manikagita / hid335 Goto Github PK

---
owner:
    hid: 335
    name: Sean Shiverick
    firtsname: Sean
    lastname: Shiverick
    latitude: "32.840054 N"
    longitude: "-96.697841 W"
    city: Dallas, TX, U.S.A.
    url: https://github.com/bigdata-i523/hid335
paper1:
    author:
        - Sean M. Shiverick
    hid:
        - 335
    title: >
        Big Data Analytics, Data Mining, and Public Health
        Informatics: Using Data Mining of Social Media to Track
        Epidemics
    abstract: >
        Data mining of internet search queries and social media for
        influenza related keywords has been used to track seasonal
        influenza and correlates highly with official reports of
        `infuenza-like-illness' (ILI). Efforts to monitor epidemics
        using big data analytics can provide early detection that
        supplements existing systems of disease surveillance.  A
        review of the literature shows that data extracted from social
        media has applications for public health
        informatics. Prediction models based on social media work best
        in areas with a high degree of internet access.
    url: https://github.com/bigdata-i523/hid335/blob/master/paper1/
    type: latex
    status: 10/25/17 100%
    chapter: Health
paper2:
    review: Nov 6 2017
    author:
        - Sean M. Shiverick
    chapter: Health
    hid:
        - 335
    title: >
        Big Health Data from Wearable Electronic Sensors (WES)
        and the Treatment of Opioid Addiction
    abstract: >
        Wearable electronic sensors (WES) and mobile health
        applications can be used to collect vital health data to
        supplement traditional forms of treatment for opioid addiction
        and may be used to predict risk factors related to overdose
        death.
    url: https://github.com/bigdata-i523/hid335/blob/master/paper2/
    type: latex
    status: 100%
project:
    type: project
    author:
        - Sean Shiverick
    hid:
        - 335
    title: >
        Using Machine Learning Classification of Opioid Addiction for
        Big Data Health Analytics
    abstract: >
        Classification of opioid addiction can identify important
        features relevant for predicting drug abuse and overdose
        death. Machine learning procedures were used on data from a
        large National Survey of Drug Use and Health (NSDUH-2015) to
        classify individuals for illicit opioid use according to
        demographic characteristics and mental health attributes (e.g.,
        depression). Classification models of opioid addiction can be
        extended for big data health analytics to include
        high-dimensional datasets, data collected over previous years,
        or expanded to the larger population of patients taking
        prescription opioid medication. The results seek to raise
        awareness of risk factors related to opioid addiction among
        patients and medication prescribers, and help decrease the risk
        of opioid overdose death.
    url: https://github.com/bigdata-i523/sample-pid000/project/report.pdf
    dataset: >
        National Survey on Drug Use and Health (NSDUH) 2015
        Substance Abuse and Mental Health Data Archive
        U.S. Department of Health and Human Services (HHS)
        https://www.datafiles.samhsa.gov/study-dataset/national-survey-drug-use-and-health-2015-nsduh-2015-ds0001-nid16894
        size TBD
    analytics: Machine Learning
    application: Health Analytics
    chapter: Health
    keywords: Health Analytics, Machine Learning, Opioid Addiction, i523, hid335
    status: 100%