Predicting Opioid Overdose Readmission and Opioid Use Disorder with Machine Learning

2020 ◽  
Author(s):  
Sarah McDougall ◽  
Priyanka Annapureddy ◽  
Praveen Madiraju ◽  
Nicole Fumo ◽  
Stephen Hargarten
Keyword(s):  
Machine Learning ◽  
Opioid Use Disorder ◽  
Opioid Overdose ◽  
Opioid Use

scholarly journals Assessing the Relationships Between COVID-19 Stay-at-Home Orders and Opioid Overdoses in the State of Pennsylvania

2021 ◽  
pp. 002204262110063
Author(s):  
Brian King ◽  
Ruchi Patel ◽  
Andrea Rishworth
Keyword(s):  
Age Groups ◽  
The United States ◽  
Opioid Use Disorder ◽  
Opioid Overdose ◽  
Policy Recommendations ◽  
Opioid Use ◽  
Fentanyl Analogs ◽  
Measure Change ◽  
Using Data ◽  
At Home

COVID-19 is compounding opioid use disorder throughout the United States. While recent commentaries provide useful policy recommendations, few studies examine the intersection of COVID-19 policy responses and patterns of opioid overdose. We examine opioid overdoses prior to and following the Pennsylvania stay-at-home order implemented on April 1, 2020. Using data from the Pennsylvania Overdose Information Network, we measure change in monthly incidents of opioid-related overdose pre- versus post-April 1, and the significance of change by gender, age, race, drug class, and naloxone doses administered. Findings demonstrate statistically significant increases in overdose incidents among both men and women, White and Black groups, and several age groups, most notably the 30–39 and 40–49 ranges, following April 1. Significant increases were observed for overdoses involving heroin, fentanyl, fentanyl analogs or other synthetic opioids, pharmaceutical opioids, and carfentanil. The study emphasizes the need for opioid use to be addressed alongside efforts to mitigate and manage COVID-19 infection.

scholarly journals A machine learning based two-stage clinical decision support system for predicting patients’ discontinuation from opioid use disorder treatment: retrospective observational study

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Md Mahmudul Hasan ◽  
Gary J. Young ◽  
Jiesheng Shi ◽  
Prathamesh Mohite ◽  
Leonard D. Young ◽  
...  
Keyword(s):  
Machine Learning ◽  
Treatment Initiation ◽  
Clinical Decision ◽  
Opioid Use Disorder ◽  
Treatment Discontinuation ◽  
Discriminative Power ◽  
Opioid Use ◽  
Stage Models ◽  
C Statistic ◽  
One Year

Abstract Background Buprenorphine is a widely used treatment option for patients with opioid use disorder (OUD). Premature discontinuation from this treatment has many negative health and societal consequences. Objective To develop and evaluate a machine learning based two-stage clinical decision-making framework for predicting which patients will discontinue OUD treatment within less than a year. The proposed framework performs such prediction in two stages: (i) at the time of initiating the treatment, and (ii) after two/three months following treatment initiation. Methods For this retrospective observational analysis, we utilized Massachusetts All Payer Claims Data (MA APCD) from the year 2013 to 2015. Study sample included 5190 patients who were commercially insured, initiated buprenorphine treatment between January and December 2014, and did not have any buprenorphine prescription at least one year prior to the date of treatment initiation in 2014. Treatment discontinuation was defined as at least two consecutive months without a prescription for buprenorphine. Six machine learning models (i.e., logistic regression, decision tree, random forest, extreme-gradient boosting, support vector machine, and artificial neural network) were tested using a five-fold cross validation on the input data. The first-stage models used patients’ demographic information. The second-stage models included information on medication adherence during the early phase of treatment based on the proportion of days covered (PDC) measure. Results A substantial percentage of patients (48.7%) who started on buprenorphine discontinued the treatment within one year. The area under receiving operating characteristic curve (C-statistic) for the first stage models varied within a range of 0.55 to 0.59. The inclusion of knowledge regarding patients’ adherence at the early treatment phase in terms of two-months and three-months PDC resulted in a statistically significant increase in the models’ discriminative power (p-value < 0.001) based on the C-statistic. We also constructed interpretable decision classification rules using the decision tree model. Conclusion Machine learning models can predict which patients are most at-risk of premature treatment discontinuation with reasonable discriminative power. The proposed machine learning framework can be used as a tool to help inform a clinical decision support system following further validation. This can potentially help prescribers allocate limited healthcare resources optimally among different groups of patients based on their vulnerability to treatment discontinuation and design personalized support systems for improving patients’ long-term adherence to OUD treatment.

