DrFirst

On top of a large network business, the models are the differentiator, and the company draws that distinction itself.

The base is infrastructure. Electronic prescribing, controlled substance prescribing, secure clinical messaging, benefits checking and a national medication history network are transaction routing and connectivity, built over twenty five years on industry messaging standards. That business would exist and function with no model in it, and the chief executive describes joining what he would then have called an electronic prescribing company.

The models are what the company now sells on and they do specific, difficult work. SmartSig parses unstructured free text sig instructions into discrete components, resolves synonym variation into a facility's own terminology, infers missing elements, and supplies alternative drug identifiers where a medication cannot be matched. Natural language processing and machine learning are both named, the technology is patented, and the output is measurable: automatic sig mapping rising from 26 percent to 86 percent at one health system across 300,000 medications is a direct measure of what the model contributes.

The company's own line on this is testable. Asked about machine learning, the chief executive said they do not believe that slapping a chatbot on top of existing products counts as artificial intelligence. A company that names the cheap version of the claim and disowns it is inviting scrutiny of its own.

A substantial share of what customers buy is the network rather than the intelligence, while the models carry the product's current commercial argument.

The company argues publicly for human oversight of its own product, and one question that follows from the design goes unanswered.

The framing is explicit and it is published under a title that states the position: keeping a human in the loop, because artificial intelligence for medication management requires clinical safety checks. A vendor writing that about its own technology, rather than about the category in general, is setting a standard it can be held to. The chief executive's rejection of superficial artificial intelligence claims is consistent with it.

The architecture supports the framing in an important structural way. SmartSig does not make a clinical decision. It converts unusable data into usable data, and the usable data then triggers the record system's own interaction and allergy checking. So the model's output feeds the existing safety machinery rather than substituting for it, and the clinician performing medication reconciliation reviews the result as they always would. Compared with a model that issues a clinical determination, the autonomy here is a data transformation with a human reviewer downstream.

The unanswered question is provenance at the point of review. When SmartSig infers a missing sig element or resolves an ambiguous drug match, nothing published states whether the clinician reconciling that medication can see which fields were inferred by the model and which came from the source record. That distinction is the whole of the oversight in practice: a pharmacist who knows a frequency was inferred will check it, and one who assumes it came from the pharmacy will not.

The approach is named concretely. SmartSig converts free text sig instructions into discrete components, codifies terminology into each facility's standard, supplies alternative drug identifiers where a medication cannot be matched, and infers missing details when the company judges it safe to do so; natural language processing and machine learning are named as the methods and the technology is described as patented.

One performance figure is published, 92 percent of free text prescription instructions converted automatically, and the problem is stated with one too, an estimated 66 percent of records in the largest medication history database missing essential sig information. The result is an accurate picture of what the software does.

What is absent is everything below that: no model architecture, training corpus description, evaluation method behind the conversion figure, error analysis, versioning or update cadence. Versioning carries real weight here, because a parser that changes behavior alters what enters patient charts, and nothing describes how a customer learns that it has. The phrase clinical grade artificial intelligence is used without a definition.

The technology's own provenance is documented through patents and acquisitions, and the model's inputs and components are not.

What is traceable is corporate and legal. The sig technology is described as patented and patent pending across multiple public announcements, so the method is documented in filings a reader can retrieve and attribute, which is a stronger form of provenance than a marketing description. The Myndshft acquisition in 2024 is documented with the acquired platform's own capabilities stated, so the medical benefit authorization capability is known to have arrived from outside and can be assessed separately. Twenty five years of continuous operation under a single founder establishes that the core network is in house rather than assembled.

The data supply chain is visible by category if not by name. Medication history is sourced from pharmacies, payers and the national prescription network, which is inherent to the product.

What is absent is the model itself. No framework, no third party component, no pretrained model and no external natural language processing service is named or ruled out, and no bill of materials is published. Nothing states whether the parsing models are built entirely in house or incorporate licensed components, which matters because it determines whether prescription text reaches a party other than DrFirst.

The training corpus is the larger gap: a sig parser learns from real prescriptions, and nothing describes whose.

A strong body of named, quantified deployment evidence, with no peer reviewed or independent validation published.

Five health systems are named with before and after figures rather than testimonials. Hackensack Meridian Health reports automatic sig mapping rising from 26 percent to 86 percent across a stated sample of 300,000 medications, and publishes that on its own newsroom rather than leaving it to the vendor, which makes it customer attested. Scripps reports medication history available for 96 percent of patients over 65 with 85 percent of home medication sigs enhanced. Monument Health reports 93 and 82 percent. Covenant HealthCare reported recapturing 15 percent productivity per shift in the first month, valued at roughly $650,000 monthly. Emory Healthcare reports a 13 percent improvement in best possible medication history. An academic medical center reported a 20 percent improvement in prescription first fill rates using the population health capability.

