{"id":31702457,"url":"https://github.com/archettialberto/interpolation_for_deep_survival_analysis","last_synced_at":"2025-10-08T21:51:57.578Z","repository":{"id":199288025,"uuid":"702543566","full_name":"archettialberto/interpolation_for_deep_survival_analysis","owner":"archettialberto","description":"This repo contains the source code of the paper \"Deep Survival Analysis for Healthcare: An Empirical Study on Post-Processing Techniques\".","archived":false,"fork":false,"pushed_at":"2024-02-25T15:21:56.000Z","size":124,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2024-02-25T16:31:24.263Z","etag":null,"topics":["datasets","healthcare","interpolation-methods","neural-networks","survival-analysis"],"latest_commit_sha":null,"homepage":"","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/archettialberto.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2023-10-09T14:13:30.000Z","updated_at":"2023-10-09T14:42:43.000Z","dependencies_parsed_at":null,"dependency_job_id":"b4e5c1e0-9973-4c9a-ab54-c40127114803","html_url":"https://github.com/archettialberto/interpolation_for_deep_survival_analysis","commit_stats":null,"previous_names":["archettialberto/interpolation_for_deep_survival_analysis"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/archettialberto/interpolation_for_deep_survival_analysis","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/archettialberto%2Finterpolation_for_deep_survival_analysis","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/archettialberto%2Finterpolation_for_deep_survival_analysis/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/archettialberto%2Finterpolation_for_deep_survival_analysis/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/archettialberto%2Finterpolation_for_deep_survival_analysis/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/archettialberto","download_url":"https://codeload.github.com/archettialberto/interpolation_for_deep_survival_analysis/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/archettialberto%2Finterpolation_for_deep_survival_analysis/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279000701,"owners_count":26082837,"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","status":"online","status_checked_at":"2025-10-08T02:00:06.501Z","response_time":56,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["datasets","healthcare","interpolation-methods","neural-networks","survival-analysis"],"created_at":"2025-10-08T21:51:53.836Z","updated_at":"2025-10-08T21:51:57.573Z","avatar_url":"https://github.com/archettialberto.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Deep Survival Analysis for Healthcare: An Empirical Study on Post-Processing Techniques\n\nSurvival analysis is a crucial tool in healthcare, allowing us to understand and predict time-to-event occurrences\nusing statistical and machine-learning techniques. As deep learning gains traction in this domain, a specific challenge\nemerges: **neural network-based survival models** often produce discrete-time outputs, with the number of discretization\npoints being much fewer than the unique time points in the dataset, leading to potentially inaccurate survival\nfunctions. To this end, our study explores post-processing techniques for survival functions. Specifically,\n**interpolation and smoothing** can act as effective regularization, enhancing performance metrics integrated over time,\nsuch as the Integrated Brier Score and the Cumulative Area-Under-the-Curve. We employed various regularization\ntechniques on diverse real-world healthcare datasets to validate this claim. Empirical results suggest a significant\nperformance improvement when using these post-processing techniques, underscoring their potential as a robust\nenhancement for neural network-based survival models. These findings suggest that integrating the strengths of neural\nnetworks with the non-discrete nature of survival tasks can yield more accurate and reliable survival predictions in\nclinical scenarios.\n\n## ⚙️ Installation\n\nClone the repository:\n\n```bash\ngit clone https://github.com/archettialberto/interpolation_for_deep_survival_analysis\n```\n\nStart a Poetry shell:\n\n```bash\npoetry shell\n```\n\nInstall the dependencies:\n\n```bash\npoetry install\n```\n\n## 🛠️ Usage\n\nRun ```exps.py``` to start the experiments:\n\n```bash\npython exps.py\n```\n\nThe results will be saved in the ```results``` directory.\n\n## 📕 Bibtex Citation\n\n```\n@inproceedings{archetti2023deep,\n  title={Deep Survival Analysis for Healthcare: An Empirical Study on Post-Processing Techniques},\n  author={Alberto Archetti and Francesco Stranieri and Matteo Matteucci},\n  booktitle={Proceedings of the 2nd AIxIA Workshop on Artificial Intelligence For Healthcare (HC@AIxIA 2023)},\n  year={2023},\n  pages={99--121},\n  editor={Francesco Calimeri and Mauro Dragoni and Fabio Stella},\n  volume={3578},\n  series={CEUR Workshop Proceedings},\n  address={Rome, Italy},\n  publisher={CEUR-WS.org},\n  url={http://ceur-ws.org/Vol-3578/},\n  date={2023-11-08},\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Farchettialberto%2Finterpolation_for_deep_survival_analysis","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Farchettialberto%2Finterpolation_for_deep_survival_analysis","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Farchettialberto%2Finterpolation_for_deep_survival_analysis/lists"}