Browsing by Subject "Interactions"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Alzheimer’s Disease Diagnosis via Deep Factorization Machine Models
    (Springer, 2021) Ronge, Raphael; Nho, Kwangsik; Wachinger, Christian; Pölsterl, Sebastian; Radiology and Imaging Sciences, School of Medicine
    The current state-of-the-art deep neural networks (DNNs) for Alzheimer’s Disease diagnosis use different biomarker combinations to classify patients, but do not allow extracting knowledge about the interactions of biomarkers. However, to improve our understanding of the disease, it is paramount to extract such knowledge from the learned model. In this paper, we propose a Deep Factorization Machine model that combines the ability of DNNs to learn complex relationships and the ease of interpretability of a linear model. The proposed model has three parts: (i) an embedding layer to deal with sparse categorical data, (ii) a Factorization Machine to efficiently learn pairwise interactions, and (iii) a DNN to implicitly model higher order interactions. In our experiments on data from the Alzheimer’s Disease Neuroimaging Initiative, we demonstrate that our proposed model classifies cognitive normal, mild cognitive impaired, and demented patients more accurately than competing models. In addition, we show that valuable knowledge about the interactions among biomarkers can be obtained.
  • Thumbnail Image
    Item
    Response to “Radiation Therapeutic Gain and Asian Botanicals,” by Stephen Sagar
    (SAGE Publications, 2010-03-21) Lawenda, Brian D.; Radiation Oncology, School of Medicine
    Numerous botanical agents, many of which are used in whole medical system practices (i.e. traditional Chinese medicine, Ayurvedic medicine, etc.), have been shown to exhibit radiomodifying effects on tumors and normal tissues in-vitro and invivo studies. Some of these agents can enhance the therapeutic gain of radiation therapy by either acting as a radiosensitizer to tumor cells and/or as a radioprotector to normal cells. Botanical agents are comprised of multiple phytochemical compounds that may work individually or synergistically to not only improve radiation therapy outcomes, but may also exhibit a variety of anti-cancer effects as well. It will be important to evaluate these botanicals for efficacy, tumor specificity, and safety profiles before they can be recommended during radiation therapy.