SIDEBAR: The Rise of Multi Channel Analyzers in Clinical Chemistry

 SIDEBAR to a broader article.

Sidebar to the Sidebar: When Did Multi-Channel Analyzers Become Common—and Why Do We Still See the Same Panels Today?

Multi-channel automated analyzers began to enter routine clinical laboratory use in the late 1970s and early 1980s, but they became truly widespread during the mid-to-late 1980s and early 1990s. This was the period when hospital and reference laboratories transitioned from largely manual or single-analyte chemistry testing to high-throughput platforms capable of measuring many analytes simultaneously from a single specimen. By the time OIG issued its guidance in 1997 and 1998, these analyzers were no longer experimental curiosities—they were the backbone of routine clinical chemistry.

The key innovation was not simply speed, but parallelization. Earlier analyzers performed one test at a time. Multi-channel analyzers, by contrast, were designed to run multiple assays together because it was operationally easier, cheaper, and analytically cleaner to do so. Once serum was loaded and the instrument calibrated, adding additional analytes often required little incremental effort. This technological reality collided directly with a reimbursement system that still conceptualized testing as a series of individually ordered services.

Out of this collision emerged the chemistry panels that are now so familiar they barely register as “panels” at all. The Basic Metabolic Panel (BMP)—typically including sodium, potassium, chloride, bicarbonate, BUN, creatinine, glucose, and sometimes calcium—reflects a core set of electrolytes and renal markers that were commonly run together on early automated systems. The Comprehensive Metabolic Panel (CMP) expanded this set to include liver-associated analytes such as AST, ALT, alkaline phosphatase, bilirubin, albumin, and total protein, yielding the familiar 14-analyte version used today. Variants with 20 or 21 analytes emerged historically as laboratories added calcium, phosphorus, or other markers depending on platform design and clinical convention.

What is often forgotten is that these panels were not originally “bundles” in a conceptual sense. They were engineering artifacts—groupings that made sense given how the machines worked. Physicians quickly adapted their ordering habits to these groupings because they were clinically useful and readily available. Over time, CPT coding and Medicare policy caught up, formalizing what had started as a technological convenience into standardized billable panels.

By the mid-1990s, however, policymakers faced a new question: what happens when technology makes it easier to run more tests than are clinically necessary for a given patient? OIG’s answer, reflected in the 1997 and 1998 guidance, was not to resist the technology, but to regulate the billing behavior around it. Laboratories could run broad panels if that was how their analyzers worked—but they could not bill indiscriminately.

Seen in this light, modern molecular panels are not a radical departure from historical practice. They are the genomic descendants of the chemistry analyzer. Just as it once made sense to run electrolytes and liver enzymes together, it may now make sense to sequence genes A, B, and C together. The regulatory question has remained strikingly stable for forty years: what matters is not what the machine runs, but what the laboratory reports and bills as medically necessary for each patient.

That continuity is precisely why the 1997–1998 OIG guidance still resonates today.

SIDEBAR: The OIG Laboratory Compliance Guides - 1997, 1998

SIDEBAR to a broader article.

[AI generated text]

• OIG (1997) Model Laboratory Compliance.   62 Fed Reg 9435 (7pp), 3/3/1997. Here.
• OIG (1998) Laboratory Compliance Update.  63 Fed Reg 45076 (12pp), 82/24/1998.   Here. 

###

Sidebar: The 1997–1998 OIG Laboratory Guidance — Why It Was Written, What It Said, and Why It Still Matters

When the Office of Inspector General issued its clinical laboratory compliance guidance in 1997 and then again in 1998, it was responding to a technology shift that now feels quaint but was genuinely disruptive at the time: the widespread adoption of automated, multi-channel analyzers. These platforms could run many chemistry tests simultaneously, often more efficiently than running a single analyte alone. The policy problem was immediate and practical. Medicare payment rules were built around individually ordered tests, but laboratory technology was increasingly optimized around bundled or parallel testing.

OIG recognized that it could not regulate laboratories by pretending this technology did not exist. Instead, the agency focused on what it viewed as the real compliance risk: billing and utilization behavior, not the internal mechanics of the analyzer. Across both guidances, OIG made clear that laboratories were not prohibited from running multiple tests together, even when only a subset was ordered for a particular patient. What mattered was that only those tests that were ordered, medically necessary, performed, and reported were billed to Medicare

This principle runs throughout both documents. OIG repeatedly emphasized that laboratories do not practice medicine and do not decide medical necessity, but they are nonetheless responsible for ensuring that claims submitted to Medicare reflect only services that meet Medicare’s coverage standards. Laboratories were expected to design requisitions, billing systems, and utilization monitoring processes that discouraged overordering and prevented the automatic billing of unnecessary test components. Running a “superset” of tests was not itself problematic; billing indiscriminately for that superset was.

Seen from today’s vantage point, this guidance maps cleanly onto modern molecular workflows. A laboratory may find it efficient to run genes A, B, and C together because they are ordered together most of the time. The OIG’s position—then and now—is not that this efficiency must be undone, but that the laboratory must ensure that gene B or C is not reported or billed when it is not ordered or medically necessary. That is the core continuity between the era of chemistry analyzers and the era of sequencing panels.

---

What the Two Documents Share

Taken together, the 1997 and 1998 guidance articulate a unified regulatory stance. First, physicians may order any tests they believe are appropriate, but Medicare will only pay for tests that are covered, reasonable, and necessary. Second, laboratories are expected to structure their operations to support conscious ordering, not passive or default overutilization. Third, laboratories must have internal controls—requisition design, notices to physicians, utilization monitoring, and billing safeguards—to prevent automated technology from driving inappropriate claims. And fourth, OIG made explicit that laboratories could face False Claims Act or kickback exposure if their pricing, marketing, or billing practices encouraged unnecessary testing

Importantly, neither document treats automation as inherently suspect. The tone is pragmatic, even permissive. OIG’s concern is not how many assays an analyzer can run, but whether the laboratory’s business practices undermine Medicare’s medical-necessity framework.

