In this paper, we introduce a unified and generalist Biomedical Generative Pre-trained Transformer (BiomedGPT) model, which leverages self-supervision on large and diverse datasets to accept multi-modal inputs and perform a range of downstream tasks. Our experiments demonstrate that BiomedGPT delivers expansive and inclusive representations of biomedical data, outperforming the majority of preceding state-of-the-art models across five distinct tasks with 20 public datasets spanning over 15 unique biomedical modalities. Through the ablation study, we also showcase the efficacy of our multi-modal and multi-task pretraining approach in transferring knowledge to previously unseen data. Overall, our work presents a significant step forward in developing unified and generalist models for biomedicine, with far-reaching implications for improving healthcare outcomes.

翻译：本文提出了一种统一且通用的生物医学生成式预训练Transformer（BiomedGPT）模型，该模型利用大规模多样化数据集上的自监督学习，能够接受多模态输入并执行一系列下游任务。实验表明，BiomedGPT能够生成广泛且包容的生物医学数据表征，在涵盖15种以上独特生物医学模态的20个公开数据集上，于五项不同任务中的表现优于大多数先前最先进的模型。通过消融研究，我们还展示了多模态及多任务预训练方法在知识迁移至未见数据方面的有效性。总体而言，本工作在开发面向生物医学领域的统一通用模型方面迈出了重要一步，对改善医疗健康结果具有深远意义。