Related Experiment Video
Updated: Jun 27, 2025
07:31
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
7.1K
Using decision tree models and comprehensive statewide data to predict opioid overdoses following prison release.
Kristina Yamkovoy1, Prasad Patil2, Devon Dunn3
1University of Colorado School of Medicine, Division of General Internal Medicine, Aurora, CO, USA.
Annals of Epidemiology
|May 6, 2024
Summary
Predicting opioid overdose after prison release is vital. Stratified models improved risk prediction across racial groups, identifying involuntary commitment as a key factor for opioid overdose prevention.
Area of Science:
- Public Health
- Criminology
- Addiction Medicine
Background:
- Opioid overdose deaths remain a critical public health issue.
- Individuals released from prison face a significantly elevated risk of opioid overdose.
- Effective prediction models are needed to guide targeted prevention efforts.
Purpose of the Study:
- To identify predictors of opioid overdose within 90 days of release from Massachusetts state prisons.
- To compare the performance of a single predictive model versus models stratified by race/ethnicity.
- To understand disparities in overdose risk prediction among different racial/ethnic groups.
Main Methods:
- Utilized a state-wide database linking individuals released from Massachusetts prisons between 2015-2020.
- Developed two decision tree modeling schemes: one with a single weight and another stratified by race/ethnicity.
- Evaluated model performance using sensitivity, specificity, and identified key predictors.
Main Results:
- 5.1% of 44,246 individuals experienced opioid overdose within 90 days of release.
- A single-weight model showed higher sensitivity for White non-Hispanic individuals compared to racial/ethnic minorities.
- Stratified models demonstrated more balanced performance across racial/ethnic groups.
Conclusions:
- Stratified models offer improved, balanced performance for predicting opioid overdose in diverse populations.
- Predictors of opioid overdose varied significantly between racial/ethnic groups.
- Involuntary commitment for substance use disorder emerged as a consistent predictor across all groups and models.
Related Concept Videos
01:19Survival Tree
80
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a...
Building a Survival Tree
Constructing a...
80
01:15Opioid Analgesics: Synthetic and Semisynthetic Opioids
283
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...
283
01:25Analgesia and Pain Management
584
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...
584
01:20Opioid Analgesics: Morphine and Other Natural Cogeners
239
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...
239
01:15Drug Abuse and Addiction: Pharmacological Phenomena
467
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...
467
01:22Opioid Receptors: Overview
749
Opioid receptors, including the mu (μ, MOR), delta (δ, DOR), and kappa (κ, KOR) types, belong to the rhodopsin family of G protein-coupled receptors. These receptors are located throughout the central and peripheral nervous systems and in non-neuronal tissues such as macrophages and astrocytes. Opioid receptor ligands can be categorized into agonists or antagonists. Highly selective agonists include [d-Ala2, MePhe4, Gly(ol)5]-enkephalin or DAMGO for MOR, [D-Pen2,...
749