there is potential for the tool in Blantyre. The manuscript finally evaluates the technology selection process for appropriate wastewater treatment systems for the city of Blantyre. The criteria for selection of appropriate wastewater treatment systems are discussed. Decision support tools and the decision tree making process for technology selection are also discussed. Based on the treatment targets and design criteria at the eight cases evaluated in this manuscript in reference to similar cases in the ED-WAVE tool, this work confirms the practical use of case-based design and case-based reasoning principles in the ED-WAVE tool in the design and evaluation of wastewater treatment 6 systems in sub-Sahara Africa, using Blantyre, Malawi, as the case study area. After encountering a new situation, already collected decision scenarios (cases) are invoked and modified in order to arrive at a particular design alternative. What is necessary, however, is to appropriately modify the case arrived at through the Case Study Manager in order to come up with a design appropriate to the local situation taking into account technical, socio-economic and environmental aspects. This work provides a training system for conceptual design and evaluation for wastewater treatment.

Classification, comorbidity, heredity, and risk factors of female sexual dysfunctions

Female sexual dysfunctions, including desire, arousal, orgasm and pain problems, have been shown to be highly prevalent among women around the world. The etiology of these dysfunctions is unclear but associations with health, age, psychological problems, and relationship factors have been identified. Genetic effects explain individual variation in orgasm function to some extent but until now quantitative behavior genetic analyses have not been applied to other sexual functions. In addition, behavior genetics can be applied to exploring the cause of any observed comorbidity between the dysfunctions. Discovering more about the etiology of the dysfunctions may further improve the classification systems which are currently under intense debate. The aims of the present thesis were to evaluate the psychometric properties of a Finnish-language version of a commonly used questionnaire for measuring female sexual function, the Female Sexual Function Index (FSFI), in order to investigate prevalence, comorbidity, and classification, and to explore the balance of genetic and environmental factors in the etiology as well as the associations of a number of biopsychosocial factors with female sexual functions. Female sexual functions were studied through survey methods in a population based sample of Finnish twins and their female siblings. There were two waves of data collection. The first data collection targeted 5,000 female twins aged 33–43 years and the second 7,680 female twins aged 18–33 and their over 18–year-old female siblings (n = 3,983). There was no overlap between the data collections. The combined overall response rate for both data collections was 53% (n = 8,868), with a better response rate in the second (57%) compared to the first (45%). In order to measure female sexual function, the FSFI was used. It includes 19 items which measure female sexual function during the previous four weeks in six subdomains; desire, subjective arousal, lubrication, orgasm, sexual satisfaction, and pain. In line with earlier research in clinical populations, a six factor solution of the Finnish-language version of the FSFI received supported. The internal consistencies of the scales were good to excellent. Some questions about how to avoid overestimating the prevalence of extreme dysfunctions due to women being allocated the score of zero if they had had no sexual activity during the preceding four weeks were raised. The prevalence of female sexual dysfunctions per se ranged from 11% for lubrication dysfunction to 55% for desire dysfunction. The prevalence rates for sexual dysfunction with concomitant sexual distress, in other words, sexual disorders were notably lower ranging from 7% for lubrication disorder to 23% for desire disorder. The comorbidity between the dysfunctions was substantial most notably between arousal and lubrication dysfunction even if these two dysfunctions showed distinct patterns of associations with the other dysfunctions. Genetic influences on individual variation in the six subdomains of FSFI were modest but significant ranging from 3–11% for additive genetic effects and 5–18% for nonadditive genetic effects. The rest of the variation in sexual functions was explained by nonshared environmental influences. A correlated factor model, including additive and nonadditive genetic effects and nonshared environmental effects had the best fit. All in all, every correlation between the genetic factors was significant except between lubrication and pain. All correlations between the nonshared environment factors were significant showing that there is a substantial overlap in genetic and nonshared environmental influences between the dysfunctions. In general, psychological problems, poor satisfaction with the relationship, sexual distress, and poor partner compatibility were associated with more sexual dysfunctions. Age was confounded with relationship length but had over and above relationship length a negative effect on desire and sexual satisfaction and a positive effect on orgasm and pain functions. Alcohol consumption in general was associated with better desire, arousal, lubrication, and orgasm function. Women pregnant with their first child had fewer pain problems than nulliparous nonpregnant women. Multiparous pregnant women had more orgasm problems compared to multiparous nonpregnant women. Having children was associated with less orgasm and pain problems. The conclusions were that desire, subjective arousal, lubrication, orgasm, sexual satisfaction, and pain are separate entities that have distinct associations with a number of different biopsychosocial factors. However, there is also considerable comorbidity between the dysfunctions which are explained by overlap in additive genetic, nonadditive genetic and nonshared environmental influences. Sexual dysfunctions are highly prevalent and are not always associated with sexual distress and this relationship might be moderated by a good relationship and compatibility with partner. Regarding classification, the results supports separate diagnoses for subjective arousal and genital arousal as well as the inclusion of pain under sexual dysfunctions.

