Learning the Probability of Activation in the Presence of Latent Spreaders

Authors: Maggie Makar, John Guttag, Jenna Wiens

AAAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Through a series of experiments on synthetic data, we measure the ability of the proposed model to identify latent spreaders, and predict the risk of infection. Applied to a real dataset of 20,000 hospital patients, we demonstrate the utility of our model in predicting the onset of a healthcare associated infection using patient room-sharing and nurse-sharing networks.
Researcher Affiliation Academia Maggie Makar CSAIL, MIT Cambridge, MA mmakar@mit.edu John Guttag CSAIL, MIT Cambridge, MA guttag@mit.edu Jenna Wiens CSE, University of Michigan Ann Arbor, MI wiensj@umich.edu
Pseudocode No The paper describes a generative process with numbered steps, but it is not presented in a formal pseudocode block or algorithm structure.
Open Source Code No The paper does not provide concrete access to source code for the methodology described, nor does it state that the code is open-source or available.
Open Datasets No Applied to a real dataset of 20,000 hospital patients... We split the data into training and testing temporally, using hospitalizations from May 2012 to May 2013 as training data. This is a private dataset; no access information (link, DOI, citation for public access) is provided.
Dataset Splits No We split the data into training and testing temporally, using hospitalizations from May 2012 to May 2013 as training data. The paper mentions training and testing splits, but does not explicitly describe a validation split.
Hardware Specification No The paper does not provide specific hardware details (e.g., CPU/GPU models, memory) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers (e.g., Python 3.8, PyTorch 1.9) needed to replicate the experiment.
Experiment Setup Yes For all experiments in this section, we generate a network of 500 individuals for training and a held-out network of 500 individuals for testing. We use a stochastic block model (SBM) to simulate the network and set the probability that two individuals within and across a sub-community form an edge is 0.5, and 0.01 respectively. We split the data into training and testing temporally, using hospitalizations from May 2012 to May 2013 as training data.