A comparison of regression methods for remote tracking of Parkinson’s disease progression

Remote patient tracking has recently gained increased attention, due to its lower cost and non-invasive nature. In this paper, the performance of Support Vector Machines (SVM), Least Square Support Vector Machines (LS-SVM), Multilayer Perceptron Neural Network (MLPNN), and General Regression Neural Network (GRNN) regression methods is studied in application to remote tracking of Parkinson’s disease progression. Results indicate that the LS-SVM provides the best performance among the other three, and its performance is superior to that of the latest proposed regression method published in the literature.     

Nurturing health-related online support groups: Exploring the experiences of patient moderators

The aim of this study was to examine the views of moderators across a diverse and geographically broad range of online support groups about their moderator experiences and to explore both the personal benefits as well as challenges involved. Thirty-three patient moderators completed an online questionnaire which included a series of open-ended questions. Thematic analysis identified three themes: emergence, empowerment, nurturing. Several moderators declared their own diagnosis and for some, being able to share personal insights motivated them to establish the group and in turn offered validation. They felt empowered by helping others and learned more about the condition through accessing the “communal brain”. Some felt the group aided patients’ access to health services and their ability to communicate with health professionals while others worried about them becoming over-dependent. Moderators described needing to nurture their group to ensure it offered a safe space for members. Clear rules of engagement, trust, organisation skills, compassion and kindness were considered essential. Patient moderated online support groups can be successfully developed and facilitated and can be empowering for both the group member and moderator alike.     

Parkinson’s disease classification using gait characteristics and wavelet-based feature extraction

This paper proposes a method to classify idiopathic PD patients and healthy controls using both the gait characteristics of idiopathic PD patients and wavelet-based feature extraction. Using the characteristics of idiopathic PD patients who shuffle their feet while they are walking, we implemented the following three preprocessing methods: (i) we used the difference between two signals that each represented the sum of eight sensor outputs from one foot; (ii) we used the difference between the maximum and minimum records among the vertical ground reaction force outputs from the eight sensors under the left foot; and (iii) we used method (i) again, but on the signals each obtained from one foot by method (ii). After thus conducting the three preprocessing tasks, we created approximation coefficients and detail coefficients using wavelet transforms (WTs). Then, we extracted 40 features from these coefficients by using statistical approaches, including frequency distributions and their variabilities. Using the 40 features as inputs to the neural network with weighted fuzzy membership functions (NEWFM), we compared the performances of the three abovementioned methods. When idiopathic PD patients and healthy controls were classified using the NEWFM, the accuracy, specificity, and sensitivity of the results were, respectively, as follows: 74.32%, 81.63%, and 73.77% by method (i); 75.18%, 74.67%, and 75.24% by method (ii); or 77.33%, 65.48%, and 81.10% by method (iii).     

Effects of disease and leader type on moderators in online support groups

This study examines the effects of illness (cancer and Parkinson’s [PD]) on three moderators, the expression of positive and negative emotions and cognitive mechanisms. Each illness makes its own unique demands on patients and may influence change mechanisms. Similarly, we are asking, what effects do the type of leadership have on mediators that have previously been linked to positive outcomes. Four types of groups were studied, professional, the wellness community (TWC) chat mixed cancer (N groups = 4) and TWC chat PD patient groups (N groups = 6). The two peer groups were bulletin boards for colorectal cancer (N groups = 1) and PD BBs (N groups = 6). The design was a 2×2, disease and leader type. Computer-based text analysis, the linguistic inquiry and word count assessed the dependent variables. The results of the Manova found that; disease is P = NS, leader type, P = .00, interaction, P = .00. The interaction between disease and leader type is statistically significant, indicating that disease in combination with whether the leader is a peer or professional effects the expression of emotions and cognitive mechanisms.     

First do no harm: Cross-sectional and longitudinal evidence for the impact of individual suicidality on the use of online health forums and support groups

Suicide is a leading cause of death worldwide, especially among the young. This study aims to disentangle the presumed causality between the use of online health forums or support groups and suicidality using a representative telephone survey and a two-wave online panel survey containing the same question wording. Cross-sectional data show positive correlations between suicidality and online health forum use, but not limited to the younger. Using longitudinal panel data and autoregressive models, a positive cross-lagged effect of suicidality on internet-based health forum use one month later was revealed. Despite the wide-spread notion that online health forums can increase suicidality the present study provides evidence for the preventive potential of accessible and helpful information online.     

