Series
Computational Health Distinguished Lecture Series

Permanent Link
https://hdl.handle.net/1853/70860
Series Type
Event Series
Description
Associated Organization(s)
Associated Organization(s)
Organizational Unit

Filters

2016 - 2017 4
4
4
4
4
4
Reset filters

Settings

Publication Search Results

Now showing 1 - 4 of 4
  • No Thumbnail Available
    Item
    Physics of the Medical Record
    ( 2017-03-16) Hripcsak, George
    Dr. George Hripcsak will discuss the national push for electronic health records that will make an unprecedented amount of clinical information available for research, with approximately one billion patient visits documented per year in the US. These data may lead to discoveries that improve understanding of biology, aid the diagnosis and treatment of disease, and permit the inclusion of diverse populations and rare diseases. Health record data also bring challenges, with missing and inaccurate data and substantial bias. Some of the bias comes about because the data are generated as part of the health care process. For example blood tests done at night select for patients who are sicker. We employ nonlinear time series methods borrowed from other fields to address the challenges, and we attempt to model and correct for biases due to the health care process. We incorporate mechanistic models to constrain the search space to create accurate predictions despite limited training sets and missing values.
  • No Thumbnail Available
    Item
    Inferring Host-Pathogen Interactions from Diverse Data Sources
    ( 2017-03-02) Craven, Mark
    Dr. Craven discusses work in several studies that involve developing and applying predictive methods in order to characterize host-pathogen interactions. In the first study, we are focused on inferring host subnetworks that are involved in viral replication from genome-wide loss-of-function experiments. Although these experiments can identify the host factors that directly or indirectly facilitate or inhibit the replication of a virus in a host cell, they do not elucidate how these genes are organized into the biological pathways that mediate host-virus interactions. We are developing novel computational methods that use a wide array of secondary data sources, including the scientific literature, to transform the measurements from these assays into hypotheses that predict the pathways in the cell that relate implicated genes to viral replication. In the second study, we are applying machine-learning methods to understand how variation in the genome of the HSV-1 virus influences multiple ocular disease phenotypes in a host. In the third study, we are investigating the extent to which risk for various infectious disease phenotypes can be predicted from electronic health records by using machine-learning methods.
  • No Thumbnail Available
    Item
    Use Cases of Big Data for Pharma
    ( 2017-02-16) Dilley, Cynthia
  • No Thumbnail Available
    Item
    Why Brains Need Computers: How Computer Science and Engineering Can Improve Neurology
    (Georgia Institute of Technology, 2016-11-10) Westover, Brandon
    Expert level GO and chess are here, while self-driving cars and human-level computer vision and speech recognition are rapidly becoming realities. Meanwhile, despite hype about "precision medicine" and "big medical data", the day-to-day practice of neurology continues to rely almost entirely on human expertise. In this talk I will introduce a range of real-world clinical problems for which computing, data science, machine learning, engineering, and other technical approaches can improve neurology, and why previous attempts at solving some of these problems have failed. These problems include: predicting which patients with brain injuries will have seizures; detecting seizures and seizure-like patterns in streaming brain monitoring (electroencephalography, EEG) data streams; diagnosing epilepsy in patients who have it, and avoiding misdiagnosing it in patients who don't; predicting which epilepsy patients will benefit from existing therapies; predicting whether a comatose patient will eventually recover consciousness; detecting impending cerebral infarction (stroke) in patients with brain aneurysms; automating the delivery of anesthesia to patients with acute brain swelling or life-threatening seizures; computing a patient's level of consciousness from the EEG and EKG signals; diagnosing delirium; and tracking sleep stages. For each of these problems, we will point out pitfalls, progress to date, and remaining challenges.