arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2501.14152cs.LGstat.ML
收藏

多模态处方深度学习

Multimodal Prescriptive Deep Learning

Operations Research Center, Massachusetts Institute of Technology(麻省理工学院运筹学中心)

Dimitris Bertsimas, Lisa Everest, Vasiliki Stoumpou

AI总结:

本文提出多模态处方神经网络(PNN),结合优化与机器学习,首个处理多模态数据,显著降低TAVR并发症和肝创伤死亡率,并在表格数据上通过知识蒸馏实现可解释性。

摘要:

我们引入了一个多模态深度学习框架——处方神经网络(PNNs),该框架结合了优化和机器学习的理念,据我们所知,这是首个能够处理多模态数据的处方方法。PNN是一种前馈神经网络,在嵌入上训练,以输出优化结果的处方。在两个真实世界的多模态数据集中,我们展示了PNN能够开出显著改善经导管主动脉瓣置换术(TAVR)程序中估计结果的处方,将估计的术后并发症率降低了32%,并在肝脏创伤损伤中将估计的死亡率降低了超过40%。在四个真实世界的单模态表格数据集中,我们展示了PNN优于或与其他知名的、最先进的处方模型表现相当;重要的是,在表格数据集上,我们还通过知识蒸馏恢复了可解释性,将可解释的最优分类树模型拟合到PNN处方上作为分类目标,这对许多现实世界应用至关重要。最后,我们证明了我们的多模态PNN模型在随机数据分割上的稳定性与其他处方方法相当,并在不同数据集上产生了现实的处方。

英文摘要:

We introduce a multimodal deep learning framework, Prescriptive Neural Networks (PNNs), that combines ideas from optimization and machine learning, and is, to the best of our knowledge, the first prescriptive method to handle multimodal data. The PNN is a feedforward neural network trained on embeddings to output an outcome-optimizing prescription. In two real-world multimodal datasets, we demonstrate that PNNs prescribe treatments that are able to significantly improve estimated outcomes in transcatheter aortic valve replacement (TAVR) procedures by reducing estimated postoperative complication rates by 32% and in liver trauma injuries by reducing estimated mortality rates by over 40%. In four real-world, unimodal tabular datasets, we demonstrate that PNNs outperform or perform comparably to other well-known, state-of-the-art prescriptive models; importantly, on tabular datasets, we also recover interpretability through knowledge distillation, fitting interpretable Optimal Classification Tree models onto the PNN prescriptions as classification targets, which is critical for many real-world applications. Finally, we demonstrate that our multimodal PNN models achieve stability across randomized data splits comparable to other prescriptive methods and produce realistic prescriptions across the different datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