Demensvården i Sverige och i andra delar av världen har på olika sätt varit i fokus de senaste åren där man påtalat behovet att utveckla metoder och riktlinjer för hur vården ska bedrivas. Detta för att möta den växande andelen äldre människor som också utvecklar demenssjukdomar. Nationella projekt har drivits, företrädesvis i syfte att förbättra vård och omsorg av personer med demenssjukdom, men även för att förbättra diagnosticering och behandling. I denna avhandling beskrivs utvecklingen av det dator-baserade beslutsstödet för demensutredning, DMSS (Dementia Management and Support System), som syftar till att fungera som ett stöd för personer som arbetar med att diagnosticera och behandla personer med kognitiv sjukdom. Domänen valdes även på grund av dess komplicerade kunskapsinnehåll, där bland annat en spännvidd av olika typer av symptom, komplexa kliniska mätmetoder sett ur ett formaliseringsperspektiv, starkt teamorienterat arbetssätt, ställer krav på hur kunskap ska och är möjlig att formaliseras och integreras i ett beslutsstödsystem för att det ska bli användbart i kliniskt arbete. De olika studierna och delprojekten som beskrivs i avhandlingen syftar till att tillsammans skapa en grund för utveckling av ett kliniskt kognitivt verktyg som stödjer och utvecklar användarens kognitiva processer (lärande, beslutsfattande, resonemang, etc.), samtidigt som det stödjer utvecklingen av det kliniska arbetet vari systemet ingår. I detta arbete fokuseras demensutredning som applikationsomr åde. Analyser har gjorts av den vidare användarkontexten, resonemangsprocesser, domän- och processkunskapen uttryckt i evidensbaserad litteratur och integrerad i klinisk praktik, terminologier samt formaliseringstekniker som kan hantera domänkunskapens egenskaper och användarsituationens krav. Prototyper har utvecklats och utvärderats i en iterativ process i samarbete med domänexperter, för användande i klinisk praktik i Sverige och Japan. För dessa studier har kvalitativa metoder använts i syfte att fånga så många olika aspekter som möjligt angående formalisering och interaktion, samt av praktiska skäl då det funnits begränsad tillgång till expertanvändare och patienter. Triangulering av metoder har tillämpats för att validera resultat. Kliniska utredningsverksamheter är komplexa processer, som är situerade, emergenta och styrda av individens behov, men även begränsade eller möjliggjorda av tillgängliga resurser på olika vårdnivåer i vårdprocessen. Det behövs metoder och verktyg som kan användas vid utveckling av system som syftar till att stödja dessa verksamheter. Det finns exempel på metoder som utvecklats för transformation av informell klinisk kunskap till en formell struktur som kan implementeras i ett beslutsstödsystem, där verktyg har utvecklats primärt i syfte att hjälpa kliniska experter att transformera sin kunskap till något en systemutvecklare kan använda. Den största nackdelen med dessa angreppssätt är att de är tidskrävande för experterna att sätta sej in i och använda. En metod har tillämpats i detta arbete där en teoribildning, som är gemensam för flera forskningsområden, använts för att strukturera klinisk process- och domänkunskap i en form som kan användas i formaliseringsarbete. Den konceptuella modellen av kliniskt arbete som utvecklats är baserad på verksamhetsteorin, kompletterad med general logics som kategoriskt, formellt teoretiskt ramverk för att möjliggöra transformationer mellan olika logiska språk och flexibel representation av riktlinjer och kunskap. Genom att göra en grundlig verksamhetsanalys utifrån ett aktivitetsperspektiv med hjälp av modellen, kan komponenter identifieras som kan formaliseras i en kunskapsbas och/eller kompletteras genom en design och implementation av ett gränssnitt som stödjer ett interaktivt resonemang och den kliniska processen. Resultatet av verkamhetsanalys och andra studier som presenteras i denna avhandling kommer att ligga till grund för vidare utveckling av DMSS för olika användarmiljöer, till att börja med i Sverige och Japan. Extensioner av systemet kommer att utvecklas som stödjer de olika ingående professionerna på olika vårdnivåer. Den konceptuella modellen kommer att utvecklas och tillämpas i framtida utvecklingsprojekt där beslutsstöd är en central komponent. Det formella ramverket kommer att utvecklas i syfte att kunna analysera och förfina kunskap i perspektivet av exempelvis olika set av kliniska riktlinjer som ställer olika krav på komplexitet hos logiken. Stödet till ett interaktivt resonemang vid användandet av systemet ska utvecklas med en kunskapsbas och ett dynamiskt gränssnitt speciellt utformat för ändamålet. Hittills har i första hand kvalitativa aspekter och syften varit i fokus i de olika projekten. Därför behöver varje utvecklingslinje ytterligare utvecklas med kvantitativa mål. Utvidgade utvärderingsstudier pågår, som syftar till att undersöka fördelning mellan olika nivåer av komplexitet hos patienter och vilken typ av stöd som behövs för respektive. När systemet är integrerat i daglig verksamhet kan faktorer som hur användande av systemet påverkar användaren och verksamheten undersökas. / There is a need to improve dementia care in Sweden. The main issues discussed are how to improve the competence of medical personnel and