@inproceedings{zheng-etal-2025-lifted,
    title = "{LIFTED}: Multimodal Clinical Trial Outcome Prediction via Large Language Models and Mixture-of-Experts",
    author = "Zheng, Wenhao  and
      Wang, Liaoyaqi  and
      Peng, Dongshen  and
      Xu, Hongxia  and
      Li, Yun  and
      Zhu, Hongtu  and
      Fu, Tianfan  and
      Yao, Huaxiu",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-luhme/2025.findings-emnlp.396/",
    doi = "10.18653/v1/2025.findings-emnlp.396",
    pages = "7503--7517",
    ISBN = "979-8-89176-335-7",
    abstract = "Clinical trials are pivotal yet costly processes, often spanning multiple years and requiring substantial expenses, motivating predictive models to identify likely-to-fail drugs early and save resources. Recent approaches leverage deep learning to integrate multimodal data for clinical outcome prediction; however, they rely heavily on manually designed modality-specific encoders, limiting their adaptability to new modalities and ability to effectively share information across modalities. To address these challenges, we propose a multimodal mixture-of-experts (LIFTED) framework. Specifically, LIFTED transforms modality-specific data into natural language descriptions, encoded via unified, noise-resilient encoders. A sparse Mixture-of-Experts mechanism then identifies shared patterns across modalities, extracting consistent representations. Finally, another mixture-of-experts module dynamically integrates these modality representations, emphasizing critical information. Experiments show that LIFTED significantly outperforms baseline methods in predicting clinical trial outcomes across all phases, highlighting the effectiveness of our proposed approach."
}