No description available.

No description available.

No description available.

Electronic Health Record (EHR) creates a huge number of databases which are being updated dynamically. Major goal of interoperability in healthcare is to facilitate the seamless exchange of healthcare related data and an environment to supports interoperability and secure transfer of data. The health care organisations face difficulties in exchanging patient’s health care information and laboratory reports etc. due to a lack of semantic interoperability. Hence, there is a need of semantic web technologies for addressing healthcare interoperability problems by enabling various healthcare standards from various healthcare entities (doctors, clinics, hospitals etc.) to exchange data and its semantics which can be understood by both machines and humans. Thus, a framework with a similarity analyser has been proposed in the thesis that dealt with semantic interoperability. While dealing with semantic interoperability, another consideration was the use of word embedding and ontology for knowledge discovery. In medical domain, the main challenge for medical information extraction system is to find the required information by considering explicit and implicit clinical context with high degree of precision and accuracy. For semantic similarity of medical text at different levels (conceptual, sentence and document level), different methods and techniques have been widely presented, but I made sure that the semantic content of a text that is presented includes the correct meaning of words and sentences. A comparative analysis of approaches included ontology followed by word embedding or vice-versa have been applied to explore the methodology to define which approach gives better results for gaining higher semantic similarity. Selecting the Kidney Cancer dataset as a use case, I concluded that both approaches work better in different circumstances. However, the approach in which ontology is followed by word embedding to enrich data first has shown better results. Apart from enriching the EHR, extracting relevant information is also challenging. To solve this challenge, the concept of analogy has been applied to explain similarities between two different contents as analogies play a significant role in understanding new concepts. The concept of analogy helps healthcare professionals to communicate with patients effectively and help them understand their disease and treatment. So, I utilised analogies in this thesis to support the extraction of relevant information from the medical text. Since accessing EHR has been challenging, tweets text is used as an alternative for EHR as social media has appeared as a relevant data source in recent years. An algorithm has been proposed to analyse medical tweets based on analogous words. The results have been used to validate the proposed methods. Two experts from medical domain have given their views on the proposed methods in comparison with the similar method named as SemDeep. The quantitative and qualitative results have shown that the proposed analogy-based method bring diversity and are helpful in analysing the specific disease or in text classification.

Digitaliseringen, uppkomsten och den ökade populariteten av on-demand musikstreamingtjänster har förändrat musikbranschen i snabb takt. Tidigare studier visar att digitaliseringen har påverkat sättet hur media skapas, publiceras, distribueras och konsumeras. Studier om digitaliseringens effekter på kreatörer och distributörer inom musikbranschen visade sig däremot vara få. Det ansågs därför som en möjlighet att utforska hur artister och oberoende skivbolag uppfattar digitaliseringens effekter för att minimera den nuvarande kunskapsluckan. Den explorativa sekventiella studien bestod av två faser och baserades på en kombination av olika metoder. Den initiala studien utgjordes av tre kvalitativa intervjuer och resulterande arbetsteorier prövades därefter i en kvantitativ enkätundersökning (n=81). Resultatet indikerar att större andelen av oberoende skivbolag har anpassat sina affärsmodeller och utvecklats till s.k. 360°-musikföretag. Resultatet visar vidare att digitaliseringen har till viss grad påverkat sättet hur musik skapas och produceras, med en tendens mot en mer individualistisk och digital process, och vidare medfört en förenkling för artister att publicera sin musik. Artisternas intäkter har däremot inte förbättrats och många upplever att arbetsklimatet har försämrats. Resultatet visar att digitaliseringen sedan uppkomsten av musikstreamingtjänster har medfört omvälvande förändringar, dock verkar dessa inte ha lett till en demokratisering av musikbranschen utan enbart till en förflyttning av makten från skivbolagen till musikstreamingtjänsterna. Både artister och oberoende skivbolag uppfattar att den nära framtidens främsta utmaningar å ena sidan är att uppnå en skälig betalning för artister, samt å andra sidan att framgångsrikt marknadsföra musiken för att nå igenom bruset. Det indikeras vidare att regler och lagar är nödvändiga för att kunna säkerställa en hållbar utveckling av musikbranschen. / The emergence and continuously growing popularity of on-demand streaming music services has changed the music landscape rapidly and new services are entering the market at a high pace. Prior studies show that digitization has affected the way media is created, published, distributed and consumed. The literature review revealed a knowledge gap regarding the effects on music professionals and provided an opportunity to explore how artists and independent record labels perceive the aspects of digitization. The study followed an exploratory sequential mixed-methods approach and consisted of two phases, an initial study including three qualitative interviews, and a quantitative follow-up study, in which working theories that had resulted from the initial study were tested through an online survey (n=81). The results indicate that many independent record labels have changed and adapted their business models and turned into so called 360° music companies. The results further show that digitization developments have to some degree affected the way music is created and produced, with a tendency towards a more individualistic and digital process, and that it has become easier for artists to publish their music; their incomes have however not improved and for many artists the working climate has become harder. The results show that the emergence of on-demand streaming services has disrupted the music industry, instead of having a democratic impact, the power that record labels used to have appears to have shifted to streaming services. Both artists and independent record labels perceive the achievement of fair payments and successful promotion to be the main future challenges. It is indicated that regulations and laws that prevent exploitation are necessary in order to ensure the music industry to be sustainable in the future.

