Using wearable technology to detect prescription opioid self-administration

Moving towards the use of artificial intelligence in pain management

BACKGROUND AND OBJECTIVE

While the development of artificial intelligence (AI) technologies in medicine has been significant, their application to acute and chronic pain management has not been well characterized. This systematic review aims to provide an overview of the current state of AI in acute and chronic pain management.

DATABASES AND DATA TREATMENT

This review was registered with PROSPERO (ID# CRD42022307017), the international registry for systematic reviews. The search strategy was prepared by a librarian and run in four electronic databases (Embase, Medline, Central, and Web of Science). Collected articles were screened by two reviewers. Included studies described the use of AI for acute and chronic pain management.

RESULTS

From the 17,601 records identified in the initial search, 197 were included in this review. Identified applications of AI were described for treatment planning as well as treatment delivery. Described uses include prediction of pain, forecasting of individualized responses to treatment, treatment regimen tailoring, image-guidance for procedural interventions and self-management tools. Multiple domains of AI were used including machine learning, computer vision, fuzzy logic, natural language processing and expert systems.

CONCLUSION

There is growing literature regarding applications of AI for pain management, and their clinical use holds potential for improving patient outcomes. However, multiple barriers to their clinical integration remain including lack validation of such applications in diverse patient populations, missing infrastructure to support these tools and limited provider understanding of AI.

SIGNIFICANCE

This review characterizes current applications of AI for pain management and discusses barriers to their clinical integration. Our findings support continuing efforts directed towards establishing comprehensive systems that integrate AI throughout the patient care continuum.

Leveraging Trauma Informed Care for Digital Health Intervention Development in Opioid Use Disorder

Digital health refers to the use of information and communication technologies in medicine (including smartphone apps, wearables, other non-invasive sensors, informatics and telehealth platforms) to prevent illness, deliver treatment, and promote wellness. This rapidly proliferating group of technologies has the potential to reduce harm for people with opioid use disorder (OUD) and facilitate the recovery process; however, development in this space for OUD has been slower compared to that for other medical conditions. Unique issues with OUD management surrounding patient provider relationships, interaction with the healthcare system, autonomy and trust sometimes hinder care approaches, including those in digital health. The trauma informed care framework (TIC), developed for use by organizations to support individuals who have experienced trauma, has particular applicability for digital health interventions in OUD care. This manuscript will serve as a review of TIC principles and how they can be applied to digital health interventions to increase access, equity, and empowerment for people with OUD. We will highlight representative current and pipeline digital technologies for OUD, challenges with these technologies, TIC models for OUD, and the integration of TIC principles into digital technology development to better serve people with OUD. Finally, we will posit strategies to incorporate the aforementioned principles into future research efforts. We ultimately aim to use TIC as a lens through which to develop digital technologies to help individuals with OUD while minimizing harm.

Developing a Wearable Sensor-Based Digital Biomarker of Opioid Dependence

BACKGROUND

Repeated opioid exposure leads to a variety of physiologic adaptations that develop at different rates and may foreshadow risk of opioid-use disorder (OUD), including dependence and withdrawal. Digital pharmacovigilance strategies that use noninvasive sensors to identify physiologic adaptations to opioid use represent a novel strategy to facilitate safer opioid prescribing. This study aims to identify wearable sensor-derived features associated with opioid dependence by comparing opioid-naïve individuals to chronic opioid users with acute pain and developing a machine-learning model to distinguish between the 2 groups.

METHODS

Using a longitudinal observational study design, continuous physiologic data were collected on participants with acute pain receiving opioid analgesia. Monitoring continued throughout hospitalization and for up to 7 days posthospital discharge. Opioid administration data were obtained from electronic health record (EHR) and participant self-report. Participants were classified as belonging to 1 of 3 categories based on opioid use history: naïve, occasional, or chronic use. Thirty features were derived from sensor data, and an additional 9 features were derived from participant demographic and treatment characteristics. Physiologic feature behavior immediately postopioid use was compared among naïve and chronic participants, and subsequently features were used to generate machine learning models which were validated using cross-validation and holdout data.

RESULTS

Forty-one participants with a combined total of 169 opioid administrations were ultimately included in the final analysis. Four interpretable decision tree-based machine learning models with 14 sensor-based and 5 clinical features were developed to predict class membership on the level of a given observation (dose) and on the participant level. Ranges for model metrics on the participant level were as follows: accuracy 70% to 90%, sensitivity 67% to 100%, and specificity 67% to 100%.

CONCLUSIONS

Wearable sensor-derived digital biomarkers can be used to predict opioid use status (naïve versus chronic) and the differentiating features may be detecting opioid dependence. Future work should be aimed at further delineating the phenomenon identified in these models (including opioid dependence and/or withdrawal) and at identifying transition states where an individual changes from 1 profile to another with repetitive opioid exposure.

