Classification of Parkinson’s Disease using MultiPass Lvq,Logistic Model Tree,K-Star for Audio Data set : Classification of Parkinson Disease using Audio Dataset

Parkinson's disease (PD) is a degenerative illness whose cardinal symptoms include rigidity, tremor, and slowness of movement. In addition to its widely recognized effects PD can have a profound effect on speech and voice.The speech symptoms most commonly demonstrated by patients with PD are reduced vocal loudness, monopitch, disruptions of voice quality, and abnormally fast rate of speech. This cluster of speech symptoms is often termed Hypokinetic Dysarthria.The disease can be difficult to diagnose accurately, especially in its early stages, due to this reason, automatic techniques based on Artificial Intelligence should increase the diagnosing accuracy and to help the doctors make better decisions. The aim of the thesis work is to predict the PD based on the audio files collected from various patients.Audio files are preprocessed in order to attain the features.The preprocessed data contains 23 attributes and 195 instances. On an average there are six voice recordings per person, By using data compression technique such as Discrete Cosine Transform (DCT) number of instances can be minimized, after data compression, attribute selection is done using several WEKA build in methods such as ChiSquared, GainRatio, Infogain after identifying the important attributes, we evaluate attributes one by one by using stepwise regression.Based on the selected attributes we process in WEKA by using cost sensitive classifier with various algorithms like MultiPass LVQ, Logistic Model Tree(LMT), K-Star.The classified results shows on an average 80%.By using this features 95% approximate classification of PD is acheived.This shows that using the audio dataset, PD could be predicted with a higher level of accuracy.

Separation and Execution of graphical engine on a cross platform IDE to enhance performance

“Biosim” is a simulation software which works to simulate the harvesting system.This system is able to design a model for any logistic problem with the combination of several objects so that the artificial system can show the performance of an individual model. The system will also describe the efficiency, possibility to be chosen for real life application of that particular model. So, when any one wish to setup a logistic model like- harvesting system, in real life he/she may be noticed about the suitable prostitution for his plants and factories as well as he/she may get information about the least number of objects, total time to complete the task, total investment required for his model, total amount of noise produced for his establishment in advance. It will produce an advance over view for his model. But “Biosim” is quite slow .As it is an object based system, it takes long time to make its decision. Here the main task is to modify the system so that it can work faster than the previous. So, the main objective of this thesis is to reduce the load of “Biosim” by making some modification of the original system as well as to increase its efficiency. So that the whole system will be faster than the previous one and performs more efficiently when it will be applied in real life. Theconcept is to separate the execution part of ”Biosim” form its graphical engine and run this separated portion in a third generation language platform. C++ is chosenhere as this external platform. After completing the proposed system, results with different models have been observed. The results show that, for any type of plants of fields, for any number of trucks, the proposed system is faster than the original system. The proposed system takes at least 15% less time “Biosim”. The efficiency increase with the complexity of than the original the model. More complex the model, more efficient the proposed system is than original “Biosim”.Depending on the complexity of a model, the proposed system can be 56.53 % faster than the original “Biosim”.

Modeling Hospital Readmissions in Dalarna County, Sweden

Unplanned hospital readmissions increase health and medical care costs and indicate lower the lower quality of the healthcare services. Hence, predicting patients at risk to be readmitted is of interest. Using administrative data of patients being treated in the medical centers and hospitals in the Dalarna County, Sweden, during 2008 – 2016 two risk prediction models of hospital readmission are built. The first model relies on the logistic regression (LR) approach, predicts correctly 2,648 out of 3,392 observed readmission in the test dataset, reaching a c-statistics of 0.69. The second model is built using random forests (RF) algorithm; correctly predicts 2,183 readmission (out of 3,366) and 13,198 non-readmission events (out of 18,982). The discriminating ability of the best performing RF model (c-statistic 0.60) is comparable to that of the logistic model. Although the discriminating ability of both LR and RF risk prediction models is relatively modest, still these models are capable to identify patients running high risk of hospital readmission. These patients can then be targeted with specific interventions, in order to prevent the readmission, improve patients’ quality of life and reduce health and medical care costs.

