FeelBetter

Two of the platform's four tools are the model and the other two deliver its output. Insight stratifies an entire population by risk of near term medication related deterioration, and Action generates the specific regimen changes a pharmacist should consider, while Navigator and Impact handle workflow and post intervention monitoring.

Remove the learned components and what remains is a pharmacist worklist with no basis for deciding which of a hundred thousand patients to open first, which is the entire proposition. Independent trade reporting describes the approach as machine learning driven rather than repeating vendor language, and the peer reviewed evaluation at Brigham and Women's Hospital assessed the model's output rather than the workflow around it.

One caution for readers: Pharmaco-Clinical Intelligence is a term the company coined for its market position and it should not be mistaken for a description of a method, since the company publishes no method.

The oversight chain is sound and conventional. Recommendations go to a clinical pharmacist who reviews them, and any medication change still requires a prescriber to act, so two licensed humans stand between the model and the patient. What deserves a buyer's attention is a second order effect specific to this product's economics, and it applies to the whole polypharmacy segment rather than only to this vendor.

Part of what is being sold is throughput, with the company's own site citing a reduction of roughly 30 percent in average review time per complex patient and its materials emphasising expanded clinical pharmacist capacity. Human review that becomes faster and covers more patients is human review that is thinner per case, so the oversight that justifies the autonomy grade is the same resource the return on investment depends on consuming. Ask what the pharmacist acceptance rate is, how often a recommendation is modified rather than adopted, and whether review time reductions were measured against equivalent case complexity.

Vendor published technical detail is close to absent. Retrieval across the company site, its news pages and the press record surfaced no model family, no method, no feature set, no risk threshold, no validation methodology and no statement of how the risk score is constructed, with the coined category name standing in for a technical description throughout.

The reason this is not graded lower is that a peer reviewed evaluation of the platform exists in the American Journal of Managed Care, authored by investigators at Brigham and Women's Hospital, which is an artifact a determined reader can obtain and which reports performance figures the company then quotes.

Scope stated plainly per index practice: that paper was identified through its announcement and its methods section was not read in this pass, so this grade describes what the vendor itself publishes and should be revisited by anyone who reads the paper in full.

The peer reviewed work is real and the distinction between what it measured and what the company claims is the important part. Investigators at Brigham and Women's Hospital published a retrospective cohort of 108,817 medically complex senior patients in the American Journal of Managed Care, reporting that the platform delivered correct medication warnings in 89.2 percent of cases and that in 97.3 percent of cases the warnings presented would be helpful to a clinician optimising therapy.

Those are judgements about the appropriateness of recommendations, not measurements of what happened to patients, so the published evidence establishes that the model gives sensible advice rather than that acting on it reduces harm.

Operational results are reported separately and are vendor published: a pilot across eight Americare long term care facilities involving 370 residents, presented at a consultant pharmacist meeting, and utilisation and capacity figures appearing in company materials. Held at B for a strong validity base without a published outcome study, and a prospective evaluation of what changes for patients is what would move it.

The data footprint is among the broadest in this category. The platform synthesises longitudinal pharmacy records, clinical data and claims across an entire covered population rather than examining one prescription at the moment it is written, and one published study alone covered 108,817 patients.

Retrieval located no retention schedule, no de identification practice, no minimum necessary scoping and no statement of whether customer data informs model development across institutions, which is the question that matters most for a risk model whose value grows with the size of the population it has learned from.

An Israeli company processing United States patient data for health systems, accountable care organisations and long term care operators also carries a cross border handling question that nothing published addresses.

Two retrieval passes across the company site, its news and blog pages and the press record surfaced no HIPAA statement, no business associate agreement terms, no execution path, no subprocessor list and no compliance page. As with other vendors in this lane the grade describes published posture rather than contractual reality, since a business associate agreement must govern the Atlantic Health System and Americare relationships or those deployments could not exist.

What is notable is the pattern rather than the individual gap. This is now the third vendor graded in this category where strong clinical evidence sits alongside no published compliance posture at all, which suggests a segment norm rather than an oversight by one company.