---

What Is Distinctive About the 1997 Guidance

The 1997 guidance is best understood as a first-generation response to automated testing. It is closely focused on multichannel chemistry panels, CPT-defined profiles, and requisition design. OIG spends considerable time on the mechanics of ordering—encouraging laboratories to design requisitions that force physicians to actively select tests, document diagnoses, and understand the billing consequences of profiles and customized panels. The document also introduces detailed recommendations around physician notices, acknowledgments for customized profiles, and internal monitoring of utilization growth, including the now-famous suggestion to investigate test volume increases exceeding 10 percent year over year

In short, the 1997 guidance is granular and operational. It reads as OIG’s attempt to translate a new technological reality into concrete compliance behaviors for laboratories that were still learning how automation intersected with Medicare rules.

---

What Is Distinctive About the 1998 Guidance

The 1998 guidance does not reverse the 1997 conclusions; instead, it refines and institutionalizes them. By 1998, OIG had issued compliance program guidance for hospitals and home health agencies, and it sought to align laboratory guidance with a broader, cross-industry compliance framework. The 1998 document is therefore more explicitly structured around the seven elements of an effective compliance program, drawing on the Federal Sentencing Guidelines and corporate integrity agreement experience.

Substantively, the 1998 guidance updates the discussion to reflect policy changes, including the elimination of certain multichannel chemistry billing codes from CPT, and it places greater emphasis on standing orders, reflex testing, and confirmation testing. OIG is more explicit about discouraging standing orders as a default practice and stresses that even where standing orders exist, laboratories must periodically revalidate their medical necessity

 The tone is less about teaching laboratories how automation works and more about embedding laboratory billing into a mature compliance culture.

---

Why This Still Matters

Read together, the 1997 and 1998 OIG guidances show an agency grappling—deliberately and incrementally—with the consequences of automation. They do not prohibit efficient testing platforms. They do not require laboratories to cripple their workflows. Instead, they insist on a separation between what technology can do and what Medicare will pay for. That distinction remains foundational today, whether the platform in question is a chemistry analyzer, a sequencing pipeline, or a digital diagnostic workflow.

Understanding this history helps explain why modern debates about molecular panels and reflex testing feel familiar to regulators. The questions are old. Only the machines have changed.

Myriad PathomIQ Coding

 Myriad and PathomIQ;

An Entry Point to Potentially Disastrous AMA CPT Changes

 

The evolution of the Myriad–PATHOMIQ relationship offers a compact case study in how cutting-edge computational pathology is colliding with a reimbursement and coding system that was never designed to recognize information extraction as a medical service. At its scientific core, PATHOMIQ represents a disciplined and unusually mature attempt to answer a legitimate clinical question: whether routinely generated histopathology images—H&E slides that already exist in every prostate cancer case—contain latent, reproducible signals that can predict recurrence, metastasis, or treatment response. From a research standpoint, the answer increasingly appears to be yes. From a business standpoint, however, the answer has become far more ambiguous, not because the science failed, but because the payment architecture has no place to put it.

PATHOMIQ’s early development reflects a rare alignment of translational oncology, pathology, molecular biology, and enterprise AI. The company did not emerge from a single academic lab nor from a purely technical AI incubator; it was constructed at the intersection of both. Its founders include senior academic pathologists and oncologists with access to long-follow-up tissue cohorts and clinically meaningful endpoints, paired with a CEO whose background signals commercial intent from the outset. That combination shaped PATHOMIQ into what might be called a “model-as-asset” company: not a workflow vendor, not a CLIA service lab, but a generator of validated prognostic models intended to be licensed into larger diagnostic ecosystems. Scientifically, this strategy made sense. Commercially, it assumed that once clinical validity was established, a payment pathway would eventually follow. That assumption is now proving increasingly fragile.

The Myriad licensing deal in early 2025 initially appeared to confirm the viability of this approach. Myriad’s first descriptions of the collaboration framed PATHOMIQ_PRAD as a distinct, AI-driven prostate cancer test—fast, image-based, independent, and in some cohorts outperforming traditional markers. The language suggested optionality: PATHOMIQ could stand beside genomic tests like Prolaris, offering orthogonal insight derived from morphology rather than RNA expression. This framing implicitly tested a bold proposition: that algorithmic interpretation of existing clinical data might itself be treated as a billable diagnostic service. In early 2025, Myriad sounded as though it was prepared to see whether the market—and perhaps the CPT system—might accept that proposition.

By late 2025, that tone had changed markedly. Myriad’s public communications no longer described PATHOMIQ as a standalone test but as an embedded analytic layer inside Prolaris. AI was reframed as an “amplifier,” not an answer; as an enhancement, not a replacement; as supportive of clinician judgment rather than an independent decision tool. This rhetorical pivot was not subtle to those who understand reimbursement mechanics. It reflects a recognition that the standalone “upload DICOM, download report” business model—however elegant scientifically—is structurally homeless in the current CPT ecosystem. What began as a potential new diagnostic modality was quietly absorbed into an already covered one.

This shift exposes the deeper problem: computational pathology sits at the intersection of two Venn diagrams that no longer overlap. On one side is science and product development. PATHOMIQ and similar companies are extracting clinically relevant information from data that medicine already collects, at marginal cost and with increasing rigor. They are not inventing new biomarkers in the classical sense; they are revealing structure in existing data. On the other side is the CPT framework, which remains stubbornly biomarker-centric. PLA codes reward the creation of new analytes. Category I codes reward established professional services. MAAA codes reward multianalyte laboratory tests. None of these categories recognize information itself as the billable output when no new wet-lab signal is produced.

The result is a slow-motion train wreck. Computational pathology tests that do not create new molecules are systematically excluded from PLA eligibility. They are incompatible with Category I because they are proprietary, versioned, and algorithmic, and because CPT resists paying twice for “interpretation” of the same specimen. MAAA is explicitly unavailable because images are not analytes. Category III offers, at best, a tracking code with little prospect of payment. CMAA—if it emerges as currently envisioned—risks becoming a registry for AI tools rather than a reimbursement pathway, a kind of Appendix S for algorithms: visible, cataloged, and unpaid.

What makes this particularly reckless from a policy standpoint is that the CPT system is not merely failing to keep up with innovation; it is actively shaping commercial behavior in ways that suppress it. Myriad’s absorption of PATHOMIQ into Prolaris is rational and probably unavoidable, but it is also telling. The AI does not disappear because it lacks value; it disappears because it cannot survive on its own economically. The cost of innovation is shifted from revenue line to internal expense. The signal is preserved, but the incentive to build similar standalone tools is weakened. Smaller companies without a Myriad-scale partner are left with no viable path at all.