Empowering processes in online support groups among people living with HIV/AIDS: A comparative analysis of ‘lurkers’ and ‘posters’

The proliferation of online support groups provides an opportunity for individuals living with HIV/AIDS to obtain support online. The present study aimed to explore how different levels of participation in online support groups are associated with empowering processes and outcomes for individuals living with HIV/AIDS. A total of 340 individuals living with HIV/AIDS were recruited. They completed an online questionnaire consisting of measures on satisfaction with online support groups, empowering processes, self-care self efficacy, loneliness, optimism, coping, depression, and health-related quality of life. Results revealed that compared to posters, members who only read the messages (lurkers) scored lower in receiving social support and receiving useful information in empowering processes, and lower in satisfaction with their relationship with group members. They also scored higher in distraction and lower in planning in the brief COPE. In addition, they scored lower in social function and higher in energy. There were no significant differences in self-care self efficacy, loneliness, depression, or optimism between posters and lurkers. Our results suggest that lurking in the online support groups may be as empowering as reading and posting messages to the groups. More research is needed to identify the long term effects of online support group use.     

The structure of support: Mapping network evolution in an online support group

Online social support groups enable individuals to create specialized networks that provide access to a variety of resources. Although the efficacy of such communities has been studied, less understood are the structural mechanisms behind their emergence and the ways these mechanisms foster ties and may subsequently affect provision of support. This paper analyzes an online support group (OSG) for parents of children with ADD/ADHD over a one-year period, focusing on the interplay of structure and technology in the creation of the emergent support network. Findings highlight a dual network structure that supports a variety of relationships and levels of participation. Whereas a core group of members generates the initial content, the network becomes self-sustaining and supports a fluid membership between active and inactive members. Structurally, the network offers four types of support: direct, indirect, relational, and functional. Together, findings emphasize the interplay among technology, structure, and communication in advancing specialized channels of communication in a digital age.     

Using discussion logic in analyzing online group discussions: A text mining approach

We propose a Discussion Logic-based Text Analytics (DiLTA) framework, which combines theories developed in social science and text mining fields. The framework extracts features that uncover discussion logic and uses these features in analyzing online discussions. A series of models are proposed including conversation disentanglement, coherence analysis, and visualization. Validation experiments showed that DiLTA achieved significantly superior performance over existing text analytics methods in reconstructing internal structure. A case study using DiLTA-enabled visualization on a healthcare forum illustrates the great potential of DiLTA in assisting comprehension of the internal linkage, structure, and logic of online group discussions.     

The effect of communication and synchronization on Amdahl’s law in multicore systems

This work analyses the effects of sequential-to-parallel synchronization and inter-core communication on multicore performance, speedup and scaling from Amdahl’s law perspective. Analytical modeling supported by simulation leads to a modification of Amdahl’s law, reflecting lower than originally predicted speedup, due to these effects. In applications with high degree of data sharing, leading to intense inter-core connectivity requirements, the workload should be executed on a smaller number of larger cores. Applications requiring intense sequential-to-parallel synchronization, even highly parallelizable ones, may better be executed by the sequential core. To improve the scalability and performance speedup of a multicore, it is as important to address the synchronization and connectivity intensities of parallel algorithms as their parallelization factor.     

Detection of Parkinson’s Disease with Multiple Feature Extraction Models and Darknet CNN Classification

Parkinson’s disease (PD) is a neurodegenerative disease in the central nervous system. Recently, more researches have been conducted in the determination of PD prediction which is really a challenging task. Due to the disorders in the central nervous system, the syndromes like off sleep, speech disorders, olfactory and autonomic dysfunction, sensory disorder symptoms will occur. The earliest diagnosing of PD is very challenging among the doctors community. There are techniques that are available in order to predict PD using symptoms and disorder measurement. It helps to save a million lives of future by early prediction. In this article, the early diagnosing of PD using machine learning techniques with feature selection is carried out. In the first stage, the data preprocessing is used for the preparation of Parkinson’s disease data. In the second stage, MFEA is used for extracting features. In the third stage, the feature selection is performed using multiple feature input with a principal component analysis (PCA) algorithm. Finally, a Darknet Convolutional Neural Network (DNetCNN) is used to classify the PD patients. The main advantage of using PCA- DNetCNN is that, it provides the best classification in the image dataset using YOLO. In addition to that, the results of various existing methods are compared and the proposed DNetCNN proves better accuracy, performance in detecting the PD at the initial stages. DNetCNN achieves 97.5 % of accuracy in detecting PD as early. Besides, the other performance metrics are compared in the result evaluation and it is proved that the proposed model outperforms all the other existing models.     

