Simultaneous prediction of symptom severity and cause in data from a test battery for Parkinson patients, using machine learning methods

The main purpose of this thesis project is to prediction of symptom severity and cause in data from test battery of the Parkinson’s disease patient, which is based on data mining. The collection of the data is from test battery on a hand in computer. We use the Chi-Square method and check which variables are important and which are not important. Then we apply different data mining techniques on our normalize data and check which technique or method gives good results.The implementation of this thesis is in WEKA. We normalize our data and then apply different methods on this data. The methods which we used are Naïve Bayes, CART and KNN. We draw the Bland Altman and Spearman’s Correlation for checking the final results and prediction of data. The Bland Altman tells how the percentage of our confident level in this data is correct and Spearman’s Correlation tells us our relationship is strong. On the basis of results and analysis we see all three methods give nearly same results. But if we see our CART (J48 Decision Tree) it gives good result of under predicted and over predicted values that’s lies between -2 to +2. The correlation between the Actual and Predicted values is 0,794in CART. Cause gives the better percentage classification result then disability because it can use two classes.

HAPPINESS INDEXTHE CONSTRUCTION AND ANALYSIS

This study aims to investigate the important indicators that contribute to happiness among Beijing residence. The residents of Beijing were taken as the target population for the survey. A questionnaire was used as the main statistical instrument to collect the data from the residents in Beijing. In so doing the investigation employs Factor analyses and chi-square analyses as the main statistical tools used for the analyses in this research. The study found that Beijing residents gained greater happiness in the family, interpersonal relationships, and health status. The analysis also shows that generally, the residence of Beijing feels happier and also in terms of gender basis, females in Beijing feel happier as compare to their male counterpart. It will find that gender, age and education are statistically significant when dealing with happiness.

Amningsduration vid sectio och vaginalförlossning : Breastfeeding duration at cesarean section and vaginal delivery. Apopulationbased register study.

Bakgrund: Amning är av stor betydelse för det nyfödda barnet och mamma, både ur närings- och trygghetsaspekter. Tidigare studier om sambandet mellan förlossningssätt och amning visar motstridiga resultat; vissa studier indikerar att sectio påverkar amningen negativt medan andra studier inte visar på något samband.Syftet: Att undersöka huruvida det finns demografiska och hälsorelaterade skillnader hos mammor gällande förlossningssätt samt om förlossningssätt påverkar amningsdurationen upp till två månaders ålder.Metod: Studien har en populationsbaserad kohortdesign och omfattar n= 35250 mamma-barn par i Örebro- och Uppsala län, där barnet fötts åren 1993-2001. Statistiska analyser har genomförts med Chi-square test, binär logistisk regressionsanalys och multivariat logistik regressionsanalys.Resultat: Visade att mammor som förlösts med sectio ammade i lägre utsträckning vid två månaders ålder i jämförelse med mammor som förlösts vaginalt. Många riskfaktorer identifierades för en ökad risk att förlösas med sectio: län, hälsofaktorer hos mamma och barn, paritet, mammans ålder, rökning samt socioekonomiska faktorer. Resultatet kan hjälpa barnmorskan i hennes profession, genom att kunskap erhålls om dessa samband. Barnmorskan kan därmed identifiera riskfaktorer, arbeta förebyggande och underlätta initieringen av amning.Konklusion: Barnmorskor kan med hjälp av denna studie öka medvetenheten hos vårdpersonal angående sectioförlösta mammors behov av extra stöd vid initiering av amning.

Health and quality of care from older peoples' and formal caregivers' perspective

Aim: The overall aim of this thesis was to gain a deeper understanding of older people's view of health and care while dependent on community care. Furthermore to describe and compare formal caregivers' perceptions of quality of care, working conditions, competence, general health, and factors associated with quality of care from the caregivers' perspective. Method: Qualitative interviews were conducted with 19 older people in community care who were asked to describe what health and ill health((I), good and bad care meant for them (II). Data were analyzed using content analysis (I) and a phenomenological analysis (II). The formal caregivers; 70 nursing assistants (NAs) 163 enrolled nurses (ENs) and 198 registered nurses (RNs), answered a questionnaire consisting of five instruments: quality of care from the patient's perspective modified to formal caregivers, creative climate questionnaire, stress of conscience, health index, sense of coherence and items on education and competence (III). Statistical analyses were performed containing descriptive statistics, and comparisons between the occupational groups were made using Kruskal-Wallis ANOVA, Mann-Whitney U-test and Pearson's Chi-square test (III). Pearson's  product moment correlation analysis and multiple regression analysis were performed studying the associations between organizational climate, stress of conscience, competence, general health and sense of coherence with quality of care (IV). Results: The older people's health and well-being were related to their own ability to adapt to and compensate for their disabilities and was described as negative and positive poles of autonomy vs. dependence, togetherness vs. being an onlooker, security vs. insecurity and tranquility vs. disturbance (I).  The meaning of good care (II) was that the formal caregivers respected the older people as unique individuals, having the opportunity to live their lives as usual and receiving a safe and secure care. Good care could be experienced when the formal caregivers had adequate knowledge and competence in caring for older people, adequate time and continuity in the care organization (II). Formal caregivers reported higher perceived quality of care in the dimensions medical-technical competence and physical-technical conditions than in identity-oriented approach and socio-cultural atmosphere (III). In the organizational climate three of the dimensions were close to the value of a creative climate and in seven near a stagnant climate. The formal caregivers reported low rate of stress of conscience. The RNs reported to a higher degree than the NAs/ENs a need to gain more knowledge, but the NAs and the ENs more often received training during working hours. The RNs reported lower emotional well-being than the NAs/ENs (III). The formal caregivers' occupation, organizational climate and stress of conscience were associated with perceived quality of care (IV). Implications: The formal caregivers should have an awareness of the importance of kindness and respect, supporting the older people to retain control over their lives. The nursing managers should employ highly competent and adequate numbers of skilled formal caregivers, organize formal caregivers having round the clock continuity. Improvements of organizational climate and stress of conscience are of importance for good quality of care.

