A Machine Learning-based Approach for Collaborative Non-Adherence Detection during Opioid Abuse Surveillance using a Wearable Biosensor

Singh, Rohitpal; Lewis, Brittany; Chapman, Brittany P.; Carreiro, Stephanie; Venkatasubramanian, Krishna K.

doi:10.5220/0007382503100318

Cited by 12 publications

(18 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wearable biosensors have been used in opioid research for automatic detection of opioid intake [6] [14], and detecting recurrent opioid toxicity in patients after being administered naloxone [15]. Wearable sensor adherence was modeled recently using data from patients with opioid use disorder [8]. None of these previous studies looked to use wearable biosensors to identify opioid withdrawal.…”

Section: Related Workmentioning

confidence: 99%

Identifying Opioid Withdrawal Using Wearable Biosensors

Kulman¹,

Chapman²,

Venkatasubramanian³

et al. 2021

Proceedings of the Annual Hawaii International Conference on System Sciences

Self Cite

View full text Add to dashboard Cite

Wearable biosensors can be used to monitor opioid use, a problem of dire societal consequence given the current opioid epidemic in the US. Such surveillance can prompt interventions that promote behavioral change. Prior work has focused on the use of wearable biosensor data to detect opioid use. In this work, we present a method that uses machine learning to identify opioid withdrawal using data collected with a wearable biosensor. Our method involves developing a set of machine-learning classifiers, and then evaluating those classifiers using unseen test data. An analysis of the best performing model (based on the Random Forest algorithm) produced a receiver operating characteristic (ROC) area under the curve (AUC) of 0.9997 using completely unseen test data. Further, the model is able to detect withdrawal with just one minute of biosensor data. These results show the viability of using machine learning for opioid withdrawal detection. To our knowledge, the proposed method for identifying opioid withdrawal in OUD patients is the first of its kind.

show abstract

Section: Related Workmentioning

confidence: 99%

Identifying Opioid Withdrawal Using Wearable Biosensors

Kulman¹,

Chapman²,

Venkatasubramanian³

et al. 2021

Proceedings of the Annual Hawaii International Conference on System Sciences

Self Cite

View full text Add to dashboard Cite

show abstract

“…A total of 3 (5%) trials measured this patient perception. 6. Value, which describes what patients can accept to forgo in terms of time or money for the intervention.…”

Section: Patients' Perceptions Toward Characteristics Of Bmds Used In Interventionsmentioning

confidence: 99%

“…Biometric monitoring devices (BMDs) are wearable or environmental trackers and devices with embedded sensors that can remotely collect high-frequency objective data on patients' physiological, biological, behavioral, and environmental contexts [1]. In recent years, there has been a surge of therapeutic interventions using BMDs to monitor patients' health and treatment response to reactively adjust patients' care "just in time" [1][2][3][4][5][6][7]. The development of these innovative interventions using BMDs has raised great interest from governments, payers, care providers, and patients given their potential to transform the delivery of care from intermittent clinical visits with clinicians to remote and continuous management of patients, at scale, in real time [2,[7][8][9][10].…”

Section: Introductionmentioning

confidence: 99%

Identification of Patient Perceptions That Can Affect the Uptake of Interventions Using Biometric Monitoring Devices: Systematic Review of Randomized Controlled Trials (Preprint)

