Heinz College of Info. Sys., Carnegie Mellon University, United States of America.
Department of Computer Science, Carnegie Mellon University, United States of America.
J Biomed Inform. 2023 Mar;139:104296. doi: 10.1016/j.jbi.2023.104296. Epub 2023 Feb 1.
Given a cardiac-arrest patient being monitored in the ICU (intensive care unit) for brain activity, how can we predict their health outcomes as early as possible? Early decision-making is critical in many applications, e.g. monitoring patients may assist in early intervention and improved care. On the other hand, early prediction on EEG data poses several challenges: (i) earliness-accuracy trade-off; observing more data often increases accuracy but sacrifices earliness, (ii) large-scale (for training) and streaming (online decision-making) data processing, and (iii) multi-variate (due to multiple electrodes) and multi-length (due to varying length of stay of patients) time series. Motivated by this real-world application, we present BeneFitter that infuses the incurred savings from an early prediction as well as the cost from misclassification into a unified domain-specific target called benefit. Unifying these two quantities allows us to directly estimate a single target (i.e. benefit), and importantly, (a) is efficient and fast, with training time linear in the number of input sequences, and can operate in real-time for decision-making, (b) can handle multi-variate and variable-length time-series, suitable for patient data, and (c) is effective, providing up to 2× time-savings with equal or better accuracy as compared to competitors.
对于在 ICU（重症监护病房）中监测脑活动的心脏骤停患者，我们如何尽早预测他们的健康状况？在许多应用中，早期决策至关重要，例如监测患者可能有助于早期干预和改善护理。另一方面，对 EEG 数据进行早期预测会带来一些挑战：（i）早期准确性权衡；观察更多的数据通常会提高准确性，但会牺牲早期性，（ii）大规模（用于训练）和流式（在线决策）数据处理，以及（iii）多变量（由于多个电极）和多长度（由于患者住院时间长短不一）时间序列。受这一实际应用的启发，我们提出了 BeneFitter，它将早期预测的节省以及分类错误的成本纳入到一个称为收益的统一特定领域目标中。统一这两个量允许我们直接估计单个目标（即收益），并且重要的是，（a）高效快速，训练时间与输入序列的数量线性相关，并且可以实时进行决策，（b）可以处理多变量和可变长度时间序列，适用于患者数据，（c）是有效的，与竞争对手相比，它可以提供高达 2 倍的时间节省和相同或更好的准确性。