Poetikk og politikk : Augusto Boal og de undertryktes teater Poetics and Politics

Poetics and Politics. AugustoBoal and the Theatre of the Oppressed deals with the ideas and methods of the Brazilian author, director and theatre theorist Augusto Boal. The main purpose of the thesis is to give a description of what can be characterized as the poetics of Augusto Boal. What is the specific nature of his theatre methods and in what way do they differ from traditional theatre? How do these methods actually work? What is the overall intention of the Theatre of the Oppressed? As objects for my research I have selected Forum Theatre and Rainbow of Desire. The reason for this choice is partly that the two methods mentioned have become the most widespread among Boal's theatre forms, partly that they complement each other, the former being a method that works with problems of the material world, in realistic action-based narratives; the latter being an expressionistic analytical method, designed to deal with psychological problems and internalized oppression. Going from a micro- to a macro-level, I first examine the theatrical text of both forms, which in this case includes not only the verbal narrative, but also the performance itself and the setting of it, and even the implied conditions of the whole theatrical situation. Secondly, I turn to the encounter between the text and its actual recipient in the theatrical space. What happens, psychologically, when the observing, but passive spectator is turned into the actor of the play? Thirdly, I discuss the ideological and political implications of the Theatre ofthe Oppressed in real life. The way I interpret Boal's poetics, this is of vital importance. The purpose of the Theatre of the Oppressed is not anything resembling l'art pour l'art. In the contrary, its intention is to teach the oppressed the use of theatre as a martial art, so that they can fight and break the oppression in a social context of the real world. Thus the title Poetics and Politics.

PET and MR imaging in Parkinson’s disease patients with cognitive impairment. A study of dopaminergic dysfunction, amyloid deposition, cortical hypometabolism and brain atrophy

Parkinson’s disease (PD) is the second most common neurodegenerative disorder. It is characterized by a severe loss of substantia nigra dopaminergic neurons leading to dopamine depletion in the striatum. PD affects movement, producing motor symptoms such as rigidity, tremor and bradykinesia. Non-motor symptoms include autonomic dysfunction, neurobehavioral problems and cognitive impairment, which may lead to dementia. The pathophysiological basis of cognitive impairment and dementia in PD is unclear. The aim of this thesis was to study the pathophysiological basis of cognitive impairment and dementia in PD. We evaluated the relation between frontostriatal dopaminergic dysfunction and the cognitive symptoms in PD patients with [18F]Fdopa PET. We also combined [C]PIB and [¹⁸F]FDG PET and magnetic resonance imaging in PD patients with and without dementia. In addition, we analysed subregional striatal [¹⁸F]Fdopa PET data to find out whether a simple ratio approach would reliably separate PD patients from healthy controls. The impaired dopaminergic function of the frontostriatal regions was related to the impairment in cognitive functions, such as memory and cognitive processing in PD patients. PD patients with dementia showed an impaired glucose metabolism but not amyloid deposition in the cortical brain regions, and the hypometabolism was associated with the degree of cognitive impairment. PD patients had atrophy, both in the prefrontal cortex and in the hippocampus, and the hippocampal atrophy was related to impaired memory. A single 15-min scan 75 min after a tracer injection seemed to be sufficient for separating patients with PD from healthy controls in a clinical research environment. In conclusion, the occurrence of cognitive impairment and dementia in PD seems to be multifactorial and relates to changes, such as reduced dopaminergic activity, hypometabolism, brain atrophy and rarely to amyloid accumulation.

