{"id":13699275,"url":"https://github.com/jaredleekatzman/DeepSurv","last_synced_at":"2025-05-04T16:32:54.925Z","repository":{"id":50423717,"uuid":"59139064","full_name":"jaredleekatzman/DeepSurv","owner":"jaredleekatzman","description":"DeepSurv is a deep learning approach to survival analysis. ","archived":false,"fork":false,"pushed_at":"2020-08-27T01:58:33.000Z","size":5298,"stargazers_count":583,"open_issues_count":58,"forks_count":173,"subscribers_count":29,"default_branch":"master","last_synced_at":"2024-10-03T07:19:29.458Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/jaredleekatzman.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2016-05-18T17:56:19.000Z","updated_at":"2024-09-24T12:32:52.000Z","dependencies_parsed_at":"2022-09-24T02:30:32.896Z","dependency_job_id":null,"html_url":"https://github.com/jaredleekatzman/DeepSurv","commit_stats":null,"previous_names":[],"tags_count":2,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jaredleekatzman%2FDeepSurv","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jaredleekatzman%2FDeepSurv/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jaredleekatzman%2FDeepSurv/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jaredleekatzman%2FDeepSurv/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jaredleekatzman","download_url":"https://codeload.github.com/jaredleekatzman/DeepSurv/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":224398823,"owners_count":17304661,"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":"2024-08-02T20:00:29.275Z","updated_at":"2024-11-13T05:30:27.922Z","avatar_url":"https://github.com/jaredleekatzman.png","language":"Jupyter Notebook","readme":"# DeepSurv\n\nDeepSurv implements a deep learning generalization of the Cox proportional hazards model using Theano and Lasagne. \n\nDeepSurv has an advantage over traditional Cox regression because it does not require an *a priori* selection of covariates, but learns them adaptively. \n\nDeepSurv can be used in numerous survival analysis applications. One medical application is provided: recommend_treatment, which provides treatment recommendations for a set of patient observations. \n\nFor more details, see full paper [DeepSurv: Personalized Treatment Recommender System Using A Cox Proportional Hazards Deep Neural Network](http://arxiv.org/abs/1606.00931).\n\n**For an updated implementation of the [Cox loss function](https://github.com/runopti/stg/blob/master/python/stg/losses.py) in PyTorch, please see [Feature Selection using Stochastic Gates (STG) by Yamada et al.](https://github.com/runopti/stg/tree/master/python).**\n\n## Installation:\n\n### From source\n\nDownload a local copy of DeepSurv and install from the directory:\n\n\tgit clone https://github.com/jaredleekatzman/DeepSurv.git\n\tcd DeepSurv\n\tpip install .\n\n### Dependencies\n\nTheano, Lasagne (bleeding edge version), lifelines, matplotlib (for visualization), tensorboard_logger, and all of their respective dependencies. \n\n### Running the tests\n\nAfter installing, you can optionally run the test suite with\n\n\tpy.test\n\nfrom the command line while in the repo's main directory. \n\n## Running Experiments\n\nExperiments are run using Docker containers built off of the [floydhub](https://github.com/floydhub/dl-docker) deep learning Docker images. DeepSurv can be run on either the CPU or the GPU with nvidia-docker. \n\nAll experiments are in the `DeepSurv/experiments/` directory. \n\nTo run an experiment, define the experiment name as an environmental variable `EXPRIMENT`and run the docker-compose file. Further details are in the `DeepSurv/experiments/` directory. \n\n## Training a Network\n\nTraining DeepSurv can be done in a few lines. \nFirst, all you need to do is prepare the datasets to have the following keys:\n\n\t{ \n\t\t'x': (n,d) observations (dtype = float32), \n\t \t't': (n) event times (dtype = float32),\n\t \t'e': (n) event indicators (dtype = int32)\n\t}\n\nThen prepare a dictionary of hyper-parameters. And it takes only two lines to train a network:\n\n\tnetwork = deepsurv.DeepSurv(**hyperparams)\n\tlog = network.train(train_data, valid_data, n_epochs=500)\n\nYou can then evaluate its success on testing data:\n\n\tnetwork.get_concordance_index(**test_data)\n\t\u003e\u003e 0.62269622730138632\n\nIf you have matplotlib installed, you can visualize the training and validation curves after training the network:\n\n\tdeepsurv.plot_log(log)\n","funding_links":[],"categories":["\u003cspan id=\"head8\"\u003e2.3. Survival Analysis\u003c/span\u003e"],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjaredleekatzman%2FDeepSurv","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjaredleekatzman%2FDeepSurv","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjaredleekatzman%2FDeepSurv/lists"}