Detecting Sources of Healthcare Associated Infections
Authors: Hankyu Jang, Andrew Fu, Jiaming Cui, Methun Kamruzzaman, B. Aditya Prakash, Anil Vullikanti, Bijaya Adhikari, Sriram V. Pemmaraju
AAAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We present experimental results on temporal contact networks based on fine-grained EMR data from three different hospitals. Our results on synthetic outbreaks on these networks show that our algorithms outperform baselines by up to 5.97 times. Furthermore, case studies based on hospital outbreaks of Clostridioides difficile infection show that our algorithms identify clinically meaningful sources. |
| Researcher Affiliation | Academia | 1Department of Computer Science, University of Iowa 2Department of Computer Science, University of Virginia 3College of Computing, Georgia Institute of Technology 4Biocomplexity Institute, University of Virginia Email: {hankyu-jang, bijaya-adhikari, sriram-pemmaraju}@uiowa.edu, {af9pn, hkz8wk, vsakumar}@virginia.edu, {jiamingcui1997, badityap}@gatech.edu |
| Pseudocode | Yes | Algorithm 1: MUKnapsack SD Input: G, τ1, τ2, Pos, and kt for each t [τ2, T 1] Output: A seed set S 1: S 2: while S has not converged do 3: Compute a linear function ˆft defined as ˆft(Y ) := ft(S) X j S\Y ft(j|S \ j) + X j Y \S ft(j| ) 4: S Multiplicative Update(g, ˆft, t [τ2, T 1]) 5: end while 6: return S |
| Open Source Code | Yes | Our code and public data is available for academic purposes 2https://github.com/Hankyu Jang/Detecting-Sources-of Healthcare-Associated-Infections |
| Open Datasets | Yes | Our code and public data is available for academic purposes 2https://github.com/Hankyu Jang/Detecting-Sources-of Healthcare-Associated-Infections |
| Dataset Splits | No | The paper describes using 'Pos' and 'Neg' sets generated from 'simulated outbreaks' for evaluation. While the experiments are designed to test algorithm performance, the paper does not specify distinct training, validation, and test splits (e.g., percentages or sample counts) for model development or hyperparameter tuning in the traditional machine learning sense. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., CPU/GPU models, memory) used for running the experiments. |
| Software Dependencies | No | The paper does not provide specific software dependency details with version numbers. |
| Experiment Setup | No | The paper specifies parameters like τ1 and τ2 for the problem setup and simulation characteristics (e.g., 'calibrated simulations yield about 5-10% infection'), but it does not provide specific hyperparameter values or detailed training configurations (e.g., learning rates, batch sizes, optimizer settings) for their proposed algorithms (MUKnapsack SD, Greedy Ratio SD). |