RESUMEN
ACMT recognizes the pivotal role of high-quality research in advancing medical science. As such, the establishment of a formal research agenda for ACMT is a leap forward in communicating the priorities of the College, its members, and the patient populations we serve. This thoughtfully crafted agenda will serve as a strategic compass for ACMT, guiding our pursuit of scientific discovery, fostering innovation, and enhancing outcomes for patients and communities affected by poisonings and exposures.
Asunto(s)
Investigación Biomédica , Toxicología , Humanos , Estados Unidos , Sociedades MédicasRESUMEN
BACKGROUND: Digital health interventions offer opportunities to expand access to substance use disorder (SUD) treatment, collect objective real-time data, and deliver just-in-time interventions: however implementation has been limited. RAE (Realize, Analyze, Engage) Health is a digital tool which uses continuous physiologic data to detect high risk behavioral states (stress and craving) during SUD recovery. METHODS: This was an observational study to evaluate the digital stress and craving detection during outpatient SUD treatment. Participants were asked to use the RAE Health app, wear a commercial-grade wrist sensor over a 30-day period. They were asked to self-report stress and craving, at which time were offered brief in-app de-escalation tools. Supervised machine learning algorithms were applied retrospectively to wearable sensor data obtained to develop group-based digital biomarkers for stress and craving. Engagement was assessed by number of days of utilization, and number of hours in a given day of connection. RESULTS: Sixty percent of participants (N=30) completed the 30-day protocol. The model detected stress and craving correctly 76 % and 69 % of the time, respectively, but with false positive rates of 33 % and 28 % respectively. All models performed close to previously validated models from a research grade sensor. Participants used the app for a mean of 14.2 days (SD 10.1) and 11.7 h per day (SD 8.2). Anxiety disorders were associated with higher mean hours per day connected, and return to drug use events were associated with lower mean hours per day connected. CONCLUSIONS: Future work should explore the effect of similar digital health systems on treatment outcomes and the optimal dose of digital interventions needed to make a clinically significant impact.
Asunto(s)
Ansia , Estrés Psicológico , Trastornos Relacionados con Sustancias , Adulto , Femenino , Humanos , Masculino , Persona de Mediana Edad , Adulto Joven , Ansia/fisiología , Aplicaciones Móviles , Estrés Psicológico/diagnóstico , Trastornos Relacionados con Sustancias/terapia , Dispositivos Electrónicos VestiblesRESUMEN
Subpopulation models have become of increasing interest in prediction of clinical outcomes because they promise to perform better for underrepresented patient subgroups. However, the personalization benefits gained from these models tradeoff their statistical power, and can be impractical when the subpopulation's sample size is small. We hypothesize that a hierarchical model in which population information is integrated into subpopulation models would preserve the personalization benefits and offset the loss of power. In this work, we integrate ideas from ensemble modeling, personalization, and hierarchical modeling and build ensemble-based subpopulation models in which specialization relies on whole group samples. This approach significantly improves the precision of the positive class, especially for the underrepresented subgroups, with minimal cost to the recall. It consistently outperforms one model for all and one model for each subgroup approaches, especially in the presence of a high class-imbalance, for subgroups with at least 380 training samples.
RESUMEN
Digital health interventions are exploding in today's medical practice and have tremendous potential to support the treatment of substance use disorders (SUD). Developers and healthcare providers alike must be cognizant of the potential for digital interventions to exacerbate existing inequities in SUD treatment, particularly as they relate to Social Determinants of Health (SDoH). To explore this evolving area of study, this manuscript will review the existing concepts of the digital divide and digital inequities, and the role SDoH play as drivers of digital inequities. We will then explore how the data used and modeling strategies can create bias in digital health tools for SUD. Finally, we will discuss potential solutions and future directions to bridge these gaps including smartphone ownership, Wi-Fi access, digital literacy, and mitigation of historical, algorithmic, and measurement bias. Thoughtful design of digital interventions is quintessential to reduce the risk of bias, decrease the digital divide, and create equitable health outcomes for individuals with SUD.
