Sensitivity, specificity, and tolerability of the BACTrack Skyn compared to other alcohol monitoring approaches among young adults in a field-based setting

A wearable alcohol biosensor: Exploring the accuracy of transdermal drinking detection

BACKGROUND

Trace amounts of consumed alcohol are detectable within sweat and insensible perspiration. However, the relationship between ingested and transdermally emitted alcohol is complex, varying across environmental conditions and involving a degree of lag. As such, the feasibility of real-time drinking detection across diverse environments has been unclear. In the current research we revisit sensor performance using new tools, exploring the accuracy of a new generation of rapid-sampling transdermal biosensor for contemporaneous drinking detection across diverse environments via machine learning.

METHODS

Regular drinkers (N = 100) attended three laboratory sessions involving the experimental manipulation of alcohol dose, rate of consumption, and environmental dosing conditions. Participants further supplied breath alcohol concentration (BAC) readings in the field over 14 days. Participants wore compact wrist sensors capable of rapid sampling (20sec intervals). Transdermal sensor data was translated into alcohol use estimates using machine learning, integrating only transdermal data collected prior to the point of BAC assessment.

RESULTS

A total of 5.39 million transdermal readings (28,615hours) and 12,699 BAC readings were collected for this research. Models indicated strong transdermal sensor accuracy for real-time drinking detection across both laboratory and field contexts (AUROC, 0.966, 95 % CI, 0.956-0.972; Sensitivity, 89.8 %; Specificity, 90.6 %). Models aimed at differentiating high-risk (≥0.08 %) drinking levels yielded intermediate (AUROC, 0.738; 95 % CI, 0.698-0.777; only drinking episodes) to strong (AUROC, 0.941, 95 % CI, 0.929-0.954; all data) accuracy levels.

CONCLUSIONS

Results indicate a range of useful future applications for transdermal alcohol sensors including long-term health tracking, medical monitoring, and just-in-time relapse prevention.

Natural language processing in mixed-methods evaluation of a digital sleep-alcohol intervention for young adults

We used natural language processing (NLP) in convergent mixed methods to evaluate young adults' experiences with Call it a Night (CIAN), a digital personalized feedback and coaching sleep-alcohol intervention. Young adults with heavy drinking (N = 120) were randomized to CIAN or controls (A + SM: web-based advice + self-monitoring or A: advice; clinicaltrials.gov, 8/31/18, #NCT03658954). Most CIAN participants (72.0%) preferred coaching to control interventions. Control participants found advice more helpful than CIAN participants (X2 = 27.34, p < 0.001). Most participants were interested in sleep factors besides alcohol and appreciated increased awareness through monitoring. NLP corroborated generally positive sentiments (M = 15.07(10.54)) and added critical insight that sleep (40%), not alcohol use (12%), was a main participant motivator. All groups had high adherence, satisfaction, and feasibility. CIAN (Δ = 0.48, p = 0.008) and A + SM (Δ = 0.55, p < 0.001) had higher reported effectiveness than A (F(2, 115) = 8.45, p < 0.001). Digital sleep-alcohol interventions are acceptable, and improving sleep and wellness may be important motivations for young adults.

A qualitative exploration of the experiences of transdermal alcohol sensor devices amongst people in receipt of treatment for alcohol use disorder

Introduction

Transdermal alcohol sensors (TAS) have the potential to be used as a clinical tool in alcohol treatment, but there is limited research with individuals with alcohol dependence using TAS. Our study is a qualitative evaluation of the views of people attending alcohol treatment and their experiences of wearing the BACtrack Skyn, within alcohol services in South London.

Methods

Participants with alcohol dependence wore a BACtrack Skyn TAS for one week and met with the researcher every two days, for a total of four meetings (for example: Monday, Wednesday, Friday, and Monday). In the final meeting, a post-wear survey (on their physical, social and comfort experience of the TAS) and semi-structured interview were completed. The Technology Acceptance Model (TAM) informed the topic guide and data analysis.

