Date of Award
Doctor of Philosophy
A variety of health and behavioral states can potentially be inferred from physiological measurements that can now be collected in the free-living environment. The major challenge, however, is to develop computational models for automated detection of health events that can work reliably. In this work, we develop a physiologically-informed model to automatically detect drug (cocaine) use events in the free-living environment of participants from their electrocardiogram (ECG) measurements. The key to reliably detect these events is to incorporate the knowledge of autonomic nervous system (ANS) behavior in the model development so as to decompose the activation effect of cocaine from the natural recovery behavior of the parasympathetic nervous system (after an episode of physical activity). We collected 89 days of data from 9 active drug users in two residential lab environments and 922 days of data from 42 active drug users in the field environment, for a total of 11,283 hours. We developed a model that tracks the natural recovery by the parasympathetic nervous system and then estimates the dampening caused to the recovery by the activation of the sympathetic nervous system due to cocaine. We developed efficient methods to screen and clean the ECG time series data and extract candidate windows to assess for potential drug use. We then applied our model on the recovery segments from these windows. Our model achieves 100% true positive rate while keeping the false positive rate to 0.87/day over (9+ hours/day of) lab data and to 1.13/day over (11+ hours/day of) field data. In order to further improve the sensitivity and specificity of our model, we proposed several new data screening methods. Also we proposed a method to remove the effects of activities that acts as a confounder. We observed the false positive rates of 0.78 and 0.98 per day when we apply the enhanced model to the lab and field data respectively. Moreover, we observed that the proposed model has high specificity to cocaine. The method also estimates the dosage amount of drug for an event. However, the predicted dosage amount is not reliable for high dosage amounts in free living conditions.
dissertation or thesis originally submitted to the local University of Memphis Electronic Theses & dissertation (ETD) Repository.
Hossain, Syed Monowar, "Identifying Drug (Cocaine) Intake Events from Acute Physiological Response in the Presence of Free-living Physical Activity" (2017). Electronic Theses and Dissertations. 1624.