Fentanyl analogue overdose: Key lessons in management in the synthetic opioid age

2019 ◽  
Vol 15 (5) ◽  
pp. 428-432
Author(s):  
Amer Raheemullah, MD ◽  
Neal Andruska, MD, PhD
Keyword(s):  
Addiction Treatment ◽  
Opioid Use Disorder ◽  
Prescription Opioid ◽  
Opioid Overdose ◽  
Health Departments ◽  
Opioid Use ◽  
Public Health Departments ◽  
Disorder Treatment ◽  
Fentanyl Analogues ◽  
Overdose Deaths

Fentanyl overdoses are growing at an alarming rate. Fentanyl is often mixed into heroin and counterfeit prescription opioid pills without the customer’s knowledge and only detected upon laboratory analysis. This is problematic because fentanyl analogues like carfentanil are 10,000 times more potent than morphine and pose new challenges to opioid overdose management. A 62-year-old male with an overdose from a rare fentanyl analogue, acrylfentanyl, was given two doses of intranasal 2 mg naloxone with improvements in respiratory rate. In lieu of more naloxone, his trachea was intubated and he was admitted to the intensive care unit. He subsequently developed ventilator-associated pneumonia and then a pulmonary embolism. He did not receive any opioid use disorder treatment and returned back to the emergency department with an opioid overdose 21 days after discharge.We are encountering an unprecedented rise in synthetic opioid overdose deaths as we enter the third decade of the opioid epidemic. Thus, it is imperative to be aware of the features and management of overdoses from fentanyl and its analogues. This includes protecting against occupational exposure, administering adequate doses of naloxone, and working with public health departments to respond to fentanyl outbreaks. Additionally, fentanyl overdoses represent a critical opportunity to move beyond acute stabilization, start buprenorphine or methadone for opioid use disorder during hospitalization, link patients to ongoing addiction treatment, and distribute naloxone into the community to help curb the overdose epidemic.

PDG36 Predicting Opioid Use Disorder Using Machine Learning Methodologies

2021 ◽  
Vol 24 ◽  
pp. S93
Author(s):  
A. Pradhan ◽  
T. Oates ◽  
F.T. Shaya
Keyword(s):  
Machine Learning ◽  
Opioid Use Disorder ◽  
Opioid Use

scholarly journals Pharmacologic and Clinical Considerations of Nalmefene, a Long Duration Opioid Antagonist, in Opioid Overdose

2021 ◽  
Vol 2 (4) ◽  
pp. 365-378
Author(s):  
Amber N. Edinoff ◽  
Catherine A. Nix ◽  
Tanner D. Reed ◽  
Elizabeth M. Bozner ◽  
Mark R. Alvarez ◽  
...  
Keyword(s):  
Respiratory Depression ◽  
The United States ◽  
Opioid Use Disorder ◽  
Opioid Antagonist ◽  
Opioid Overdose ◽  
Opioid Use ◽  
Physical Damage ◽  
Onset Of Action ◽  
Duration Of Action ◽  
Opioid Intoxication

Opioid use disorder is a well-established and growing problem in the United States. It is responsible for both psychosocial and physical damage to the affected individuals with a significant mortality rate. Given both the medical and non-medical consequences of this epidemic, it is important to understand the current treatments and approaches to opioid use disorder and acute opioid overdose. Naloxone is a competitive mu-opioid receptor antagonist that is used for the reversal of opioid intoxication. When given intravenously, naloxone has an onset of action of approximately 2 min with a duration of action of 60–90 min. Related to its empirical dosing and short duration of action, frequent monitoring of the patient is required so that the effects of opioid toxicity, namely respiratory depression, do not return to wreak havoc. Nalmefene is a pure opioid antagonist structurally similar to naltrexone that can serve as an alternative antidote for reversing respiratory depression associated with acute opioid overdose. Nalmefene is also known as 6-methylene naltrexone. Its main features of interest are its prolonged duration of action that surpasses most opioids and its ability to serve as an antidote for acute opioid overdose. This can be pivotal in reducing healthcare costs, increasing patient satisfaction, and redistributing the time that healthcare staff spend monitoring opioid overdose patients given naloxone.

scholarly journals Canadian Guidelines on Opioid Use Disorder Among Older Adults

2020 ◽  
Vol 23 (1) ◽  
pp. 123-134
Author(s):  
Launette M. Rieb ◽  
Zainab Samaan ◽  
Andrea D. Furlan ◽  
Kiran Rabheru ◽  
Sid Feldman ◽  
...  
Keyword(s):  
Older Adults ◽  
English Language ◽  
Oral Morphine ◽  
Opioid Use Disorder ◽  
Opioid Overdose ◽  
Opioid Use ◽  
Chronic Noncancer Pain ◽  
Assessment And Treatment ◽  
Noncancer Pain ◽  
Health Canada

BackgroundIn Canada, rates of hospital admission from opioid overdose are higher for older adults (≥ 65) than younger adults, and opioid use disorder (OUD) is a growing concern. In response, Health Canada commissioned the Canadian Coalition of Seniors’ Mental Health to create guidelines for the prevention, screening, assessment, and treatment of OUD in older adults.MethodsA systematic review of English language literature from 2008–2018 regarding OUD in adults was conducted. Previously published guidelines were evaluated using AGREE II, and key guidelines updated using ADAPTE method, by drawing on current literature. Recommendations were created and assessed using the GRADE method.ResultsThirty-two recommendations were created. Prevention recommendations: it is key to prioritize non-pharmacological and non-opioid strategies to treat acute and chronic noncancer pain. Assessment recommendations: a comprehensive assessment is important to help discern contributions of other medical conditions. Treatment recommendations: buprenorphine is first line for both withdrawal management and maintenance therapy, while methadone, slow-release oral morphine, or naltrexone can be used as alternatives under certain circumstances; non-pharmacological treatments should be offered as an integrated part of care.ConclusionThese guidelines provide practical and timely clinical recommendations on the prevention, assessment, and treatment of OUD in older adults within the Canadian context.

Sign in / Sign up

Export Citation Format

Share Document