Results

Adults (N = 16) receiving alcohol treatment were recruited. Three core topics guided analysis: perceived usefulness, perceived ease of use and attitudes towards use. Participants found the TAS easy to wear and felt positive about its appearance and comfort. The only challenges reported were side effects, mostly skin irritation. The main two perceived uses were 1) TAS working as a drinking deterrent and 2) reducing daily breathalyser visits during detox.

Conclusion

Findings support the use of TAS amongst alcohol service users. Wearing the TAS for one week was acceptable and feasible for objective alcohol concentration measurement. Participants reported high perceived ease of use and usefulness of the Skyn in the context of alcohol treatment. These results are encouraging for the use of TAS in clinical settings.

Baseline protective behavioral strategy use predicts more moderate transdermal alcohol concentration dynamics and fewer negative consequences of drinking in young adults' natural settings

OBJECTIVE

Test whether frequent protective behavioral strategies (PBS) users report (a) fewer alcohol-related consequences and (b) less risky alcohol intoxication dynamics (measured via transdermal alcohol concentration [TAC] sensor "features") in daily life.

METHOD

Two hundred twenty-two frequently heavy-drinking young adults (Mage = 22.3 years) wore TAC sensors for 6 consecutive days. TAC features peak (maximum TAC), rise rate (speed of TAC increase), and area under the curve (AUC) were derived for each day. Negative alcohol-related consequences were measured in the morning after each self-reported drinking day. Past-year PBS use was measured at baseline.

RESULTS

Young adults reporting more frequent baseline PBS use showed (a) fewer alcohol-related consequences and (b) lower intoxication dynamics on average (less AUC, lower peaks, and slower rise rates). Limiting/stopping and manner of drinking PBS showed the same pattern of findings as the total score. Serious harm reduction PBS predicted fewer negative alcohol-related consequences, but not TAC features. Multilevel path models showed that TAC features peak and rise rate partially explained associations between PBS (total, limiting/stopping, and manner of drinking) and consequences. Independent contributions of PBS subscales were small and nonsignificant, suggesting that total PBS use was a more important predictor of risk/protection than the specific types of PBS used.

CONCLUSIONS

Young adults using more total PBS may experience fewer alcohol-related consequences during real-world drinking episodes in part through less risky intoxication dynamics (TAC features). Future research measuring PBS at the daily level is needed to formally test TAC features as day-level mechanisms of protection from acute alcohol-related consequences. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Transdermal alcohol concentration features predict alcohol-induced blackouts in college students

BACKGROUND

Alcohol-induced blackouts (AIBs) are common in college students. Individuals with AIBs also experience acute and chronic alcohol-related consequences. Research suggests that how students drink is an important predictor of AIBs. We used transdermal alcohol concentration (TAC) sensors to measure biomarkers of increasing alcohol intoxication (rise rate, peak, and rise duration) in a sample of college students. We hypothesized that the TAC biomarkers would be positively associated with AIBs.

METHODS

Students were eligible to participate if they were aged 18-22 years, in their second or third year of college, reported drinking 4+ drinks on a typical Friday or Saturday, experienced ≥1 AIB in the past semester, owned an iPhone, and were willing to wear a sensor for 3 days each weekend. Students (N = 79, 55.7% female, 86.1% White, Mage = 20.1) wore TAC sensors and completed daily diaries over four consecutive weekends (89.9% completion rate). AIBs were assessed using the Alcohol-Induced Blackout Measure-2. Logistic multilevel models were conducted to test for main effects.

RESULTS

Days with faster TAC rise rates (OR = 2.69, 95% CI: 1.56, 5.90), higher peak TACs (OR = 2.93, 95% CI: 1.64, 7.11), and longer rise TAC durations (OR = 4.16, 95% CI: 2.08, 10.62) were associated with greater odds of experiencing an AIB.

