The rate of Emergency Department (ED) visits due to mental health and drug abuse among children and youth has been increasing for more than a decade and is projected to become the leading cause of ED visits. Identifying high-risk patients well before an ED visit will enable mental health care providers to better predict ED resource utilization, improve their service, and ultimately reduce the risk of a future ED visit. Many studies in the literature utilized medical history to predict future hospitalization. However, in mental health care, the medical history of new patients is not always available from the first visit and it is crucial to identify high risk patients from the beginning as the rate of drop-out is very high in mental health treatment. In this study, a new approach of creating a text representation of questionnaire data for deep learning analysis is proposed. Employing this new text representation has enabled us to use transfer learning and develop a deep Natural Language Processing (NLP) model that estimates the possibility of 6-month ED visit among children and youth using mental health patient reported outcome measures (PROM). The proposed method achieved an Area Under Receiver Operating Characteristic Curve of 0.75 for classification of 6-month ED visit. In addition, a novel method was proposed to identify the words that carry the highest amount of information related to the outcome of the deep NLP models. This measurement of word information using Entropy Gain increases the explainability of the model by providing insight to the model attention. Finally, the results of this method were analyzed to explain how the deep NLP model achieved a high classification performance. / Dissertation / Master of Applied Science (MASc) / In this document, an Artificial Intelligence (AI) approach for predicting 6-month Emergency Department (ED) visits is proposed. In this approach, the questionnaires gathered from children and youth admitted to an outpatient or inpatient clinic are converted to a text representation called Textionnaire. Next, AI is utilized to analyze the Textionnaire and predict the possibility of a future ED visit. This method was successful in about 75% of the time. In addition to the AI solution, an explainability component is introduced to explain how the natural language processing algorithm identifies the high risk patients.

Neck pain is the second most common musculoskeletal disorder after low back pain adding to the global burden of disease. A focus on evaluating outcomes for musculoskeletal conditions is imperative to evaluate the effect of interventions and to track the progression of disease. As evidence based practice and associated use of patient-based outcomes are taken up across different countries, it becomes imperative for cross-cultural translation studies. Given the uptake of technology in workplaces, it is also important to understand the prevalence of neck pain in this context. This thesis has focused on two objectives: 1. Translating a newly developed patient-report outcome measure of neck-related disability and testing its psychometric properties. 2. Estimating the prevalence of neck pain in computer-using workers. The first manuscript focusses on cross cultural translation and validation of ND10 (Neck difficulty10) that was designed to measure neck-related disability. A new English outcome measure for neck disability (ND10) was cross culturally translated and validated in computer users in India using forward and backward translation, and cognitive interviewing to determine a final version. The ND10-H demonstrated high reliability (ICC= 0.93) and convergent construct validity with the NDI and DASH (r= 0.78 and 0.86) The second manuscript reported the prevalence of neck pain in computer users in India. Sampling was performed in two different companies: A Spiritual Media Publication Organization (SMPO) and an Information Technology (IT) company. The companies were selected based on computer use and their willingness to participate. The survey was administered to all employees (n=150 & n=54) at these two companies. The overall prevalence of neck pain was 64%. In the IT company, 78% of employees reported neck pain; and in the SMPO the prevalence was 40%. There were no significant differences in prevalence based on gender or age. All of the IT company computer users worked more than seven hours at their computers, while 38% of the SMPO workers did so. Chronic pain was present in 48%of the total sample. The ND10-H can be used to assess neck-related disability in Hindi-speaking individuals. It should be accompanied by a valid pain measure when assessing patient outcomes. The prevalence of neck pain is high in computer-using workers in India. / Thesis / Master of Science Rehabilitation Science (MSc) / 1. Translating a newly developed patient-report outcome measure of neck-related disability and testing its psychometric properties. 2. Estimating the prevalence of neck pain in computer-using workers. The first manuscript focusses on cross cultural translation and validation of ND10 (Neck difficulty10) that was designed to measure neck-related disability. A new English outcome measure for neck disability (ND10) was cross culturally translated and validated in computer users in India using forward and backward translation, and cognitive interviewing to determine a final version. The ND10-H demonstrated high reliability (ICC= 0.93) and convergent construct validity with the NDI and DASH (r= 0.78 and 0.86)

