Prediction of stress and drug craving ninety minutes in the future with passively collected GPS data

Epstein, David H.; Tyburski, Matthew; Kowalczyk, William J.; Burgess-Hull, Albert J.; Phillips, Karran A.; Curtis, Brenda; Preston, Kenzie L.

doi:10.1038/s41746-020-0234-6

Cited by 46 publications

(24 citation statements)

References 69 publications

(72 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recently, mental health relevant research using personal sensing of raw data streams other than self-report is emerging. This includes methods to sense geolocation [14][15][16], cellular communications [16][17][18][19][20], sleep [20], and physiology [21,22], as examples.…”

Section: Personal Sensingmentioning

confidence: 99%

Acceptability of Personal Sensing Among People with Alcohol Use Disorder: Observational Study

Wyant¹,

Moshontz

Ward³

et al. 2022

Preprint

View full text Add to dashboard Cite

Personal sensing may improve digital therapeutics for mental health care by facilitating early screening, symptom monitoring, risk prediction, and personalized/adaptive interventions. However, further development and use of personal sensing first requires better understanding of its acceptability to people targeted for these mental health applications. We assessed the acceptability of both active and passive personal sensing methods in a sample of people with moderate to severe alcohol use disorder using both behavioral and self-report measures. Participants (N = 154; 50% female; mean age = 41; 87% White, 97% Non-Hispanic) in early recovery (1 – 8 weeks of abstinence) from alcohol use disorder were recruited from the Madison, WI area to participate in a 3-month longitudinal study. Participants engaged with active (ecological momentary assessment; EMA, audio check-in, and sleep quality) and passive (geolocation, cellular communication logs, and text message content) personal sensing methods. We assessed 3 behavioral indicators of acceptability: participants’ choices about their participation in the study at various stages in the study procedure, their choice to opt-in to provide data for each personal sensing method, and their compliance for a subset of the active methods (EMA, audio check-in). We also assessed 3 self-report measures of acceptability (interference, dislike, and willingness to use for 1 year) for each method. All but 1 of the individuals who were eligible to participate consented to the personal sensing procedures. Most of these individuals (88%) also returned 1 week later to formally enroll in the study and begin to provide these data. All participants (100%) opted-in to provide data for EMA, sleep quality, and all passive methods (geolocation, cellular communication logs, text message content). Three participants (2%) did not provide any audio check-ins while on study. The average completion rate for all requested EMAs (4X daily) was 81% for 4x daily and 94% for 1x daily. The completion rate for the daily audio check-in was 55%. Aggregate participant ratings indicated all personal sensing methods to be significantly more acceptable (all P’s < .05) compared to neutral across subjective measures of interference, dislike, and willingness to use for 1 year. Participants did not significantly differ in their dislike of active compared to passive methods (P = .23). However, participants reported a higher willingness to use passive methods for 1 year compared to active methods (P = .04). The results of our study suggest that both active and passive personal sensing methods are generally acceptable to people with alcohol use disorder over a longer period than has previously been assessed. This was true even for data streams that contained potentially more sensitive information (e.g., geolocation, cellular communications). Important individual differences were observed both across people and methods which indicate opportunities for future improvements.

show abstract

Section: Personal Sensingmentioning

confidence: 99%

Acceptability of Personal Sensing Among People with Alcohol Use Disorder: Observational Study

Wyant¹,

Moshontz

Ward³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…One study used a random forest algorithm to predict opioid craving or stress in the user through their movement as assessed by GPS. [77] The other study tested an AI enabled peer support platform that patients with OUD could use to support their recovery. [78] In both cases, further development of the model was being planned.…”