CONCLUSIONS

In a sample of "risky" drinking college students, three TAC drinking features identified as being related to rising intoxication independently predicted the risk for daily AIBs. Our findings suggest that considering how an individual drinks (assessed using TAC biomarkers), rather than quantity alone, is important for assessing risk and has implications for efforts to reduce risk. Not only is speed of intoxication important for predicting AIBs, but the height of the peak intoxication and the time spent reaching the peak are important predictors, each with different implications for prevention.

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).

Leveraging Natural Language Processing to Evaluate Young Adults' User Experiences with a Digital Sleep Intervention for Alcohol Use

Evaluating user experiences with digital interventions is critical to increase uptake and adherence, but traditional methods have limitations. We incorporated natural language processing (NLP) with convergent mixed methods to evaluate a personalized feedback and coaching digital sleep intervention for alcohol risk reduction: 'Call it a Night' (CIAN; N = 120). In this randomized clinical trial with young adults with heavy drinking, control conditions were A + SM: web-based advice + active and passive monitoring; and A: advice + passive monitoring. Findings converged to show that the CIAN treatment condition group found feedback and coaching most helpful, whereas participants across conditions generally found advice helpful. Further, most participants across groups were interested in varied whole-health sleep-related factors besides alcohol use (e.g., physical activity), and many appreciated increased awareness through monitoring with digital tools. All groups had high adherence, satisfaction, and reported feasibility, but participants in CIAN and A + SM reported significantly higher effectiveness than those in A. NLP corroborated positive sentiments across groups and added critical insight that sleep, not alcohol use, was a main participant motivator. Digital sleep interventions are an acceptable, novel alcohol treatment strategy, and improving sleep and overall wellness may be important motivations for young adults. Further, NLP provides an efficient convergent method for evaluating experiences with digital interventions.

Comparison of transdermal alcohol concentration and self-reported alcohol consumption in people with alcohol dependence attending community alcohol treatment services

AIM

We aimed to assess the accuracy and wearability of a transdermal alcohol sensor (TAS) (BACtrack Skyn) with people currently receiving treatment at alcohol services.

METHOD

A mixed methods observational study involving three NHS alcohol services in south London was conducted. All participants (7=male, 9=female) wore a TAS for 1 week and met with the researcher every other weekday to complete the TAS data download and a TimeLine Follow Back (TLFB). At the end of the week, a post-wear survey was completed. Transdermal Alcohol Concentration (TAC) from the TAS was compared to the TLFB. Post-wear survey responses, attendance voucher incentives and descriptive TAS data (removals, missing and skin temperature data) were analysed. We investigated different drinking event thresholds changing the criteria of TAC level and length of time TAC was increased and analysed each drinking threshold sensitivity, specificity, positive and negative predicative values, and percentage accuracy classification.

RESULTS

The TAS recorded the number of alcohol-drinking days with a high degree of accuracy compared to the TLFB as gold-standard. However, of the participation time of the 16 participants, 14.5% of the TAS data was missing in output and 16.4% of the recorded data suggests the TAS was not currently being worn. Of the data recorded, in line with the drinking event threshold of >15 ug/l TAC, >15minutes, we found that sensitivity = 93%, specificity = 84% and a Pearson correlation of r(16) =.926, p = <.001, BCa 95% CI [.855 -.981]. The threshold with the highest accuracy was TAC>15 ug/l, >60minutes which classified alcohol events with 90% accuracy, AUC =.910, sensitivity = 90%, specificity = 96%. The post-wear survey reported that most participants found it comfortable and that wearing it did not interfere with daily activities. Six participants reported side effects, including itching and a rash, but these would not deter them from wearing it again with all six reporting they would wear the TAS again and for longer than one week.

CONCLUSIONS

The TAS did not capture every drinking event that was self-reported but maintained a high correlation. There were instances of missing TAS data and TAS removals. Overall, our findings would support the acceptability and feasibility of TAS as a tool that could be used in clinical settings for objective alcohol monitoring with patients being responsible for the TAS.