Indicent reporting in shipping. Experiences and best practices for the Baltic Sea

Incident and near miss reporting is one of the proactive tools of safety management. By analyzing incidents and near misses and by corrective actions, severe accidents can potentially be avoided. Near miss and incident reporting is widely used in many riskprone industries such as aviation or chemical industry. In shipping incident and near miss reporting is required by the mandatory safety management system International Safety Management Code (ISM Code). However, in several studies the conclusion has been that incidents are reported poorly in the shipping industry. The aim of this report is to highlight the best practices for incident reporting in shipping and to support the shipping industry in the better utilization of incident reporting information. The study consists of three parts: 1) voluntary, shared reporting systems in shipping (international experiences), 2) interview study at four shipping companies in Sweden and in Finland (best practices), 3) expert workshop on incident reporting (problems and solutions). Preconditions for a functional reporting system are an existing no blame culture, commitment of the top management, feedback, good communication, training and an easy-to-use system. Although preconditions are met, problems can still appear, for example due to psychological, interpersonal or nationality-related reasons. In order to keep the reporting system functioning, the shipping company must be committed to maintain and develop the system and to tackle the problems. The whole reporting process from compiling, handling and analyzing a report, creating corrective actions and implementing them has to be handled properly in order to gain benefits from the reporting system. In addition to avoiding accidents, the functional reporting system can also offer other benefits by increasing safety awareness, by improving the overall safety and working conditions onboard, by enhancing team work and communication onboard and between ships and the land-based organization of shipping companies. Voluntary shared reporting systems are supported in the shipping industry in principle, but their development in the Baltic Sea is still in its infancy and the potential benefits of sharing the reports have not been realized. On the basis of this study we recommend that a common reporting system be developed for the Baltic Sea area which all the ships operating in the area could use regardless of their flag. Such a wider system could prevent some of the problems related to the current national systems. There would be more incident cases available in the database and this would support anonymity and thus encourage shipping companies to report to a shared database more frequently. A shared reporting system would contribute to the sharing of experiences and to the wider use of incident information in the shipping industry.

Financial Slack and Bidding Firms’ Takeover Announcement Stock Returns – an Event Study

Despite the fact that the literature on mergers and acquisitions is extensive, relatively little effort has been made to examine the relationship between the acquiring firms’ financial slack and short-term post-takeover announcement abnormal stock returns. In this study, the case is made that the financial slack of a firm is not only an outcome of past business and financing activities but it also may affect the quality of acquisition decisions. We will hypothesize that the level of financial slack in a firm is negatively associated with the abnormal returns following acquisition announcements because slack reduces managerial discipline over the use of corporate funds and also because it may give rise to managerial self-serving behavior. In this study, financial slack is measured in terms of three financial statements ratios: leverage ratio, cash and equivalents to total assets ratio and free cash flow to total assets ratio. The data used in this paper is collected from two main sources. A list comprising 90 European acquisition announcements is retrieved from Thomson One Banker database. The stock price data and financial statements information for the respective firms is collected using Datastream. Our empirical analysis is two-fold. First, we conduct a two-sample t-test where we find that the most slack-rich firms experience lower abnormal returns than the most slack-poor firms in the event window [-1, +1], significant at 5% risk level. Second, we perform a cross sectional regression for sample firms using three financial statements ratios to explain cumulative abnormal returns (CAR). We find that leverage shows a statistically significant positive relationship with cumulative abnormal returns in event window [-1; +1] (significance 5%). Moreover, cash to total assets ratio showed a weak negative relationship with CAR (significant at 10%) in event window [-1; +1]. We conclude that our hypothesis for the inverse relationship between slack and abnormal returns receives empirical support. Based on the results of the event study we get empirical support for the hypothesis that the capital markets expect the acquisitions undertaken by slack-rich firms to more likely be driven by managerial self-serving behavior and hubris than do those undertaken by slackpoor firms, signaling possible agency problems and behavioral biases.

