{"id":26997177,"url":"https://github.com/adityalab/neurabm","last_synced_at":"2025-04-04T02:17:06.079Z","repository":{"id":272191666,"uuid":"915788079","full_name":"AdityaLab/NeurABM","owner":"AdityaLab","description":null,"archived":false,"fork":false,"pushed_at":"2025-03-08T18:15:44.000Z","size":3947,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-08T19:22:29.680Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/AdityaLab.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2025-01-12T19:54:20.000Z","updated_at":"2025-03-08T18:15:48.000Z","dependencies_parsed_at":"2025-01-12T20:27:25.716Z","dependency_job_id":"6219b7b3-ceb4-42dd-a012-6094ced06ce2","html_url":"https://github.com/AdityaLab/NeurABM","commit_stats":null,"previous_names":["adityalab/neurabm"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AdityaLab%2FNeurABM","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AdityaLab%2FNeurABM/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AdityaLab%2FNeurABM/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AdityaLab%2FNeurABM/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AdityaLab","download_url":"https://codeload.github.com/AdityaLab/NeurABM/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247107827,"owners_count":20884797,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-04-04T02:17:05.597Z","updated_at":"2025-04-04T02:17:06.073Z","avatar_url":"https://github.com/AdityaLab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Identifying and Forecasting Importation and Asymptomatic Spreaders of Multi-drug Resistant Organisms in Hospital Settings\n\nThis code showcases that the our NeurABM framework identifies not only importation cases but also forecasts nosocomial infection cases better than other machine learning or modeling-based baselines.\n\nWe demonstrate our NeurABM in identifying MRSA importation and nosocomial infection cases in the ICUs of the UVA hospital in 2019. We used EHR data from the UVA hospital to construct patient contact networks (used by the ABM) and collect patient risk factors (used by the neural network). We use the SIS-ABM model (Cui, Jiaming, et al. \"Using spectral characterization to identify healthcare-associated infection (HAI) patients for clinical contact precaution.\" Scientific Reports 13.1 (2023): 16197.) as the ABM for disease transmission in NeurABM. Ground-truth MRSA infections are identified from lab test results for each patient in the EHR. \n\nThe outputs of our model are available in this repo. The electronic health record (EHR) data used in developing the models is not available since it is highly sensitive, and we do not have permission to release it.\n\n## Citation\n\nIf you use any part of the code or find the repo useful, please cite our paper.\n\n```\n@article{cui2025identifying,\n  title={Identifying and forecasting importation and asymptomatic spreaders of multi-drug resistant organisms in hospital settings},\n  author={Cui, Jiaming and Heavey, Jack and Klein, Eili Y and Madden, Gregory R and Sifri, Costi D and Vullikanti, Anil K and Prakash, B Aditya},\n  journal={npj Digital Medicine},\n  volume={8},\n  number={147},\n  year={2025}\n}\n```\n\n## Setup\n\nFirst install Anaconda. The dependencies are listed in `environment.yml` file. \n\nThen run the following commands:\n\n```bash\nconda env create --prefix ./envs/neurabm --file environment.yml\nsource activate ./envs/neurabm\n```\n\n## Directory structure\n\n```\n-Figure2 -\u003e This folder allows you to reproduce Figure 2 in the main article.\n       - data -\u003e Experiment results to reproduce Figure 2.\n\t- Figure2.py -\u003e Running this code directly will reproduce Figure 2.\n-Figure3 -\u003e This folder allows you to reproduce Figure 3 in the main article.\n       - data -\u003e Experiment results to reproduce Figure 3.\n\t- Figure3.py -\u003e Running this code directly will reproduce Figure 3.\n-Figure4 -\u003e This folder allows you to reproduce Figure 4 in the main article.\n       - data -\u003e Experiment results to reproduce Figure 4.\n\t- Figure4.py -\u003e Running this code directly will reproduce Figure 4.\n-Figure5 -\u003e This folder allows you to reproduce Figure 5 in the main article.\n       - data -\u003e Experiment results to reproduce Figure 5.\n       - Figure5.py -\u003e Running this code directly will reproduce Figure 5.\n- data\n       - synthetic.pkl -\u003e EHR data as pkl file\n- run.sh -\u003e shell file to run the NeurABM\n- main.py -\u003e code to train NeurABM\n- framework.py -\u003e NeurABM framework implementation\n- model.py -\u003e SIS-ABM model code\n- environment.yml -\u003e environment file\n- output -\u003e save results\n```\n\n## Dataset\n\nThe dataset is at `data` folder. It contains the synthetic EHR data used for NeurABM.\n\n## Demo\n\nWe provde a demo code and a synthetic dataset to run the NeurABM. The demo code usually takes 1-2 hours to run,\n\n```\n./run.sh\n```\nThis will save the results in output folder.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fadityalab%2Fneurabm","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fadityalab%2Fneurabm","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fadityalab%2Fneurabm/lists"}