The danger here is not that CPT is conservative—that has always been true—but that it is enforcing an outdated ontology of diagnostics at precisely the moment medicine is becoming information-centric. Computational pathology challenges the assumption that value arises only when a new biomolecule is measured. It argues instead that value can arise when existing data are interpreted more deeply. By rejecting that premise and diverting these services into non-payable categories, the AMA risks creating a perverse outcome: encouraging molecular redundancy while discouraging informational efficiency.

Seen in this light, the Myriad–PATHOMIQ story is less about one partnership than about a systemic mismatch. The science is converging on morphology-derived insight as a legitimate predictor of outcome. The business models are converging on licensing and integration as survival strategies. Meanwhile, CPT is converging on exclusion—pushing these technologies out of PLA, away from Category I, and into administrative limbo. If this trajectory continues, the U.S. risks building a diagnostics ecosystem that pays generously for new molecules while quietly strangling tools that extract more value from what we already have. That is not just a coding problem; it is a policy failure with long-term consequences for how innovation in pathology is financed, scaled, and ultimately delivered to patients.

 

 

##

Below is a single, continuous essay-style report, written independently and analytically, designed to give you language, framing, and “color” you can mine for a white paper that is openly critical of AMA CPT policy direction. I am deliberately not footnoting or citing documents; this is an interpretive synthesis, not a compliance memo.

 

ESSAY PART TWO: WHERE IS AMA TAKING US?

The current AMA CPT posture toward artificial intelligence is not malicious, but it is conceptually misaligned with where large parts of diagnostic medicine are actually headed. The principles now being articulated—particularly the resistance to autonomous AI services, the insistence on physician mediation, and the fear of RVU dilution—make internal sense in the world of adjunctive AI in radiology, but they break down badly when applied to computational pathology and genomics, where AI is not advisory, not suggestive, and not subordinate to human interpretation. In those domains, AI is the test.

Radiology AI, which appears to be the tacit reference model for many CPT deliberations, is structurally different. Most radiology AI tools flag regions of interest, highlight subtle findings, prioritize worklists, or suggest second looks. They operate as overlays on a physician’s interpretive act. The radiologist remains the locus of judgment, liability, and narrative authority. From a CPT perspective, it is therefore natural—almost inevitable—to treat these tools as adjunctive, non-billable, or bundled services. They enhance physician work; they do not replace it. In that context, concerns about double payment, RVU inflation, and erosion of physician control are at least internally coherent.

Computational pathology and genomics do not fit that model at all. In these fields, the “result” is not a suggestion to a physician; it is a probabilistic or categorical determination derived from data at a scale no human can meaningfully process. When a genomic assay analyzes hundreds of millions or billions of DNA fragments and reports a pathogenic mutation linked to an FDA-approved therapy, there is no meaningful point at which a pathologist’s opinion is injected into the result. The interpretive act has already occurred—algorithmically, deterministically, and reproducibly—before the report is generated. The physician’s role is clinical integration, not analytical interpretation. Treating this process as if it were analogous to a radiologist glancing at a highlighted corner of a mammogram fundamentally misunderstands the epistemology of the test.

Computational pathology occupies the same conceptual space. When an AI model analyzes a digitized H&E slide and produces a validated risk score for recurrence or metastasis, the output is not a “second opinion” on what a pathologist already saw. It is a new informational product derived from high-dimensional pattern recognition across thousands or millions of features. No human pathologist could reproduce it, even in principle. The insistence that such outputs must be framed as physician-mediated services, or else relegated to non-payable registries, reflects an outdated belief that diagnostic legitimacy flows only through human visual interpretation. That belief is already obsolete in genomics, and it is rapidly becoming obsolete in digital pathology.

The AMA’s resistance is further complicated by a category error about money. Much of the anxiety around AI within CPT appears rooted in the physician fee schedule: fears that new AI services will siphon dollars from E/M and procedural services, accelerate RVU proliferation, and force further conversion-factor deflation. Those are real concerns inside the physician payment system. But they are largely irrelevant to computational pathology and genomics, which live on the Clinical Laboratory Fee Schedule, not the RVU-based PFS. These tests do not compete with physician work RVUs; they compete with other diagnostics. Blocking them does nothing to protect physician income, but it does distort innovation in laboratory medicine.

In effect, CPT is using governance principles designed to prevent AI from unbundling physician interpretation in radiology and applying them wholesale to domains where interpretation has already been disintermediated by data scale. The result is not thoughtful containment but structural exclusion. By rejecting these services from PLA eligibility, declaring them incompatible with Category I, and shunting them toward Category III, Appendix-like registries, or future CMAA constructs that lack payment authority, CPT is signaling that algorithmic information extraction from existing clinical material is not a legitimate diagnostic act. That position is increasingly untenable.

The Myriad–PATHOMIQ evolution illustrates the consequences. Initially, PATHOMIQ was framed as a standalone AI diagnostic test, reflecting confidence in its scientific validity. Within months, it was repositioned as an embedded, invisible enhancement inside an already covered genomic assay. This was not a scientific retreat; it was a reimbursement survival maneuver. The AI did not fail. The coding system did. Smaller companies without a Myriad-scale sponsor will not be able to make this pivot, and many will simply disappear or remain trapped in perpetual pilot status.

The deeper risk is that CPT policy is unintentionally privileging molecular redundancy over informational efficiency. If payment is available only when a new analyte is measured, innovators will be driven to create ever more complex wet-lab assays—even when equivalent or superior information could be extracted computationally from data we already generate. That is not cost containment; it is technological distortion. It rewards chemistry over computation, not because chemistry is better, but because the coding ontology cannot see computation as a test.

In short, AMA CPT is not trying to cause a disaster, but it is governing the future with the wrong mental model. AI in radiology is not the template for AI in pathology or genomics. Advisory tools are not autonomous diagnostics. RVU anxiety is not relevant to CLFS innovation. Until CPT explicitly recognizes that some AI systems are the diagnostic act—rather than aids to it—the collision between policy and science will intensify. And when that collision becomes visible to payers, industry, and Congress, it will not be interpreted as prudent stewardship. It will be seen as an institutional failure to adapt to how medicine now produces knowledge.

# #

Myriad February to October 2025

# #

ARe there any interesting differences between Myriad's description of its pATHomIQ collaboration initially (February, march 2025) and recently (October-November 2025)?