Förändrade intimitetsformer bland äldre i det senmoderna samhället

Changing forms of intimacy among older people in late modern society The purpose of this paper is to draw attention to a neglected reality in Swedish social research: New romantic relationships in later life. Our theoretical points of departure are the transformation of intimacy and the transition from a culture of marriage to a culture of divorce. We ask if the transformation of intimacy has reached later life and investigate late life divorce, attitudes to and choice of union form in late life heterosexual relationships, relationship history and the importance of a relationship for life satisfaction. The results, which are based both on demographic data and a survey to 60–90 year old Swedes (n=1225), show that changing relationship patterns in late modern Sweden have reached older people. In romantic relationships initiated in later life LAT is the preferred union form, followed by cohabitation, while marriage is a rare choice. In some respects this makes older people an avant-garde in the investigation of alternative union forms. The results also show the importance of romantic relationships for life satisfaction in later life – independent of union form. Finally we criticize Swedish census data, which is based on civil status, for giving a somewhat distorted image of older people’s family and romantic lives.    

Usual clinical practice for early supported discharge after stroke with continued rehabilitation at home : an observational comparative study

Introduction: Based on randomised controlled trials, evidence exists that early supported discharge (ESD) from the hospital with continued rehabilitation at home has beneficial effects after stroke; however, the effects of ESD service in regular clinical practice have not been investigated. The purpose of the current study was to compare ESD service with conventional rehabilitation in terms of patient outcomes, caregiver burden at 3 and 12 months and the use and costs of healthcare during the first year after stroke. Material and methods: This study was a subgroup analysis of a longitudinal observational study of patients who received care in the stroke unit at Karolinska University Hospital in Sweden. Patients who met the inclusion criteria for ESD in previous experimental studies were included. The patients were referred to available rehabilitation services at discharge, and comparisons between those who received ESD service (the ESD group, n = 40) and those who received conventional rehabilitation (the NoESD group, n = 110) were performed with regard to independence in activities of daily living (ADL), the frequency of social activities, life satisfaction, and caregiver burden and the use and costs of healthcare during the first year after stroke. Results: At 3 and 12 months, no differences were observed with regard to patient outcomes; however, ESD was associated with a lower caregiver burden (p = 0.01) at 12 months. The initial length of stay (LOS) at the hospital was 8 days for the ESD group and 15 days for the NoESD group (p = 0.02). The median number of outpatient rehabilitation contacts was 20.5 for the ESD group (81% constituting ESD service) and 3 for the NoESD group (p<0.001). There was no difference between the groups with regard to overall healthcare costs. Conclusions: ESD service in usual clinical practice renders similar health benefits as conventional rehabilitation but a different pattern of resource use and with released capacity in acute stroke care.

Self-reported fatigue and associated factors six years after stroke

Several studies have found that fatigue is one of the most commonly reported symptoms after stroke and the most difficult to cope with. The present study aimed to investigate the presence and severity of self-reported fatigue six years after stroke onset and associated factors. The cohort "Life After Stroke Phase I" (n = 349 persons) was invited at six years to report fatigue (Fatigue Severity Scale 7-item version), perceived impact of stroke and global recovery after stroke (Stroke Impact Scale), anxiety and depression (Hospital Anxiety and Depression Scale), life satisfaction (Life Satisfaction Checklist) and participation in everyday social activities (Frenchay Activities Index). At six years 37% of the 102 participants in this cross-sectional study reported fatigue. The results showed that in nearly all SIS domains the odds for post-stroke fatigue were higher in persons with a higher perceived impact. Furthermore, the odds for post-stroke fatigue were higher in those who had experienced a moderate/severe stroke and had signs of depression and anxiety. Fatigue is still present in one-third of persons as long as six years after stroke onset and is perceived to hinder many aspects of functioning in everyday life. There is an urgent need to develop and evaluate interventions to reduce fatigue.