RESUMEN
Syndromic surveillance is an effective tool for enabling the timely detection of infectious disease outbreaks and facilitating the implementation of effective mitigation strategies by public health authorities. While various information sources are currently utilized to collect syndromic signal data for analysis, the aggregated measurement of cough, an important symptom for many illnesses, is not widely employed as a syndromic signal. With recent advancements in ubiquitous sensing technologies, it becomes feasible to continuously measure population-level cough incidence in a contactless, unobtrusive, and automated manner. In this work, we demonstrate the utility of monitoring aggregated cough count as a syndromic indicator to estimate COVID-19 cases. In our study, we deployed a sensor-based platform (Syndromic Logger) in the emergency room of a large hospital. The platform captured syndromic signals from audio, thermal imaging, and radar, while the ground truth data were collected from the hospital's electronic health record. Our analysis revealed a significant correlation between the aggregated cough count and positive COVID-19 cases in the hospital (Pearson correlation of 0.40, p-value < 0.001). Notably, this correlation was higher than that observed with the number of individuals presenting with fever (ρ = 0.22, p = 0.04), a widely used syndromic signal and screening tool for such diseases. Furthermore, we demonstrate how the data obtained from our Syndromic Logger platform could be leveraged to estimate various COVID-19-related statistics using multiple modeling approaches. Aggregated cough counts and other data, such as people density collected from our platform, can be utilized to predict COVID-19 patient visits related metrics in a hospital waiting room, and SHAP and Gini feature importance-based metrics showed cough count as the important feature for these prediction models. Furthermore, we have shown that predictions based on cough counting outperform models based on fever detection (e.g., temperatures over 39°C), which require more intrusive engagement with the population. Our findings highlight that incorporating cough-counting based signals into syndromic surveillance systems can significantly enhance overall resilience against future public health challenges, such as emerging disease outbreaks or pandemics.
Asunto(s)
COVID-19 , Vigilancia de Guardia , Humanos , COVID-19/epidemiología , Salas de Espera , Hospitales , Brotes de Enfermedades/prevención & control , Fiebre/epidemiologíaRESUMEN
Long-term and high-dose prescription opioid use places individuals at risk for opioid misuse, opioid use disorder (OUD), and overdose. Existing methods for monitoring opioid use and detecting misuse rely on self-reports, which are prone to reporting bias, and toxicology testing, which may be infeasible in outpatient settings. Although wearable technologies for monitoring day-to-day health metrics have gained significant traction in recent years due to their ease of use, flexibility, and advancements in sensor technology, their application within the opioid use space remains underexplored. In the current work, we demonstrate that oral opioid administrations can be detected using physiological signals collected from a wrist sensor. More importantly, we show that models informed by opioid pharmacokinetics increase reliability in predicting the timing of opioid administrations. Forty-two individuals who were prescribed opioids as a part of their medical treatment in-hospital and after discharge were enrolled. Participants wore a wrist sensor throughout the study, while opioid administrations were tracked using electronic medical records and self-reports. We collected 1,983 hours of sensor data containing 187 opioid administrations from the inpatient setting and 927 hours of sensor data containing 40 opioid administrations from the outpatient setting. We demonstrate that a self-supervised pre-trained model, capable of learning the canonical time series of plasma concentration of the drug derived from opioid pharmacokinetics, can reliably detect opioid administration in both settings. Our work suggests the potential of pharmacokinetic-informed, data-driven models to objectively detect opioid use in daily life.
RESUMEN
Digital phenotyping is a process that allows researchers to leverage smartphone and wearable data to explore how technology use relates to behavioral health outcomes. In this Research Concepts article, we provide background on prior research that has employed digital phenotyping; the fundamentals of how digital phenotyping works, using examples from participant data; the application of digital phenotyping in the context of substance use and its syndemics; and the ethical, legal and social implications of digital phenotyping. We discuss applications for digital phenotyping in medical toxicology, as well as potential uses for digital phenotyping in future research. We also highlight the importance of obtaining ground truth annotation in order to identify and establish digital phenotypes of key behaviors of interest. Finally, there are many potential roles for medical toxicologists to leverage digital phenotyping both in research and in the future as a clinical tool to better understand the contextual features associated with drug poisoning and overdose. This article demonstrates how medical toxicologists and researchers can progress through phases of a research trajectory using digital phenotyping to better understand behavior and its association with smartphone usage.
