Learning Higher-Order Dynamics in Video-Based Cardiac Measurement
This work addresses the need for more accurate waveform morphology in cardiac monitoring for clinical applications, representing an incremental improvement over existing methods.
The paper tackled the problem of accurately estimating higher-order dynamics like acceleration in video-based cardiac measurements, which are crucial for clinical assessments such as blood pressure indicators, and showed that explicitly optimizing neural models for these dynamics in the loss function improves performance, specifically in estimating left ventricle ejection time intervals.
Computer vision methods typically optimize for first-order dynamics (e.g., optical flow). However, in many cases the properties of interest are subtle variations in higher-order changes, such as acceleration. This is true in the cardiac pulse, where the second derivative can be used as an indicator of blood pressure and arterial disease. Recent developments in camera-based vital sign measurement have shown that cardiac measurements can be recovered with impressive accuracy from videos; however, most of the research has focused on extracting summary statistics such as heart rate. Less emphasis has been put on the accuracy of waveform morphology that is necessary for many clinically meaningful assessments. In this work, we provide evidence that higher-order dynamics are better estimated by neural models when explicitly optimized for in the loss function. Furthermore, adding second-derivative inputs also improves performance when estimating second-order dynamics. We illustrate this, by showing that incorporating the second derivative of both the input frames and the target vital sign signals into the training procedure, models are better able to estimate left ventricle ejection time (LVET) intervals.