BioBERT 与 BioMistral 在临床试验结果预测上超越 HINT 基线
Advancing Clinical Trial Outcome Prediction with Domain-Specific Large Language Models
研究者拿 BioBERT 和 BioMistral 预测试验成败，PR-AUC 比 HINT 高 10–20%，而且冻结模型加分类器就够了，微调都省了。
一篇 arXiv 论文用 BioBERT（108M 参数）和 BioMistral（7B 参数）在 TOP 基准的 12,477 项试验上做阶段级结果预测，试验文本由 ClinicalTrials.gov 的十个字段拼接而成。四个语言模型变体的 ROC-AUC 达 0.613–0.772，PR-AUC 达 0.649–0.901，相比 HINT（Hierarchical Interaction Network）有 10–20% 的相对 PR-AUC 提升。冻结 BioMistral 嵌入加轻量分类器的 probing 方案在 Phase III 达到 ROC-AUC 0.772，与微调效果接近。论文同时指出各模型 F1 差异很小，包括 HINT 在内都不明显高于把所有试验都判成功的平凡分类器。
Advancing Clinical Trial Outcome Prediction with Domain-Specific Large Language Models
Clinical trial failures are a major barrier to efficient drug development, incurring substantial costs and delaying patient access to effective therapies. Structured approaches such as the Hierarchical Interaction Network (HINT) predict trial outcomes by explicitly modelling interactions between drugs, diseases and protocols, but make limited use of the free text in trial registrations. We evaluate two domain-specific language models, BioBERT (108M parameters) and BioMistral (7B parameters), for phase-level outcome prediction on the TOP benchmark (12,477 trials), representing each trial as text built from ten ClinicalTrials.gov fields. We compare fine-tuning (full fine-tuning for BioBERT, low-rank adaptation for BioMistral) with probing, in which the pretrained model is frozen and only a lightweight classifier is trained on its embeddings. On the held-out test set of each phase, all four language-model variants achieved higher ROC-AUC (0.613--0.772) and PR-AUC (0.649--0.901) than the published HINT results, corresponding to relative PR-AUC gains of 10--20\%. F1 differences were small and mixed, and no model, including HINT, clearly exceeded the F1 of a trivial classifier that predicts success for every trial. Under the configurations tested, probing performed comparably to fine-tuning: fine-tuned models scored highest on ROC-AUC and PR-AUC in Phases I and II, and frozen BioMistral embeddings in Phase III (ROC-AUC 0.772; PR-AUC 0.901), although most differences between variants were below 0.03 and were not tested for significance. These results suggest that pretrained biomedical representations already encode signal relevant to trial outcome, and that probing is a computationally cheaper alternative to fine-tuning for this task.