Friday, April 11, 2025

Journal Watch: How to Achieve NYState Approval for NGS

Galbo et al. have published, "A Comprehensive Guide to Achieving New York State Clinical Laboratory Evaluation Program Approval for Next-Generation Sequencing Assays," in J Molec Dx, March 28, 2025.  Even better, it's open-access.

Many labs have to get NYState approval, either because they're based in NY State, or have patients who originate in NYState.   What's more, understanding this template for NYState approval for NGS tests will probably give you a leg-up with Medicare MolDx tech assessment as well (a review system that has no comparable publication.)

Find it here:

https://www.jmdjournal.org/article/S1525-1578(25)00067-4/fulltext

17 pages.


AI CORNER

Here’s a detailed summary of the new Galbo et al. 2025 Journal of Molecular Diagnostics paper for your genomic policy blog readers:

Galbo et al., 2025: A Practical Roadmap for NY State CLEP Approval of NGS Assays

Title: A Comprehensive Guide to Achieving New York State Clinical Laboratory Evaluation Program Approval for Next-Generation Sequencing Assays
Authors: Galbo, Klees, Burgher, Miles, Morrison, and Glenn
Journal: Journal of Molecular Diagnostics, April 2025
Link: https://doi.org/10.1016/j.jmoldx.2025.02.009

Why This Paper Matters

Given a prominent role in FDA's plan to regulate LDTs, New York State's CLEP program offers a longstanding and rigorous model for oversight. 

However, detailed peer-reviewed documentation of what CLEP actually requires—especially for complex NGS oncology panels—has been limited. This paper addresses that gap.

What’s in the Paper

The authors walk readers through step-by-step CLEP approval using their own in-house validated assay—RPPH (Rapid Pan-Heme)—as a case study. RPPH is a DNA/RNA-based NGS assay targeting >400 genes relevant to hematologic malignancies.

Key features of the paper include:

  • Structure of CLEP Approval: CLEP validation is broken down into six major phases:

    1. SOP documentation

    2. Quality control (QC) metrics

    3. Run-level control requirements

    4. Analytical validation for accuracy

    5. Precision/reproducibility studies

    6. Clinical reporting

  • Detailed Protocols: The paper provides meticulous documentation of wet lab methods for DNA and RNA workflows (e.g., extraction, library prep, sequencing on Illumina NextSeq, QC thresholds).

  • QC Criteria and Controls: It defines exact metrics for pass/fail thresholds (e.g., >90% coverage at 200×, SNV/indel detection ≥80% in positive controls, contamination cutoffs in NTCs).

  • Performance Studies:

    • Batch size impact: The RPPH panel shows high concordance (≥98%) for SNVs, indels, and fusions across batch sizes from 1 to 21 samples.

    • Sensitivity studies: Variant detection was reliable down to VAF ~5%, but sensitivity dropped sharply below that—particularly for indels.

    • Orthogonal validation: Over 200 SNVs and 200 indels were confirmed using Sanger sequencing, achieving ~98% concordance.

  • Fusion Detection: RNA-based fusion detection showed robust performance, with 100% detection of known fusions in positive controls and low false positives in NTCs.

Who Should Download This

  • Lab directors navigating CLEP submissions

  • Regulatory consultants preparing for increased LDT scrutiny

  • Molecular pathologists seeking a CLEP-aligned SOP template

  • Assay developers designing new heme panels or preparing orthogonal validation datasets

Bottom Line

This paper isn’t just a report of a validated assay—it’s a roadmap for CLEP approval. Think of it as both a how-to manual and a regulatory benchmark. For labs seeking New York approval—or preparing for a future FDA-aligned world—this is one of the most practically useful publications in recent years.

Let me know if you’d like a one-slide version of this summary or a visual comparing CLEP to FDA expectations.

Thursday, April 10, 2025

Changing Gender Words in the CMS Program Manuals

Gender words being updated by CMS, as the new burocracy works through its numerous online manuals and publications.

For example, I was comparing the current verson of Publication 8, Program Integrity, Chapter 10, "Medicare Enrollment" to its newest update.  See:  (Revision 12796, 08-15-24) versus a newly revised version released as Revision 13154, 4-4-2025).

The older vision 12796 was still online this morning here.  (It will be replaced; so a cloud copy of 12796 is here.)   The newer April 2025 version 13154 is online here.