The overall aim of this thesis was to develop, deploy and evaluate new IT-based methods for supporting treatment and assessment of treatment of advanced Parkinson’s disease. In this condition a number of different motor and non-motor symptoms occur in episodes of varying frequency, duration and severity. In order to determine outcome of treatment changes, repeated assessments are necessary. Hospitalization for observation is expensive and may not be representative for the situation at home. Paper home diaries have questionable reliability and storage and retrieval of results are problematic. Approaches for monitoring using wearable sensors are unable to address important non-motor symptoms. A test battery system consisting of both self-assessments of symptoms and motor function tests was constructed for a touch screen mobile phone. Tests are performed on several occasions per day during test periods of one week. Data is transmitted over the mobile net to a central server where summaries in different symptom dimensions and an overall test score per patient and test period are calculated. There is a web application that graphically presents the results to treating clinical staff. As part of this work, a novel method for assessment of spiral drawing impairment useful during event-driven sampling was developed. To date, the system has been used by over 100 patients in 10 clinics in Sweden and Italy. Evidence is growing that the test battery is useful, reliable and valid for assessment of symptoms during advanced Parkinson’s disease. Infusion of a levodopa/carbidopa gel into the small intestine has been shown to reduce variation in plasma drug levels and improve clinical response in this patient category. A pharmacokinetic-pharmacodynamic model of this intestinal gel infusion was constructed. Possibly this model can assist the process of individualization of dosage for this treatment through in numero simulations. Results from an exploratory data analysis indicate that severity measures during oral levodopa treatment may be factors to consider when deciding candidates for infusion treatment.

During recent decades, lumbar spinal stenosis (LSS) has become the most common indication for spine surgery, a change that coincides with a higher worldwide prevalence of overweight and obesity. Thus, surgical treatment of LSS in the overweight and obese population is common and increasing in scope. The overall aim of this thesis was to investigate whether body mass index (BMI) is related to the development of LSS, and whether BMI is linked to outcome after surgery for LSS. We further evaluated whether there are specific experiences of LSS from a patient perspective. Data were obtained for all patients registered in the Swedish Spine Register who had undergone surgery for LSS between January 1, 2006 and June 30, 2008. After adjusting for differences in baseline characteristics, patients with obesity showed both poorer results after surgery and a higher rate of dissatisfaction than patients with normal weight (odds ratio 1.73; 95% confidence interval, CI, 1.36-2.19). Furthermore, patients with obesity in the cohort reported modest weight loss at follow-up (2.0 kg; 95% CI, 1.5-2.4), and only 8% reported a clinical important weight loss 2 years after surgery. Our analysis of 389,132 construction workers, showed that overweight (incidence rate ratio, IRR 1.68; 95% CI, 1.54-1.83) and obesity (IRR 2.18; 95% CI, 1.87-2.53) were associated with an increased future risk in developing LSS when compared with patients with normal weight. To gain insight into the patients' perspective of LSS, we performed interviews with 18 patients who were on a waiting list for LSS surgery. The transcripts, analyzed with content analysis, revealed that living with LSS is a physical, mental and social challenge in which resources to cope with the condition are of major importance. In summary, obesity is associated with poorer results after surgery, and patients with obesity report modest weight loss during follow-up. In addition, obesity is associated with an increased risk to develop LSS. Our findings revealed that being a patient with LSS, naturally involves considerable suffering and pain, but it also implies being a person with his or her own resources who is able to cope with these adverse conditions.

