A Pilot, Predictive Surveillance Model in Pharmacovigilance Using Machine Learning Approaches.

INTRODUCTION: The identification of a new adverse event (AE) caused by a drug product is one of the key activities in the pharmaceutical industry to ensure the safety profile of a drug product. Machine learning (ML) has the potential to assist with signal detection and supplement traditional pharmacovigilance (PV) surveillance methods. This pilot ML modeling study was designed to detect potential safety signals for two AbbVie products and test the model's capability of detecting safety signals earlier than humans. METHODS: Drug X, a mature product with post-marketing data, and Drug Y, a recently approved drug in another therapeutic area, were selected. Gradient boosting-based ML approaches (e.g., XGBoost) were applied as the main modeling strategy. RESULTS: For Drug X, eight true signals were present in the test set. Among 12 potential new signals generated, four were true signals with a 50.0% sensitivity rate and a 33.3% positive predictive value (PPV) rate. Among the remaining eight potential new signals, one was confirmed as a signal and detected six months earlier than humans. For Drug Y, nine true signals were present in the test set. Among 13 potential new signals generated, five were true signals with a 55.6% sensitivity rate and a 38.5% PPV rate. Among the remaining eight potential new signals, none were confirmed as true signals upon human review. CONCLUSION: This model demonstrated acceptable accuracy for safety signal detection and potential for earlier detection when compared to humans. Expert judgment, flexibility, and critical thinking are essential human skills required for the final, accurate assessment of adverse event cases.

Effects of Fear and Humor Appeals in Public Service Announcements (PSAs) on Intentions to Purchase Medications via Social Media.

The increasing prevalence of online purchase of medications, specifically via social media platforms, poses significant health risks due to high chances of such medications being substandard and falsified (SF). The current study uses a 2 (persuasive appeal: fear vs. humor) x 3 (message repetition) mixed factorial experiment to investigate the effectiveness of persuasive appeals (on intentions to purchase medications online via social media referrals, mediated by psychological reactance (threat to freedom and anger), attitudes toward the public service announcements (PSAs), and viral behavioral intentions. ANOVA results showed the superiority of humor appeals compared to fear appeals in (1) reducing psychological reactance, (2) igniting favorable responses to the PSA, and (3) marginally reducing the intentions to purchase medications vial social media despite lower online engagement intentions (viral behavioral intentions). Pre-existing risk perceptions moderated these differences. A moderated serial mediation model, conducted using PROCESS models, was examined to assess the mechanism by which persuasive appeals and risk perceptions interact in influencing purchase intentions. Findings are discussed theoretically in regard to extending the psychological reactance model within the digital environment and practically in terms of public health, brand protection, and law enforcement recommendations.

A Continuous Observation Workflow Time Study to Assess Intravenous Push Waste.

Background: There are significant costs associated with proper controlled substance disposal, management, and regulatory compliance. Given the high abuse potential of fentanyl, hydromorphone, and morphine it is imperative that (1) product waste is minimized; and (2) waste procedures are followed to ensure safe disposal. Research is needed to better understand the financial and workforce impacts of drug waste on inpatient hospital units. The primary objective of this study was to quantify the waste associated with administering fentanyl, hydromorphone, and morphine via the intravenous push route. Two categories of waste were evaluated: (1) the quantity (mg/µg) of drug disposed; and (2) workforce time associated with the waste disposal process. Methods: A workflow time study design, a sub-set of continuous direct observation time motion studies, was employed to achieve the research objectives. A data collection tool was developed to capture medication type, waste amount, activity time stamps, total time, and number of interruptions at two separate study sites. Descriptive statistics were conducted on all the data measures. The number of assessments, total values, and mean values were reported for each drug (fentanyl, hydromorphone, and morphine) separately as well as grouped data. Results: A total of 669 distinct waste observations meeting inclusion criteria were collected during a study period of 15 days. In total, 207 mg of hydromorphone and 17 962.50 µg of fentanyl were wasted during this study. Nursing staff time associated with the wasting process totaled 50 990 seconds (849.83 minutes or 14.16 hours). A combined waste (loss) of approximately $1605.39 was associated with controlled substance wasting. The cost per dose wasted in this study was found to be $2.40 for all medications. When a yearly extrapolation model was applied to the four study units, the total combined product and workforce waste cost was $35 425. Conclusion: There are financially significant costs associated with wasting both the product and the valuable time of a skilled workforce. Optimizing product size, taking special note to match product availability with common practice use, would reduce the associated financial burden on our health-systems nationwide.

Guidelines for Leading a Safe Medication Error Reporting Culture.

Background: A safe medication error reporting culture is one that promotes, fosters, and rewards the reporting of errors and events across the spectrum of harm (none to significant harm). For this culture to develop, leaders must key department cultural norms. These cultural norms include making employees feel psychologically safe to report errors, and to establish a culture of error review and follow-up that complies with best practices. Objective: This article reviews how pharmacy leaders can establish this environment by describing (1) setting an appropriate vision for safety as a priority; (2) establishing and actively supporting the concept of psychological safety; and (3) implementing medication error review that support an effective safety culture. Finally, the article discusses a case where the relationships between psychological safety, safety culture, and reporting culture are described. Methods: This article reviews the literature and authors' experiences in designing a safety culture for a pharmacy department. Concluson: A safe reporting culture requires leaders to be humble, engage their staff in dialogue, objectively measure culture, consistently provide feedback, and empower its people. Employing these leadership traits with best practices can improve overall medication safety and the quality of patient-centered pharmacy services.