Using Machine Learning to Predict Treatment Adherence in Patients on Medication for Opioid Use Disorder
Albert J Burgess-Hull1, Caleb Brooks, David H Epstein
1From the Intramural Research Program, National Institute on Drug Abuse, Baltimore, MD (AJB-H, DHE); Department of Psychiatry, University of Maryland School of Medicine, Baltimore, MD (DG); Department of Child and Adolescent Psychiatry, University of Maryland School of Medicine, Baltimore, MD (EO); MATClinics, Dundalk, MD (AJB-H, CB, EO).
Journal of Addiction Medicine
|August 1, 2022
Summary
Predicting treatment adherence for patients with opioid use disorder (OUD) is crucial. An automated risk-modeling framework using machine learning, like XGBoost, shows promise in predicting adherence and improving care for OUD patients.
Area of Science:
- Data Science in Healthcare
- Clinical Informatics
- Addiction Medicine Research
Background:
- Patients with opioid use disorder (OUD) on medication may struggle with adherence or use non-prescribed drugs.
- Predicting which patients will face these challenges is difficult.
- Improved risk prediction tools are needed to enhance the delivery of medication for opioid use disorder (MOUD).
Purpose of the Study:
- To develop and validate an automated risk-modeling framework.
- To predict opioid abstinence and medication adherence at a patient's next appointment.
- To evaluate machine learning algorithms against logistic regression for predictive performance.
Main Methods:
- Utilized urine drug screen and attendance records from 40,005 appointments across 2742 patients.
- Trained logistic regression, logistic ridge regression, and XGBoost models.
- Predicted a composite indicator of treatment adherence at the next attended appointment.
Main Results:
- XGBoost model achieved 88% accuracy and 0.87 AUC, similar to logistic regression models.
- XGBoost demonstrated nearly perfect calibration; logistic models slightly overestimated adherence.
- Key predictors included historical adherence, attendance rate, and current fentanyl-positive urine.
Conclusions:
- An automated, portable risk-modeling framework can predict treatment adherence for patients receiving medication for opioid use disorder.
- XGBoost offers comparable accuracy to logistic regression with potentially better calibration of risk estimates.
- This framework can aid in improving the management and outcomes for OUD patients.
Related Concept Videos
01:15Drug Abuse and Addiction: Pharmacological Phenomena
640
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...
640
01:28Drug Therapy
92
The advent of drug therapy has profoundly shaped modern mental health care, providing targeted treatments for a range of psychological disorders. Psychotherapeutic drugs, classified into antianxiety, antidepressant, and antipsychotic medications, address symptoms across anxiety disorders, mood disorders, and schizophrenia. While these medications have transformed patient outcomes, they require careful management due to their potential side effects and limitations.
Antianxiety Medications
Antianxiety Medications
92
01:15Opioid Analgesics: Synthetic and Semisynthetic Opioids
411
Synthetic and semisynthetic opioids are pivotal in pain management and tackling opioid addiction. Semisynthetic opioids, including morphinans (morphine derivatives), oxycodone, oxymorphone, hydrocodone, and hydromorphone, have improved pharmacokinetic profiles compared to morphine. Additionally, heroin and 6-MAM (6-Monoacetylmorphine) show better CNS penetration than morphine due to heightened lipid solubility. Hydromorphone, a potent opioid, undergoes hepatic metabolism to form the active...
411
01:25Analgesia and Pain Management
777
Pain is critical to various clinical pathologies, provoking an urgent need for effective management. Pain, whether acute or chronic, is a complex neurochemical process. Its alleviation depends on the type, with nonopioid analgesics effective for mild to moderate pain, such as musculoskeletal or inflammatory pain, while neuropathic pain responds best to anticonvulsants, tricyclic antidepressants, or serotonin/norepinephrine reuptake inhibitors. For severe acute or chronic pain, opioids may be...
777
01:24Substance Use Disorders Affecting Sleep
212
Substance use disorders involve a pattern of using drugs more extensively than intended and continuing use despite harmful consequences. This includes legal substances like alcohol and nicotine, as well as illegal drugs. These disorders often involve both physical and psychological dependence, reflecting compulsive use of substances that significantly alter thoughts, feelings, and behaviors, contributing to a major public health issue.
Understanding the concepts of physical dependence,...
Understanding the concepts of physical dependence,...
212
01:20Opioid Analgesics: Morphine and Other Natural Cogeners
351
Opioids are a class of drugs that mimic endogenous opioid peptides and act on opioid receptors, and help in pain relief. These compounds are classified as natural, synthetic, or semi-synthetic. Natural opioids, like morphine, codeine, and thebaine, are derived from the opium poppy plant (Papaver somniferum or Papaver album) and are termed opiates. Synthetic opioids are artificial, while semi-synthetic opioids combine natural and synthetic compounds. Morphine, a prototypical opioid, possesses a...
351