Those are operational measures with denominators in at least one case, drawn from different institutions on different record systems, and they point consistently the same way.

No peer reviewed publication or independent evaluation is published. The model figure that does exist, 92 percent of free text instructions converted automatically, is vendor stated with no method, sample or error analysis. And no study connects improved sig completeness to reduced adverse drug events, which is the clinical outcome the whole argument rests on, even though medication reconciliation is a national patient safety goal and the causal chain is plausible.

The company's own published statistic reveals the scale of what it holds, and nothing describes the terms on which it holds it.

That statistic is the tell. DrFirst states that an estimated 66 percent of records in the nation's largest medication history database are missing essential sig information. Producing that figure requires analyzing the national database at population scale, which establishes both the reach of the company's data position and its willingness to study the corpus. It is a useful and honest disclosure about the state of the data, and it is silent about the governance around it.

Nothing published states whether prescription and medication history records inform model training, whether learning is confined per customer or pooled across the network, what de identification standard applies, what retention governs medication history, or whether a health system can decline secondary use. For a model whose entire function is learning how prescribers and pharmacies write sig instructions, the training corpus is very likely real prescriptions written for real patients, and the provenance of that corpus is unaddressed.

The patent position implies documented methodology exists, since patents describe technique, and it says nothing about data rights.

The HITRUST i1 certification covering all medication management solutions is real assurance about controls over the data, which is the handling half of the question. It does not address whether the data should be repurposed, which is the stewardship half.

A HIPAA compliance claim appears in the company's own material, describing Backline's messaging as HIPAA compliant, and its certifications page names HITRUST and SOC 2 Type II coverage across its medication management products. No business associate status is stated, no business associate agreement is offered, referenced or published, and no HIPAA statement or notice covering how medication history and prescription data are handled is published.

The website privacy policy excludes information governed by HIPAA from its scope. The certifications are real assurance about controls. The data flows are extensive: a national medication history network, prescription records from pharmacies and payers, structured medication data written into hospital records and clinical messaging, so the missing contractual layer matters, including what governs data acquired through the Myndshft platform.

DrFirst lists three attestations on its certifications page, each with a product scope: HITRUST and SOC 2 Type II, both covering Backline, electronic prescribing of controlled substances, iPrescribe, medication history, price transparency, e-prescribing and patient engagement (named as Backline, EPCSGold, iPrescribe, MedHx, myBenefitCheck, Rcopia and RxInform), and TX-RAMP, the Texas state cloud security program, for e-prescribing.

The HITRUST certification was announced in March 2025 as an i1 validated assessment covering all medication management solutions. Recognized certifications are named in the vendor's own material with their scope, and there is no artifact to open without asking. No trust center, report request process, penetration testing statement, vulnerability disclosure policy or incident notification commitment is published.

Two currency points for a buyer: the i1 is an annual certification, so the March 2025 assessment is due for renewal, and neither the SOC 2 report period nor the TX-RAMP level is stated. The i1 is HITRUST's moderate assurance tier rather than its most rigorous. Whether the Myndshft prior authorization platform sits inside these scopes is not stated.

A regulatory credential under another framework is published, and the products are positioned within prescribing regulation. The certifications page records ONC-ATCB certification of RcopiaMU under the 2014 edition criteria (certification number 1314E01P4X4AEAR) and earlier certification as an EHR module in 2010, alongside TX-RAMP for electronic prescribing, and the company describes its controlled substance prescribing as built to satisfy regulatory mandates.

No device claim is made for any product, and the marketed capabilities, prescribing, medication history, sig conversion and benefits checking, carry no diagnostic claim. Two gaps remain. The ONC certification shown is for the 2014 edition, and nothing states current certification status.

And nothing published places sig inference relative to clinical decision support regulation: inferring a missing dose or frequency and writing it into a chart that then drives interaction checking sits closer to that boundary than transaction routing does, and the company does not address it. The Myndshft acquisition extends the business into medical benefit prior authorization, an area under active federal rulemaking.

Nothing published describes how the sig models are governed or tested: no model card, training data description, accuracy breakdown, subgroup analysis or bias statement. The distribution question is specific here. Sig parsing performance can vary by source: prescriptions from large chain pharmacy systems arrive formatted consistently and at volume, while those from independent pharmacies, small practices, compounding pharmacies and long term care systems are more varied.

The published figure of 92 percent of free text instructions converted automatically is an aggregate and does not say where the remainder falls. Complex instructions such as tapers, split doses, as needed regimens and uncommon formulations are common among elderly patients on polypharmacy and patients on psychiatric or specialty therapy, who are also the patients for whom reconciliation errors carry the most risk.