Yes — there are meaningful and revealing shifts between Myriad’s initial description (Feb–Mar 2025) of the PATHOMIQ collaboration and the later framing (Oct–Nov 2025). They are subtle in wording but significant in strategic intent, especially when viewed through a reimbursement, coding, and commercialization lens.

Below is a structured comparison, grounded directly in the documents you uploaded.

________________________________________

1. February–March 2025: PATHOMIQ as a standalone AI test

In the initial press release (Feb 24–25, 2025) and contemporaneous coverage (e.g., Urology Times), Myriad presents PATHOMIQ_PRAD very much as its own clinical test, albeit one licensed and commercialized by Myriad.

Key characteristics of the early framing:

a) Explicit “AI-driven clinical test” language

The press release repeatedly states Myriad intends to “commercially launch its first AI-driven prostate cancer clinical test later this year.” The implication is a distinct test offering, parallel to Prolaris, not merely an internal analytic component 

2025 Myriad 0225 PathomIQ PRAD …

.

b) Emphasis on speed, independence, and outperforming markers

PATHOMIQ_PRAD is described as:

• Analyzing digitized H&E whole-slide images

• Returning results within 1 day

• Outperforming Gleason, TNM, and genomic tools in some cohorts

This language positions PATHOMIQ_PRAD as a competitive prognostic modality, not just a complementary add-on 

2025 Urol Times 0301 Myriad and…

.

c) Strong hints at future platform expansion

The early materials stress that although the current model is post-prostatectomy, the foundational model could apply broadly across solid tumors. That reads like a platform commercialization vision, not merely a prostate-specific enhancement 

2025 Myriad 0225 PathomIQ PRAD …

.

Interpretation:

At launch, Myriad appears to be testing the waters for whether PATHOMIQ could stand as a billable, brand-recognizable AI test—even if bundled operationally with Myriad infrastructure.

________________________________________

2. October–November 2025: PATHOMIQ as a component inside Prolaris

By October 2025, especially in Myriad’s own blog post (“Enhancing Prostate Cancer Genomics with AI-Powered Morphometric Analysis”), the framing shifts decisively.

a) PATHOMIQ is no longer framed as a standalone test

Nowhere in the October 2025 blog does Myriad describe PATHOMIQ_PRAD as a separate, orderable test. Instead, the language is:

“Soon, the Prolaris Test will integrate AI from PATHOMIQ…” 

2025 Myriad 1023 Progress with …

That is a major rhetorical downgrade from “launching our first AI-driven test.”

b) AI is repositioned as an “amplifier,” not an answer

Repeated phrases include:

• “AI plus genomics”

• “Not a replacement; it’s an upgrade”

• “A precision amplifier”

This is a clear de-risking move. PATHOMIQ is now framed as:

• Supporting clinician judgment

• Enhancing an already-covered genomic assay

• Avoiding claims of independence or displacement 

2025 Myriad 1023 Progress with …

.

c) Independence is explicitly walked back

The October post even critiques tools that market themselves as “independent decision aids”, arguing instead for consolidated, integrated reports that already incorporate CAPRA, clinicopathology, and genomics.

That passage reads, frankly, like a quiet repudiation of how PATHOMIQ_PRAD was initially positioned earlier in 2025 

2025 Myriad 1023 Progress with …

.

Interpretation:

By fall 2025, Myriad appears to have concluded that selling PATHOMIQ as a standalone AI test is commercially and policy-risky, and that its highest value is as an embedded analytic layer inside Prolaris.

________________________________________

3. What changed — and why it matters

From a reimbursement perspective

The shift aligns almost perfectly with the CPT realities you outlined earlier:

• A standalone “upload DICOM → download report” test has no clean CPT home

• PLA is unavailable

• Cat I is structurally hostile

• Cat III is weak and unattractive

• CMAA is uncertain and likely non-paying

Embedding PATHOMIQ inside Prolaris allows Myriad to:

• Avoid new CPT battles

• Preserve existing coverage

• Treat AI costs as internal COGS, not billable services

From a risk-management perspective

The early 2025 language was ambitious and externally facing (investors, urologists, media).

The late 2025 language is defensive, integrative, and payer-aware.

This is classic Myriad behavior:

innovate aggressively, then stabilize within reimbursement reality.

________________________________________

4. Bottom line

Yes — the evolution is real and important.

• Early 2025: PATHOMIQ_PRAD is framed as a new AI clinical test that could stand alongside or even outperform existing tools.

• Late 2025: PATHOMIQ becomes an embedded morphometric layer inside Prolaris, explicitly positioned as complementary, supportive, and non-disruptive.

That shift strongly suggests Myriad learned — quickly — that AI-only morphology products face structural barriers in CPT and payer systems, and that the winning move is absorption, not exposure.

If you want, next we could:

• Map this transition onto specific CPT committee anxieties, or

• Compare this arc to other AI pathology companies that failed to make the same pivot.

Links - FDA recognizes CLINVAR; Issue is Sequencing Tests (even FDA) with off-site software

 AMA PLA codes are now not allowed if you have distributed inputs to testing (though this is allowed by CAP).

FDA allows use of outside databases for FDA approved sequence tests.

https://clinicalgenome.org/docs/fda-recognizes-clingen-assertions-in-clinvar-frequently-asked-questions/

https://www.fda.gov/media/119313/download

####

A few years ago, FDA specifically allowed outside approved databases to be used in conjunction with FDA approved sequencing tests. (I don't remember if they were tests at 23andMe or if they were BRCAC tests getting FdA cleared by Myriad, or some other context.) Please find citations specific to Fda allowing outside databases as part of sequencing test approvals (or clearances.)

https://chatgpt.com/share/6941a0d2-47a0-8005-96ea-a5c772b1c263

####

Here are FDA-primary citations showing FDA explicitly allowing “outside” (third-party) variant databases to be used to support FDA clearance/approval of sequencing / genetic tests—especially for clinical validity evidence in premarket submissions:

1. FDA final guidance (core policy hook): public variant databases can be used as valid scientific evidence in FDA review of NGS/genetic tests

• FDA guidance page (“Use of Public Human Genetic Variant Databases…”) states that publicly accessible variant databases can serve as sources of valid scientific evidence to support clinical validity in FDA’s regulatory review of NGS-based tests and other genetic/genomic tests. (U.S. Food and Drug Administration)

• In the guidance PDF, FDA explains that if databases follow the recommendations, their “data and assertions… would generally constitute valid scientific evidence… to support clinical validity” for FDA approval, and it describes the voluntary FDA recognition process for such databases. (U.S. Food and Drug Administration)