Accuracy of transdermal alcohol monitoring devices in a laboratory setting

The development of transdermal alcohol sensors (TASs) presents a new method to monitor alcohol consumption with the ability to objectively measure data 24/7. We aimed to evaluate the accuracy of two TASs (BACtrack Skyn and Smart Start BARE) in a laboratory setting. Thirty-two adults received a dose of ethanol 0.56 g/kg body weight as a 20% solution while wearing the two TASs and provided Breath Alcohol Concentration (BrAC) measurements for 3.5 h postalcohol consumption. Pearson's correlations and repeated measures analysis of variance tests were conducted on the peak, time-to-peak, and area under the curve data. Bland-Altman plots were derived. A time series analysis and cross-correlations were conducted to adjust for time lag. Both TASs were able to detect alcohol and increase within 20 min. BrAC peaked significantly quicker than Skyn and BARE. BrAC and Skyn peaks were negatively significantly correlated (r = -0.381, P = .035, n = 31), while Skyn and BARE peaks were positively significantly correlated (r = 0.380, P = .038, n = 30). Repeated measures analysis of variance found a significant difference between BrAC, Skyn, and BARE (F(1.946, 852.301) = 459.873, P < .001)). A time series analysis found when BrAC-Skyn and BrAC-BARE were adjusted for the delay to peak, and there was still a significant difference. Failure rates: 1.7% (Skyn) and 4.8% (BARE). Some evidence was obtained for TAS validity as both consistently detected alcohol. Failure rates and time lag show improvements in older device generations. However, neither TAS presented strong equivalence to the breathalyser even when the lag time was adjusted. With further testing and technology advancements, TAS could be a potential alcohol monitoring tool. Two of the newest TAS devices were worn in laboratory conditions for one afternoon to compare their accuracy of alcohol monitoring to a breathalyser. Findings suggest that the two TASs (BACtrack Skyn and SmartStart BARE) recorded significantly similar data postalcohol consumption, but not with the breathalyser.

Acceptability and anklet user experience with the SCRAM-CAM transdermal alcohol concentration sensor in regularly drinking young adults' natural environments

Recent developments in wearable technologies have allowed for device-based capture of alcohol concentration among participants in their natural environments. Currently, the Continuous Alcohol Monitor from SCRAM systems (SCRAM-CAM) is the most extensively studied and validated transdermal alcohol concentration (TAC) sensor. However, there has been relatively little work focusing on its acceptability from the participants' perspective. In the current study, we assess the user experience of the SCRAM-CAM anklet in a sample of 222 regularly heavy drinking young adults (mean age = 22.3) who wore the anklet in their natural environments for five 24-h periods spanning 6 consecutive days. Differences in the anklet user experience were measured along a number of dimensions, and differences were tested by sex at birth, white/non-white racial/ethnic group membership, and alcohol use disorder (AUD) risk (measured through Alcohol Use Disorder Identification Test [AUDIT] scores). Males and females differed significantly on six of the eight acceptability items, with males showing more positive responses toward the anklet than females. No differences were found by white/non-white racial/ethnic groups nor AUD risk. Results suggest positive levels of acceptability toward the device overall while in natural environments, further validating the usage of the device in studies that measure alcohol consumption among different groups, including those with high levels of alcohol consumption. Researchers should take into consideration the different levels of burden or discomfort in male versus female participants when using the device.

Flux-Type versus Concentration-Type Sensors in Transdermal Measurements

New transdermal biosensors measure analytes that diffuse from the bloodstream through the skin, making it important to reduce the system response time and understand measurement output. While highly customized models have been created for specific sensors, a generalized model for transdermal sensor systems is lacking. Here, a simple one-dimensional diffusion model was used to characterize the measurement system and classify biosensors as either flux types or concentration types. Results showed that flux-type sensors have significantly faster response times than concentration sensors. Furthermore, flux sensors do not measure concentration, but rather have an output measurement that is proportional to skin permeability. These findings should lead to an improved understanding of transdermal measurements and their relation to blood analyte concentration. In the realm of alcohol research, where the majority of commercially available sensors are flux types, our work advocates toward moving away from transdermal alcohol concentration as a metric, and instead suggests embracing transdermal alcohol flux as a more suitable alternative.