the quality of diagnosis and intervention. In this thesis the process of developing a decision-support system for the investigation of dementia is described, as one means to meet the need. The resulting prototype system DMSS (Dementia Management Support System) has been developed in cooperation with domain experts, and has been evaluated and redesigned in the process in an iterative development process. The process involves the assessment of evidence-based domain knowledge and its characteristics, the assessment of the procedural knowledge residing in clinical practice, and reasoning processes. Further, the terminology and main reasoning process integrated in the system have been validated. Qualitative methods have been used for these parts of the project for the purpose of assessing as many different aspects as possible, and for practical reasons due to the limited access to domain experts, patients and primary care physicians in the area. Triangulation of methods has been applied in order to validate results in the process. The development has been extended to also include prototypes for Japanese clinical environments. Clinical investigation activities are complex processes, which are situated, emergent and directed by the individual need of the patient, but also restricted or enhanced by the available resources at different points and at different care levels in the process. For the purpose of creating a system which provides support throughout the investigation process, the domain knowledge and the clinical investigation process was analysed and formalised in a conceptual model of clinical activity, developed based on activity theory and case studies of patients. The need for methods for the transformation of informal results from field studies into formal knowledge and design is addressed by providing the framework, which integrates the conceptual model of clinical activity and a method for the assessment and transformation of the knowledge to be integrated in a decision-support system. The model was used to identify actions and their characteristics suitable for formalisation in a decision-support system. Several sources of domain knowledge need to be integrated that express the knowledge differently, which increases the demands on a formalism for representation. The work towards formalising the diagnostic reasoning process in both typical and atypical patient's cases is presented, where the evidence in ambiguous cases is valued within different frames of references in order to improve specificity. Different logical frameworks have been applied, evaluated and developed using case studies of patients. Two lines of work towards a dementia logic and flexible guideline representation is presented; the defeasible, non-monotonic approach where many-valued dictionaries are used in a context-based argumentation framework; and the monotonic approach of integrating reasoning in a fundamental view of transformations between logics, using general logics as generalised and categorical framework.

Introdução: A Medicina Baseada em Evidências, apesar da grande profusão de publicações da área, enfrenta desafios no intuito de melhorar a qualidade da assistência à saúde. O conhecimento gerado por suas publicações demora a ser posta em prática. Os softwares CDSS de apoio à decisão clínica, podem ser a solução de incorporação das evidências na prática clínica. Esses sistemas já foram associados a melhorias na qualidade de diversos aspectos da assistência à saúde, como a organização, minimização de erros, redução de custos, aumento da eficiência dos cuidados, mas pesquisas com desfechos centrados no paciente ainda são raras. Como outra qualquer intervenção em saúde, as afirmações de que os CDSS são benéficos para o paciente necessitam de confirmação por ensaios clínicos. Objetivos: Verificar se o uso dos CDSS com base em evidências, está associado com melhores resultados clínicos orientados para o paciente. Métodos: Revisão sistemática da literatura dos ensaios clínicos controlados e randomizados que compararam diretamente o uso de CDSS com práticas clínicas convencionais considerando os desfechos clínicos classificados como orientados para o paciente. Resultados: Nossa estratégia de pesquisa identificou 51283 artigos na base MEDLINE-PubMed, sendo 311 selecionados para leitura de título e resumo após a aplicação do filtro para ensaio clínico randomizado, 45 selecionados para leitura do texto completo, dos quais 19 preencheram o critério de elegibilidade. Outros 9 ensaios foram incluídos através da realização de um overview das revisões sistemáticas anteriores. Os ensaios foram publicados entre os anos de 1995 e 2015 e realizados em cinco contextos assistenciais, com duração máxima de 12 meses. A maioria das fontes de evidências que alimentaram os sistemas foram diretrizes de órgão governamental ou sociedades de especialidades. Doze ensaios avaliaram mortalidade, 14 avaliaram hospitalizações ou atendimento de emergência e 6 avaliaram desfechos relacionados a presença de sintomas. Foram realizadas meta-análises de acordo com o contexto assistencial e o tipo de desfecho. Somente uma meta-análise envolvendo a mortalidade de pacientes tratados em ambulatório por diferentes condições clínicas se mostrou estatisticamente