2. FDA “database recognition” program page (explicit permission language for sponsors): sponsors can use FDA-recognized database assertions in submissions

• FDA says recognition means FDA believes the database’s “data and assertions… can be considered valid scientific evidence,” and: “This program will allow sponsors to use the assertions within FDA-recognized databases to support the clinical validity of their tests.” (U.S. Food and Drug Administration)

• Same page also lists recognized databases (examples), including ClinGen (recognized 12/4/2018) and MSK OncoKB (recognized 10/7/2021). (U.S. Food and Drug Administration)

3. A concrete FDA recognition decision (ClinGen) stating FDA intends its assertions to be usable in future premarket submissions

• FDA’s ClinGen recognition decision summary concludes that ClinGen’s procedures provide reasonable assurance that its assertions “constitute valid scientific evidence” and “can be used to support clinical validity of genetic tests in future premarket submissions.” (U.S. Food and Drug Administration)

4. FDA press announcement reinforcing the policy (how test developers may rely on FDA-recognized public databases)

• FDA press announcement (Dec 4, 2018) explains FDA’s approach “clarifying how test developers may rely on clinical evidence provided in FDA-recognized public databases to support clinical claims for their tests” and help assure clinical validity. (U.S. Food and Drug Administration)

5. Federal Register notice for the guidance (useful for docketing / formal citation)

• Federal Register notice for the guidance describes publicly accessible databases as valid scientific evidence supporting clinical validity in FDA review of genetic/genomic tests. (Federal Register)

If you tell me which context you’re writing for (e.g., BRCA / hereditary risk like 23andMe, versus tumor/CDx somatic variants like OncoKB), I can point you to the most on-point recognized database + decision summary language for that specific use case.

Freenome Deck read by Chat GPT 5

 Below is a concise, graduate-professional summary of the upcoming Freenome SPAC transaction based on the company’s current investor deck.

---

Freenome: Impending SPAC Transaction (~$330M) – Professional Summary

According to a document from 12/05/2025, Freenome anticipates entering into a business combination with Perceptive Capital Solutions Corp (PCSC; Nasdaq: PCSC), a special purpose acquisition company (SPAC) sponsored by Perceptive Advisors. The transaction is intended to take Freenome public and provide substantial new capital to fund clinical development and commercialization of its multiomic, blood-based cancer screening platform.

---

Transaction Structure & Size

The deal includes multiple capital components:

• Cash held in the SPAC trust: ~$90M

• Target PIPE financing: ~$250M

  • PIPE commitments by Perceptive & RA Capital: $75M

• Assumed total “IPO-like” proceeds: ~$330M (trust + PIPE)

• Convertible note from Roche: $75M

When combined with existing balance-sheet cash and recent Exact Sciences upfront payment, the combined company projects approximately $493M in pro forma cash at close, assuming no shareholder redemptions.

---

Valuation & Timing

• Post-transaction equity value: ~$1.09B
  (assuming no redemptions)

• Target closing: H1 2026

The SPAC route is framed as a more efficient path to the public markets, with a curated shareholder base and lower execution risk versus a conventional IPO.

---

Use of Proceeds

Proceeds are intended to fund:

1. Clinical development (CRC and multi-cancer programs)

2. Ongoing and new studies

3. Commercial launch preparation

4. Expansion of commercial operations

Additionally, Freenome highlights potential $700M in downstream milestone payments from Exact Sciences, which are not included in its immediate projections.

---

Strategic Rationale

Key goals of going public via SPAC:

• Institutionalize capital access for multi-year clinical and commercial scale-up

• Achieve value inflection milestones before requiring additional fundraising

• Leverage strong sponsorship (Perceptive, RA Capital, Roche, Exact Sciences)

The deck emphasizes that Perceptive Advisors has successfully executed four high-profile life-science de-SPACs and brings sectoral expertise.

---

Broad Strategic Context

Freenome is positioning itself as a platform-based oncology diagnostics company using:

• Multiomics data extraction

• Machine learning modeling

• High-automation lab processes

Addressing:

• Colorectal cancer screening first, as the entry market

• Followed by personalized multi-cancer early detection, across 10+ indications

Total targeted TAM: $50B

---

Implications for the Market

This transaction amounts to a major capital event, roughly equivalent in scale and structure to a traditional mid-cap IPO, at a time when:

• Public markets remain challenging for diagnostics

• Traditional biotech IPOs have slowed

• Cancer screening economics place high value on scale, sensitivity, and data moat

The SPAC pathway enables:

• Accelerated public status

• Access to deep-pocketed healthcare investors

• Strategic partnerships with Exact Sciences and Roche

This creates a potentially durable funding runway to differentiate in an increasingly competitive early-detection landscape (Guardant, Grail, Delfi, etc.).

---

Bottom Line

Freenome is preparing an IPO-like public market entry via SPAC with ~$330M in capital raised (trust + PIPE), supporting a pro forma valuation of ~$1.1B, and targeting H1 2026 closing. Proceeds are intended to fund late-stage clinical development and initial commercialization of its blood-based early cancer detection portfolio, starting with colorectal cancer.

---

If you want, I can produce:

• A one-page investor brief

• A policy / reimbursement analysis of their go-to-market strategy

• A comparative landscape vs Guardant, Grail, Exact, Delfi, or Thrive

• A board-level opportunity / risk matrix

Just say so.

##

Comparative

##

Here’s a comparative landscape you can drop straight into a grad-/professional-level memo.

---

1. Freenome in context

Positioning. Freenome is building a multiomic, AI/ML-based platform for early cancer detection, with CRC screening as the lead indication and a roadmap to personalized multi-cancer early detection (MCED) across 10+ indications.

Capitalization. Via its planned de-SPAC with Perceptive Capital Solutions (PCSC), Freenome targets roughly $330M of IPO-like gross proceeds (SPAC trust + PIPE), contributing to ~$493M pro forma cash on the balance sheet at close, assuming no redemptions and including a Roche convertible plus an upfront from Exact Sciences.

Clinical performance (v1 – PREEMPT CRC, JAMA). In PREEMPT CRC, a 48,995-subject prospective study, the first-generation Freenome blood test showed:

• CRC sensitivity: 79.2% overall (Stage I 57.1%, Stage II 100%, Stage III 82.4%, Stage IV 100%)

• Specificity: 91.5% vs non-advanced neoplasia

• Advanced adenoma sensitivity: 12.5% (29% for AAs with high-grade dysplasia) (Freenome)

Early buy-side commentary suggests v2 performance is “competitive” with Guardant Shield v2, but detailed peer-reviewed v2 data are not yet public; you probably want to treat v1 JAMA data as the anchor for now.

