{"id":30776273,"url":"https://github.com/vintasoftware/icd-ai-poc","last_synced_at":"2025-09-05T04:34:59.594Z","repository":{"id":289879369,"uuid":"967630458","full_name":"vintasoftware/icd-ai-poc","owner":"vintasoftware","description":"Leverages OpenAI's API to sort ICD-10 codes into different categories","archived":false,"fork":false,"pushed_at":"2025-07-28T12:23:54.000Z","size":1460,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-07-28T14:31:07.120Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"TypeScript","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/vintasoftware.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,"zenodo":null}},"created_at":"2025-04-16T18:47:47.000Z","updated_at":"2025-07-28T12:23:57.000Z","dependencies_parsed_at":"2025-04-25T15:22:51.687Z","dependency_job_id":"4926d4d0-df13-47b0-bf1e-35ecbc0131a0","html_url":"https://github.com/vintasoftware/icd-ai-poc","commit_stats":null,"previous_names":["vintasoftware/icd-ai-poc"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/vintasoftware/icd-ai-poc","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vintasoftware%2Ficd-ai-poc","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vintasoftware%2Ficd-ai-poc/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vintasoftware%2Ficd-ai-poc/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vintasoftware%2Ficd-ai-poc/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/vintasoftware","download_url":"https://codeload.github.com/vintasoftware/icd-ai-poc/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vintasoftware%2Ficd-ai-poc/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273713468,"owners_count":25154609,"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":"2025-09-05T02:00:09.113Z","response_time":402,"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":[],"created_at":"2025-09-05T04:32:29.505Z","updated_at":"2025-09-05T04:34:59.536Z","avatar_url":"https://github.com/vintasoftware.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ICD-10 AI Code Search\n\nWelcome! This is a proof of concept that looks to leverage AI to sort ICD-10 codes into either Problems or Allergies. This example comes from a real need we identified in one of our projects and we decided to make it public so the whole community can benefit from the experiment.\n\n## Demo video\n\n[![Sorting ICD-10 into categories with AI](http://img.youtube.com/vi/evU1zOTS8Bg/0.jpg)](http://www.youtube.com/watch?v=evU1zOTS8Bg \"Sorting ICD-10 into categories with AI\")\n\n## How to run the example\n\n1. Clone the repository.\n2. Set up a `.env` file with your OpenAI API key.\n3. Run the project with `npm run dev`.\n4. Access it at `localhost:3000`.\n\n## Important considerations\n\n### AI models\n\nDifferent OpenAI models were tested during the development of this proof of concept, here are the ones that were considered:\n\n- GPT-4 Turbo\n- GPT-4.1\n- GPT-4.5 Preview\n- o3-mini\n- o1\n\nAfter manual testing, we found that o1 model produced the most consistent results.\n\n### Production use\n\nThis is not a production-ready solution. EHR development demands caution, as mistakes can have serious consequences for patients and providers. However, this can be used as an experimental feature provided that:\n\n- You implement code to verify that the AI’s filtered results are correct and present in the original list.\n- Users can always access the full, unfiltered list from your chosen ICD-10 source.\n\nEnjoy!\n\n## Commercial Support\n\n[![Vinta Software Logo](https://avatars2.githubusercontent.com/u/5529080?s=80\u0026v=4 \"Vinta Logo\")](https://www.vintasoftware.com/)\n\nThis is an open-source project maintained by [Vinta Software](https://www.vinta.com.br/). We are always looking for exciting work! If you need any commercial support, feel free to get in touch: contact@vinta.com.br\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvintasoftware%2Ficd-ai-poc","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvintasoftware%2Ficd-ai-poc","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvintasoftware%2Ficd-ai-poc/lists"}