Asunto(s)
Trastornos Relacionados con Sustancias , Dispositivos Electrónicos Vestibles , Humanos , Teléfono Inteligente , Sindémico , Fenotipo , Trastornos Relacionados con Sustancias/diagnóstico , Trastornos Relacionados con Sustancias/epidemiologíaRESUMEN
BACKGROUND: Respiratory rate is a crucial indicator of disease severity yet is the most neglected vital sign. Subtle changes in respiratory rate may be the first sign of clinical deterioration in a variety of disease states. Current methods of respiratory rate monitoring are labor-intensive and sensitive to motion artifacts, which often leads to inaccurate readings or underreporting; therefore, new methods of respiratory monitoring are needed. The PulsON 440 (P440; TSDR Ultra Wideband Radios and Radars) radar module is a contactless sensor that uses an ultrawideband impulse radar to detect respiratory rate. It has previously demonstrated accuracy in a laboratory setting and may be a useful alternative for contactless respiratory monitoring in clinical settings; however, it has not yet been validated in a clinical setting. OBJECTIVE: The goal of this study was to (1) compare the P440 radar module to gold standard manual respiratory rate monitoring and standard of care telemetry respiratory monitoring through transthoracic impedance plethysmography and (2) compare the P440 radar to gold standard measurements of respiratory rate in subgroups based on sex and disease state. METHODS: This was a pilot study of adults aged 18 years or older being monitored in the emergency department. Participants were monitored with the P440 radar module for 2 hours and had gold standard (manual respiratory counting) and standard of care (telemetry) respiratory rates recorded at 15-minute intervals during that time. Respiratory rates between the P440, gold standard, and standard telemetry were compared using Bland-Altman plots and intraclass correlation coefficients. RESULTS: A total of 14 participants were enrolled in the study. The P440 and gold standard Bland-Altman analysis showed a bias of -0.76 (-11.16 to 9.65) and an intraclass correlation coefficient of 0.38 (95% CI 0.06-0.60). The P440 and gold standard had the best agreement at normal physiologic respiratory rates. There was no change in agreement between the P440 and the gold standard when grouped by admitting diagnosis or sex. CONCLUSIONS: Although the P440 did not have statistically significant agreement with gold standard respiratory rate monitoring, it did show a trend of increased agreement in the normal physiologic range, overestimating at low respiratory rates, and underestimating at high respiratory rates. This trend is important for adjusting future models to be able to accurately detect respiratory rates. Once validated, the contactless respiratory monitor provides a unique solution for monitoring patients in a variety of settings.
RESUMEN
Once-daily oral HIV pre-exposure prophylaxis (PrEP) is an effective strategy to prevent HIV, but is highly dependent on adherence. Men who have sex with men (MSM) who use substances face unique challenges maintaining PrEP adherence. Digital pill systems (DPS) allow for real-time adherence measurement through ingestible sensors. Integration of DPS technology with other digital health tools, such as digital phenotyping, may improve understanding of nonadherence triggers and development of personalized adherence interventions based on ingestion behavior. This study explored the willingness of MSM with substance use to share digital phenotypic data and interact with ancillary systems in the context of DPS-measured PrEP adherence. Adult MSM on PrEP with substance use were recruited through a social networking app. Participants were introduced to DPS technology and completed an assessment to measure willingness to participate in DPS-based PrEP adherence research, contribute digital phenotyping data, and interact with ancillary systems in the context of DPS-based research. Medical mistrust, daily worry about PrEP adherence, and substance use were also assessed. Participants who identified as cisgender male and were willing to participate in DPS-based research (N = 131) were included in this subsample analysis. Most were White (76.3%) and non-Hispanic (77.9%). Participants who reported daily PrEP adherence worry had 3.7 times greater odds (95% CI: 1.03, 13.4) of willingness to share biometric data via a wearable device paired to the DPS. Participants with daily PrEP adherence worry were more likely to be willing to share smartphone data (p = 0.006) and receive text messages surrounding their daily activities (p = 0.003), compared to those with less worry. MSM with substance use disorder, who worried about PrEP adherence, were willing to use DPS technology and share data required for digital phenotyping in the context of PrEP adherence measurement. Efforts to address medical mistrust can increase advantages of this technology for HIV prevention.