significante, favorável ao grupo CDSS, em 3 ensaios randomizados por aglomerado, com risco de viés considerado moderado, que compromete a qualidade da evidência. Conclusões Apesar do potencial dos CDSS no apoio de intervenções de saúde, não há evidência de boa qualidade de que sejam efetivos para aumentar a sobrevida ou a qualidade de vida dos pacientes. O número de ensaios que avaliam esses desfechos, os períodos de tempo pelos quais os pacientes foram seguidos, o número insuficiente de participantes, bem como a heterogeneidade entre os estudos analisados quanto aos cenários clínicos e as fontes de informação que alimentam os softwares não permitiram resultados mais conclusivos / Background: In spite of the wealth of publications in the field, Evidence-Based Medicine faces challenges in order to improve quality of health care. It takes too long for knowledge produced by its publications to be put into practice. Clinical Decision Support Systems (CDSS) may be a solution for incorporation of evidence into clinical practice. These systems have been associated with improvements in quality of various aspects of health care, including its organization, error minimizations, cost reductions and increases in its efficiency, but patient-oriented outcomes are still rare in research literature. Like any other healthcare intervention, claims that CDSS are beneficial for patients need to be confirmed by clinical trials. Objective: To verify whether the use of evidence-based Clinical Decision Support Systems is associated with improved patient-oriented clinical outcomes. Methods: Systematic literature review of randomized controlled trials that directly compared the use of CDSS with usual practice considering clinical outcomes classified as patient-oriented. Results: Our search strategy has identified 51,283 entries in MEDLINE-PubMed and, after filtering for randomized controlled trials 311 papers were selected for title and abstract reading. Forty-five were selected for full-text reading of which 19 have met eligibility criteria. Another nine trials were included after an overview of previous systematic reviews. Trials were published between 1995 and 2015 and performed in five care settings with a maximum follow-up of 12 months. Most evidence sources feeding systems´ knowledge bases were government agency guidelines or specialty societies. Twelve trials have assessed mortality, 14 have assessed hospital admissions and/or emergency visits and nine have assessed symptom-related outcomes. Meta-analyses were performed according to trials´ care setting and outcome types. Only a meta-analysis of three cluster-randomized trials involving mortality among outpatients with different clinical conditions was statistically significant, favouring CDSS group, but risk of bias was moderate, compromising the quality of evidence. Conclusions: Despite the potential of CDSS to improve healthcare quality there is no reliable evidence that they improve patients´ life extension or quality. The insufficient numbers of trials assessing these outcomes, studies´ subjects and follow-up periods, the heterogeneities of clinical settings across studies and knowledge bases feeding the systems impede achieving results that are more conclusive

Research has focused heavily on the study of Clinical Decision Support Systems. However, CDS systems have generally had little impact on clinical practice. One of the most important reasons is the lack of human-computer interaction (HCI) considerations in designing these systems. Although physicians play an essential role in healthcare decision-making, there is little literature describing physicians' expectations and preferences prior to the development of these systems, which is an essential phase in user-centered design.This study aims to answer the following research question: What do physicians expect of interacting with future clinical decision support systems? An exploratory qualitative study was conducted, and data were collected by interviewing 9 physicians practicing in Sweden. A thematic analysis was used for data analysis, and the findings are four themes: 1) physicians' Expectations related to clinical practice; 2) physicians' expectations related to physician-patient relationship; 3) physicians' expectations related to the physician's role 4) physicians' expectations related to CDS governance.The research findings contribute to the knowledge of Anticipated UX in the context of healthcare and CDS systems. The empirical findings on potential user expectations are valuable for understanding the diversity of user experience and user expectations as phenomena in the specific domain of CDS systems. Service designers can utilize and build on the empirical findings to develop positive user experiences of future CDS systems