Influence of tail biting on weight gain, lesions and condemnations at slaughter of finishing pigs

The present study assessed the association of tail-biting lesions in finishing pigs with weight gain, occurrence of locomotion or respiratory disorders and abscesses during finishing period, and carcass condemnation at slaughter. The study was carried out on 4 different farms. For each animal with a tail biting lesion, two control pigs were selected. The total number of animals in the study was 312, with 104 of them being tail-bitten. Tail lesions were classified according to the degree of severity into four scores: score 0 -normal tail withou lesion; score 1-3 - increasing lesion severity, and score 4 - healed lesions. Overall, the occurrence of severe tail lesions (score 3) varied from 55 to 73% of tail-bitten pigs among farms. On all farms, healing of tail lesions was observed in 95% to 100% of the animals at the evaluation performed within 41-43 days after the commencement of the study. In two out of the four evaluated farms, pigs with score of 3 showed lower weight gain (P<0.05) compared with score 0 pigs. Before slaughter, the occurrence of locomotion problems and nodules/abscesses was associated (P<0.05) with the presence of tail-biting lesions. At slaughter, tail-biting lesions were associated (P<0.05) with the presence of abscesses, lung lesions (pleuritis and embolic pneumonia) or arthritis in carcasses. Carcass condemnation was associated with the presence of tail-biting lesions (P<0.05). Overall, carcass condemnation rate was 21.4%, of which animals with tail-biting lesions accounted for 66.7% of condemnations. Among the animals diagnosed with cannibalism at farm level, only two had not healed their lesions at slaughter. The fact that there were a lot of carcass condemnations, despite the fact that tail-bitten animals had no more active lesions, suggests that different situations may be observed between the field and slaughter, reinforcing the need to analyze pigs both at farm and slaughter to allow proper assessment of losses related to tail biting. Collectively, the observations of the present study show that complications associated with tail-biting found in slaughterhouses are probably underestimating field prevalence.

A Well Stated Time Domain Integral Representation for Elastodynamic Analysis and Applications

This article discusses three possible ways to derive time domain boundary integral representations for elastodynamics. This discussion points out possible difficulties found when using those formulations to deal with practical applications. The discussion points out recommendations to select the convenient integral representation to deal with elastodynamic problems and opens the possibility of deriving simplified schemes. The proper way to take into account initial conditions applied to the body is an interesting topict shown. It illustrates the main differences between the discussed boundary integral representation expressions, their singularities and possible numerical problems. The correct way to use collocation points outside the analyzed domain is carefully described. Some applications are shown at the end of the paper, in order to demonstrate the capabilities of the technique when properly used.

Evaluation of behavioral states among morning and evening active healthy individuals

The Horne-Östberg questionnaire partly covers some factors that may be important determinants of peak time and characterize patterns of behavior. We conducted a study for the evaluation of self-reported behavioral states (hunger sensation, availability for study, physical exercise, solving daily problems, and time preferences) as expressions of underlying cyclic activity. Three hundred and eighteen community subjects without history of medical, psychiatric, or sleep disorders were evaluated in a cross-sectional design. A self-report about daily highest level of activity was used to categorize individuals into morning, evening, and indifferently active. Time-related behavioral states were evaluated with 23 visual analog questions. The responses to most analogic questions were significantly different between morning and evening active subjects. Logistic regression analysis identified a group of behaviors more strongly associated with the self-reported activity pattern (common wake up time, highest subjective fatigue, as well as wake up, bedtime, exercise and study preferences). These findings suggested that the patterns of activity presented by normal adults were related to specific common behavioral characteristics that may contribute to peak time.