{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/learning-eligibility-in-cancer-clinical","title":"Learning Eligibility in Cancer Clinical Trials using Deep Neural Networks","arxiv_id":"1803.08312","date":"2018-03-22","proceeding":null,"authors":["Aurelia Bustos","Antonio Pertusa"],"abstract":"Interventional cancer clinical trials are generally too restrictive, and some\npatients are often excluded on the basis of comorbidity, past or concomitant\ntreatments, or the fact that they are over a certain age. The efficacy and\nsafety of new treatments for patients with these characteristics are,\ntherefore, not defined. In this work, we built a model to automatically predict\nwhether short clinical statements were considered inclusion or exclusion\ncriteria. We used protocols from cancer clinical trials that were available in\npublic registries from the last 18 years to train word-embeddings, and we\nconstructed a~dataset of 6M short free-texts labeled as eligible or not\neligible. A text classifier was trained using deep neural networks, with\npre-trained word-embeddings as inputs, to predict whether or not short\nfree-text statements describing clinical information were considered eligible.\nWe additionally analyzed the semantic reasoning of the word-embedding\nrepresentations obtained and were able to identify equivalent treatments for a\ntype of tumor analogous with the drugs used to treat other tumors. We show that\nrepresentation learning using {deep} neural networks can be successfully\nleveraged to extract the medical knowledge from clinical trial protocols for\npotentially assisting practitioners when prescribing treatments.","url_abs":"http://arxiv.org/abs/1803.08312v3","url_pdf":"http://arxiv.org/pdf/1803.08312v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"learning-eligibility-in-cancer-clinical","repo_url":"https://github.com/auriml/capstone","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}