Publication

Article

Pharmacy Practice in Focus: Health Systems
September 2024
Volume 13
Issue 5

The Power of Integrated Data Feeds to Support Drug Diversion Detection

A centralized, artificial intelligence–driven approach can integrate diverse data and foster multidisciplinary collaboration.

Health care professionals using AI -- Image credit: Nuttapong punna | stock.adobe.com

Image credit: Nuttapong punna | stock.adobe.com

About the Author

Beth Richter, PharmD, is a director of sales at Wolters Kluwer Health in Chicago, Illinois.

In the intricate network of a health care system, detecting drug diversion across multiple sites or care areas poses additional challenges compared with single sites. Drug diversion, or the illicit transfer of prescription medications from lawful channels to unauthorized individuals or for illegal purposes, threatens patient safety, compromises the integrity of health care institutions, and undermines public trust.

The scope of this issue is vast, with ramifications ranging from potential harm to patients to legal and regulatory consequences for health care providers. Additionally, although nearly all health care leaders agree drug diversion occurs, 79% believe that most cases go undetected, according to the results of Wolters Kluwer’s State of Drug Diversion 2023 Report.1

Unlike single-site hospitals, where monitoring may be more localized and straightforward, multisite health systems require a broader, systemic approach to diversion detection that navigates additional logistical complexities. The interconnectedness of various departments and the movement of personnel across sites within a health system necessitate a centralized monitoring system capable of aggregating data from disparate sources. Only by adopting a comprehensive view and integrating various data feeds can health care institutions effectively identify and address instances of drug diversion across their entire network.

Diverse Data Feeds: Building a Comprehensive Detection System

When thinking about how to approach drug diversion detection in a health system, the first consideration is personnel movement. Consider a float nurse who may be moving from one site to another to fill gaps—could you determine whether they were diverting medications with your current detection system?

A centralized approach enables a holistic view of an individual’s activity across sites, allowing monitoring personnel to observe their movements and behaviors as they move through the organization. However, this centralization cannot come at the expense of depth, as detection requires a mix of holistic pattern detection, monitoring, and points of risk.

Achieving this balance requires access to a wealth of data across the system, facilitating both broad observations and detailed scrutiny when anomalies arise. Beyond basic transactional data, such as dispensed medication without proper administration documentation, inputs like time clock data, administration and waste delays, anesthesia administration analysis, and controlled substance movement in and out of the pharmacy’s narcotics vault play pivotal roles. Time clock data, for example, can reveal irregularities, such as staff accessing medication cabinets outside their shifts.

Moreover, pharmacy records offer insights into wholesaler shipments and cabinet restocking activities. Additionally, the integration of electronic health record flow sheet data for infusion and patient-controlled analgesia reconciliation and patient pain scores further enriches the detection process, enabling the identification of irregular behavior patterns indicative of potential diversion. Further, growth or changes within a health system through mergers or acquisitions might result in disparate data systems, demanding technological solutions to consolidate these inputs efficiently.

Streamlining Data Analysis With Artificial Intelligence for Enhanced Detection

Although drug diversion monitoring and detection requires a human element to navigate the complexities of care in a health care system and help break down data trends, it is also one area where advanced analytics and technology add immense value. Integrating artificial intelligence (AI) technologies helps simplify the management of diverse data inputs across health systems, processing the vast volume of data generated within health care settings to illuminate trends. By normalizing data from disparate systems and identifying patterns, AI enhances the accuracy of diversion alerts, enabling proactive intervention.

Rather than isolated incidents, diversion often manifests as a series of irregularities. Detecting these trends is challenging, emphasizing the need for technological solutions that offer actionable alerts and facilitate trend analysis and investigation management. Such platforms are one-stop shops that not only aid in identifying suspicious behaviors but also serve as repositories for ongoing investigations, ensuring continuity and preserving institutional knowledge even amid personnel changes.

The Importance of Multidisciplinary Collaboration

A successful drug diversion prevention program requires the collaboration of various stakeholders within the health care system who can help determine whether trends flagged by AI are justified or cause for concern. Although the pharmacy department typically spearheads these efforts, involvement from nursing, compliance, risk management, and even human resources departments is essential. A multidisciplinary approach ensures a comprehensive understanding of diversion risk and facilitates effective mitigation strategies.

Training also plays a crucial role in mitigating the risk of diversion. Educating health care professionals about prevention and monitoring protocols fosters awareness and vigilance. Emphasizing the educational aspect over punitive measures encourages a culture of transparency and accountability, empowering staff to participate in diversion prevention efforts and take an all-encompassing approach to prevention. With 78% of health care leaders1 admitting they know someone who has diverted medication, this on-the-ground vigilance is essential.

Technology and Clinical Insights: Synergy for Effective Prevention

Combining technology with clinical insights is paramount in informing diversion detection and prevention. Although technology provides the framework for data analysis and alert generation, clinical expertise offers contextual understanding. For example, patients in an orthopedic department may, by nature, require higher levels of pain management, which technology systems could flag as drug diversion. For high accuracy, diversion systems must provide peer comparison by department and patient population. A clinical leader would expect a different pattern of care for the orthopedic department. This synergy ensures a comprehensive and accurate assessment of diversion risk, enhancing the effectiveness of prevention measures.

Despite drug diversion being a known threat to patient and staff safety, the battle against it within health care systems wages on—but AI-enabled technology systems may help parse insights from data pools. By integrating diverse data feeds, employing AI-driven analytics, and fostering a culture of vigilance and transparency, health care institutions can fortify their defenses against diversion, protecting patient safety and preserving health care system integrity.

REFERENCE

1. Wolters Kluwer. The State of Drug Diversion 2023 Report. September 12, 2023. Accessed June 5, 2024. https://www.wolterskluwer.com/en/expert-insights/the-state-of-drug-diversion-2023-report#gc
Related Videos
Practice Pearl #1 Active Surveillance vs Treatment in Patients with NETs