Michigan system for opioid overdose surveillance

Goldstick, Jason E.; Ballesteros, Amanda; Flannagan, Carol A. C.; Roche, Jessica; Schmidt, Carl J.; Cunningham, Rebecca M.

doi:10.1136/injuryprev-2020-043882

Cited by 8 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We selected these data sources for several reasons. First, they represent a standard set accessible to most public health authorities, 9,34 which may facilitate replication of the modeling approach elsewhere. Second, they contain features across several domains (e.g., physical environment, social capital) known to be associated with neighborhood-level overdose mortality rates.…”

Section: Study Setting and Periodmentioning

confidence: 99%

PROVIDENT: Development and Validation of a Machine Learning Model to Predict Neighborhood-level Overdose Risk in Rhode Island

Allen,

Schell,

Jent

et al. 2024

Epidemiology

View full text Add to dashboard Cite

Background: Drug overdose persists as a leading cause of death in the United States, but resources to address it remain limited. As a result, health authorities must consider where to allocate scarce resources within their jurisdictions. Machine learning offers a strategy to identify areas with increased future overdose risk to proactively allocate overdose prevention resources. This modeling study is embedded in a randomized trial to measure the effect of proactive resource allocation on statewide overdose rates in Rhode Island (RI). Methods: We used statewide data from RI from 2016-2020 to develop an ensemble machine learning model predicting neighborhood-level fatal overdose risk. Our ensemble model integrated gradient boosting machine and Super Learner base models in a moving window framework to make predictions in 6-month intervals. Our performance target, developed a priori with the RI Department of Health, was to identify the 20% of RI neighborhoods containing at least 40% of statewide overdose deaths, including at least one neighborhood per municipality. The model was validated after trial launch. Results: Our model selected priority neighborhoods capturing 40.2% of statewide overdose deaths during the test periods and 44.1% of statewide overdose deaths during validation periods. Our ensemble outperformed the base models during the test periods and performed comparably to the best-performing base model during the validation periods. Conclusions: We demonstrated the capacity for machine learning models to predict neighborhood-level fatal overdose risk to a degree of accuracy suitable for practitioners. Jurisdictions may consider predictive modeling as a tool to guide allocation of scarce resources.

show abstract

Section: Study Setting and Periodmentioning

confidence: 99%

PROVIDENT: Development and Validation of a Machine Learning Model to Predict Neighborhood-level Overdose Risk in Rhode Island

Allen,

Schell,

Jent

et al. 2024

Epidemiology

View full text Add to dashboard Cite

show abstract

“…54 pandemic and expediting referral to treatment. 55 Pharmacists can work with their local and state pharmacy associations to meet with their legislators to introduce bills aimed to improve public health. Pharmacists can contact their elected officials to request their support on legislative initiatives and bills in Congress.…”

Section: De-stigmatization and Educationmentioning

confidence: 99%

Pharmacists and opioid use disorder care during COVID‐19: Call for action

Mohammad

Berri

Lehr

2021

J Am Coll Clin Pharm

View full text Add to dashboard Cite

Opioid use disorder (OUD) is a chronic relapsing condition characterized by problematic opioid use causing significant impairment in daily life. Medication for opioid use disorder using buprenorphine, methadone, and naltrexone with behavioral therapy reduces illicit opioid use and risk of overdose death. Despite evidence and decades of experience, barriers limit access to treatment and care for individuals with OUD.Barriers include a lack of treatment centers particularly in rural areas, regulations on buprenorphine prescribing, and stigma from the community and health care professionals. While many barriers are longstanding, the coronavirus disease 2019 (COVID-19) pandemic-forced isolation and associated stress has exacerbated challenges for individuals with mental health conditions such as OUD. Pharmacists are wellpositioned to bridge existing gaps in OUD care, particularly during the COVID-19 pandemic. Roles for pharmacists include OUD risk identification and screening, referral of patients to treatment and support programs, ensuring medication access, expanding naloxone access, and advocacy initiatives. This review article identifies barriers to care for patients with OUD during the COVID-19 pandemic and explores opportunities and resources for pharmacists to improve OUD care during the pandemic and beyond.

show abstract

“…Enhanced surveillance systems for firearm injuries could also be constructed in analogous fashion to those developed for opioid overdose surveillance in the wake of the opioid epidemic. States such as Michigan have leveraged data systems such as the Emergency Medical Services Information System (EMSIS), and data from autopsies to create near real‐time passive surveillance systems (Goldstick et al, 2021). Other bespoke systems such as the Overdose Detection and Mapping Application Program (http://www.odmap.org/), where responders can enter data at the scene, have also been mobilized to generate near real‐time overdose surveillance.…”

Section: Enhanced Surveillance Of Firearm Injuriesmentioning

confidence: 99%

Commentary: Reducing youth firearm violence and the associated health disparities requires enhanced surveillance and modern behavioral intervention strategies – a commentary on Bottiani et al. (2021)

Goldstick

Kaufman

Delgado

et al. 2021

Child Psychology Psychiatry

View full text Add to dashboard Cite

Youth firearm injury is a worsening public health crisis, and the risks are not distributed evenly. Bottiani et al. skillfully explicated those health disparities, described sociological factors underlying them, and explored avenues for prevention. We supplement their analysis by detailing problems and solutions related to a critical barrier to firearm violence prevention – the nonexistence both of reliable ‘gold standard’ nonfatal firearm injury surveillance data, and systems for near real‐time surveillance of firearm injuries at granular spatial scales that would enable to optimization of rapid response protocols and neighborhood‐based prevention programs. We conclude with a discussion of modern, scalable, behavioral intervention approaches that could be leveraged to fill the largely absent evidence base resulting from the documented underfunding of youth firearm violence prevention research.

show abstract

Michigan system for opioid overdose surveillance

Cited by 8 publications

References 10 publications

PROVIDENT: Development and Validation of a Machine Learning Model to Predict Neighborhood-level Overdose Risk in Rhode Island

PROVIDENT: Development and Validation of a Machine Learning Model to Predict Neighborhood-level Overdose Risk in Rhode Island

Pharmacists and opioid use disorder care during COVID‐19: Call for action

Commentary: Reducing youth firearm violence and the associated health disparities requires enhanced surveillance and modern behavioral intervention strategies – a commentary on Bottiani et al. (2021)

Contact Info

Product

Resources

About