Perlmutter¹,

Benchoufi²,

Ravaud³

et al. 2020

Preprint

View full text Add to dashboard Cite

BACKGROUND Biometric monitoring devices (BMDs) are wearable or environmental trackers and devices with embedded sensors that can remotely collect high-frequency objective data on patients’ physiological, biological, behavioral, and environmental contexts (for example, fitness trackers with accelerometer). The real-world effectiveness of interventions using biometric monitoring devices depends on patients’ perceptions of these interventions. OBJECTIVE We aimed to systematically review whether and how recent randomized controlled trials (RCTs) evaluating interventions using BMDs assessed patients’ perceptions toward the intervention. METHODS We systematically searched PubMed (MEDLINE) from January 1, 2017, to December 31, 2018, for RCTs evaluating interventions using BMDs. Two independent investigators extracted the following information: (1) whether the RCT collected information on patient perceptions toward the intervention using BMDs and (2) if so, what precisely was collected, based on items from questionnaires used and/or themes and subthemes identified from qualitative assessments. The two investigators then synthesized their findings in a schema of patient perceptions of interventions using BMDs. RESULTS A total of 58 RCTs including 10,071 participants were included in the review (the median number of randomized participants was 60, IQR 37-133). BMDs used in interventions were accelerometers/pedometers (n=35, 60%), electrochemical biosensors (eg, continuous glucose monitoring; n=18, 31%), or ecological momentary assessment devices (eg, carbon monoxide monitors for smoking cessation; n=5, 9%). Overall, 26 (45%) trials collected information on patient perceptions toward the intervention using BMDs and allowed the identification of 76 unique aspects of patient perceptions that could affect the uptake of these interventions (eg, relevance of the information provided, alarm burden, privacy and data handling, impact on health outcomes, independence, interference with daily life). Patient perceptions were unevenly collected in trials. For example, only 5% (n=3) of trials assessed how patients felt about privacy and data handling aspects of the intervention using BMDs. CONCLUSIONS Our review showed that less than half of RCTs evaluating interventions using BMDs assessed patients’ perceptions toward interventions using BMDs. Trials that did assess perceptions often only assessed a fraction of them. This limits the extrapolation of the results of these RCTs to the real world. We thus provide a comprehensive schema of aspects of patient perceptions that may affect the uptake of interventions using BMDs and which should be considered in future trials. CLINICALTRIAL PROSPERO CRD42018115522; https://tinyurl.com/y5h8fjgx

show abstract

“…One study used accelerometry to show a decrease in psychomotor arm steadiness (arm-droop) and an increase in tremor in current and former recreational stimulant users versus those who have never used stimulants [ 21 ]. Other studies compared the bodily movements of abstinent stimulant users with nonuser controls [ 22 , 23 ], sleep disturbance in patients using opioids [ 24 , 25 , 26 , 27 ], or non-compliance with biosensor use in patients with OUD [ 28 ]. Other studies have used alternate methods to analyze opioid withdrawal, but these methods primarily focus on withdrawal in neonates, and may not be as feasible to use to monitor a patient as they go about their daily activities due to requiring video tracking and patient samples to analyze genetic expression [ 29 , 30 , 31 ].…”

Section: Introductionmentioning

confidence: 99%

Leveraging Accelerometry as a Prognostic Indicator for Increase in Opioid Withdrawal Symptoms

et al. 2022

View full text Add to dashboard Cite

Treating opioid use disorder (OUD) is a significant healthcare challenge in the United States. Remaining abstinent from opioids is challenging for individuals with OUD due to withdrawal symptoms that include restlessness. However, to our knowledge, studies of acute withdrawal have not quantified restlessness using involuntary movements. We hypothesized that wearable accelerometry placed mid-sternum could be used to detect withdrawal-related restlessness in patients with OUD. To study this, 23 patients with OUD undergoing active withdrawal participated in a protocol involving wearable accelerometry, opioid cues to elicit craving, and non-invasive Vagal Nerve Stimulation (nVNS) to dampen withdrawal symptoms. Using accelerometry signals, we analyzed how movements correlated with changes in acute withdrawal severity, measured by the Clinical Opioid Withdrawal Scale (COWS). Our results revealed that patients demonstrating sinusoidal–i.e., predominantly single-frequency oscillation patterns in their motion almost exclusively demonstrated an increase in the COWS, and a strong relationship between the maximum power spectral density and increased withdrawal over time, measured by the COWS (R = 0.92, p = 0.029). Accelerometry may be used in an ambulatory setting to indicate the increased intensity of a patient’s withdrawal symptoms, providing an objective, readily-measurable marker that may be captured ubiquitously.

show abstract

A Machine Learning-based Approach for Collaborative Non-Adherence Detection during Opioid Abuse Surveillance using a Wearable Biosensor

Cited by 12 publications

References 11 publications

Identifying Opioid Withdrawal Using Wearable Biosensors

Identifying Opioid Withdrawal Using Wearable Biosensors

Identification of Patient Perceptions That Can Affect the Uptake of Interventions Using Biometric Monitoring Devices: Systematic Review of Randomized Controlled Trials (Preprint)

Leveraging Accelerometry as a Prognostic Indicator for Increase in Opioid Withdrawal Symptoms

Contact Info

Product

Resources

About