The main edit style appears to be to search all "he/she" referenences, and change them to non-gendered terms like "technician," "iindividiual," or "physician."   The new version is "he she free."

OLD "HE/SHE"


NEW: "INDIVIDUAL"
###

CMS's interest might also be drawn to the glaucoma screening benefit due to its racial content.  

Glaucoma screening was created by BIPA 2000 and is codified at SSA 1861(s)(2)(U).   The statute states,  screening for glaucoma (as defined in subsection (uu)) for individuals determined to be at high risk for glaucoma, individuals with a family history of glaucoma and individuals with diabetes;...(uu) The term “screening for glaucoma” means a dilated eye examination with an intraocular pressure measurement, and a direct ophthalmoscopy or a slit–lamp biomicroscopic examination for the early detection of glaucoma which is furnished by or under the direct supervision of an optometrist or ophthalmologist who is legally authorized to furnish such services under State law (or the State regulatory mechanism provided by State law) of the State in which the services are furnished, as would otherwise be covered if furnished by a physician or as an incident to a physician’s professional service, if the individual involved has not had such an examination in the preceding year.

While the statute 1861(s) does not mention racial groups, the regulation written by CMS staff in 2001 and 2005 at 42 CFR 410.23 does:

§ 410.23 Screening for glaucoma: Conditions for and limitations on coverage.
(a) Definitions: As used in this section, the following definitions apply:  (1) Direct supervision in the office setting means the optometrist or the ophthalmologist must be present in the office suite and be immediately available to furnish assistance and direction throughout the performance of the procedure. It does not mean the physician must be present in the room when the procedure is performed.

(2) Eligible beneficiary means individuals in the following high risk categories:
  • (i) Individual with diabetes mellitus.
  • (ii) Individual with a family history of glaucoma.
  • (iii) African-Americans age 50 and over.
  • (iv) Hispanic-Americans age 65 and over.
See also the same CMS race-specific information quoted at a public-facing page here.  

The rulemaking for the CFR dates to November 1, 2001 (66 FR 55328, p. 55272-5) and to November 21, 2005 (70 FR 70330; adding "Hispanic," p20270-72).






Tuesday, April 8, 2025

Quick Triangulations: (1) The Cost/Benefit of Prevention, (2) Insourcing-Outsourcing Genomics,

Connecting the dots between some Linked In articles and journal publications in the last several days.

PREVENTION - Does it save money?

The general answer is probably no, and the general better-question is "is prevention money well spent?"

At Linked In, Peter Neumann raises this topic here.   His point is, we should evaluate health case services on health-value created per cost, not only on whether absolute dollars are saved.   

He directs readers to a new article in JAMA Forum, by Baicker and Chandra, "Can Prevention Save Money?"  Here.  They argue that Cost/QALY and similar approaches are better than asking "does it save money?"

I made a comment that we got here in part because of too many years of glib assertions (and not by economists) that "prevention saves so much money."

On the same themes, see an April 7 Op Ed in the Washington Post by Ward & Goldman about Medicare's mistake in not covering GLP-1 drugs.   The article argues they are cost-reducing and some readers might imply cost-saving ("wide access would have extraordinary benefits to society...benefits would pour through the economy."  But many editorial factors are included like future generic pricing.


GENOMICS - The Insourcing / Outsourcing Question

A few weeks ago, Robert Boorstein wrote an article at Linked In about the perpetual debate about insourcing and outsourcing genomics - here.  His point, insourcing investments still need to be made prudently.   

In-House MRD?

I was reminded of Boorstein's points when I saw a new article on Linked IN from Decibio's Megan Nacar. It features Decibiol's data for the growth and diversity of in-house minimal residual disease testing (MRD).   See their 3-page open access PDF here.  This expansion will only be encouraged (unleashed) by the demise of the FDA LDT regulation.

(I'm not sure exactly how this works reimbursement-wise, as there are no general CPT codes nor general reimbursement policies for MRD, and MolDx seems to cover MRD only from large labs (e.g. Nataera.))

Genomic TAT?

But pair these citations with a new article (?abstract) by Wang et al. in JNCCN on biomarker turnaround time in US patients with NSCLC - here.   Using Flatiron records, they find that in a sample of 34000 patients,  NGS TAT ran to 3 weeks by 2023.   "Use of NGS increased tunaround time" and "TAT has stagnated and remains suboptimal."  

