S016 Memorial Union
Researching the communication structure of online health communities with social network analysis and computational linguistics, a group informatics approach
Online communities are virtual social structures that promote communication among Internet users on various discussion subjects. Research has found that online communities make communication possible for every person and are highly active with almost every Web user being a member of a forum. Online health communities connect people facing health concerns, exchange health information, and offer emotional support. In health care, online support fora are shown to enable emotional support and information sharing.
Objective: This research analyzes the interactions of an online health community and study its participants’ interests and level of engagement. The objective is to develop an informatics pipeline to improve our understanding of informational and social support in online communities and identify highly central participants. The outcome can identify patterns that may be useful more generally across online health forum research.
Methods: Integrating qualitative research methods from grounded theory with computational linguistics and network analysis to aid a more systematic evaluation of the effectiveness of communication in online health communities.
Results: Network and text analyses of online community data project a central and highly influential participant, distribution of participants based on online discussions, correlation of discussion topics, and similarity between participants’ post structure.
S110 Memorial Union
Large-scale biomedical image analysis using Big Data Infrastructure
Biomedical imaging informatics involves the analysis, manipulation, and computational calculation of digitally acquired biomedical images to gain knowledge and insights. Informatics technologies are being developed to assist biomedical researchers to identify meaningful objects from raw images, extract content, process information, discover relationships, and share knowledge. However, as the ‘Big Data’ era arrives, the ever-exploding image quantity, resolution, and imaging modalities are challenging the already computationally intensive methods. Big Data Ecosystem is expected to accelerate the computing speed and therefore leaves more room to improve the efficiency and accuracy of image analysis, storage, retrieval and sharing. Last but not least, researchers are looking for useful informatics tools to not only help them analyze images but also conduct advanced research and education for the whole research community. I am developing a framework based upon the Big Data ecosystem for the analysis of biomedical images with the applications in digital pathology and palynology. Progress and challenges will be presented in this seminar.
Abu Saleh Mohammad MosaDate:
S110 Memorial Union
Developing a Decision Support Software for CINV Prevention
The US National Center for Health Statistics estimated that more than 19 million adults in the US have ever been diagnosed with cancer. Chemotherapy is one of the important modality of cancer treatments. Chemotherapy-Induced Nausea and Vomiting (CINV) are the two most dreadful and unpleasant side effects of chemotherapy. CINV substantially degrades the patients’ life quality (due to dehydration, nutritional deficits, electrolyte imbalance, etc.) and increases the healthcare cost (by requiring further management of CINV including outpatient visits, drugs, hospitalization, etc.). In addition, cancer patients sometimes discontinue chemotherapy due to intolerable CINV. Thus, this is imperative to identify and treat the patients at high-risk of CINV before chemotherapy. In this presentation, the development of a decision support software for improving the prevention of CINV will be discussed.
Knowledge Discovery System for Research Hypothesis Generation from Serendipitous Findings
From the discovery of penicillin and x-rays to the development of many of today’s chemotherapy agents, serendipitous findings tangential to the researcher’s intended purpose, the “That’s funny…” moments, have greatly impacted the health and well-being of society. As an information behavior, these unexpected findings are an example of the Opportunistic Discovery of Information (ODI). ODI has been described in many contexts, from information behavior in virtual worlds to the impact of information encountering on health behaviors. Yet, little is known about instances of ODI within the context of scientific research. A major difficulty in the study of the ODI is the transient nature of the experience. People do not plan to find information unexpectedly, nor is it easy to develop an experimental environment that consistently fosters the ODI experience.
Content analysis may prove to be a useful methodology in revealing instances of ODI in documents, such as journal articles, and can be analyzed for both their manifest content (word use or count) and their latent content (themes and meanings). We believe that the current research literature holds latent references to these ODI experiences and can be systematically analyzed to reveal traces of this human information behavior.
We propose taxonomy of term use indicating the presence of serendipity in the research process and reveal the relationship between the authors’ word choice for serendipity and specific types of ODI experiences.
Model-, structure-, and sequence-based methods for prediction of protein binding sites
Identification of protein-protein binding sites is important in understanding the protein function. The binding site prediction methods that rely on structure are generally more accurate than those ones relying on sequence. However, the coverage of structure-based methods is significantly lower than of the sequence-based method due to the lack of experimental structures.
Here, we propose a sequence-based protein binding site prediction approach that utilizes structure-based methods’ benefits. We utilize L1-regularized logistic regression to integrate sequence- and structure-based predictions for comparative models. The method relies on a series of features, including evaluation of comparative models, geometric features, solvent accessibility, hydrophobicity, secondary structure based on comparative models and name of residues. The non-redundant dataset of feature vectors for training and testing is automatically generated from the hetero-oligomer structures. The assessment of our binding site prediction strategy has demonstrated that it is able to use protein sequences as the only input and obtain comparable accuracies to the state-of-art structure based predictors across different quality levels of homology models. Our method could be useful in the large-scale functional annotation of proteins whose structures are represented only by the comparative models.
« Previous 1 … 19 20 21 22 23 Next »