Task- and Metric-Specific Signal Quality Indices for Medical Time Series
This work addresses the need for more reliable signal quality indices in medical applications, where automated algorithms inform clinical decisions, but it is incremental as it builds on existing SQI concepts by adding task and metric specificity.
The paper tackled the problem of signal quality assessment for medical time series like ECGs and PPGs, which is critical for reliable automated analysis, by proposing a perturbation-based signal quality index (pSQI) that is task- and metric-specific. The result showed that pSQI consistently outperformed existing methods in identifying unreliable inputs on benchmarks for R-peak detection and atrial fibrillation classification without requiring training.
Medical time series such as electrocardiograms (ECGs) and photoplethysmograms (PPGs) are frequently affected by measurement artifacts due to challenging acquisition environments, such as in ambulances and during routine daily activities. Since automated algorithms for analyzing such signals increasingly inform clinically relevant decisions, identifying signal segments on which these algorithms may produce unreliable outputs is of critical importance. Signal quality indices (SQIs) are commonly used for this purpose. However, most existing SQIs are task agnostic and do not account for the specific algorithm and performance metric used downstream. In this work, we formalize signal quality as a task- and metric-dependent concept and propose a perturbation-based SQI (pSQI) that aims to detect an algorithm's performance degradation on an input signal with respect to a metric. The pSQI is defined as the worst-case value of the performance metric under an additive, colored Gaussian noise perturbation with a lower-bounded signal-to-noise ratio. We introduce formal requirements for task- and metric-specific SQIs, including monotonicity of the metric in expectation and maximal separation under thresholding. Experiments on R-peak detection and atrial fibrillation classification benchmarks demonstrate that the proposed pSQI consistently outperforms existing feature- and deep learning-based SQIs in identifying unreliable inputs without requiring training.