---

2. CRC screening: stool vs blood

Exact Sciences – Cologuard / Cologuard Plus & blood

• Cologuard / Cologuard Plus (stool DNA): In the most recent Cologuard Plus data set, CRC sensitivity is ~95% with ~91% specificity in average-risk adults. (Cologuard) Advanced adenoma sensitivity (not in the snippet you pulled) is typically in the ~40% range in older Imperiale data (still the benchmark for precancer detection).

• Channel power: Exact already owns the primary care + GI screening channel, with a large, well-trained salesforce and guideline-embedded products.

• Blood-based CRC: In 2025, Exact licensed Freenome’s blood-based CRC technology, paying $75M upfront with up to $700M in milestones plus royalties, after concluding that Freenome’s assay outperformed Exact’s internal blood test program. (Investors) This is a strong external validation of the Freenome platform and simultaneously an implicit admission that Exact did not have the best-in-class blood test on its own.

Implication vs Freenome:
For CRC blood tests, Freenome is not directly competing with Exact in the U.S. so much as supplying the engine: Exact will likely brand and distribute the test through its existing primary-care network (and protect Cologuard for those willing/able to do stool testing). Freenome keeps centralized multi-cancer and ex-US options, while CRC ordered alone is licensed to Exact.

So in CRC:

• Exact = channel + brand + guidelines

• Freenome = underlying blood-test IP and broader MCED platform

---

Guardant Health – Shield CRC

• Shield v1 / NEJM ECLIPSE data: Earlier data showed 91% CRC sensitivity, 92% specificity, and ~20% advanced adenoma sensitivity. (Guardant Health)

• Updated Shield v2: More recent updates show ~84% CRC sensitivity, 90% specificity, and 13% advanced adenoma sensitivity, viewed as only a modest improvement and somewhat below bulls’ expectations. (Guardant Health Investors)

• Portfolio breadth: Guardant also has large businesses in tumor profiling, therapy selection, and MRD, so Shield is only one revenue pillar.

Implication vs Freenome:
On headline CRC metrics, Freenome v1 (79% / 91.5%) is in the same neighborhood as Shield v2 (84% / 90%). Freenome’s advanced adenoma detection is similarly low-teens, so neither company has cracked the “true precancer” problem yet. (Freenome)

The real competitive difference is business model + channel:

• Guardant is an oncology-centric lab pushing into population screening from the specialist side.

• Freenome, via Exact, is effectively plugging into primary care + payers through an incumbent CRC screening leader.

That makes Freenome more “embedded” in the existing CRC screening infrastructure, rather than standing up its own new, national screening brand from scratch.

---

3. MCED: Freenome vs Galleri and fragmentomics players

Grail – Galleri (MCED)

• Scope: Galleri is an MCED test that can detect 50+ cancer types and predict cancer signal origin with >94% accuracy when a signal is present. (GRAIL)

• Performance: Overall sensitivity ~51.5% across stages and tumor types; specificity is high (~99% in many datasets). (Galleri® Test)

• New data (PATHFINDER 2): Recent results suggest Galleri detected cancer ~7x more often than standard screenings in adults ≥50, especially in cancers without established screening (pancreas, ovary, etc.). FDA filing is expected around 2026, with approval potentially in 2027, but coverage (especially Medicare) remains limited today. (Barron's)

Implication vs Freenome:
Galleri is positioned as an “add-on” MCED to existing single-cancer screenings, sold mostly as self-pay or limited institutional pilots. Freenome, by contrast:

• Leads with CRC, a single cancer with well-defined guidelines and a clear reimbursement frame.

• Uses CRC as the anchor population to layer in personalized MCED tests over time.

So the strategic contrast is:

• Grail: “Top-down” multi-cancer screen first, fighting for guideline + reimbursement from a new category.

• Freenome: “Bottom-up” strategy; start with a familiar CRC benefit category, then expand MCED off the same infrastructure and data lake.

Delfi Diagnostics and other fragmentomics players

• Technology: DELFI uses cfDNA fragmentation profiles plus machine learning to distinguish cancer vs non-cancer and is being explored in multi-cancer and organ-specific tests. Early data show strong discrimination capabilities in a multi-cancer setting using low-coverage WGS. (DELFI)

• Clinical focus: Recent work emphasizes treatment monitoring and response prediction rather than front-line average-risk population screening. (nki.nl)

Implication vs Freenome:
Delfi’s angle is “ultra-cheap fragmentomics” and broad oncology use cases (screening + MRD + monitoring). Freenome’s angle is multiomics (frags + methylation + mutations + proteins + clinical data) tuned specifically for screening in average-risk populations, with a strong focus on CRC first.

---

4. Strategic differentiation for Freenome

For a strategy slide, you can frame Freenome’s position as:

1. Platform scope vs single-modality rivals

   • Freenome: Multiomics + AI (multi-layer signal) aimed at screening-grade performance and rapid “versioning” of assays.

   • Guardant / Delfi: Primarily ctDNA / fragmentomics; strong, but narrower, molecular signal.

   • Grail: Methylation-heavy; strong MCED but less focused on a single, guideline-anchored indication.

2. Channel strategy

   • Freenome + Exact: CRC blood test distributed through an existing primary care/GI screening network with payer relationships and USPSTF-style benefit framing. (Investors)

   • Guardant: Building a new screening channel from an oncology base.

   • Grail: Cash-pay / pilot model, seeking future FDA + coverage for MCED as a new category.

3. Capital & runway

   • Freenome’s de-SPAC + PIPE + Roche + Exact milestone potential yields a multi-hundred-million-dollar runway to get through pivotal work and initial commercial scale-up.

   • Guardant, Exact, and Grail already burn significant public-company cash; Freenome is effectively joining that cohort with a fresh balance sheet and a more tightly focused product portfolio.

4. Regulatory & reimbursement path

   • CRC blood tests can be evaluated by payers in a well-understood CRC screening benefit bucket (Cologuard, FIT, colonoscopy comparators).

   • Galleri-style MCED requires new frameworks for evidence, cost-effectiveness, and care pathways, which is intellectually exciting but commercially slower.

