Statistical methods for predicting e-cigarette use events based on beat-to-beat interval (BBI) data collected from wearable devices.

The prevalence of e-cigarette use among young adults in the USA is high (14%). Although the majority of users plan to quit vaping, the motivation to make a quit attempt is low and available support during a quit attempt is limited. Using wearable sensors to collect physiological data (eg, heart rate) holds promise for capturing the right timing to deliver intervention messages. This study aims to fill the current knowledge gap by proposing statistical methods to (1) de-noise beat-to-beat interval (BBI) data from smartwatches worn by 12 young adult regular e-cigarette users for 7 days; and (2) summarize the de-noised data by event and control segments. We also conducted a comprehensive review of conventional methods for summarizing heart rate variability (HRV) and compared their performance with the proposed method. The results show that the proposed singular spectrum analysis (SSA) can effectively de-noise the highly variable BBI data, as well as quantify the proportion of total variation extracted. Compared to existing HRV methods, the proposed second order polynomial model yields the highest area under the curve (AUC) value of 0.76 and offers better interpretability. The findings also indicate that the average heart rate before vaping is higher and there is an increasing trend in the heart rate before the vaping event. Importantly, the development of increasing heart rate observed in this study implies that there may be time to intervene as this physiological signal emerges. This finding, if replicated in a larger scale study, may inform optimal timings for delivering messages in future intervention.