Looking for trouble: A multilevel analysis of disagreeable contacts in online social networks

Identifying characteristics of troublemakers in online social networks, those contacts who violate norms via disagreeable or unsociable behaviour, is vital for supporting preventative strategies for undesirable, psychologically damaging online interactions. To date characterising troublemakers has relied on self-reports focused on the network holder, largely overlooking the role of network friends. In the present study, information was obtained on 5113 network contacts from 52 UK-based Facebook users (age range 13–45; 75% female) using digitally derived data and in-depth network surveys. Participants rated their contacts in terms of online disagreement, relational closeness and interaction patterns. Characteristics of online troublemakers were explored using binary logistic multilevel analysis. Instances of online disagreement were most apparent in the networks of emerging adults (19–21 years). Contacts were more likely to be identified as online troublemakers if they were well connected within the network. Rates of offline and Facebook exchanges interacted such that contacts known well offline but with low rates of Facebook communication were more likely to be identified as troublemakers. This may indicate that users were harbouring known troublemakers in a bid to preserve offline relationships and reputational status. Implications are discussed in terms of an individual's susceptibility to undesirable encounters online.     

An analysis of social support exchanges in online HIV/AIDS self-help groups

Hundreds of thousands of people sharing concerns about HIV/AIDS have taken advantage of online self-help groups to exchange resources and support. Little research so far has focused on the nature and content of actual messages exchanged by group members. To provide an in-depth understanding of social support exchanges in online HIV/AIDS self-help groups, this study identifies and analyzes the dimensions and corresponding frequencies of exchanged social support as well as the group interactions facilitating those exchanges. A total of 5000 postings created within a 1 year period were randomly selected from a selected online HIV/AIDS forum. Content analysis was then conducted to assess the types and proportions of exchanged social support. A thematic analysis of the postings that could not be categorized with the adopted coding system was performed to find further patterns of positive group interactions. The results show that information support (41.6%) and emotional support (16.0%) were exchanged most frequently, followed by network support (6.8%) and esteem support exchanges (6.4%), whereas tangible assistance was quite rare (0.8%). The authors also suggest that three types of group interactions including sharing personal experience, expression of gratitude, and offering congratulations can facilitate social support exchanges among group members.     

Dual effects of social support seeking in patient-centric online healthcare communities: A longitudinal study

This study investigates exploratory and purposeful social support-seeking behaviors in the patient-centric online healthcare community (POHC). The antecedents and varying effects of the two behaviors on uncertainties in diagnosis and treatment are examined. Two rounds of field surveys are conducted among users in three POHCs. Findings indicate that exploratory and purposeful social support-seeking behaviors exert varying effects on the change in uncertainty in illness and are influenced differently by the perceived information credibility of users, their identification with a community, and the perceived severity of their illness.     

A comparative content analysis of face-to-face vs. asynchronous group decision making

A field experiment was conducted to analyze the process and contents of group discussions. Groups solved a case study either orally or through an asynchronous computer-mediated communication system. Findings show that asynchronous groups had broader discussions and submitted more complete reports than their face-to-face counterparts. However, there was no difference in the ability to transfer information from the discussion to the report; under both conditions, about 15% of the issues mentioned in the discussion were omitted from the final report. In terms of coordination, face-to-face teams covered the case study questions sequentially, while asynchronous groups were more focused on solving their general disagreements.     

A visualisation tool to aid exploration of students’ interactions in asynchronous online communication

Much research in recent years has focused on the introduction of virtual learning environments (VLEs) to universities, documenting practice, and sharing experience ( [Armitage et?al., 2001], [Browne and Jenkins, 2003], [Moron-Garcia, 2004] and [Weller, 2007]). Attention has been directed towards the importance of online dialogue for learning as a defining feature of the VLE.Communicative tools are an important means by which VLEs have the potential to transform learning with computers from being passive and transmissive in nature, to being active and constructivist (Pavey & Garland, 2004). However, practical methods of reviewing and analysing online communication to trace cycles of real dialogue (and learning) have proved somewhat elusive. Qualitative methods are also under-used for VLE discussions, since they demand new sets of research skills for those unfamiliar with them, and can be time intensive.This paper describes a visualisation tool to aid the analysis of online communication. The tool has two purposes: first, it can be used on a day-to-day basis by teachers or forum moderators to review the development of a discussion and to support appropriate interventions. Second, the tool can support research activities since the visualisations generated provide the basis for further qualitative and quantitative analysis of online dialogue.The visualisation software is designed to encode interaction types simply and quickly. The software was tested and then used to analyse data from a sample of forums within the Moodle VLE. The paper discusses both the method of visualisation and analysis of the online interactions as a pilot for further research analysing interaction in discussion forums.     