Retrieval located no SOC 2 attestation of either type, no HITRUST certification, no ISO 27001, no trust centre, no penetration testing cadence and no vulnerability disclosure policy, with a targeted second pass specifically for compliance material returning nothing belonging to this vendor.

The deployments imply that customer security reviews were passed, since a health system and a long term care operator would each have run one, but private diligence is not an artifact a prospective buyer can read. For a platform holding longitudinal medication and clinical histories for entire senior populations, publishing an attestation would be the single highest value change available to this record.

No clearance was located and none is claimed, which is consistent with a product that stratifies risk and proposes options to a clinical pharmacist rather than computing a dose or acting on a patient. That position is available under the statutory exclusion for non device clinical decision support, and the pharmacist plus prescriber review chain is the kind of arrangement the exclusion contemplates.

The company states no regulatory position anywhere, which is the same gap seen across most of this category and which matters because the boundary is contested. A buyer should also note that a model recommending discontinuation of a medication, which is what deprescribing means in practice, is making a therapeutic proposal rather than surfacing a reference fact, and should establish how the vendor characterises that distinction.

Retrieval located no subgroup performance reporting, no bias assessment, no governance documentation and no statement of post deployment monitoring. The exposure here is specific rather than generic. The model predicts near term hospitalisation, and hospitalisation prediction is the best documented failure case in clinical machine learning fairness, because utilisation reflects who has access to care as much as who is unwell, and models trained on it have been shown elsewhere to under identify need in populations that historically received less care.

A platform whose purpose is to direct scarce clinical pharmacist attention is deciding who receives an intervention, so the distributional question is the whole question. The company holds the data to answer it, since its published cohort already exceeds a hundred thousand patients.

Integration is asserted at a general level and confirmed only by inference. The platform is described as fitting into existing claims and electronic health record workflows, and three live deployments across a health system, a long term care operator and an Israeli health maintenance organisation establish that data flows in practice.

What is missing is any specific evidence a buyer could check: no named electronic health record certification, no Epic or Oracle marketplace listing, no FHIR conformance statement, no published API and no description of whether ingestion is claims based, clinical feed based or both.

Since the product depends on assembling a longitudinal pharmacy and clinical picture across sources, the ingestion architecture is a material procurement question and it is currently unanswerable from public material.

The product is delivered as a hosted platform and operates for customers in both the United States and Israel, which is as much as public material establishes. Retrieval located no named hosting provider, no cloud region, no data residency commitment, no on premise option and no statement of where United States patient data is processed relative to the company's Israeli engineering base.

Third party company profiles list infrastructure details that the vendor itself does not confirm and which are not relied on here. For customers in long term care and accountable care organisations, both of which carry their own contractual data obligations upstream, this is a gap that will surface during security review rather than before it.

Pricing is undisclosed and the presentation is worth noting precisely. The company's own site lists its impact metrics as labelled categories, savings per high risk patient per month and average review time per complex patient, with one carrying a figure and the other left as a heading, so even the return side is only partly quantified while the cost side is entirely absent.

Retrieval located no price, no unit, no pricing basis, no contract shape and no implementation fee guidance, and no indication of whether the commercial unit is the covered life, the high risk patient, the pharmacist seat or the intervention. For a product sold into accountable care organisations on a total cost of care argument, the pricing unit determines whether the economics work at all.

Coverage is narrow by population and unusually broad by buyer. The population is consistent throughout, older adults with multiple chronic conditions and complex regimens, which is the group where polypharmacy causes the most harm and where the intervention has the clearest value.

Against that focus the platform has been deployed across three structurally different settings: an accountable care organisation model at Atlantic Health System, long term care at Americare, and a health maintenance organisation at Leumit Health Services in Israel, each with different data, different clinical staffing and different incentives. That breadth of buyer is harder than breadth of specialty and it is evidence the platform is not built around one customer's data model. Held at B because the specialty scope is essentially internal medicine and geriatrics, and the named footprint remains small.