RESUMEN
OBJECTIVES: Opioid overdose deaths remain a major health issue in the United States (US). As future physicians, medical students must receive comprehensive training to recognize and manage opioid overdoses. This study aimed to highlight training gaps at the medical student level and understand students' attitudes toward patients with opioid use disorder (OUD). METHODS: We assessed baseline knowledge of and attitudes toward the management of opioid overdoses and naloxone administration among medical students in the US. Two validated survey tools (Opioid Overdose Knowledge Scale and Opioid Overdose Attitude Scale) were administered to medical students training at accredited institutions along with supplemental questions measuring knowledge and attitudes towards opioid overdose management, naloxone administration, and prior training. RESULTS: The final sample had N = 73 participants from US medical schools with a mean age of 25.3 (range of 22-37): 72.6% of respondents were female. Although most respondents reported personal/professional experience with OUD before medical school, they expressed interest in additional training. Knowledge surrounding opioid overdoses increased insignificantly over the 4 years of medical school. However, there was a significant increase in both perceived competence in overdose recognition/management and in concerns about intervening from the first to fourth year of medical school. Female respondents had significantly lower perceived competence and readiness to intervene sub-scores than male counterparts; however, there was no significant difference in overall attitude and knowledge scores when stratified by sex. Incorporating opioid overdose prevention training (OOPT) into early medical education was favorable among respondents, who expressed an overwhelming interest in learning and supporting patients with OUD. CONCLUSIONS: Given the ongoing opioid crisis, medical students are ideally placed to identify and manage opioid overdoses. Medical students are ready to receive this training, thus strengthening the argument for OOPT integration into early medical student curricula.
RESUMEN
INTRODUCTION: ∆-8 tetrahydrocannabinol (THC) is a psychoactive cannabinoid and structural isomer of ∆-9 THC that is technically legal under United States Federal law. Commercial ∆-8-THC products being sold are currently unregulated. This study aims to (1) describe the advertising and labeling of Δ-8 THC retail products; (2) compare the advertised amount of Δ-8 THC for each product to that found during independent laboratory analysis; and (3) evaluate the presence and amount of other cannabinoids in those products. METHODS: Twenty ∆-8 THC products were purchased from retail stores in Pittsburgh, PA, USA. Samples were analyzed to determine cannabinoid content using a validated UPLC-MS/MS method. Descriptive statistics were calculated for all variables. Spearman's rank order correlation was calculated for the labeled ∆-8 THC content compared to ∆-8 THC content found on our analysis. Differences in continuous variables were compared using ANOVA, Wilcoxon Rank Sum, or Kruskal-Wallis tests. RESULTS: ∆-8 THC was detected in 95% (N=19) of the sample products. A weakly positive correlation (Spearman's rho =0.40) was found between the advertised ∆-8 THC content and our analysis results. Factors associated with decreased difference in these variables included (1) solid matrix (chocolate, gummies) and (2) absence of a "lab-tested" label. Δ-9 THC was found in 35% (N=7) of the products, and CBD was found in one. CONCLUSION: A majority of the products analyzed contained ∆-8 THC in amounts that could cause intoxication. The range of ∆-8 THC content on independent analysis was wide and weakly correlated to the advertised content. ∆-8 THC, ∆-9 THC, and CBD were the only cannabinoids detected.
Asunto(s)
Cannabinoides , Cannabis , Humanos , Estados Unidos , Dronabinol , Cromatografía Liquida , Espectrometría de Masas en Tándem/métodosRESUMEN
Opioid use disorder (OUD) is one of the most pressing public health problems of the past decade, with over eighty thousand overdose related deaths in 2021 alone. Digital technologies to measure and respond to disease states encompass both on- and off-body sensors. Such devices can be used to detect and monitor end-user physiologic or behavioral measurements (i.e. digital biomarkers) that correlate with events of interest, health, or pathology. Recent work has demonstrated the potential of digital biomarkers to be used as a tools in the prevention, risk mitigation, and treatment of opioid use disorder (OUD). Multiple physiologic adaptations occur over the course of opioid use, and represent potential targets for digital biomarker based monitoring strategies. This review explores the current evidence (and potential) for digital biomarkers monitoring across the spectrum of opioid use. Technologies to detect opioid administration, withdrawal, hyperalgesia and overdose will be reviewed. Driven by empirically derived algorithms, these technologies have important implications for supporting the safe prescribing of opioids, reducing harm in active opioid users, and supporting those in recovery from OUD.