Interest is a guiding force in helping an individual to realize the pattern he is making through his day by day experiences. All children have not had the same experiences. They may or may not be interested in the same activity. It has been said that behavior is caused. If behavior is caused, then, to know the interests of children may be very valuable in diverting or guiding their activities which are desirable to help them better fit themselves to the society in which they live. Thus, the problem of this thesis is to discover the interests and activities of a seventh-grade group of boys and girls attending Huey School, Wichita Falls, Texas.

This dissertation develops explainable and sparse predictive models applied to two main healthcare applications: reproductive health and oncology. Through the application of advanced machine learning techniques and survival analysis, we aim to enhance predictive accuracy and provide actionable insights in these critical areas. The thesis is structured into four distinct problems, each focusing on a particular research question. The first problem concerns the prediction of the probability of conception among couples actively trying to conceive. Using self-reported health data from a North American preconception cohort study, we analyzed factors such as sociodemographics, lifestyle, medical history, diet quality, and specific male partner characteristics. Machine learning algorithms were employed to predict the probability of conception demonstrating improved discrimination and potential clinical utility. The second problem explores the application of machine learning algorithms to electronic health record (EHR) data for identifying predictor variables associated with polycystic ovarian syndrome (PCOS) diagnosis. Employing gradient boosted trees and feed-forward multilayer perceptron classifiers, we developed a scoring system that improved the model's performance, providing a valuable tool for early detection and intervention. The third problem focuses on predicting the risk of miscarriage among female participants who conceived during the study period. Utilizing both static and survival analysis, including Cox proportional hazard models, we developed predictive models to assess miscarriage risk. The study revealed that most miscarriages were due to random genetic errors during early pregnancy, indicating that miscarriage is not easily predicted based on preconception sociodemographic and lifestyle characteristics. Finally, the fourth problem focuses on the development of predictive models for managing Chronic Myeloid Leukemia (CML) patients. We developed models to predict whether patients will achieve deep molecular response (DMR) at later treatment stages and maintaining this status up to 60 months post-treatment initiation. These models offer insights into treatment effectiveness and patient management, aiming to support clinical decision-making and improve long-term patient outcomes. By emphasizing the explainability of these models, this dissertation not only aims to provide accurate predictions but also to ensure that the results are interpretable and actionable for healthcare professionals. Overall, this thesis showcases the potential of predictive modeling to improve reproductive health and oncology-related outcomes. The development and validation of various models in these contexts underscore the value of machine learning algorithms in healthcare research, analysis of epidemiologic data, and prediction of critical health events. The findings have significant implications for enhancing patient care, informing clinical practices, and guiding healthcare policy decisions.