(Re TAT and insourcing, see also Dowdell 2024.)


Monday, April 7, 2025

Brief Blog; Chat GPT Beats Google

 An example from my workdesk this morning where Chat GPT beats Google.

CMS has a statute - buried somewhere - that it must finalize notice & comment proposals within three years, or they expire.   

I asked Google, and it gave me no help.

I asked Chat GPT, and it answered instantly.

###

Here's Google, click to enlarge.    cms must finalize proposed regulations within 3 years statute

Google

###

Here's Chat GPT:

There is a clause in the Medicare statute (Social Security Act) requiring policy proposals to be finalized within 3 years.   Can you tell me where that is?

#

Yes — the clause you're referring to is Section 1871(a)(3)(B) of the Social Security Act, which sets a 3-year deadline for the finalization of certain Medicare regulations.

Here’s the relevant language:

Section 1871(a)(3)(B) of the Social Security Act [42 U.S.C. § 1395hh(a)(3)(B)]:
If the Secretary publishes a proposed rule (including any proposed rule that the Secretary is required to publish under paragraph (2)) and does not issue a final rule within 3 years after the date of the publication of the proposed rule, such proposed rule shall be deemed withdrawn unless the Secretary publishes a notice of continuation explaining why the rule has not been finalized and the timeline for finalization.

Key Points:

  • Applies to Medicare regulations published through notice-and-comment rulemaking.

  • If a final rule is not published within 3 years of the proposed rule’s publication, the proposed rule is withdrawn by law.

  • The Secretary may issue a notice of continuation to keep it alive, but must explain the delay and provide a timeline.

This clause was added in the Medicare Modernization Act of 2003 (MMA) to prevent indefinite delays in finalizing policies.

Let me know if you want the full citation or legislative history — happy to dig deeper.

Sunday, April 6, 2025

Two News Items: (1) FDA PDUFA in Jeopardy?? (2) Tariffs versus Fixed Payment Prices

Two items from the national news this week.

PDUFA, MDUFA - AT RISK?

In a Linked In article, accompanied by an 8-page PDF from AGENCY-IQ, the consultancy argues that PDFUA and MDUFA dollars - which fund half the FDA - could be at risk.   "Exploding" clauses in the statutes require that FDA hit certain spending and performance targets must be met by FDA, or else, all the monies go back to industry.  

For details see here:

https://www.linkedin.com/posts/ccmiles_the-future-of-fdas-user-fee-programs-ugcPost-7313907487147970560-hC-N/ 

TARIFF PRICE HIKES VS FIXED MEDICAL PAYMENTS

As reported in Forbes and elsewhere, large tariffs, if left in place, could substantially raise the cost of medical equipment and supplies (from pacemakers to insulin pumps).  But hospitals and physicians are generally paid at fixed fee schedules by Medicare and under other contracts.   At least in the case of physicians, those fee schedules already substantially lag inflation (as emphasized by AMA and others).   This means that tariff fees are "a rock hitting a hard place" in terms of payments.  

Forbes here:

https://www.forbes.com/sites/amyfeldman/2025/04/04/trumps-tariffs-could-raise-the-price-of-pacemakers-and-insulin-pumps/


Saturday, April 5, 2025

Where Is Digital Pathology Going? Articles Debate.

The buzz on digital pathology includes "good news, bad news" in the path month.

Digital Path - Good News

At Linked In, see Katie Maloney's summary and graphics for recent funding events in digital pathology - over a few months, five companies raise well over $100M.  (See new-news, for April,  Proscia raises $50M.)

https://www.linkedin.com/posts/katie-maloney-442639148_digital-pathology-funding-update-the-activity-7308502645005000705-Lz2z/

Digital Path - Not-so-good News

But a blog by Abhishajke Mahajan at "Owl Posting" summarizes the "bear" or negative view that might might not add up yet.

https://www.owlposting.com/p/what-happened-to-pathology-ai-companies? 

To which see comments at Linked In by Thago Carvalho, W Kemp Watson.

https://www.linkedin.com/posts/thiago-carvalho-93464125a_what-happened-to-pathology-ai-companies-activity-7314203940357648384-UHWC/ 

Third View - CAP TODAY

For a third view, see a February 2025 roundtable discussion at CAP TODAY which I think could be summarized as, "digital pathology is almost here."

###

Separately, see a public-facing article today at Washington Post about the robust growth of AI-Radiology.