RESUMEN
Mainstays of opioid overdose prevention include medications for opioid use disorder (e.g., methadone or buprenorphine) and naloxone distribution. Inadequate access to buprenorphine limits its uptake, especially in communities of color, and people with opioid use disorders encounter multiple barriers to obtaining necessary medications including insurance, transportation, and consistent availability of telephones. UMass Memorial Medical Center and our community partners sought to alleviate these barriers to treatment through the deployment of a mobile addiction service, called the Road to Care. Using this approach, multidisciplinary and interprofessional providers deliver holistic addiction care by centering our patients' needs with respect to scheduling, location, and convenience. This program also extends access to buprenorphine and naloxone among people experiencing homelessness. Additional systemic and individualized barriers encountered are identified, as well as potential solutions for future mobile addiction service utilization. Over a two-year period, we have cared for 1,121 individuals who have accessed our mobile addiction service in over 4,567 encounters. We prescribed buprenorphine/naloxone (Suboxone®) to 330 individuals (29.4% of all patients). We have distributed nearly 250 naloxone kits directly on-site or and more than 300 kits via prescriptions to local pharmacies. To date, 74 naloxone rescue attempts have been reported back to us. We have demonstrated that a community-based mobile addiction service, anchored within a major medical center, can provide high-volume and high-quality overdose prevention services that facilitate engagement with additional treatment. Our experience is described as a case study below.
Asunto(s)
Buprenorfina , Sobredosis de Droga , Trastornos Relacionados con Opioides , Humanos , Servicios de Salud Comunitaria , Naloxona/uso terapéutico , Combinación Buprenorfina y Naloxona/uso terapéutico , Trastornos Relacionados con Opioides/prevención & control , Trastornos Relacionados con Opioides/tratamiento farmacológico , Buprenorfina/uso terapéutico , Sobredosis de Droga/tratamiento farmacológico , Sobredosis de Droga/prevención & controlRESUMEN
Syndromic surveillance is an effective tool for enabling the timely detection of infectious disease outbreaks and facilitating the implementation of effective mitigation strategies by public health authorities. While various information sources are currently utilized to collect syndromic signal data for analysis, the aggregated measurement of cough, an important symptom for many illnesses, is not widely employed as a syndromic signal. With recent advancements in ubiquitous sensing technologies, it becomes feasible to continuously measure population-level cough incidence in a contactless, unobtrusive, and automated manner. In this work, we demonstrate the utility of monitoring aggregated cough count as a syndromic indicator to estimate COVID-19 cases. In our study, we deployed a sensor-based platform (Syndromic Logger) in the emergency room of a large hospital. The platform captured syndromic signals from audio, thermal imaging, and radar, while the ground truth data were collected from the hospital's electronic health record. Our analysis revealed a significant correlation between the aggregated cough count and positive COVID-19 cases in the hospital (Pearson correlation of 0.40, p-value < 0.001). Notably, this correlation was higher than that observed with the number of individuals presenting with fever (ρ = 0.22, p = 0.04), a widely used syndromic signal and screening tool for such diseases. Furthermore, we demonstrate how the data obtained from our Syndromic Logger platform could be leveraged to estimate various COVID-19-related statistics using multiple modeling approaches. Our findings highlight the efficacy of aggregated cough count as a valuable syndromic indicator associated with the occurrence of COVID-19 cases. Incorporating this signal into syndromic surveillance systems for such diseases can significantly enhance overall resilience against future public health challenges, such as emerging disease outbreaks or pandemics.
RESUMEN
INTRODUCTION: Medications for addiction treatment (MAT) are the evidence-based standard of care for treatment of opioid use disorder (OUD), but stigma continues to surround their use. We conducted an exploratory study to characterize perceptions of different types of MAT among people who use drugs. METHODS: We conducted this qualitative study in adults with a history of non-medical opioid use who presented to an emergency department for complications of OUD. A semi-structured interview that explored knowledge, perceptions, and attitudes toward MAT was administered, and applied thematic analysis conducted. RESULTS: We enrolled 20 adults. All participants had prior experience with MAT. Among participants indicating a preferred treatment modality, buprenorphine was the commonly favored agent. Previous experience with prolonged withdrawal symptoms upon MAT discontinuation and the perception of "trading one drug for another" were common reasons for reluctance to engage in agonist or partial-agonist therapy. While some participants preferred treatment with naltrexone, others were unwilling to initiate antagonist therapy due to fear of precipitated withdrawal. Most participants strongly considered the aversive nature of MAT discontinuation as a barrier to initiating treatment. Participants overall viewed MAT positively, but many had strong preferences for a particular agent. CONCLUSION: The anticipation of withdrawal symptoms during initiation and cessation of treatment affected willingness to engage in a specific therapy. Future educational materials for people who use drugs may focus on comparisons of respective benefits and drawbacks of agonists, partial agonists, and antagonists. Emergency clinicians must be prepared to answer questions about MAT discontinuation to effectively engage patients with OUD.