In the last decade, the deployment of Electronic Health Records has increased tremendously in many developed countries. This increasing trend intensifies the need for developing countries like South Africa to implement electronic health record systems in state owned hospitals to facilitate e-referral processes to improve health care delivery. The aim of this research was to investigate the current process of patient record keeping, management, and the referral process of patients within the same hospital and to other hospitals and based on the findings compile an Electronic Health Record (EHR) framework to facilitate e- referral processes. This research study was based on a qualitative case study approach. A multiple data collection technique was used which included group interviews, questionnaires, document analysis and informal discussions with the hospital workers. Data were analysed by categorization and thematic approach. The findings obtained from state hospitals indicated that there is no EHR system which accommodates patient health record systems to facilitate e-referral processes. These findings led to a compilation of the Limpopo Electronic Health Record System (LEHRS) to aid e-referral processes in state hospitals. The increasing need for accurate, reliable, available and accessible EHR will be addressed by the implementation of LEHRS as information will be stored in a central database in a useable format and will be easily accessed. / Computing / M. Tech. (Information Technology)

In the last decade, the deployment of Electronic Health Records has increased tremendously in many developed countries. This increasing trend intensifies the need for developing countries like South Africa to implement electronic health record systems in state owned hospitals to facilitate e-referral processes to improve health care delivery. The aim of this research was to investigate the current process of patient record keeping, management, and the referral process of patients within the same hospital and to other hospitals and based on the findings compile an Electronic Health Record (EHR) framework to facilitate e- referral processes. This research study was based on a qualitative case study approach. A multiple data collection technique was used which included group interviews, questionnaires, document analysis and informal discussions with the hospital workers. Data were analysed by categorization and thematic approach. The findings obtained from state hospitals indicated that there is no EHR system which accommodates patient health record systems to facilitate e-referral processes. These findings led to a compilation of the Limpopo Electronic Health Record System (LEHRS) to aid e-referral processes in state hospitals. The increasing need for accurate, reliable, available and accessible EHR will be addressed by the implementation of LEHRS as information will be stored in a central database in a useable format and will be easily accessed. / Computing / M. Tech. (Information Technology)