Users' Acceptability and Perceived Efficacy of mHealth for Opioid Use Disorder: Scoping Review

BACKGROUND

The opioid crisis continues to pose significant challenges to global public health, necessitating the development of novel interventions to support individuals in managing their substance use and preventing overdose-related deaths. Mobile health (mHealth), as a promising platform for addressing opioid use disorder, requires a comprehensive understanding of user perspectives to minimize barriers to care and optimize the benefits of mHealth interventions.

OBJECTIVE

This study aims to synthesize qualitative insights into opioid users' acceptability and perceived efficacy of mHealth and wearable technologies for opioid use disorder.

METHODS

A scoping review of PubMed (MEDLINE) and Google Scholar databases was conducted to identify research on opioid user perspectives concerning mHealth-assisted interventions, including wearable sensors, SMS text messaging, and app-based technology.

RESULTS

Overall, users demonstrate a high willingness to engage with mHealth interventions to prevent overdose-related deaths and manage opioid use. Users perceive mHealth as an opportunity to access care and desire the involvement of trusted health care professionals in these technologies. User comfort with wearing opioid sensors emerged as a significant factor. Personally tailored content, social support, and encouragement are preferred by users. Privacy concerns and limited access to technology pose barriers to care.

CONCLUSIONS

To maximize benefits and minimize risks for users, it is crucial to implement robust privacy measures, provide comprehensive user training, integrate behavior change techniques, offer professional and peer support, deliver tailored messages, incorporate behavior change theories, assess readiness for change, design stigma-reducing apps, use visual elements, and conduct user-focused research for effective opioid management in mHealth interventions. mHealth demonstrates considerable potential as a tool for addressing opioid use disorder and preventing overdose-related deaths, given the high acceptability and perceived benefits reported by users.

A Wearable Device Towards Automatic Detection and Treatment of Opioid Overdose

Opioid-induced overdose is one of the leading causes of death among the US population under the age of 50. In 2021 alone, the death toll among opioid users rose to a devastating number of over 80,000. The overdose process can be reversed by the administration of naloxone, an opioid antagonist that rapidly counteracts the effects of opioid-induced respiratory depression. The idea of a closed-loop opioid overdose detection and naloxone delivery has emerged as a potential engineered solution to mitigate the deadly effects of the opioid epidemic. In this work, we introduce a wrist-worn wearable device that overcomes the portability issues of our previous work to create a closed-loop drug-delivery system, which includes (1) a Near-Infrared Spectroscopy (NIRS) sensor to detect a hypoxia-driven opioid overdose event, (2) a MOSFET switch, and (3) a Zero-Voltage Switching (ZVS) electromagnetic heater. Using brachial artery occlusion (BAO) with human subjects (n = 8), we demonstrated consistent low oxygenation events. Furthermore, we proved our device's capability to release the drug within 10 s after detecting a hypoxic event. We found that the changes in the oxyhemoglobin, deoxyhemoglobin and oxygenation saturation levels ( SpO2) were different before and after the low-oxygenation events ( 0.001). Although additional human experiments are needed, our results to date point towards a potential tool in the battle to mitigate the effects of the opioid epidemic.

Acceptance of digital phenotyping linked to a digital pill system to measure PrEP adherence among men who have sex with men with substance use

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.

Digital Biomarker Applications Across the Spectrum of Opioid Use Disorder

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.

Artificial Intelligence for Automatic Pain Assessment: Research Methods and Perspectives

Although proper pain evaluation is mandatory for establishing the appropriate therapy, self-reported pain level assessment has several limitations. Data-driven artificial intelligence (AI) methods can be employed for research on automatic pain assessment (APA). The goal is the development of objective, standardized, and generalizable instruments useful for pain assessment in different clinical contexts. The purpose of this article is to discuss the state of the art of research and perspectives on APA applications in both research and clinical scenarios. Principles of AI functioning will be addressed. For narrative purposes, AI-based methods are grouped into behavioral-based approaches and neurophysiology-based pain detection methods. Since pain is generally accompanied by spontaneous facial behaviors, several approaches for APA are based on image classification and feature extraction. Language features through natural language strategies, body postures, and respiratory-derived elements are other investigated behavioral-based approaches. Neurophysiology-based pain detection is obtained through electroencephalography, electromyography, electrodermal activity, and other biosignals. Recent approaches involve multimode strategies by combining behaviors with neurophysiological findings. Concerning methods, early studies were conducted by machine learning algorithms such as support vector machine, decision tree, and random forest classifiers. More recently, artificial neural networks such as convolutional and recurrent neural network algorithms are implemented, even in combination. Collaboration programs involving clinicians and computer scientists must be aimed at structuring and processing robust datasets that can be used in various settings, from acute to different chronic pain conditions. Finally, it is crucial to apply the concepts of explainability and ethics when examining AI applications for pain research and management.