Predictive models for chronic renal disease using decision trees, naïve bayes and case-based methods

Data mining can be used in healthcare industry to “mine” clinical data to discover hidden information for intelligent and affective decision making. Discovery of hidden patterns and relationships often goes intact, yet advanced data mining techniques can be helpful as remedy to this scenario. This thesis mainly deals with Intelligent Prediction of Chronic Renal Disease (IPCRD). Data covers blood, urine test, and external symptoms applied to predict chronic renal disease. Data from the database is initially transformed to Weka (3.6) and Chi-Square method is used for features section. After normalizing data, three classifiers were applied and efficiency of output is evaluated. Mainly, three classifiers are analyzed: Decision Tree, Naïve Bayes, K-Nearest Neighbour algorithm. Results show that each technique has its unique strength in realizing the objectives of the defined mining goals. Efficiency of Decision Tree and KNN was almost same but Naïve Bayes proved a comparative edge over others. Further sensitivity and specificity tests are used as statistical measures to examine the performance of a binary classification. Sensitivity (also called recall rate in some fields) measures the proportion of actual positives which are correctly identified while Specificity measures the proportion of negatives which are correctly identified. CRISP-DM methodology is applied to build the mining models. It consists of six major phases: business understanding, data understanding, data preparation, modeling, evaluation, and deployment.

No consensus on gestational diabetes mellitus screening regimes in Sweden : pregnancy outcomes in relation to different screening regimes 2011 to 2012, a cross-sectional study

Background: Although associated adverse pregnancy outcomes, no international or Swedish consensus exists that identifies a cut-off value or what screening method to use for definition of gestational diabetes mellitus. This study investigates the following: i) guidelines for screening of GDM; ii) background and risk factors for GDM and selection to OGTT; and iii) pregnancy outcomes in relation to GDM, screening regimes and levels of OGTT 2 hour glucose values. Methods: This cross-sectional and population-based study uses data from the Swedish Maternal Health Care Register (MHCR) (2011 and 2012) combined with guidelines for GDM screening (2011-2012) from each Maternal Health Care Area (MHCA) in Sweden. The sample consisted of 184, 183 women: 88, 140 in 2011 and 96,043 in 2012. Chi-square and two independent samples t-tests were used. Univariate and multivariate logistic regression analyses were performed. Results: Four screening regimes of oral glucose tolerance test (OGTT) (75 g of glucose) were used: A) universal screening with a 2-hour cut-off value of 10.0 mmol/L; B) selective screening with a 2-hour cut-off value of 8.9 mmol/L; C) selective screening with a 2-hour cut-off value of 10.0 mmol/L; and D) selective screening with a 2-hour cut-off value of 12.2 mmol/L. The highest prevalence of GDM (2.9%) was found with a 2-hour cut-off value of 8.9 mmol/L when selective screening was applied. Unemployment and low educational level were associated with an increased risk of GDM. The OR was 4.14 (CI 95%: 3.81-4.50) for GDM in obese women compared to women with BMI <30 kg/m(2). Women with non-Nordic origin presented a more than doubled risk for GDM compared to women with Nordic origin (OR = 2.24; CI 95%: 2.06-2.43). Increasing OGTT values were associated with increasing risks of adverse pregnancy outcomes. Conclusions: There was no consensus regarding screening regimes for GDM from 2011 through 2012 when four different regimes were applied in Sweden. Increasing levels of OGTT 2-hour glucose values were strongly associated with adverse pregnancy outcomes. Based on these findings, we suggest that Sweden adopts the recent recommendations of the International Association of Diabetes and Pregnancy Study Group (IADPSG) concerning the performance of OGTT and the diagnostic criteria for GDM.