Für viele Krankheitsbilder und Indikationen ist ein breites Spektrum an Arzneimitteln und Arzneimittelkombinationen verfügbar. Darüber hinaus stellen Therapieziele oft Kompromisse zwischen medizinischen Zielstellungen und Präferenzen und Erwartungen von Patienten dar, um Zufriedenheit und Adhärenz zu gewährleisten. Die Auswahl der optimalen Therapieoption kann daher eine große Herausforderung für den behandelnden Arzt darstellen. Klinische Entscheidungsunterstützungssysteme, die Wirksamkeit oder Risiken unerwünschter Arzneimittelwirkung für Behandlungsoptionen vorhersagen, können diesen Entscheidungsprozess unterstützen und \linebreak Leitlinien-basierte Empfehlungen ergänzen, wenn Leitlinien oder wissenschaftliche Literatur fehlen oder ungeeignet sind. Bis heute sind keine derartigen Systeme verfügbar. Im Rahmen dieser Arbeit wird die Anwendung von Methoden aus der Domäne der Recommender Systems (RS) und des Maschinellen Lernens (ML) in solchen Unterstützungssystemen untersucht. Aufgrund ihres erfolgreichen Einsatzes in anderen Empfehlungssystemen und der einfachen Interpretierbarkeit werden zum einen Nachbarschafts-basierte Collaborative Filter (CF) an die besonderen Anforderungen und Herausforderungen der Therapieempfehlung angepasst. Zum anderen werden ein Modell-basierter CF-Ansatz (SLIM) und ein ML Algorithmus (GBM) erprobt. Alle genannten Ansätze werden anhand eines exemplarischen Therapieempfehlungssystems evaluiert, das auf die Behandlung der Autoimmunkrankheit Psoriasis abzielt. Um das Risiko der Empfehlung kontraindizierter oder gar gesundheitsgefährdender Medikamente zu reduzieren, werden Regeln aus evidenzbasierten Leitlinien und Expertenempfehlungen implementiert, um solche Therapieoptionen aus den Empfehlungslisten herauszufiltern. Insbesondere die Nachbarschafts-basierten CF-Algorithmen zeigen insgesamt kleine durchschnittliche Abweichungen zwischen geschätztem und tatsächlichem Therapie-Outcome. Auch die aus den Outcome-Schätzungen abgeleiteten Empfehlungen zeigen eine hohe Übereinstimmung mit der tatsächlich angewandten Behandlung. Die Modell-basierten Ansätze sind den Nachbarschafts-basierten Ansätzen insgesamt unterlegen, was auf den begrenzten Umfang der verfügbaren Trainingsdaten zurückzuführen ist und die Generalisierungsfähigkeit der Modelle erschwert. Im Vergleich mit menschlichen Experten sind alle untersuchten Algorithmen jedoch hinsichtlich Übereinstimmung mit der tatsächlich angewandten Therapie unterlegen. Eine objektive und effiziente Bewertung des Behandlungserfolgs kann als Voraussetzung für ein erfolgreiches ``Krankheitsmanagement'' angesehen werden. Daher wird in weiteren Untersuchungen für ausgwählten klinische Anwendungen der Einsatz von ML Methoden zur automatischen Quantifizierung von Gesunheitszustand und Therapie-Outcome erprobt. Zusätzlich, als weitere Quelle für Informationen über Therapiewirksamkeiten, wird der Einsatz von Sentiment Analysis Methoden zur Extraktion solcher Informationen aus Medikamenten-Bewertungen untersucht. / Under most medical conditions and indications, a great variety of pharmaceutical drugs and drug combinations are available. Beyond that, trade-offs need to be found between the medical requirements and the patients' preferences and expectations in order to support patients’ satisfaction and adherence to treatments. As a consequence, the selection of an optimal therapy option for an individual patient poses a challenging task to prescribers. Clinical Decision Support Systems (CDSSs), which predict outcome as effectiveness and risk of adverse effects for available treatment options, can support this decision-making process and complement guideline-based decision-making where evidence from scientific literature is missing or inappropriate. To date, no such systems are available. Within this work, the application of methods from the Recommender Systems (RS) domain and Machine Learning (ML) in such decision support systems is studied. Due to their successful application in other recommender systems and good interpretability, neighborhood-based CF algorithms are transferred to the medical domain and are adapted to meet the requirements and challenges of the therapy recommendation task. Moreover, a model-based CF method (SLIM) and a state of the art ML algorithm (GBM) are employed. All algorithms are evaluated in an exemplary therapy recommender system, targeting the treatment of the autoimmune skin disease Psoriasis. In order to reduce the risk of recommending contraindicated or even health-endangering drugs, rules derived from evidence-based guidelines and expert recommendations are implemented to filter such options from the recommendation lists. Especially the neighborhood-based CF algorithms show small average errors between estimated and observed outcome. Also, the recommendations derived from outcome estimates show high agreement with the ground truth. The performance of both model-based approaches is inferior to the neighborhood-based recommender. This is primarily assumed to be due to the limited training data sizes, which renders generalizability of the learned models difficult. Compared with recommendations provided by various experts, all proposed approaches are, however, inferior in terms of agreement with the ground truth. An objective and efficient assessment of treatment response can be regarded a prerequisite for successful ``disease management''. Therefore, the use of ML methods for the automatic quantification of health status and therapy outcome for selected clinical applications is investigated in further experiments. Moreover, as additional source of information about drug effectiveness, the use of Sentiment Analysis, in order to extract such information from drug reviews, is investigated.