A longitudinal observational study with ecological momentary assessment and deep learning to predict non-prescribed opioid use, treatment retention, and medication nonadherence among persons receiving medication treatment for opioid use disorder
Contact us if these videos are not relevant.
Contact us if these videos are not relevant.
View abstract on PubMed
Summary
This summary is machine-generated.Deep learning and ecological momentary assessment effectively predict opioid use disorder outcomes. This approach enables personalized interventions to reduce relapse and treatment dropout in patients receiving medication for opioid use disorder (MOUD).
Area Of Science
- Digital Health
- Machine Learning in Medicine
- Addiction Psychiatry
Background
- Opioid Use Disorder (OUD) treatments are effective, but relapse and dropout reduce efficacy, increasing mortality risks.
- Predicting non-prescribed opioid use (NPOU) and treatment discontinuation in patients receiving Medication for Opioid Use Disorder (MOUD) is crucial for proactive care.
- Ecological Momentary Assessment (EMA) and deep learning offer novel methods for predicting these adverse outcomes.
Purpose Of The Study
- To utilize EMA and deep learning to predict momentary NPOU, medication nonadherence, and treatment retention in MOUD patients.
- To develop predictive models that can identify individuals at high risk for negative outcomes.
- To inform the development of personalized, just-in-time adaptive interventions (JITAIs).
Main Methods
- Adults receiving MOUD at an outpatient program participated in the study.
- Recurrent deep learning models with 7-day sliding windows were used to predict next-day outcomes (NPOU, medication nonadherence, treatment retention).
- Context-sensitive EMAs (stress, pain, social setting) and Electronic Health Record (EHR) data were incorporated; SHapley additive Explanations (SHAP) were used for feature analysis.
Main Results
- Models demonstrated varying performance (AUC 0.58-0.97) across different outcomes and EMA subtypes.
- Recent substance use best predicted EMA-based NPOU (AUC=0.97).
- Life-contextual factors predicted EMA-based medication nonadherence (AUC=0.68) and retention (AUC=0.89); substance use risk factors and MOUD adherence predicted EHR-based nonadherence (AUC=0.79).
Conclusions
- EMA combined with deep learning effectively forecasts actionable outcomes for MOUD patients.
- These predictive capabilities can facilitate the creation of dynamic risk profiles.
- The findings support the development of JITAIs to mitigate high-risk OUD outcomes and improve patient care.
Contact us if these videos are not relevant.
Contact us if these videos are not relevant.
Related Concept Videos
Longitudinal studies are also widely used in other medical and social science fields. For instance, in cardiovascular research, they can monitor patients' health over decades to identify risk factors for heart disease, such as high cholesterol or smoking, and evaluate the long-term effectiveness of preventive measures. Similarly, in mental health studies, researchers might follow individuals from adolescence into adulthood to understand the development and progression of conditions like...
Sometimes we want to see how people change over time, as in studies of human development and lifespan. When we test the same group of individuals repeatedly over an extended period of time, we are conducting longitudinal research. Longitudinal research is a research design in which data-gathering is administered repeatedly over an extended period of time. For example, we may survey a group of individuals about their dietary habits at age 20, retest them a decade later at age 30, and then again...
Drug dependence, abuse, and addiction are complex phenomena that can precipitate various abnormal states. Physical dependence refers to a state of pharmacological adaptation to a drug. This adaptation often results in tolerance—a reduced response to the drug after repeated administrations. When the drug use is abruptly stopped, withdrawal symptoms occur due to the body's need to readjust from the pharmacologically induced imbalance. However, tolerance and withdrawal symptoms do not...