Ensemble learning to predict opioid-related overdose using statewide prescription drug monitoring program and hospital discharge data in the state of Tennessee

Ripperger, Michael; Lotspeich, Sarah C.; Wilimitis, Drew; Fry, Carrie; Roberts, Allison; Lenert, Matthew C.; Cherry, Charlotte Buehler; Latham, Sanura M.; Robinson, Katelyn; Chen, Qingxia; McPheeters, Melissa L; Tyndall, Benjamin D.; Walsh, Colin G.

doi:10.1093/jamia/ocab218

Cited by 10 publications

(15 citation statements)

References 32 publications

(26 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[ 14 ] aimed to predict opioid misuse or poisoning as well as dependence, in advance of the first opioid prescription, using Medicaid data for the US state of Rhode Island. [ 19 ] aimed to predict opioid-related overdose using statewide prescription drug monitoring program and hospital discharge data in the US state of Tennessee. [ 20 ], using data from Alberta, Canada, aimed to predict overdose risk within 30 days after an opioid dispensation on the basis of features related to opioid dispensations.…”

Section: Related Workmentioning

confidence: 99%

Using machine learning to study the effect of medication adherence in Opioid Use Disorder

et al. 2022

View full text Add to dashboard Cite

Background Opioid Use Disorder (OUD) and opioid overdose (OD) impose huge social and economic burdens on society and health care systems. Research suggests that Medication for Opioid Use Disorder (MOUD) is effective in the treatment of OUD. We use machine learning to investigate the association between patient’s adherence to prescribed MOUD along with other risk factors in patients diagnosed with OUD and potential OD following the treatment. Methods We used longitudinal Medicaid claims for two selected US states to subset a total of 26,685 patients with OUD diagnosis and appropriate Medicaid coverage between 2015 and 2018. We considered patient age, sex, region level socio-economic data, past comorbidities, MOUD prescription type and other selected prescribed medications along with the Proportion of Days Covered (PDC) as a proxy for adherence to MOUD as predictive variables for our model, and overdose events as the dependent variable. We applied four different machine learning classifiers and compared their performance, focusing on the importance and effect of PDC as a variable. We also calculated results based on risk stratification, where our models separate high risk individuals from low risk, to assess usefulness in clinical decision-making. Results Among the selected classifiers, the XGBoost classifier has the highest AUC (0.77) closely followed by the Logistic Regression (LR). The LR has the best stratification result: patients in the top 10% of risk scores account for 35.37% of overdose events over the next 12 month observation period. PDC score calculated over the treatment window is one of the most important features, with better PDC lowering risk of OD, as expected. In terms of risk stratification results, of the 35.37% of overdose events that the predictive model could detect within the top 10% of risk scores, 72.3% of these cases were non-adherent in terms of their medication (PDC <0.8). Targeting the top 10% outcome of the predictive model could decrease the total number of OD events by 10.4%. Conclusions The best performing models allow identification of, and focus on, those at high risk of opioid overdose. With MOUD being included for the first time as a factor of interest, and being identified as a significant factor, outreach activities related to MOUD can be targeted at those at highest risk.

show abstract

Section: Related Workmentioning

confidence: 99%

Using machine learning to study the effect of medication adherence in Opioid Use Disorder

et al. 2022

View full text Add to dashboard Cite

show abstract

“…RNNs like LSTMs and GRUs) 26,27 to transformer networks 28 . However, public health studies that are geared towards prediction often opt instead for traditional cross-sectional modeling with linear/logistic regression, support vector machines, or gradient boosting trees [29][30][31] ). This new architecture allows sequences to be analyzed with multiple representations, called attention-heads, which give it a strong ability to see how each step of the sequence interacts with past steps.…”