Freenome’s explicit story is: get CRC blood test over the line (with Exact as the megaphone), build a data moat across millions of average-risk individuals, and then extend MCED from a position of reimbursement and operational strength rather than as a speculative category creator.

---

5. Risks / watch-points

For completeness in a professional brief:

• Performance margin vs Shield & future entrants is modest; if any competitor shows substantially higher early-stage and/or advanced adenoma sensitivity, positioning could shift quickly.

• Dependence on Exact for U.S. CRC commercialization is a double-edged sword: it gives channel, but also means Freenome is partially “upstream” IP rather than the visible brand in its lead indication.

• MCED economics and coverage remain unsettled; Freenome’s MCED upside rests on payers eventually accepting multi-indication blood screening as cost-effective and operationally manageable.

---

If you tell me which audience you’re writing for (e.g., Freenome board, Exact commercial, buy-side investor, or CMS/MAC audience), I can recut this into a 1–2 page memo with the right emphases and sound bites.

##

Strategic policy

##

Below is a policy + reimbursement–focused analysis of Freenome’s U.S. go-to-market strategy, written for a graduate-professional audience (biotech strategy, health policy, diagnostics reimbursement).

---

1. Strategic Context: Why Freenome’s Go-to-Market Looks the Way It Does

Freenome’s lead indication—colorectal cancer (CRC) screening—is among the most policy-constrained and policy-driven diagnostic markets in the U.S. Because CRC screening is a USPSTF Grade A preventive service, it is:

• Covered without patient cost-sharing under commercial plans (ACA)

• Covered by Medicare without coinsurance (under separate statutory authority)

• Embedded in clinical guidelines

• Supported by ongoing public-health messaging and provider workflow

Therefore, Freenome’s commercialization strategy aims to attach a blood-based test to an already-defined and subsidized benefit category, rather than inventing a new one.

This differs sharply from MCED-first models (Grail) where companies must justify:

• A new benefit category

• A new evidence framework

• A new cost-effectiveness model

• A new workflow

• A new billing policy and prior auth regime

That path is 5–10 years slower.

Lesson: Freenome is not just selecting CRC for biology; they are selecting CRC because it is regulatory and reimbursement tractable.

---

2. The Policy Advantage of a “CRC-First Blood Test”

A blood-based CRC test is conceptually substitutable for:

• FIT (fecal immunochemical test)

• Stool DNA (Cologuard)

• Colonoscopy (for average-risk screening)

Thus, payers can evaluate Freenome’s CRC test inside existing coverage categories, not as novel technology requiring national coverage reconsideration.

That means Freenome can seek coverage via:

• Local coverage determinations (LCDs) (MolDx, NGS MAC)

• Commercial payer policies

• Possibly USPSTF adoption in the medium-term (crucial for ACA prevention)

Reimbursement is likely to follow a pattern similar to Cologuard, with an eventual dedicated CPT/PLA code and valuation anchored to precedent.

---

3. The Exact Sciences Partnership: Channel + Policy Signaling

Freenome’s deal with Exact Sciences is as much about policy infrastructure as it is about commercial infrastructure.

Key elements from the deck:
CRC ordered alone is licensed to Exact for U.S. commercialization.

Why that matters:

1. Exact already established the category norms for a high-priced CRC screening test (~$500–$600)

2. Exact built payer contracts, prior auth carve-outs, and benefit routing

3. Exact trained PCPs on “screening by mail”

4. Exact built a nationwide claims-processing and appeals infrastructure

5. Exact proved that payers tolerate higher unit cost per screen if:

   • sensitivity is high,

   • compliance rises,

   • downstream cost avoidance is demonstrable.

So, by outsourcing U.S. CRC commercialization to Exact, Freenome avoids 10 years of frictional policy and payer education, while achieving rapid payer alignment and PCP adoption.

This is a major competitive differentiator relative to Guardant’s Shield.

---

4. Economics of CRC Screening: Who Will Pay?

Payers view CRC screening as a population intervention.

The economic logic is:

• CRC costs ~$100K–$200K when discovered late

• Lower-stage disease is dramatically cheaper

• Early detection saves lives and money—but only if participation is high

Fit, stool DNA, and colonoscopy all suffer from adherence gaps, especially in lower-SES groups.

Thus, payers view blood-based CRC tests as a compliance lever.

If:

• CRC sensitivity ≥ FIT (~74%)

• Specificity ≥ FIT (~90%)

• Adherence increases from ~65% to 85–90%

Then a CRC blood test can be cost-effective even at high price points ($400–$800).

Therefore, Freenome’s clinical claims must be framed around:

• Stage I–II detection

• Adherence increase among never-screened

• Population-level cost avoidance

Not just test accuracy.

---

5. MCED: High Strategic Value, High Policy Friction

Freenome’s broader value proposition is multi-cancer early detection (MCED).

However:

• MCED does not fit into an existing preventive benefit category

• It is not covered by USPSTF

• It is not a statutory benefit for Medicare

• It is not professionally mandated

• It is not recognized in payer medical policy frameworks

MCED requires new evidence domains, including:

• Stage shift modeling

• Cost-effectiveness across multiple indications

• Downstream capacity modeling (how many false positives can the system absorb?)

• Ethical and distributional impact

This is decade-scale policy work.

Freenome’s insight is to avoid leading with MCED and instead bootstrap MCED onto CRC-screened populations, where:

• Baseline risk is known

• Infrastructure exists

• Payers already reimburse

• Data can accumulate at population scale

Thus, Freenome substitutes a high-risk policy strategy (MCED-first) with a low-risk, CRC-first policy strategy that still generates MCED data exhaust.

---

6. Reimbursement Mechanisms: Path to Payment

For CRC, the near-term code path is:

1. Proprietary Laboratory Analyses (PLA) code

2. MolDx LCD with defined coverage criteria

3. Gapfill initial pricing

4. Crosswalk to Cologuard or FIT

5. Commercial parity via existing contracts

Exact Sciences has already proven the playbook:

• Launch at ~$500–$600

• Negotiate coverage

• Achieve “screening parity”

• Avoid high prior auth friction

Freenome is likely to pursue premium pricing justified by stage I–II sensitivity, not by advanced adenoma detection.

This is subtle but important: payers value stage I detection more than precancer detection because the economic certainty is higher.