Use of the BACtrack Skyn alcohol biosensor: Practical applications for data collection and analysis

AIMS

Alcohol biosensors, including the BACtrack Skyn, provide an objective and passive method of continuously assessing alcohol consumption in the natural environment. Despite the many strengths of the Skyn, six key challenges in the collection and processing of data include (1) identifying consumed alcohol; (2) identifying environmental alcohol; (3) identifying and determining the source of missing or invalid data; (4) achieving high participant adherence; (5) integrating Skyn and self-report data; and (6) implications for statistical inference. In this report we outline these challenges, provide recommendations to address them and identify future needs.

DESIGN AND SETTINGS

Procedures from several laboratory and field-based pilot studies are presented to demonstrate practical recommendations for Skyn use. Data from a pilot study including a 7-day ecological momentary assessment period are also presented to evaluate effects of environmental alcohol on BACtrack Skyn readings.

CONCLUSIONS

To address challenges in the collection and processing of data from the BACtrack Skyn alcohol biosensor, researchers should identify goals in advance of data collection to anticipate the processing necessary to interpret Skyn data. The Transdermal Alcohol Sensor Data Macro (TASMAC) version 2.0 software can help to process data rapidly; identify drinking events, missing data and environmental alcohol; and integrate the sensor with self-report data. Thorough participant orientation and regular contact in field studies can reduce missing data and enhance adherence. Many recommended methods for Skyn use are applicable to other alcohol sensors and wearable devices.

Acceptability and validity of using the BACtrack skyn wrist-worn transdermal alcohol concentration sensor to capture alcohol use across 28 days under naturalistic conditions - A pilot study

Wrist-worn transdermal alcohol concentration (TAC) sensors have the potential to provide detailed information about day-level features of alcohol use but have rarely been used in field-based research or in early adulthood (i.e., 26-40 years) alcohol users. This pilot study assessed the acceptability, user burden, and validity of using the BACtrack Skyn across 28 days in individuals' natural settings. Adults aged 26-37 (N = 11, Mage = 31.2, 55% female, 73% non-Hispanic white) participated in a study including retrospective surveys, a 28-day field protocol wearing Skyn and SCRAM sensors and completing ecological momentary assessments (EMA) of alcohol use and duration (daily morning reports and participant-initiated start/stop drinking EMAs), and follow-up interviews. Day-level features of alcohol use extracted from self-reports and/or sensors included drinks consumed, estimated Blood Alcohol Concentration (eBAC), drinking duration, peak TAC, area under the curve (AUC), rise rate, and fall rate. Repeated-measures correlations (rrm) tested within-person associations between day-level features of alcohol use from the Skyn versus self-report or the SCRAM. Participants preferred wearing the Skyn over the SCRAM [t (10) = -6.79, p < .001, d = 2.74]. Skyn data were available for 5614 (74.2%) out of 7566 h, with 20.7% of data lost due to syncing/charging issues and 5.1% lost due to device removal. Skyn agreement for detecting drinking days was 55.5% and 70.3% when compared to self-report and the SCRAM, respectively. Correlations for drinking intensity between self-report and the Skyn were 0.35 for peak TAC, 0.52 for AUC, and 0.30 for eBAC, which were smaller than correlations between self-report and SCRAM, at 0.78 for peak TAC, 0.79 for AUC, and 0.61 for eBAC. Correlations for drinking duration were larger when comparing self-report to the Skyn (rrm = 0.36) versus comparing self-report to the SCRAM (rrm = 0.31). The Skyn showed moderate-to-large, significant correlations with the SCRAM for peak TAC (rrm = 0.54), AUC (rrm = 0.80), and drinking duration (rrm = 0.63). Our findings support the acceptability and validity of using the Skyn for assessing alcohol use across an extended time frame (i.e., 28 days) in individuals' natural settings, and for providing useful information about day-level features of alcohol use.