Section: Table S1mentioning

confidence: 99%

Artificial intelligence and opioid use: a narrative review

Gadhia

Richards

Marriott

et al. 2022

Preprint

View full text Add to dashboard Cite

BackgroundThere are concerns about the balance of benefits and harms in people using opioids for chronic non-cancer pain. Technologies using artificial intelligence (AI) are being developed to examine and optimise the use of opioids. Yet, this research has not been synthesised to determine the types of AI models being developed and the application of these models.MethodsWe aimed to synthesise studies exploring the use of AI in people taking opioids. We searched three databases: the Cochrane Database of Systematic Reviews, EMBASE, and Medline, on 4 January 2021. Studies were included if they were published after 2010, conducted in a real-life community setting involving humans, and used AI to understand opioid use. Data on the types and applications of AI models were extracted and descriptively analysed.ResultsEighty-one articles were included in our review, representing over 5.3 million participants and 14.6 million social media posts. Most (93%) studies were conducted in the USA. The types of AI technologies included natural language processing (46%) and a range of machine learning algorithms, the most common being random forest algorithms (36%). AI was predominately applied for the surveillance and monitoring of opioids (46%), followed by risk prediction (42%), pain management (10%), and patient support (2%). Few of the AI models were ready for adoption, with most (62%) being in preliminary stages.ConclusionsA variety of AI models are being developed and applied to understand opioid use. However, there is a need for these AI technologies to be externally validated and robustly evaluated to determine whether they can improve the use and safety of opioids.SUMMARY BOXKey PointsAcross the landscape of opioid research, natural language processing models (46%) and ensemble algorithms, particularly random forest algorithms (36%), were the most common types of AI technologies studied.There were four main domains that AI was applied to assess the use of opioids, including surveillance and monitoring (46%), risk prediction (42%), pain management (10%), and patient support (2%).The AI technologies were at various stages of development, validation, and deployment, with most (62%) models in preliminary stages, 11% required external validation, and few models were openly available to access (6%).

show abstract

“…Assessment of geography via passive sensing of geolocation using GPS has demonstrated that drug craving, stress, and mood among persons with an opioid use disorder were predicted by exposure to visible signs of environmental disorder along a GPS-derived [ 74 , 75 ] track (such as visible signs of poverty, violence, and drug activity). A recent digital health EMA study demonstrated a stronger link between drug craving and drug use than between stress and drug use—a result that was not well-documented or understood from prior traditional clinical assessment [ 76 ].…”

Section: The State Of the Science Of Digital Health Data-driven Appromentioning

confidence: 99%

Digital health data-driven approaches to understand human behavior

Marsch¹

2020

Neuropsychopharmacol.

View full text Add to dashboard Cite

Advances in digital technologies and data analytics have created unparalleled opportunities to assess and modify health behavior and thus accelerate the ability of science to understand and contribute to improved health behavior and health outcomes. Digital health data capture the richness and granularity of individuals’ behavior, the confluence of factors that impact behavior in the moment, and the within-individual evolution of behavior over time. These data may contribute to discovery science by revealing digital markers of health/risk behavior as well as translational science by informing personalized and timely models of intervention delivery. And they may help inform diagnostic classification of clinically problematic behavior and the clinical trajectories of diagnosable disorders over time. This manuscript provides a review of the state of the science of digital health data-driven approaches to understanding human behavior. It reviews methods of digital health assessment and sources of digital health data. It provides a synthesis of the scientific literature evaluating how digitally derived empirical data can inform our understanding of health behavior, with a particular focus on understanding the assessment, diagnosis and clinical trajectories of psychiatric disorders. And, it concludes with a discussion of future directions and timely opportunities in this line of research and its clinical application.

show abstract

Prediction of stress and drug craving ninety minutes in the future with passively collected GPS data

Cited by 46 publications

References 69 publications

Acceptability of Personal Sensing Among People with Alcohol Use Disorder: Observational Study

Acceptability of Personal Sensing Among People with Alcohol Use Disorder: Observational Study

Artificial intelligence and opioid use: a narrative review

Digital health data-driven approaches to understand human behavior

Contact Info

Product

Resources

About