Medicare Advantage Final Rule: Drops Chapter with Problematic LCD Language

Last fall, CMS proposed its usual, elaborate Part C/Part D rulemaking in November.  The final has just come out (April 4,2025).  A problematic section about Medicare Advantage was dropped.

See 90 FR 15792, April 15, 2025 (130pp).  The proposal was 240pp, but many sections were dropped from further comment.  The proposal's Table 1 had 17 topics. The final's Table 1 has 8 topics.  The proposal use "equity" about 50 times; the final about 8, mostly to refer to the topic being dropped.


  • The highest-publicity part was a proposal to cover Wegovy-type obesity drugs under Part D.
    • Adminstration has dropped this propoal, period.
    • It was always a little squirrely, since statute for Part D blocks coverage of weight loss drugs, so you had to argue the new-generation drugs were for "treating obesity" not "weight loss."
  • The Problematic LCD Language
    • Medicare Advantage plans are required to cover all regular Part B services (LCD or NCD), but barriers may intervene.
    • CMS has done several rounds of recent policy-making to reduce tardy or absent compliance.
    • In November 2024, CMS proposed that Medicare Advantage plans need only follow the clear language of LCDs, and SHALL NOT USE billing articles or other resources.
    • This was a hang-up, because many LCDs state general coverage themes, but it's impossible to know which services (eg codes) are covered or not covered without the billing article.
    • This is even a bigger deal with MolDx, which may explicitly guide readers to its DEX database for specific coverage (NOT billing articles, NOT the original LCD.)
    • CMS simply eliminated this chapter, including public comment, from its final rule.
CMS also dropped several parts of the November proposal that referred to equity, social determinants of health, or language access. CMS dropped a section about "guardails" about using AI in denials or prior auth.   The proposed rule had 17 topics (proposed, Table 1); the final maybe will have half or less topics.  

Generally, when CMS disagreed with a proposal, it dropped it from the final rule rather than debate it.

The early, or typescript, version of the rule was released April 4, the final Federal Register version will appear April 15.
___
Some long sections of the November 2024 proposed rule were simply dropped from the April 4 final rule.   However, CMS has the option to return to them within 3 years of the original publication (see SSA 1873(a)(3)(B).)     If CMS does not finalize  the November 2024 proposals by November 2027 they are considered withdrawn by default under SSA 1873.

Wednesday, April 2, 2025

One More Note About the FDA LDT "Vacatur" Ruling (cf WSJ today)

Court tosses out FDA LDT rule.  If the government appeals, will it also ask the court to "delay" the effect of the "vacatur" of the rule, until appeals are heard?  

First, the government is unlikely to appeal, and if it does, it's unlikely to ask the result of the decision be stayed-during-appeal.   However, Let's look down the rabbit hole, becausae it's also true that  national rulings by local judges is a hot-button topic in 2025.

###

As we've all heard by now, on March 31, 2025, a Texas federal judge ruled that the FDA LDT regulation was outside the legal scope of the FDA.   After his 51-page decision, he added that the LDT regulation was VACATED (nationwide.)  Rather than ruling against a particular FDA decision or approval or denial, he's ruling against the regulation in itself.

While that might be the end of it, there's a LOT of question in the Trump administration about any local judge who issues any nationwide ban or ruling, against a policy held by the administration.

There's an article about this in today's WSJ. Scroll down to the subtitle, "Defunding the Judiciary."

https://www.wsj.com/opinion/trumps-election-muddle-ad46e69f

See below for some limited direct quotes from WSJ.

In the next 60 days, (A) the DOJ can decide whether to file a notice of appeal (merely one sentence).  But don't forget, (B) the DOJ can also make motions to have the regulation stay in place while court motions proceed.  (If granted, the FDA reg would remain active.)  For example, various parts of  the ACA have lost in court (including the whole act; including its preventative benefits) yet remained in effect during their appeals.   A judge tossed out FDA clerance of mifepristone, but higher courts kept the drug available, despite the loss, during years of appeals.  See the case history in this appeals court decision.  Local judge issues "stay & injunction" both, page 8, and a higher court "stayed" the "vacatur" while the case proceeded, page 9.

See the cited HOUSE letter from the chair of its Judiciary committee -  here.   The letter and proposed legislation - Rogue Rulings - are about "injunctions" not "vacatur," but it shows the issue of national impact of local judges is a hot potato.

