Validation of Psychophysiological Measures for Caffeine Oral Films Characterization by Machine Learning Approaches.

抄録

(1) Background: The oral films are a new delivery system that can carry several molecules, such as neuromodulator molecules, including caffeine. These delivery systems have been developed and characterized by pharmacokinetics assays. However, new methodologies, such as psychophysiological measures, can complement their characterization. This study presents a new protocol with psychophysiological parameters to characterize the oral film delivery systems based on a caffeine model. (2) Methods: Thirteen volunteers (61.5% females and 38.5% males) consumed caffeine oral films and placebo oral films (in different moments and without knowing the product). Electrocardiogram (ECG), electrodermal (EDA), and respiratory frequency (RF) data were monitored for 45 min. For the data analysis, the MATLAB environment was used to develop the analysis program. The ECG, EDA, and RF signals were digitally filtered and processed, using a windowing process, for feature extraction and an energy mean value for 5 min segments. Then, the data were computed and presented to the entries of a set of Machine Learning algorithms. Finally, a data statistical analysis was carried out using SPSS. (3) Results: Compared with placebo, caffeine oral films led to a significant increase in power energy in the signal spectrum of heart rate, skin conductance, and respiratory activity. In addition, the ECG time-series power energy activity revealed a better capacity to detect caffeine activity over time than the other physiological modalities. There was no significant change for the female or male gender. (4) Conclusions: The protocol developed, and the psychophysiological methodology used to characterize the delivery system profile were efficient to characterize the drug delivery profile of the caffeine. This is a non-invasive, cheap, and easy method to apply, can be used to determine the neuromodulator drugs delivery profile, and can be implemented in the future.