Asunto(s)
Buprenorfina , Trastornos Relacionados con Opioides , Síndrome de Abstinencia a Sustancias , Adulto , Humanos , Tratamiento de Sustitución de Opiáceos , Trastornos Relacionados con Opioides/tratamiento farmacológico , Buprenorfina/uso terapéutico , Servicio de Urgencia en Hospital , Síndrome de Abstinencia a Sustancias/tratamiento farmacológico , Analgésicos Opioides/uso terapéuticoRESUMEN
Novel technologies have great potential to improve the treatment of individuals with substance use disorder (SUD) and to reduce the current high rate of relapse (i.e. return to drug use). Wearable sensor-based systems that continuously measure physiology can provide information about behavior and opportunities for real-time interventions. We have previously developed an mHealth system which includes a wearable sensor, a mobile phone app, and a cloud-based server with embedded machine learning algorithms which detect stress and craving. The system functions as a just-in-time intervention tool to help patients de-escalate and as a tool for clinicians to tailor treatment based on stress and craving patterns observed. However, in our pilot work we found that to deploy the system to diverse socioeconomic populations and to increase usability, the system must be able to work efficiently with cost-effective and popular commercial wearable devices. To make the system device agnostic, methods to transform the data from a commercially available wearable for use in algorithms developed from research grade wearable sensor are proposed. The accuracy of these transformations in detecting stress and craving in individuals with SUD is further explored.
RESUMEN
Prescription opioid use is a risk factor for the development of opioid use disorder. Digital solutions, including wearable sensors, represent a promising opportunity for health monitoring, risk stratification and harm reduction in this treatment space. However, data on their usability and acceptability in individuals using opioids is limited. To address this gap, factors that impact usability and acceptability of wearable sensor-based opioid detection were qualitatively studied in participants enrolled in a wearable sensor-based opioid monitoring research study. At the conclusion of the monitoring period, participants were invited to take part in semi-structured interviews developed based on the technology acceptance model. Thematic analysis was conducted first using deductive, then inductive coding strategies. Forty-four participants completed the interview; approximately half were female. Major emergent themes include sensor usability, change in behavior and thought process related to sensor use, perceived usefulness in sensor-based monitoring, and willingness to have opioid use patterns monitored. Overall acceptance for sensor-based monitoring was high. Aesthetics, simplicity, and seamless functioning were all reported as key to usability. Perceived behavior changes related to monitoring were infrequent while perceived usefulness in monitoring was frequently projected onto others, requiring careful consideration regarding intervention development and targeting. Specifically, care must be taken to avoid stigma associated with opioid use and implied misuse. The design of sensor systems targeted for opioid use must also consider the physical, social, and cognitive alterations inherent in the respective disease processes compared to routine daily life.
RESUMEN
Opioid use disorder is one of the most pressing public health problems of our time. Mobile health tools, including wearable sensors, have great potential in this space, but have been underutilized. Of specific interest are digital biomarkers, or end-user generated physiologic or behavioral measurements that correlate with health or pathology. The current manuscript describes a longitudinal, observational study of adult patients receiving opioid analgesics for acute painful conditions. Participants in the study are monitored with a wrist-worn E4 sensor, during which time physiologic parameters (heart rate/variability, electrodermal activity, skin temperature, and accelerometry) are collected continuously. Opioid use events are recorded via electronic medical record and self-report. Three-hundred thirty-nine discreet dose opioid events from 36 participant are analyzed among 2070 h of sensor data. Fifty-one features are extracted from the data and initially compared pre- and post-opioid administration, and subsequently are used to generate machine learning models. Model performance is compared based on individual and treatment characteristics. The best performing machine learning model to detect opioid administration is a Channel-Temporal Attention-Temporal Convolutional Network (CTA-TCN) model using raw data from the wearable sensor. History of intravenous drug use is associated with better model performance, while middle age, and co-administration of non-narcotic analgesia or sedative drugs are associated with worse model performance. These characteristics may be candidate input features for future opioid detection model iterations. Once mature, this technology could provide clinicians with actionable data on opioid use patterns in real-world settings, and predictive analytics for early identification of opioid use disorder risk.