"A flood of judge-issued national injunctions against Trump policies continue to inspire a counterflood of Republican proposals to rein in judges. That includes a brand new suggestion from House Judiciary Chair Jim Jordan: Cut off federal dollars.

"In a Monday letter to House Appropriations Chair Tom Cole, Jordan urges the committee to use “the power of the purse” to “enhance judicial restraint and reaffirm democratic principles.” Specifically, he suggests appropriations language “prohibiting the use of taxpayer dollars and federal resources to issue or enforce these overbroad injunctions beyond the specific parties in front of an issuing court,” backed by a more specific bar on any funds that would be used to “compel compliance, impose fines, or conduct contempt proceedings related to such injunctions.”

"The Jordan proposal comes amid a broader GOP push for legislation to curb “judicial policymaking.” The House Rules Committee voted on Tuesday to advance Rep. Darrell Issa’s “No Rogue Rulings Act”—which would limit district court judges’ ability to issue universal injunctions—while both Sens. Chuck Grassley and Josh Hawley have introduced Senate versions of the same." 

[For WSJ links see original]
[Kimberley Strassel, April 2]

###

###

AI CORNER CHAT GPT4o

###

Let's emphasize, the most likely situation is the government does NOTHING.   But let's suppose - go down the rabbit hole - that the government DOES file a notice of appeal.   Is there any additional action the government could do, to keep the FDA LDT regulation active during the long appeals process.   (The government has gotten this before, such as when a judge issued a VACATUR in Braidwood, yet, the preventive policy remained active during the appeals.)

####

Yes, the government does have options to preserve the FDA’s LDT rule during the lengthy appeals process—even though the district court vacated the rule outright on March 31, 2025. Drawing from both Braidwood (2024) and general APA precedent, here’s a practical overview of what could happen next:

🔹 Default Path (if Government Does Nothing):

If DOJ files no motion to stay the vacatur or delay implementation, then:

  • The vacatur takes effect immediately.

  • The LDT rule is effectively nullified nationwide under the APA’s “set aside” clause (5 U.S.C. § 706(2)).

  • Laboratories would not be subject to the FDA’s new LDT framework, and the case proceeds to the Fifth Circuit on appeal.

  • The FDA would remain in regulatory limbo, as it cannot enforce a rule that has been vacated.

🔹 Option 1: DOJ Files Notice of Appeal Only (within 60 days)

A notice of appeal is a short, boilerplate filing—often one page—saying the government intends to appeal. However:

  • Filing a notice does not automatically stay the vacatur.

  • FDA still cannot enforce the LDT rule unless additional relief is sought.

🔹 Option 2: DOJ ALSO Moves to Stay the Vacatur Pending Appeal

This is the key parallel to Braidwood.

In Braidwood v. Becerra (2024), the district court both vacated parts of the preventive services mandate and issued an injunction. But the Fifth Circuit granted a partial stay of that vacatur during the appeal—so the mandate continued in effect despite the district court’s ruling against it.

In the LDT case, the government could:

  1. File a motion to stay the vacatur in the district court (Judge Jordan).

    • He is bound by 5th Circuit precedent, but could still stay his own ruling temporarily.

  2. If denied, they could file a motion for a stay pending appeal with the Fifth Circuit.

  3. If again denied, they could escalate to SCOTUS for an emergency stay.

Such motions typically argue that:

  • The government has a likelihood of success on appeal, or at least serious legal questions exist;

  • There would be irreparable harm to public health or regulatory interests;

  • A stay would serve the public interest.

In Braidwood, the stay was granted on these grounds—even after vacatur—so there’s a viable path to keep the FDA rule alive during appeal.

🔹 Practical Considerations

Even with vacatur:

  • The FDA rule was not yet in effect and was to be phased in over 4 years.

  • No lab is currently harmed by its absence, so urgency is limited.

  • This weighs against a stay [against keeping the regulation alive], unless the government can show that the industry will create chaos or fragment if FDA is sidelined during appeal.

But on the flip side:

  • Letting implementation proceed during appeal would cause enormous burdens on laboratories, only to be potentially reversed later. That would support keeping vacatur in place.

So, IF the government files a notification of appeal, which it probably won't, the court probably wouldn't change the policy status, which is current on "vacatur."

