Signal processing and machine learning with transdermal alcohol concentration to predict natural environment alcohol consumption.

Wrist-worn alcohol biosensors continuously and discreetly record transdermal alcohol concentration (TAC) and may allow alcohol researchers to monitor alcohol consumption in participants' natural environments. However, the field lacks established methods for signal processing and detecting alcohol events using these devices. We developed software that streamlines analysis of raw data (TAC, temperature, and motion) from a wrist-worn alcohol biosensor (BACtrack Skyn) through a signal processing and machine learning pipeline: biologically implausible skin surface temperature readings (< 28°C) were screened for potential device removal and TAC artifacts were corrected, features that describe TAC (e.g., rise duration) were calculated and used to train models (random forest and logistic regression) that predict self-reported alcohol consumption, and model performances were measured and summarized in autogenerated reports. The software was tested using 60 Skyn data sets recorded during 30 alcohol drinking episodes and 30 nonalcohol drinking episodes. Participants (N = 36; 13 with alcohol use disorder) wore the Skyn during one alcohol drinking episode and one nonalcohol drinking episode in their natural environment. In terms of distinguishing alcohol from nonalcohol drinking, correcting artifacts in the data resulted in 10% improvement in model accuracy relative to using raw data. Random forest and logistic regression models were both accurate, correctly predicting 97% (58/60; AUC-ROCs = 0.98, 0.96) of episodes. Area under TAC curve, rise duration of TAC curve, and peak TAC were the most important features for predictive accuracy. With promising model performance, this protocol will enhance the efficiency and reliability of TAC sensors for future alcohol monitoring research. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Holding your liquor: Comparison of alcohol-induced psychomotor impairment in drinkers with and without alcohol use disorder.

BACKGROUND: Behavioral tolerance to alcohol underscores the widely accepted notion that individuals who regularly drink alcohol become less sensitive to its impairing effects. However, previous research assessing alcohol-induced impairment in humans has primarily focused on social drinkers. This has limited our understanding of the nature and extent of behavioral tolerance among heavier drinkers, such as those with alcohol use disorder (AUD). METHODS: Data from three cohorts of the Chicago Social Drinking Project were evaluated to examine the acute effects of alcohol on psychomotor performance across the breath alcohol curve in light drinkers (LDs; n = 86), heavy drinkers (HDs; n = 208), and individuals with AUD (AUDs; n = 103). Before and at several intervals after ingesting either alcohol (0.8 g/kg, peak BrAC = 0.09 g/dL) or placebo in two random-order laboratory sessions, participants completed a test of fine motor coordination (Grooved Pegboard), a test of perceptual-motor processing (Digit Symbol Substitution Task), and a self-reported survey of perceived impairment. Sixty individuals with AUD completed a third session with a very high dose of alcohol (1.2 g/kg, peak BrAC = 0.13 g/dL). RESULTS: The AUD and HD groups, relative to the LD group, perceived less impairment and demonstrated greater behavioral tolerance to an intoxicating dose of alcohol, exhibited by reduced peak impairment and a quicker return to baseline performance on psychomotor measures. Among individuals with AUD who consumed the very high dose, impairment was more than double that following the usual high dose, and it exceeded the impairment among LDs following the usual high dose. CONCLUSIONS: In this sample of young adult drinkers, relative to the LD group, those with heavier drinking patterns (AUD and HD groups) showed greater behavioral tolerance to 0.8 g/kg alcohol, a dose typically associated with a binge drinking episode. However, when challenged with a very high alcohol dose commensurate with high-intensity drinking, individuals with AUD showed substantial psychomotor impairment.

Effects of Visual Exposure to IQOS Use on Smoking Urge and Behavior.

OBJECTIVES: In this study, we examined whether visual exposure to the heated tobacco product (HTP) IQOS, which was authorized for sale by the US Food and Drug Administration in 2019, acts as a cue to increase cigarette craving and smoking behavior among smokers. METHODS: Young adult smokers (N = 105) were randomly assigned to view a video depicting use of either IQOS or bottled water. Main outcomes were changes in cigarette and e-cigarette desire and latency to smoke between the groups. We also examined participants' attitudes about the actors using IQOS and drinking water in the videos. RESULTS: Exposure to the use of IQOS acutely increased observers' ratings of smoking urge and desire for a cigarette and an e-cigarette. The IQOS cue, compared with the water cue, also produced a marginally significant shorter latency to smoke. Participants perceived actors as less likeable and friendly when using IQOS than when drinking water. CONCLUSIONS: Results showed that exposure to IQOS produced smoking urge and behavior in young adult smokers, implicating IQOS use as a smoking and vaping cue. As HTPs gain popularity, product impact on passive observers should be included in their risk-benefit profile.