Sentri7 Drug Diversion

The determination is the product. Sentri7 Drug Diversion exists to weigh more than 60 risk determinants across more than seven transaction sources and return a judgment about which behavior warrants investigation, and the vendor names machine learning as the method in its own voice rather than hiding behind the word analytics. Remove the model and nothing sellable remains. That applies to the diversion module specifically, not to the sibling products around it.

Staff are prioritized for investigation by the proprietary HEAT score, which measures a person's risk relative to peers in their unit, and the scoring does not act on its own: administrators review transactions, investigators work from a dashboard showing alerts, trends, outlier calculations and documentation, and users can see why a transaction was flagged and how the risk score is weighted.

Alert parameters such as late wasting, late administration and barcode scanning can be set by care area to match the organization's policies, the risk determinants are validated regularly by the vendor's clinicians, and the FAQ says plainly that some elements of a person's behavior are not tracked by the technology. The published study frames the aim as returning pharmacist time to patient care, citing the American Society of Health-System Pharmacists position on AI in pharmacy.

Taken together, that is a described oversight structure with thresholds the customer configures. What is missing is what happens after a flag proves wrong, and no qualification is stated for the person reviewing a flagged clinician.

The method is named as machine learning and advanced analytics, the input surface is enumerated as more than seven distinct data sources with each named, the model is described as weighing and combining more than 60 determinants of risk into the proprietary HEAT score, and the performance is reported in the American Journal of Health-System Pharmacy with accuracy, specificity and sensitivity given separately rather than collapsed into a single marketing figure.

Yet the determinants themselves are counted rather than listed, the model family and training procedure are described only at the level a journal abstract permits, and the published characterization dates from 2022 with no subsequent update published for the current build, although the FAQ says the product is continuously updated.

What is described is the architecture: machine learning risk models that weigh more than 60 determinants from more than seven named data sources into a proprietary HEAT score comparing each staff member with peers in their unit, running on Wolters Kluwer's SoleSource platform, which also applies data mapping and natural language processing to enrich incoming data.

No model provider, framework, library or third party analytics component is named, no subprocessor list is published, and no distinction is drawn between capability built by Invistics before the 2023 acquisition and capability added since. The gap around the acquisition matters here because the published performance evidence dates from 2022, and nothing published shows how much of the system that produced it is the system being sold.

Peer reviewed efficacy evidence with a defined population and method. A study in the American Journal of Health-System Pharmacy, funded by the National Institutes of Health, evaluated the software across ten acute care inpatient hospitals in four health systems, more than 20,000 clinicians and over 25 million medication movement transactions, and reported detection of all 22 known diversion incidents at 96.3 percent accuracy, 95.9 percent specificity and 96.6 percent sensitivity, with known cases surfaced a mean of 160 days and a median of 74 days earlier than existing methods.

That is a defined population, a stated gold standard and a measured result. The study assesses the vendor's own software, so its independence turns on the authorship and funding declarations. It also examined the platform as Invistics operated it before the 2023 acquisition, so it describes the product's lineage rather than certifying its current build.

Wolters Kluwer publishes general assurances: the SoleSource platform on which Sentri7 runs is described as using encryption, role based permissions, staff training and a SOC 2 audited data center, and its corporate AI principles commit to privacy and security in AI design. None of it answers the questions artificial intelligence raises.

Nothing states whether customer transaction data trains models that persist beyond the tenant, whether risk weightings and the HEAT score are fitted per customer or across the installed base, what retention applies to behavioral records about named clinicians, or whether anything is de identified. The question has particular force here because the product joins employee time clock data, wholesaler records and retail pharmacy transactions into a behavioral picture of individual staff. No safety engineering is published: nothing describes guardrails on the risk scoring or how a safety event is handled.

Wolters Kluwer's own announcement describes Sentri7 as an interoperable software as a service platform and a HIPAA compliant clinical surveillance solution, and the SoleSource platform on which Sentri7 applications, including Drug Diversion, are now deployed is described as holding data to strict security standards: a SOC 2 audited data center, encryption, role based permissions and staff training. That is a status stated without the document behind it.

The HIPAA compliant description dates from a 2017 announcement about the surveillance platform, six years before the diversion module joined the suite through the Invistics acquisition in 2023, so nothing published says whether it covers this module. No business associate agreement, data ownership statement or description of how protected health information is handled is published for a product that reads identified clinician and patient medication records.

The SoleSource platform, on which Sentri7 Drug Diversion is deployed, is described by Wolters Kluwer as meeting strict data security standards such as a SOC 2 audited data center, data encryption, role based permissions and employee training. The SOC 2 statement is attached to the data center rather than to Wolters Kluwer's application or operations, and whose data center it is and whose report it is are not stated, so it cannot be read as an attestation covering this product.