F-FDG PET imaging analysis for computer aided Alzheimer’s diagnosis

Finding sensitive and appropriate technologies for non-invasive observation and early detection of Alzheimer’s disease (AD) is of fundamental importance to develop early treatments. In this work we develop a fully automatic computer aided diagnosis (CAD) system for high-dimensional pattern classification of baseline ¹⁸F-FDG PET scans from Alzheimer’s disease neuroimaging initiative (ADNI) participants. Image projection as feature space dimension reduction technique is combined with an eigenimage based decomposition for feature extraction, and support vector machine (SVM) is used to manage the classification task. A two folded objective is achieved by reaching relevant classification performance complemented with an image analysis support for final decision making. A 88.24% accuracy in identifying mild AD, with 88.64% specificity, and 87.70% sensitivity is obtained. This method also allows the identification of characteristic AD patterns in mild cognitive impairment (MCI) subjects.     

A comparison of empathic communication pattern for teenagers and older people in online support communities

This article reports a study that investigated the occurrences of empathy in online support communities for teenagers. Qualitative content analysis with 400 messages from a discussion board about depression was used to identify how empathy was expressed in the specific online communication. Emphasis was also placed on the comparison of this age group to older people, by comparing the results with those from a previous study on empathy in an online support community about depression for older people. Specifically, the analysis focused on the frequencies of the categories of the code scheme, linguistic characteristics of the communication content, the occurring components of empathy, and the roles as well as activities of the members. From our analysis, we concluded that young people exchanged a substantial amount of empathic emotional communication when participating in an online support community, and they communicated on a more personal level compared to older people, who tended to engage in a more formal communication. In addition, teenagers also showed a high level of understanding but lower level of concern compared to older persons when expressing empathy online.     

Explaining personality and contextual differences in beneficial role of online versus offline social support: A moderated mediation model

With more than three billion “Netizens” worldwide, online social support obtained through social networking sites (SNS) has a pervasive influence on their users’ affective experiences. Social support generally fosters affective well-being, but such support can also threaten some recipients’ self-esteem that compromises their affective well-being. However, little is known of whether (a) this self-esteem threat varied by the mode (i.e., online vs. offline) of supportive interactions, and (b) such variations were explained by public self-consciousness across distinct modes of supportive interactions. A moderated mediation model was formulated to test these hypothesized personality and contextual differences using a quasi-experimental design. The results revealed that the mode of supportive interactions moderated the relationship between self-esteem and public self-consciousness, indicating that individuals higher in self-esteem are less likely to feel exposed to the potentially unfavorable evaluations in online (vs. offline) supportive interactions. Moreover, the results showed that the heightened levels of public self-consciousness explained the positive link between self-esteem and negative affect in offline but not online supportive interactions, providing further evidence that social support obtained through SNS is likely superior to that obtained through face-to-face interactions.     

Mapping the intellectual structure of research in decision support systems through author cocitation analysis (1971–1993)

This study applies factor analysis of an author cocitation frequency matrix derived from a database file that consists of a total of 23,768 cited reference records taken from 944 citing articles. Factor analysis extracted eleven factors consisting of six major areas of DSS research (group DSS, foundations, model management, interface systems, multicriteria DSS, and implementation) and five contributing disciplines (multiple criteria decision making, cognitive science, organizational science, artificial intelligence, and systems science). This research provides hard evidence that the decision support system has made meaningful progress over the past two decades and is in the process of solidifying its domain and demarcating its reference disciplines. Especially, much progress has been made in the subareas of model management such as representation, model base processing, model integration, and artificial intelligence application to model management leading towards the development of a theory of models. To facilitate the transition from the pre- to post-paradigm period in DSS research, this study has completed important groundwork.     

The process of team communication in multi-cultural contexts: An empirical study using Bales’ interaction process analysis (IPA)

The main goal of the present study was to empirically investigate the manner in which cultural diversity and communication mode affect team communication process. Two independent variables were manipulated in the study: (1) cultural diversity (homogeneous versus heterogeneous); and (2) communication mode (face-to-face versus computer-mediated communication). Team members’ communication exchanges were measured by using Bales’ interaction process analysis (IPA) that divides the function (as opposed to the topical content) of communication during group discussion into either task-related or socio-emotional contributions at two-levels: communication profile and functional area. Results of this study indicated homogeneous teams used more showing agreement, giving opinions, and showing tension communication patterns compared to heterogeneous teams. Additionally, when considering the higher-level functional areas, teams using face-to-face (FTF) communication strategies were characterized by greater positive socio-emotional communication, more attempted answers, more questions, and more frequent negative socio-emotional communications. The results of the present study also suggested that the impact of communication mode on team communication varies by the level of diversity within the team. The outcomes of this research should have a broad impact on the management of a multi-cultural team, a task-oriented team consisting of people with different national cultures. Relevance to industry: Results of the present study should provide valuable insights into the ways in which cultural diversity and communication mode influence the communication mechanisms which take place among members during team interaction.