Dataset Information

Advanced models for improved prediction of opioid-related overdose and suicide events among Veterans using administrative healthcare data

ABSTRACT: Veterans suffer disproportionate health impacts from the opioid epidemic, including overdose, suicide, and death. Prediction models based on electronic medical record data can be powerful tools for identifying patients at greatest risk of such outcomes. The Veterans Health Administration implemented the Stratification Tool for Opioid Risk Mitigation (STORM) in 2018. In this study we propose changes to the original STORM model and propose alternative models that improve risk prediction performance. The best of these proposed models uses a multivariate generalized linear mixed modeling (mGLMM) approach to produce separate predictions for overdose and suicide-related events (SRE) rather than a single prediction for combined outcomes. Further improvements include incorporation of additional data sources and new predictor variables in a longitudinal setting. Compared to a modified version of the STORM model with the same outcome, predictor and interaction terms, our proposed model has a significantly better prediction performance in terms of AUC (84% vs. 77%) and sensitivity (71% vs. 66%). The mGLMM performed particularly well in identifying patients at risk for SREs, where 72% of actual events were accurately predicted among patients with the 100,000 highest risk scores compared with 49.7% for the modified STORM model. The mGLMM’s strong performance in identifying true cases (sensitivity) among this highest risk group was the most important improvement given the model’s primary purpose for accurately identifying patients at most risk for adverse outcomes such that they are prioritized to receive risk mitigation interventions. Some predictors in the proposed model have markedly different associations with overdose and suicide risks, which will allow clinicians to better target interventions to the most relevant risks.

Supplementary Information

The online version contains supplementary material available at 10.1007/s10742-021-00263-7.

SUBMITTER: Ward R

PROVIDER: S-EPMC8561350 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:ObjectiveTo examine the associations between stopping treatment with opioids, length of treatment, and death from overdose or suicide in the Veterans Health Administration.DesignObservational evaluation.SettingVeterans Health Administration.Participants1 394 102 patients in the Veterans Health Administration with an outpatient prescription for an opioid analgesic from fiscal year 2013 to the end of fiscal year 2014 (1 October 2012 to 30 September 2014).Main outcome measuresA multivariable Cox non-proportional hazards regression model examined death from overdose or suicide, with the interaction of time varying opioid cessation by length of treatment (≤30, 31-90, 91-400, and >400 days) as the main covariates. Stopping treatment with opioids was measured as the time when a patient was estimated to have no prescription for opioids, up to the end of the next fiscal year (2014) or the patient's death.Results2887 deaths from overdose or suicide were found. The incidence of stopping opioid treatment was 57.4% (n=799 668) overall, and based on length of opioid treatment was 32.0% (≤30 days), 8.7% (31-90 days), 22.7% (91-400 days), and 36.6% (>400 days). The interaction between stopping treatment with opioids and length of treatment was significant (P<0.001); stopping treatment was associated with an increased risk of death from overdose or suicide regardless of the length of treatment, with the risk increasing the longer patients were treated. Hazard ratios for patients who stopped opioid treatment (with reference values for all other covariates) were 1.67 (≤30 days), 2.80 (31-90 days), 3.95 (91-400 days), and 6.77 (>400 days). Descriptive life table data suggested that death rates for overdose or suicide increased immediately after starting or stopping treatment with opioids, with the incidence decreasing over about three to 12 months.ConclusionsPatients were at greater risk of death from overdose or suicide after stopping opioid treatment, with an increase in the risk the longer patients had been treated before stopping. Descriptive data suggested that starting treatment with opioids was also a risk period. Strategies to mitigate the risk in these periods are not currently a focus of guidelines for long term use of opioids. The associations observed cannot be assumed to be causal; the context in which opioid prescriptions were started and stopped might contribute to risk and was not investigated. Safer prescribing of opioids should take a broader view on patient safety and mitigate the risk from the patient's perspective. Factors to address are those that place patients at risk for overdose or suicide after beginning and stopping opioid treatment, especially in the first three months.