---

7. Guardant’s Shield: Different Policy Risk Profile

Shield is attempting to create a market via:

• Specialty oncology channel

• Self-pay and opportunistic coverage

• A brand-new primary care sales motion

That requires:

• New contracts

• New coverage criteria

• New provider education

Shield competes directly in CRC, but is doing so with high friction, and without leveraging the benefit category expertise that Exact has sustained for a decade.

Result: commercial uptake has been slow, despite strong performance.

---

8. Regulatory Horizons: USPSTF and CMS

Freenome’s CRC positioning matters because:

• USPSTF will update CRC screening recommendations in the late 2020s

• If blood-based screening is incorporated as an option, it becomes:

  • Mandatory coverage under commercial plans

  • Zero-cost-sharing

  • Automatically legitimized

  • Massively scaled through primary care

This is the single largest value unlock in the space.

Exact will prosecute that policy mission.

Grail and Guardant may also benefit, but Freenome would have:

• Earlier clinical data

• Earlier population-level adoption

• More payer experience

---

9. Risks

Technical:

• Marginal differences in sensitivity may affect payer willingness to reimburse at premium levels

Economic:

• Uptake hinges on provider ordering behavior, not just patient preference

Policy:

• USPSTF deliberation cycles are slow and unpredictable

Strategic:

• Dependence on Exact puts Freenome’s economics partly outside its own control

---

10. Summary: What Freenome is Actually Doing

Freenome’s strategy is not “take a great diagnostic and sell it.”

It is a policy arbitrage strategy:

1. Enter a highly subsidized, guideline-embedded benefit category (CRC)

2. Avoid the MCED policy quagmire

3. Leverage Exact’s payer contracting and PCP workflow infrastructure

4. Use CRC screens to accumulate multiomic data at population scale

5. Transition to personalized MCED when policy and evidence environments mature

The advantage is speed to revenue, speed to coverage, and lower commercialization risk, with long-term upside in multi-cancer detection.

---

Bottom Line

Freenome’s go-to-market is a policy-optimized sequencing strategy:

• Lead with CRC because it is reimbursable, incentivized, guideline-protected, and operationally tractable

• Partner with Exact to accelerate payer access and reduce friction

• Build MCED off the back of reimbursed CRC volume

• Avoid the “new category penalty” that Grail is suffering

This is a highly rational reimbursement-first commercialization strategy, not a technology-first strategy.

---

If you want, I can draft:

• A 1-page policy brief

• A payer messaging document

• A Medicare LCD argument framework

• A USPSTF nomination strategy

• A payer economic model (Excel or python)

Just tell me which you need.

Chat GPT UBIOME

 You’re thinking of uBiome, Inc.

They were a San Francisco microbiome startup (poop-testing kits by mail) founded in 2012 and shut down in 2019 after an FBI raid and insurance-billing investigations. Wikipedia+1

A few anchor details to match your memory:

• Location & era: San Francisco–based, peak hype mid-2010s, collapsed around 2019—so right in your 5–10 year window. Wikipedia

• Business model: Sequencing fecal samples and other microbiome sites (products like SmartGut) and billing insurers thousands of dollars per test for “clinical” versions. CBS News+1

• Billing scandal: Federal prosecutors allege they sought ~$300M in claims and were paid $35M+ for tests that weren’t medically necessary or properly validated, often repeatedly billed and pushed through via aggressive tactics with physicians. Office of Inspector General+2CBS News+2

• Aftermath: FBI raid (April 2019), bankruptcy later that year, then 2021 DOJ/SEC charges against co-founders Jessica Richman and Zachary Apte for securities and health-care fraud; they’re now considered fugitives. Wikipedia+2Department of Justice+2

So: uBiome is the poop-analysis lab you’re remembering.

You said:

The story peetered out with the top executives in hiding or vanished? Fled overseas? Dead trail?

ChatGPT said:

Here’s what is known (or at least commonly reported) today about the fate of the top executives from uBiome — and yes, the trail has largely gone cold.

✅ What we do know

• Their names are Jessica Richman and Zachary Apte. They were co-founders/CEOs of uBiome, and in 2021 were indicted on a 47-count federal indictment (securities fraud, healthcare fraud, money laundering, etc.) for allegedly defrauding investors and insurers. Department of Justice+2SEC+2

• The financial and fraud allegations are serious: prosecutors say uBiome submitted over $300 million in insurance claims (of which insurers paid $35 M+), and misled investors about the business’s sustainability and growth. UCSF Synapse+2Department of Justice+2

• The company declared bankruptcy in 2019, and has been defunct since then. Wikipedia+1

🚨 What happened to them — “fugitives,” abroad, trail largely cold

• According to public reporting and government filings, Richman and Apte relocated to Germany in mid-2020, after uBiome’s offices were raided and while investigations had begun. Business of Business+2Wikipedia+2

• U.S. authorities have described them as “fugitives” evading prosecution, and there are outstanding warrants for their arrest. Wall Street Journal+2UCSF Synapse+2

• Because Apte has German citizenship (and Richman is his spouse), U.S. prosecutors believe extradition may be difficult or impossible. UCSF Synapse+1

• As of the last publicly available reporting, their whereabouts are not definitively known; reports suggest they may be living somewhere in Berlin or elsewhere in Germany — but efforts by journalists to locate them reportedly failed. UCSF Synapse+1

🧩 Why the trail went cold — and remains cold

• They fled the U.S. before charges were unsealed — timing likely chosen to thwart legal action. Business of Business+1

• The complexity of international extradition and their German citizenship complicate U.S. attempts to bring them to trial. UCSF Synapse+1

• There appear to have been only limited updates afterwards: while there are still civil lawsuits (e.g. insurance-related D&O suits) tied to the collapse of uBiome and claims against the former executives, their criminal prosecution seems stalled. Insurance Business+1

• Media coverage on their whereabouts has dwindled — there’s little recent public information on their current status or location.

✅ Conclusion: Yes — they “vanished,” in the sense of leaving the U.S. and remaining fugitives abroad

So in summary: the senior leaders of uBiome — Richman and Apte — fled the U.S., are officially fugitives, and have lived abroad (reportedly Germany) since around 2020. As of the last public reports, their exact whereabouts are uncertain, and no public record shows they’ve returned or been extradited.

If you like — I can check the most recent public court filings or media reporting (2024–2025) to see if there’s any update on them (arrests, death, extradition efforts, etc.).
Do you want me to fetch that now?