✅ Summary:

ScenarioActionFDA Rule Enforceable?
No actionDOJ appeals only❌ Rule vacated; not enforceable
Motion to Stay Filed (granted)District/Fifth Circuit/SCOTUS✅ Temporarily enforceable
Motion to Stay Filed (denied)Vacatur remains❌ Rule remains blocked
Rule implemented then reversed on appealHigh cost, potential chaos❌ Not preferred

So yes—DOJ can request a stay, and if the Fifth Circuit echoes its Braidwood logic, it may be granted, allowing FDA to enforce the rule during appeal. But politics, optics, and the upcoming election may weigh against pushing too hard.

 


Oncotype Dx Test Turns 21 Years Old

 As I was writing a deck on some bits of genomic history, I noticed the OncotypeDx test had its 20th anniversary in April 2020.   While this event got a bit of attention (check Google), I don't recall seeing any.

So, on April 11, 2025, Oncotype Dx has its 21st birthday.  Based on their iniitial April 2004 publication in NEJM.


https://www.nejm.org/doi/full/10.1056/NEJMoa1804710


Tuesday, April 1, 2025

National Academies: Release Booklet on "Clinical Guidelines & Adoption of Genomic Testing"

In October 2024, the National Academies held a workshop on the topic, "Exploring Clinical Guidelines for the Adoption of Genomic Testing."

In 2025, they have released a 15-page summary of the conference.

Find it here:

https://nap.nationalacademies.org/catalog/28572/exploring-clinical-guidelines-for-the-adoption-of-genomic-testing-proceedings

See my blog at the time, and the workshop home page, which has videos and powerpoints.



##


See a June 2024 National Academies report on racial-ethnic problems in health care.

https://www.nationalacademies.org/news/2024/06/little-progress-has-been-made-in-closing-racial-and-ethnic-gaps-in-u-s-health-care-federal-government-should-act-to-fix-structural-inequities



AMA Releases Newest PLA Codes (April 2025)

AMA releases new PLA codes quarterly and to no one's surprise, the list for the second quarter is now online.

https://www.ama-assn.org/system/files/cpt-pla-codes-long.pdf

AMA releases a cumulate PDF that includes codes not included in this year's AMA CPT book.   In practice, this means codes submitted on around June 15 or later (for the July quarter review, or later) appear in this PDF.  The new codes are those released April 1, 2025. Events released on April 1 will be effective for use on July 1.

  • AMA summarizes that it revised one code (0285U), deleted 6 codes, and added 23 codes.
  • There were editorial updates, such as manufacturer, for 5 additiional codes.
  • New codes begin at 0552U and run up to 0574U.

Among publicly held companies, see Guardant REVEAL (for MRD), 0569U; Biomerieux Biofire respiratory tract 0564U.  Haystack/Quest has 2 MRD codes (0560U, 0561U), for baseline and for monitoring. Illumina's FDA approved TruSight test, 517 genes, 0543U.  

Not new, from December 2024, I notice CareDx Allosure, not organ specific, 0540U.  

##

Code applications for the Spring quarter (Q2) were due about March 11 and AMA is currently reviewing them.  Will be posted for comment April 15, 2025.

Monday, March 31, 2025

The FDA LDT Rule Struck Down: What's Next?

 The FDA LDT rule was struck down - see prior blog.

And the Texas judge ruled that the LDT regulation was void - it is canceled nationwide, called vacatur.

What happens next?

One track is whether DOJ files an appeal.   They have 60 days, and that's for a "notice of appeal" - which keeps the case alive even if DOJ is still considering its options.

As discussed below, they're not likely to appeal.

But, going down the unlikely rabbit hole, if they DID appeal, which they probably won't, would they also ask for the "vacatur" to be stayed for the duration of the appeal?

See also a subscription article at 360Dx. 

##

The Texas judge ruled that the  FDA LDT regulation was not within the FDA's power to make, because,  lab procedures are not a "device."  

  • The judge puts most weight on the definitions of what the FDA can regulate as devices.  
  • The judge noted that LDT's were legal under CLIA law.
  • The judge also noted the history.  In the first 16 years from 1976, FDA never mentioned regulation LDTs, which is odd, if it was obvious to Congress and everyone else that the FDA had been given FDA regulatory authority and that LDTs were illegal devices subject to criminal penalties since 1976.)    