Section: Introductionmentioning

confidence: 99%

Opioid death projections with AI-based forecasts using social media language

et al. 2023

View full text Add to dashboard Cite

Targeting of location-specific aid for the U.S. opioid epidemic is difficult due to our inability to accurately predict changes in opioid mortality across heterogeneous communities. AI-based language analyses, having recently shown promise in cross-sectional (between-community) well-being assessments, may offer a way to more accurately longitudinally predict community-level overdose mortality. Here, we develop and evaluate, TrOP (Transformer for Opiod Prediction), a model for community-specific trend projection that uses community-specific social media language along with past opioid-related mortality data to predict future changes in opioid-related deaths. TOP builds on recent advances in sequence modeling, namely transformer networks, to use changes in yearly language on Twitter and past mortality to project the following year’s mortality rates by county. Trained over five years and evaluated over the next two years TrOP demonstrated state-of-the-art accuracy in predicting future county-specific opioid trends. A model built using linear auto-regression and traditional socioeconomic data gave 7% error (MAPE) or within 2.93 deaths per 100,000 people on average; our proposed architecture was able to forecast yearly death rates with less than half that error: 3% MAPE and within 1.15 per 100,000 people.

show abstract

“…Five studies 9,23,42,44 limited inclusion to patients who were continuously enrolled in an insurance plan. The most common study settings were within the community 17-19,22,24,25,32,33,36,40,41,47,49 and in hospitals and health care systems 21,28,35,37,42,43,46,52,54,55 …”

Section: Resultsmentioning

confidence: 99%

“…This may be due to the shorter time frame of PDMP-derived models, which typically only covered 1 year of data. Model calibration, defined as the comparison between a system's actual output and its expected output, was assessed by 9 studies 18,20,28,32,39,43,46,53,54 using the Brier score 18,32,43,53,54 or goodness of fit. 20…”

Section: Model Performancementioning

confidence: 99%

Predictive Models to Assess Risk of Persistent Opioid Use, Opioid Use Disorder, and Overdose

Song,

Dandapani,

Estrada

et al. 2024

J Addict Med

View full text Add to dashboard Cite

Background This systematic review summarizes the development, accuracy, quality, and clinical utility of predictive models to assess the risk of opioid use disorder (OUD), persistent opioid use, and opioid overdose. Methods In accordance with Preferred Reporting Items for a Systematic Review and Meta-analysis guidelines, 8 electronic databases were searched for studies on predictive models and OUD, overdose, or persistent use in adults until June 25, 2023. Study selection and data extraction were completed independently by 2 reviewers. Risk of bias of included studies was assessed independently by 2 reviewers using the Prediction model Risk of Bias ASsessment Tool (PROBAST). Results The literature search yielded 3130 reports; after removing 199 duplicates, excluding 2685 studies after abstract review, and excluding 204 studies after full-text review, the final sample consisted of 41 studies that developed more than 160 predictive models. Primary outcomes included opioid overdose (31.6% of studies), OUD (41.4%), and persistent opioid use (17%). The most common modeling approach was regression modeling, and the most common predictors included age, sex, mental health diagnosis history, and substance use disorder history. Most studies reported model performance via the c statistic, ranging from 0.507 to 0.959; gradient boosting tree models and neural network models performed well in the context of their own study. One study deployed a model in real time. Risk of bias was predominantly high; concerns regarding applicability were predominantly low. Conclusions Models to predict opioid-related risks are developed using diverse data sources and predictors, with a wide and heterogenous range of accuracy metrics. There is a need for further research to improve their accuracy and implementation.

show abstract

Ensemble learning to predict opioid-related overdose using statewide prescription drug monitoring program and hospital discharge data in the state of Tennessee

Cited by 10 publications

References 32 publications

Using machine learning to study the effect of medication adherence in Opioid Use Disorder

Using machine learning to study the effect of medication adherence in Opioid Use Disorder

Opioid death projections with AI-based forecasts using social media language

Predictive Models to Assess Risk of Persistent Opioid Use, Opioid Use Disorder, and Overdose

Contact Info

Product

Resources

About