RNN在心电序列预测中仍具竞争力，任务不同表现各异。
Renaissance of RNNs in Streaming Clinical Time Series: Compact Recurrence Remains Competitive with Transformers
- 用紧凑GRU-D和Transformer对比，控制训练资源一致
- 心率异常风险预测中GRU-D略胜，预报误差上Transformer更优
- 适合长期监测场景下短期风险评估与精确预报任务
我们在MIT-BIH心律失常数据库上，基于每秒心率数据，构建了一个紧凑、严格因果的流式临床时间序列基准。研究两个任务：未来十秒内心动过速风险预测与单步心率预报，采用记录级非重叠划分。在相同训练预算下，比较GRU-D（RNN）与Transformer，并与强非学习基线对比。分类任务采用校准感知评估，预报任务使用温度缩放与分组自助法置信区间。在MIT-BIH数据集上，GRU-D在心动过速风险预测中略优于Transformer；而Transformer在心率预报上显著降低误差，优于GRU-D和持续性基线。结果表明，在纵向监测中，模型选择依赖任务：紧凑RNN在短时风险评分中仍具竞争力，而紧凑Transformer在点预测中优势更明显。
原文摘要 · Abstract (English)
We present a compact, strictly causal benchmark for streaming clinical time series on the MIT--BIH Arrhythmia Database using per-second heart rate. Two tasks are studied under record-level, non-overlapping splits: near-term tachycardia risk (next ten seconds) and one-step heart rate forecasting. We compare a GRU-D (RNN) and a Transformer under matched training budgets against strong non-learned baselines. Evaluation is calibration-aware for classification and proper for forecasting, with temperature scaling and grouped bootstrap confidence intervals. On MIT-BIH, GRU-D slightly surpasses the Transformer for tachycardia risk, while the Transformer clearly lowers forecasting error relative to GRU-D and persistence. Our results show that, in longitudinal monitoring, model choice is task-dependent: compact RNNs remain competitive for short-horizon risk scoring, whereas compact Transformers deliver clearer gains for point forecasting.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。