No certification, attestation, trust portal or security page is published for Sentri7 Drug Diversion or for the Sentri7 line. Wolters Kluwer publishes ISO 27001 certification for some tax and accounting products, and nothing equivalent is published for this one. For a product that reads controlled substance records and identified clinician behavior, nothing published shows whether the SOC 2 report's scope covers the application.

Sentri7 Drug Diversion is positioned as surveillance and investigation software that supports compliance with the Controlled Substances Act and DEA enforcement through automated audit reports, evidence collection and alignment with state and federal requirements. It makes no device claim and stays within that scope.

The company publishes no statement of its own regulatory position, meaning what claims it does and does not make, and no guidance on how its output should and should not be used in a disciplinary or law enforcement process, which a diversion finding frequently becomes.

The product's study in the American Journal of Health-System Pharmacy reports specificity of 95.9 percent across 25 million transactions, which makes it possible to estimate how many transactions get wrongly flagged and therefore how much investigative burden and unwarranted suspicion the system generates. Publishing that figure is a real disclosure.

Wolters Kluwer also publishes corporate AI principles covering privacy and security, transparency and explainability, governance and accountability, fairness and human focus, and the product FAQ says the vendor's clinicians regularly validate the risk determinants. Those are principles and a validation practice rather than a governance framework with named process: no responsible body, contact, evaluation method or monitored metrics are published.

What is absent is analysis of who absorbs the false positive load. No breakdown by role, shift, unit or seniority has been published, and a score drawing on overrides, timing and time clock data can concentrate on staff whose work is most interrupted or irregular. Nothing describes model monitoring, drift or review.

An error rate is published, and the vendor adopts it as its own. Wolters Kluwer publishes the results of a peer reviewed study in the American Journal of Health-System Pharmacy (2022), funded by the National Institutes of Health: across ten acute care hospitals in four health systems, more than 20,000 clinicians and over 25 million medication movement transactions, the software detected all 22 known diversion incidents with 96.3 percent accuracy, 95.9 percent specificity and 96.6 percent sensitivity. The figure comes with its method and denominator. The study examined the platform as Invistics operated it before the 2023 acquisition, so it describes the product's lineage rather than its current build.

Mechanisms also let a hospital examine and contest a flag before acting on it. The product FAQ says users can see why a transaction was flagged and what contributes to a person's risk score, including the weighting, and that investigators see all alerts, trends, outlier calculations and documentation on one page, with notes carrying their author.

Nothing contractual stands behind the output. No accuracy commitment or remediation obligation is published, and there is no route for the clinician whose score may enter a disciplinary, licensure or law enforcement process to learn of the flag or challenge it. The 95.9 percent specificity means wrong flags occur at a knowable rate, which makes that missing route sharper. A separate product page claims over 90 percent alert accuracy with no method behind it.

Integration breadth is the product's structural advantage and it is specified rather than implied. Named sources include the electronic health record, automated dispensing cabinets, CII Safe, the narcotics vault, reverse distributor systems, retail pharmacy systems, wholesaler systems and the employee time clock, and procedural monitoring uses procedure start and end times documented in the electronic health record.

Reaching outside clinical systems into the supply chain and workforce records is what allows reconciliation from purchase through to administration. Specific electronic health record and dispensing cabinet vendors go unnamed, and nothing published describes the depth or method of each connection beyond extraction from existing systems.

Sentri7 Drug Diversion is delivered as a hosted application on Wolters Kluwer's SoleSource platform, which Wolters Kluwer describes as a single platform for its surveillance and compliance applications running from a SOC 2 audited data center, and its implementation extracts data from the hospital's existing systems rather than installing the analytics on site. That is a single hosted option, with location implied rather than committed.

No cloud provider, region, residency commitment or customer option is stated. The system aggregates identified clinician behavior from eight source systems, and nothing published says which jurisdiction that aggregate sits in or who operates the data center.

No price, packaging tier or basis of charge is published for Sentri7 Drug Diversion or the wider platform. What is published is the shape of the offering: Sentri7 and Simplifi+ applications are deployed on the SoleSource platform, which Wolters Kluwer says makes it easier to add applications and locations as programs grow, and implementation is team based with clinical and technical specialists and acceptance signed off by the health system.

That describes a modular platform sale without saying what any module or location costs, or whether the diversion module is licensed per facility, per bed, per clinician monitored or per transaction. The cost cannot be sized before a sales conversation, and the unit matters especially here because the product's value argument rests on transaction volume.

Coverage is defined by where medication actually moves rather than by care setting alone, which is the more useful cut for this problem. The product spans pharmacy, nursing and anesthesia inside the hospital, with procedural areas such as the operating room and recovery monitored using alert rules tied to documented procedure times, and it reaches either side of the hospital through wholesaler and reverse distributor data, retail pharmacy systems and the narcotics vault.

It monitors non controlled medications and masking agents alongside controlled ones. Wolters Kluwer names hospitals and health systems, clinics and ambulatory surgery centers as intended settings, but the published deployment evidence is concentrated in acute care inpatient hospitals, so the other settings are stated rather than demonstrated.