Aim: The overall aim of this thesis is to explore School health nursing through school nurses’ descriptions of school children’s health and to analyse factors influencing the recording of schoolchildren’s health in the School Health Record (SHR). An additional aim is to evaluate family nursing interventions as a tool for the school nurses in the School Health Service (SHS).Methods: The thesis comprises four papers. A combination of qualitative and quantitative methods was used through individual interviews with a strategic sample of school nurses (n=12) (PI), a national survey to a representative sample of school nurses (n=129) (PII, III) and the implementation of family nursing models developed in Canada with girls in their early adolescence with recurrent health complaints and their families (n=4) in co-operation with their school nurses (n=2) (PIV). The Strengths and Difficulties Questionnaire (SDQ) was used as pre and post test. Evaluation interviews were conducted with the families and the nurses separately. Qualitative content analyses were used to analyze the interview text with the school nurses and the families. Manifest content analysis was used to analyze the free text answers of the survey and the evaluation interview with the school nurses. Descriptive statistical analyses were used to describe demographic data in all four papers. The SDQ was hand-scored statistically.Findings: The findings showed that nurses judged the schoolchildren’s mental health as deteriorated, especially in socially disadvantaged areas and more generally among girls expressed as psychosomatic symptoms. Individual factors related to lifestyle affected the schoolchildren’s physical health, and the mental health was, to a large extent, affected by the school environment and family relations. The latter seemed to be the most important factor affecting schoolchildren’s mental health. The basis for the school nurses judgement of the physical health was health check-ups and the health dialogues. Spontaneous visits were more commonly used to judge the mental health. Recording schoolchildren’s mental health was a challenge for school nurses. Difficulties were related to ethical considerations, tradition, lack of time and the improper structure of the SHR. Fears of marking the schoolchild for life related to the schoolchild itself, the parents or to other authorities/successive caregivers were brought up as hinders for recording mental and social health. Family sessions may be useful within the profession when handling recurrent health complaints among adolescence girls. The girls and their families experienced relief, they felt confirmed and that their feelings and reactions were normal in that situation. The families became aware of their own strengths and possibilities and this was supported by the SDQ which showed an increased well-being. The school nurses valued this way of working and meant that the sessions seemed to start a changing process within the families.Conclusions: The results indicate that school nurses have a deep knowledge about schoolchildren’s health which is not used to its full potential in a public health perspective. However, the experienced difficulties recording schoolchildren’s mental health seem obvious, which would demand developing the SHR for the needs of today. Family sessions in SHS with the school nurse as a collaborator with the family seemed useful and may be transferable to other health problems expressed by the schoolchildren. Bronfenbrenner’s ecological systems theory and other models for health determinants are used to illustrate the school nurse as a mediator working on the bridge over different health streams with schoolchildren’s health on an individual and a population level. / Syfte: Avhandlingens övergripande syfte är att undersöka skolsköterskors uppfattning om skolbarns hälsa och att analysera faktorer som påverkar dokumentation av skolbarns hälsa i skolhälsovårdsjournalen. Ett ytterligare syfte är att utvärdera modeller för familjeinterventioner som redskap för skolsköterskor i skolhälsovård.Metoder: Avhandlingen består av fyra delarbeten. En kombination av kvalitativa och kvantitativa metoder användes. I delarbete I genomfördes intervjuer med ett strategiskt urval av skolsköterskor (n=12). Intervjuerna analyserades med kvalitativ innehållsanalys. I delarbeten II och III distribuerades en nationell enkät till ett representativt urval av Sveriges skolsköterskor (n=129). Manifest innehållsanalys användes vid analys av de öppna frågorna. I delarbete IV genomfördes en interventionsstudie med familjesamtal, inspirerad av modeller för familjefokuserad omvårdnad utvecklade i Kanada. Skolflickor i tidig adolescens med återkommande subjektiva hälsoproblem (n=4) och deras föräldrar i samarbete med deras verksamma skolsköterskor (n=2) ingick i studien. Separata utvärderingsintervjuer genomfördes med familjer och skolsköterskor. Intervjuerna analyserades med kvalitativ och manifest innehållsanalys respektive. The Strengths and Difficulties Questionnaire (SDQ) användes som före/efter test vid interventionen och resultatet bearbetades statistiskt manuellt. Deskriptiv statistik användes för analys av demografisk data i samtliga delarbeten.Resultat: Resultatet visade att skolsköterskorna bedömde skolbarnens mentala hälsa som försämrad särskilt bland flickor och i socioekonomiskt utsatta områden. Individuella livsstilsfaktorer påverkade skolbarnens fysiska hälsa och den mentala hälsan var i stor utsträckning påverkad av skolmiljö och familjerelationer. Det sistnämnda verkade vara den mest betydelsefulla påverkansfaktorn för skolbarnens mentala hälsa. Bedömningen av den fysiska hälsan baserades på hälsokontroller och hälsosamtal medan spontana besök var vanligare för bedömning av den mentala hälsan. Dokumentation av mentala hälsa var en utmaning för skolsköterskorna. Svårigheterna kunde relateras till etiska överväganden, tradition och tidsbrist samt till skolhälsovårdsjournalens struktur som inte ansågs uppfylla dagens krav. Skolsköterskorna uttryckte en rädsla för att journalanteckningarna skulle märka skolbarnet för livet. Framtida tolkningar relaterade till skolbarnet själv, föräldrar eller andra/påföljande vårdgivare uttrycktes som hinder för att dokumentera mental och social hälsa. Familjesamtal visade sig vara användbara i skolhälsovården. De medverkande flickorna och deras familjer kände sig bekräftade i att deras känslor och reaktioner var normala. De sade sig bli medvetna om egna styrkor och möjligheter vilket styrktes av SDQ som visade ett ökat välbefinnande efter sammankomsterna, både hos skolbarnen och hos föräldrarna. Skolsköterskorna var positiva till att arbeta med familjesamtal och upplevde sig mer som samverkanspartner än som expert. Samtalen ledde till att en förändringsprocess startade i familjerna enligt skolsköterskorna.Slutsatser: Resultatet indikerar att skolsköterskor har en djup kunskap om skolbarns hälsa som sannolikt kunde tas tillvara på ett bättre sätt ur ett folkhälsoperspektiv på såväl nationell som lokal nivå. Behovet av att utveckla skolhälsovårdsjournalen efter dagens behov och fördjupad kunskap om de upplevda svårigheterna att dokumentera skolbarns mentala hälsa är uppenbar. Familjesamtal, där skolsköterskan intar en roll som samverkanspartner, visade sig användbara och kan sannolikt överföras till andra hälsoproblem bland skolbarn. Bronfenbrenners utvecklingsekologiska systemteori och andra modeller för hälsodeterminanter används för att illustrera skolsköterskans arbete med skolbarns hälsa på såväl en individuell nivå som folkhälsonivå.