The rising rates of high-risk behaviours, such as substance abuse, unsafe sexual practices and violence in South African schools, have accentuated the need for intervention and prevention programmes in the education system. High-risk behaviour is related to changes and uncertainties at community level. The traditional values and behavioural codes are undermined and there is no corrective action from the community to control this behaviour. This study describes the need for support of adolescents, who are in a state of development and change and whose abilities are increasingly being tested by stress factors from a rapidly changing environment. To meet these needs for support, an experimental peer support programme was implemented in schools. Peer support involves the provision of information about healthy lifestyles and high-risk behaviour, such as substance abuse, crime and HIV/AIDS-related aspects. Through peer support, healthy lifestyles can be modelled, and a forum for the discussion of problems established. Peer supporters can assist their peers in dealing with problems and a context can be created in which new and healthier behavioural patters can develop. Peer support is important because educators and teachers are unable to manage the large number of learners who are experiencing problems and schools offer limited professional psychological support to learners. The objectives mainly entailed the prevention of high-risk behaviour related to HIV/AIDS, crime and substance abuse, as well as the enhancement of learners’ psychological well-being and the social climate in schools. The peer support system was implemented in four experimental schools and four similar schools served as a control group. The schools involved were selected by means of a stratified sampling method. A total amount of 2045 respondents between the ages of 12 and 21 years participated in this study. The peer support system was evaluated in terms of a pre and post-measurement in order to determine the impact of the system on the schools and learners in the schools, and to determine whether the set objectives have been achieved. The hypothesis was that the peer support system would have a positive effect in reducing high-risk behaviour and improving the psychological well-being of learners. A questionnaire was used as a pre and post-measurement tool to determine whether there had been significant changes and/or improvements regarding high-risk behaviour, crime, school climate and psychological well-being in the school system. The experimental and control school communities were compared. Significant differences were found between the experimental group and the control group in terms of behavioural problems in the school, school climate, high-risk sexual behaviour and psychological well-being. Learners’ perception of problem behaviour in the school remained unchanged in the experimental group, whilst the control group’s measurements became statistically significantly (p<0,05) more negative over time. A statistically significant difference at the 5% significance level was found between the control group’s pre and post-measurements regarding learners’ experience of the school climate. The control group’s experience had become more negative at post-measurement, whilst the experimental group’s experience had remained unchanged over time. A statistically significant difference was found between the experimental and control groups (p<0,001) in respect of the level of sexual experience. The number of sexually experienced learners in the control group had increased at post-measurement, whilst the level of learners’ sexual experience had remained constant in the experimental group. Furthermore, a significant increase (p<0,001) was found in the level of sexual activity among the control group during the last 30 days, but not in the experimental group. This implicates that the intervention has had a preventative effect that counters the normal tendency of increased sexual activity with age. More than 60% of learners viewed their friends as sexually experienced. The perceived group norm for the experimental group remained the same over 18 months, whereas a significant increase (p<0,001) was found in the control group. No decrease was found in the psychological well-being of learners in the experimental group at post-measurement, whereas that of the control group had decreased significantly (p<0,05). No statistically significant differences were found for substance abuse and personal control of risk among learners. Although many other variables could play a role in these changes, the conclusion can be made that the peer support system probably had a preventative effect in schools. The study further indicates that approximately two thirds of all learners had been aware of the system and about 40% had used it. The peer system was generally evaluated as positive and the biggest problems were related to the implementation and organization of the system, as well as the confidentiality of information. Recommendations have been made regarding the improvement of project implementation. If enhanced co-operation from school staff can be obtained during implementation of the intervention, the peer support system could function better and a bigger impact in schools could be achieved. In conclusion, it is important that intervention programmes be promoted efficiently in schools in order to facilitate optimal functioning. / Dissertation (MA (Research Psychology))--University of Pretoria, 2006. / Psychology / unrestricted

Background: Patient empowerment is viewed as a priority by policy makers, patients and practitioners worldwide. Although there are a number of measures available, none have been developed specifically for patients in the UK with long-term conditions. It is the aim of this study to report the development and preliminary validation of an empowerment instrument for patients with long-term conditions in primary care.Methods: The study involved three methods. Firstly, a systematic review was conducted to identify existing empowerment instruments, and to describe, compare and appraise their content and quality. The results supported the need for a new instrument. Item content of existing instruments helped support development of the new instrument. Secondly, empowerment was explored in patients with long-term conditions and primary care practitioners using qualitative methods, to explore its meaning and the factors that support or hinder empowerment. This led to the development of a conceptual model to support instrument development. Thirdly, a new instrument for measuring empowerment in patients with long-term conditions in primary care was developed. A cross-sectional survey of patients was conducted to collect preliminary data on acceptability, reliability and validity, using pre-specified hypotheses based on existing theoretical and empirical work. Results: Nine instruments meeting review inclusion criteria were identified. Only one instrument was developed to measure empowerment in long-term conditions in the context of primary care, and that was judged to be insufficient in terms of content and purpose. Five dimensions (‘identity’, ‘knowledge and understanding’, ‘personal control’, personal decision-making’, and ‘enabling other patients’) of empowerment were identified through published literature and the qualitative work and incorporated into a preliminary version of the new instrument. A postal survey achieved 197 responses (response rate 33%). Almost half of the sample reported circulatory, diabetic or musculoskeletal conditions. Exploratory factor analysis suggested a three factor solution (‘identity’, ‘knowledge and understanding’ and ‘enabling’). Two dimensions of empowerment (‘identity’ and ‘enabling’) and total empowerment showed acceptable levels of internal consistency. The measure showed relationships with external measures (including quality of chronic illness care, self-efficacy and educational qualifications) that were generally supportive of its construct validity.Conclusion: Initial analyses suggest that the new measure meets basic psychometric criteria and has potential for the measurement of patient empowerment in long-term conditions in primary care. The scale may have a role in research on quality of care for long-term conditions, and could function as a patient-reported outcome measure. However, further validation is required before more extensive use of the measure.