Project description:ImportanceScreening adolescents in emergency departments (EDs) for suicidal risk is a recommended strategy for suicide prevention. Comparing screening measures on predictive validity could guide ED clinicians in choosing a screening tool.ObjectiveTo compare the Ask Suicide-Screening Questions (ASQ) instrument with the Computerized Adaptive Screen for Suicidal Youth (CASSY) instrument for the prediction of suicidal behavior among adolescents seen in EDs, across demographic and clinical strata.Design, setting, and participantsThe Emergency Department Study for Teens at Risk for Suicide is a prospective, random-series, multicenter cohort study that recruited adolescents, oversampled for those with psychiatric symptoms, who presented to the ED from July 24, 2017, through October 29, 2018, with a 3-month follow-up to assess the occurrence of suicidal behavior. The study included 14 pediatric ED members of the Pediatric Emergency Care Applied Research Network and 1 Indian Health Service ED. Statistical analysis was performed from May 2021 through January 2023.Main outcomes and measuresThis study used a prediction model to assess outcomes. The primary outcome was suicide attempt (SA), and the secondary outcome was suicide-related visits to the ED or hospital within 3 months of baseline; both were assessed by an interviewer blinded to baseline information. The ASQ is a 4-item questionnaire that surveys suicidal ideation and lifetime SAs. A positive response or nonresponse on any item indicates suicidal risk. The CASSY is a computerized adaptive screening tool that always includes 3 ASQ items and a mean of 8 additional items. The CASSY's continuous outcome is the predicted probability of an SA.ResultsOf 6513 adolescents available, 4050 were enrolled, 3965 completed baseline assessments, and 2740 (1705 girls [62.2%]; mean [SD] age at enrollment, 15.0 [1.7] years; 469 Black participants [17.1%], 678 Hispanic participants [24.7%], and 1618 White participants [59.1%]) completed both screenings and follow-ups. The ASQ and the CASSY showed a similar sensitivity (0.951 [95% CI, 0.918-0.984] vs 0.945 [95% CI, 0.910-0.980]), specificity (0.588 [95% CI, 0.569-0.607] vs 0.643 [95% CI, 0.625-0.662]), positive predictive value (0.127 [95% CI, 0.109-0.146] vs 0.144 [95% CI, 0.123-0.165]), and negative predictive value (both 0.995 [95% CI, 0.991-0.998], respectively). Area under the receiver operating characteristic curve findings were similar among patients with physical symptoms (ASQ, 0.88 [95% CI, 0.81-0.95] vs CASSY, 0.94 [95% CI, 0.91-0.96]). Among patients with psychiatric symptoms, the CASSY performed better than the ASQ (0.72 [95% CI, 0.68-0.77] vs 0.57 [95% CI, 0.55-0.59], respectively).Conclusions and relevanceThis study suggests that both the ASQ and the CASSY are appropriate for universal screening of patients in pediatric EDs. For the small subset of patients with psychiatric symptoms, the CASSY shows greater predictive validity.

Project description:IntroductionCommunity programs to teach nonmedical laypeople how to recognize an opioid overdose and effectively resuscitate the victim using naloxone have proliferated recently as a significant component of harm-reduction efforts. Although many such programs target laypeople like first responders or friends and family members of people who use drugs, there are currently no programs that specifically target addiction counselors, despite their work with a client population at high risk of an opioid overdose.MethodsThe four-hour curriculum designed by the authors covered opioid agonist and antagonist pharmacology; opioid toxidrome signs; legal implications and indications for using the naloxone kits; and hands-on training. Participants were two cohorts of addiction counselors and addiction counseling trainees at our institution and an affiliated Opioid Treatment Program methadone clinic. Surveys testing participant knowledge and confidence were conducted at baseline, immediately post-training, six months post-training, and 12 months post-training.ResultsOverall, opioid and naloxone pharmacology knowledge, as well as the confidence to intervene in an overdose emergency, improved among participants in both cohorts. Knowledge scores at baseline (n = 36, median 5/10) improved significantly immediately post-training (n = 31, median 7/10, P < 0.0001, Wilcoxon signed-rank test) and were sustained six (n = 19) and 12 months (n = 11) later. Two participants reported using their naloxone kits to successfully reverse a client overdose in the 12 months after taking the course.DiscussionThese results from our knowledge translation pilot project suggest that our educational program to train addiction counselors in opioid pharmacology and toxicology, allowing them to recognize and respond to an opioid overdose, is feasible and could be effective. Specific barriers to implementing such educational programs include cost, stigma, and unclear best practice for designing and conducting these programs.ConclusionsFurther study of providing opioid pharmacology education and overdose and naloxone training to addiction counselors and counseling trainees appears to be warranted.

Dataset Information

Advanced models for improved prediction of opioid-related overdose and suicide events among Veterans using administrative healthcare data

Supplementary Information

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets