Spatial Scan for Disease Mapping on a Mobile Population
Authors: Liang Lan, Vuk Malbasa, Slobodan Vucetic
AAAI 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | The experimental results demonstrate that the proposed algorithm is computationally efficient and outperforms the traditional disease clustering approaches at discovering high-risk regions in mobile populations. |
| Researcher Affiliation | Academia | Liang Lan Department of Computer and Information Sciences, Temple University lanliang@temple.edu Vuk Malbasa Faculty of Technical Science, University of Novi Sad, Serbia vmalbasa@gmail.com Slobodan Vucetic Department of Computer and Information Sciences, Temple University slobodan.vucetic@temple.edu |
| Pseudocode | No | The paper describes the algorithm steps in narrative text (e.g., in the 'Scalability' section) but does not include formal pseudocode blocks or figures explicitly labeled as 'Algorithm'. |
| Open Source Code | No | The paper does not provide any explicit statement or link indicating that the source code for the described methodology is publicly available. |
| Open Datasets | Yes | Epi Sims Data In order to evaluate the proposed spatial scan algorithm and to compare usefulness of residential and movement data in detecting significant overdensity clusters, we used Epi Sims data set from Network Dynamics and Simulation Science Laboratory (NDSSL 2006). |
| Dataset Splits | No | The paper describes a randomization technique using 'B shuffled data sets' (B = 100 or B = 1,000) for statistical significance testing, which is not a train/validation/test split. It does not provide specific percentages or counts for training, validation, or test splits of the main dataset used for model training. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory, or specific computing cluster specifications) used for running its experiments. |
| Software Dependencies | No | The paper mentions 'Sa TScan software' as a tool, but it does not specify any software dependencies with version numbers for their own described methodology or experiment implementation. |
| Experiment Setup | Yes | In our first experiment, we used a square with size 3 3 centered on Milwaukie Business Industrial... We set rin = log(199) and rout = log(999), such that an individual spending all time inside the sub-region would have disease probability ρi = 0.005, while an individual spending all time outside would have disease probability ρi = 0.001. In this setting, we randomly sampled N = 100, 000 people. ... We also checked how the discretization impacts the detected regions. Our empirical results show we could get the same detected region and p-value as the original data by setting M to 100. |