学习为临床结局预测选择最佳预测任务
Learning to Select the Best Forecasting Tasks for Clinical Outcome Prediction
AI总结：
提出一种元学习自监督患者轨迹预测学习规则的方法，通过优化表征在临床结局预测中的效用，在MIMIC-III数据集上验证了其在低资源下优于直接监督学习和全观测预训练。
摘要：
我们提出通过元训练一个元目标来元学习自监督患者轨迹预测学习规则，该目标直接优化患者表征在后续临床结局预测中的效用。该元目标直接针对从无标签临床测量预测生成的表征对后续监督任务的有用性。元学习所得规则可直接用于目标风险预测，且有限的可用样本可用于进一步微调模型性能。我们在真实开源患者EHR数据集MIMIC-III上测试了方法的有效性。我们能够证明，与直接监督学习和使用全观测轨迹预测的预训练相比，我们基于注意力的患者状态表征方法能在低资源下实现更好的目标风险预测性能。
英文摘要：
We propose to meta-learn an a self-supervised patient trajectory forecast learning rule by meta-training on a meta-objective that directly optimizes the utility of the patient representation over the subsequent clinical outcome prediction. This meta-objective directly targets the usefulness of a representation generated from unlabeled clinical measurement forecast for later supervised tasks. The meta-learned can then be directly used in target risk prediction, and the limited available samples can be used for further fine-tuning the model performance. The effectiveness of our approach is tested on a real open source patient EHR dataset MIMIC-III. We are able to demonstrate that our attention-based patient state representation approach can achieve much better performance for predicting target risk with low resources comparing with both direct supervised learning and pretraining with all-observation trajectory forecast.
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。
