German Research Center for AI (DFKI).
Technische Universitat, Berlin, Germany.
AMIA Annu Symp Proc. 2021 Jan 25;2020:1060-1069. eCollection 2020.
Recent medical prognostic models adapted from high data-resource fields like language processing have quickly grown in complexity and size. However, since medical data typically constitute low data-resource settings, performances on tasks like clinical prediction did not improve expectedly. Instead of following this trend of using complex neural models in combination with small, pre-selected feature sets, we propose EffiCare, which focuses on minimizing hospital resource requirements for assistive clinical prediction models. First, by embedding medical events, we eliminate manual domain feature-engineering and increase the amount oflearning data. Second, we use small, but data-efficient models, that compute faster and are easier to interpret. We evaluate our approach on four clinical prediction tasks and achieve substantial performance improvements over highly resource-demanding state-of-the-art methods. Finally, to evaluate our model beyond score improvements, we apply explainability and interpretability methods to analyze the decisions of our model and whether it uses data sources and parameters efficiently..
最近，一些源于语言处理等高数据资源领域的医学预后模型在复杂性和规模上迅速发展。然而，由于医学数据通常属于低数据资源环境，因此在临床预测等任务上的表现并没有如预期般得到改善。我们没有遵循使用复杂的神经网络模型结合小的、预先选择的特征集的趋势，而是提出了 EffiCare，它专注于最小化辅助临床预测模型的医院资源需求。首先，通过嵌入医疗事件，我们消除了手动的领域特征工程，并增加了学习数据的数量。其次，我们使用小而高效的数据模型，这些模型计算速度更快，更容易解释。我们在四个临床预测任务上评估了我们的方法，并在性能上取得了显著的提高，超过了高资源需求的最先进方法。最后，为了评估我们的模型除了评分提高之外的效果，我们应用可解释性和可理解性方法来分析我们模型的决策以及它是否有效地利用了数据来源和参数。
