Appendix for PulseImpute

In our proposed challenge, we draw from clinical pulsative waveform datasets to mimic mHealth pulsative waveforms, and in this section, we provide additional justification for this approach. A1.1 What is the rationale for constructing a dataset for mHealth signal imputation from equivalent signals connected in the clinical setting? While there are differences between clinical pulsative signals collected in a hospital setting and mHealth pulsative signals collected in the field, this was a necessary approach due to the scarcity of large, publicly-available mHealth datasets (e.g. PPG-DaLiA, an mHealth dataset, has 15 subjects whereas our curated MIMIC-III PPG dataset, derived from a clinical dataset, has 18,210 subjects). We can mimic real-world mHealth settings by applying realistic patterns of mHealth missingness. The original ablated samples are the ground truth, which makes it possible to quantify and visualize the imputation accuracy. A1.2 What are the differences in how the ECG/PPG sensors collect pulsative signals across both settings?