DrFirst has published its own analysis of the national medication history data, so the breakdown by drug class, sig complexity, source system or patient age is one it is placed to produce, and none is published.

DrFirst describes a review step and a limit on inference, and nothing that stands behind the output. Its medication history page says the patented AI automates data mapping for easy verification and reconciliation, so the converted history is presented to the clinician reconciling the chart before it becomes the active medication list, and the company says its AI infers missing medication details only when safe to do so. That review before commit is a mechanism for catching a wrong value.

What is missing is everything behind it. The pathway from error to harm is short: an inferred frequency, dose or route written into the chart looks complete to the reconciling clinician, and the record system's interaction and allergy checks then run on the same value.

Nothing published states an accuracy commitment, indemnity, error reporting route, what 'when safe to do so' means in practice, or how responsibility divides between DrFirst, the source pharmacy whose record was incomplete and the clinician who reconciled it. The published figure, 92 percent of free text instructions converted automatically, is a conversion rate rather than an accuracy commitment.

Interoperability is not a feature of this company, it is the company, and the depth is evidenced by customers rather than asserted.

The integration is embedded rather than adjacent. Medication history and sig enhancement operate inside the record system's own medication reconciliation workflow, populating discrete fields in the chart so the record system's interaction and allergy checking can fire. The vendor's output becomes the customer's data rather than sitting in a parallel view, and the named health systems describe it working inside Epic specifically.

Three major record systems are named across the material, Epic, Cerner and MEDITECH, with a dedicated product line built for the third. Prescription messaging runs on industry standards, so the outbound side is standards based rather than proprietary.

The network dimension extends interoperability beyond the hospital entirely. DrFirst describes a medication history network combining Surescripts, pharmacy fill, payer and health information exchange data, and the Myndshft acquisition added connectivity to more than 600 payers for benefit and authorization data.

The customer evidence confirms it in operational terms. Hackensack Meridian's automatic sig mapping rising from 26 to 86 percent in its Epic integrated deployment is a measure of how much data successfully crossed the boundary into structured chart fields, which is interoperability measured as an outcome rather than claimed as a capability.

The products are delivered as hosted services: medication history is available within seconds through a web or EHR interface with go live in as little as two weeks, and DrFirst holds TX-RAMP certification, the Texas state program for cloud services, for e-prescribing. That is a single hosted option with location implied rather than committed. No hosting provider, region, residency option, subprocessor list, retention position or export term is published. Availability is also unaddressed.

Medication history is queried at the moment of admission and sig enhancement sits between the source data and the chart, so an outage returns the hospital to manual reconciliation; DrFirst sells a downtime product for EHR outages, but no uptime commitment, status history or continuity position is published for its own services. The Myndshft acquisition adds a second infrastructure for benefit and authorization checking, and nothing states whether it has been consolidated.

iPrescribe, DrFirst's standalone e-prescribing app for individual prescribers and practices, publishes tiers with figures on its own pricing page: Mobile at $30 and Practice at $50 per license per month, billed annually and purchasable online, with an Enterprise tier on custom pricing plus a one time integration fee. Those prices describe a side product and size nothing else.

For the hospital products, medication history with SmartSig, Rcopia and the Fuzion platform, no price, unit of charge, module structure, contract term or buying route is published, and nothing says whether medication history is charged per query, per bed, per prescriber or per site. Cost cannot be sized before a sales conversation. Volume is why the missing unit matters: medication history is queried at every admission and transition of care, so a per transaction basis and a site license diverge sharply at hospital scale.

Coverage spans the full medication pathway across both care settings, and the breadth is a consequence of twenty five years of network building rather than a marketing claim.

Setting coverage runs from ambulatory prescribing through hospital admission, transfer and discharge. Electronic prescribing and controlled substance prescribing serve the outpatient prescriber, medication history and sig enhancement serve the hospital at every transition of care, and discharge prescribing and adherence work extend past the encounter. Medication reconciliation is recommended at every transition, so the product touches the same patient repeatedly across settings.

Specialty coverage is inherent rather than configured. Every prescriber writes prescriptions and every admitted patient has a medication history, so the addressable population is not a specialty at all. The named customers reflect that spread, running from a large integrated network and two academic systems to a community hospital and a rural medical center in Mississippi.

Record system coverage is the practical enabler, with Epic, Cerner and MEDITECH all named and integrations built to industry prescribing standards rather than per customer.

The Myndshft acquisition extended coverage from pharmacy benefit into medical benefit, reaching eligibility for 95 percent of insured patients and authorization requirements for more than 600 payers. Expensive infused and specialty drugs sit on the medical benefit and are exactly the therapies where authorization delay causes harm.