Correspondence between alcohol use measured by a wrist-worn alcohol biosensor and self-report via ecological momentary assessment over a 2-week period

BACKGROUND

Transdermal alcohol biosensors measure alcohol use continuously, passively, and non-invasively. There is little field research on the Skyn biosensor, a new-generation, wrist-worn transdermal alcohol biosensor, and little evaluation of its sensitivity and specificity and the day-level correspondence between transdermal alcohol concentration (TAC) and number of self-reported drinks.

METHODS

Participants (N = 36; 61% male, M age  = 34.3) wore the Skyn biosensor and completed ecological momentary assessment (EMA) surveys about their alcohol use over 2 weeks. A total of 497 days of biosensor and EMA data were collected. Skyn-measured drinking episodes were defined by TAC > 5 μg/L. Skyn data were compared to self-reported drinking to calculate sensitivity and specificity (for drinking day vs. nondrinking day). Generalized estimating equations models were used to evaluate the correspondence between TAC features (peak TAC and TAC-area under the curve (AUC)) and number of drinks. Individual-level factors (sex, age, race/ethnicity, body mass index, human immunodeficiency virus status, and hazardous drinking) were examined to explore associations with TAC controlling for number of drinks.

RESULTS

Using a minimum TAC threshold of 5 μg/L plus coder review, the biosensor had sensitivity of 54.7% and specificity of 94.6% for distinguishing drinking from nondrinking days. Without coder review, the sensitivity was 78.1% and the specificity was 55.2%. Peak TAC (β = 0.92, p < 0.0001) and TAC-AUC (β = 1.60, p < 0.0001) were significantly associated with number of drinks. Females had significantly higher TAC levels than males for the same number of drinks.

CONCLUSIONS

Skyn-derived TAC can be used to measure alcohol use under naturalistic drinking conditions, additional research is needed to accurately identify drinking episodes based on Skyn TAC readings.

Examining new-generation transdermal alcohol biosensor performance across laboratory and field contexts

BACKGROUND

Wrist-worn transdermal alcohol sensors have the potential to change how alcohol consumption is measured. However, hardware and data analytic challenges associated with transdermal sensor data have kept these devices from widespread use. Given recent technological and analytic advances, this study provides an updated account of the performance of a new-generation wrist-worn transdermal sensor in both laboratory and field settings.

METHODS

This work leverages machine learning models to convert transdermal alcohol concentration data into estimates of Breath Alcohol Concentration (BrAC) in a large-scale laboratory sample (N = 256, study 1) and a pilot field sample (N = 27, study 2). Specifically, in both studies, the accuracy of the translation is evaluated by comparing BAC estimates yielded by BACtrack Skyn to real-time breathalyzer measurements collected in the laboratory and in the field.

RESULTS

The newest version of the Skyn device demonstrates a substantially lower error rate than older hand-assembled prototypes (0% to 7% vs. 29% to 53%, respectively). On average, real-time estimates of BrAC yielded by these transdermal sensors are within 0.007 of true BAC readings in the laboratory context and within 0.019 of true BrAC readings in the field. In both contexts, the distance between true and estimated BrAC was larger when only alcohol episodes were examined (laboratory = 0.017; field = 0.041). Finally, results of power-law-curve projections indicate that, given their accuracy, transdermal BrAC estimates in real-world contexts have the potential to improve markedly (>25%) with adequately sized datasets for model training.

CONCLUSION

Findings from this study indicate that the latest version of the transdermal wrist sensor holds promise for the accurate assessment of alcohol consumption in field contexts. A great deal of additional work is needed to provide a full picture of the utility of these devices, including research with large participant samples in field contexts.