{"paper":{"title":"Can artificial intelligence predict clinical trial outcomes?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.AP"],"primary_cat":"cs.LG","authors_text":"Hongru Ding, Lu Chen, Lun Yu, Meijie Wang, Shuyi Jin","submitted_at":"2024-11-26T17:05:27Z","abstract_excerpt":"This study evaluates the performance of large language models (LLMs) and the HINT model in predicting clinical trial outcomes, focusing on metrics including Balanced Accuracy, Matthews Correlation Coefficient (MCC), Recall, and Specificity. Results show that GPT-4o achieves superior overall performance among LLMs but, like its counterparts (GPT-3.5, GPT-4mini, Llama3), struggles with identifying negative outcomes. In contrast, HINT excels in negative sample recognition and demonstrates resilience to external factors (e.g., recruitment challenges) but underperforms in oncology trials, a major c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17595","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.17595/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}