The Trump administration is unlikely to appeal, because while the FDA LDT regulation has some supporters, it had more opponents.  And if the FDA LDT regulation was moving forward, it would land a mountain of problems on the desk of the new Commissioner.   So the Administration will probably take the loss and hope few people notice.

Peeking Down the Rabbit Hole 

But, let's peek down the rabbit hole for alternativies.  

First, the Trump administration does not like to lose in court, and here, it lost in court.   (So the FDA LDT regulation would be repositioned as a bad 2024 Biden regulation, not as a good and important regulation as defended in oral hearings by the Trump DOJ in, well, February 2025.)  

Second - while a local judge's national injunction and a local judge's national"vacatur" are two different things - the administration and the Hill is currently very displeased with local judges making national rulings..  (See a second blog here.)  When a politician grandstands that local judges shouldn't be making national decisions, he rarely pauses to explain injunction vs vacatur.

Third - by not making a peep about this national ruling, the administration puts itself in a position of supporting some national rulings of local judges…while decrying others as "activist judges."

Scenario One

The Trump administratioin doesn't do anything at all.   (MOST LIKELY).

Scenario Two (5%)

The Trump admiinstration files a one-sentence "notification of appeal" within 60 days.  

Then it can figure out what to really do (like quietly withdraw the appeal later when no one is watching).  During the appeals, the regulation remains inactive, the status as of March 31.  Throwing in the towel becomes an obscure event 12 months from now, when the ACLA/AMP's win is old news that is taken for granted.

Scenario Three (0.01%)

If and only if the administration does file a notificatoin of appeal, it could also ask the effect of the district court decision be delayed.   Such things have happened.  A  single local judge in district court in the Braidwood case both issued an injunction against USPSTF preventive benefits, AND a vacatur (voiding the relevant law).   However, all those preventive benefits remained in place - in spite of his vacatur - because the government asked for a delay during appeals, and got it.   See second blog here.   Or Braidwood p 8-9.

Scenario Three is very unlikely - Phase 1,2,3 of the FDA LDT rule would keep happening, because the government asked for and won a "stay" during further proceedings.   But, down the rabbit hole, it's a hypothetical and you can find examples (vacatur on hold) as precedent (Braidwood).

What About Partial Implementation?

Sometimes you hear about partial implementation - e.g., a certain ruling only applies to parties in the case.  My understnading (as a policy expert but non attorney) is that, that isn't really in the cards here.  A vacatur ruling says that the regulation itself is illegal in some way.  By its nature, a vacatur is national in scope when it occurs at all.  (Though it can be stayed.)  (Yet much of this is not without some debate, Braidwood p.30 and its fn 94-98).





Judge Strikes Down FDA LDT Regulation!


On March 31, 2025, federal judge Sean Jordan sided with ACLA and AMP and struck down the FDA's plan to regulate all laboratory-developed tests nationwide.

The President of AMP writes,

  • Today, the U.S. District Court ruled in favor of the Association for Molecular Pathology in our lawsuit challenging the FDA’s final rule on laboratory-developed testing procedures (LDTs). 
  • Judge Sean D. Jordan’s decision vacates the FDA’s final rule, which sought to regulate LDTs as medical devices — an overreach that would have significantly increased costs, financially burdened laboratories, stifled innovation and, most critically, restricted patient access to essential tests.
  • This ruling reaffirms what we have long advocated: The FDA’s attempt to impose these regulations was unlawful. It also underscores the invaluable role of laboratory professionals in developing and delivering high-quality, innovative diagnostics that advance precision medicine.
The two page "judgment" is here:


The full 51-page opinion is here:

What next?

The judge delivered a resounding negative opinion from A to Z and also ruled that the regulation was "vacated" (canceled.)

  1. Will FDA appeal?  It's more White House and HHS and DOJ than "FDA."  DOJ (for FDA) would need to file an intention to appeal within 60 days.  They might file this even if they are considering their options.
  2. LDT Stakeholders?  Will message politicians and public that the case should be viewed as over (thus implying government ought not appeal.
  3. Watch this:  Will government file emergency motions to undo the cancellation of the regulation? So that, FDA enforcement will go forward at great expense at full speed, maybe for years, as if nothing happened - while court battles creep onward.  TBD.  
    1. See a second blog with discussion of these in's and out's - here.


In December, AI Predicted the Result

In December I fed the final briefs (government, plaintiffs) to Chat GPT 4o, and after reading them, it predicted the judge would rule against the FDA.  It even provided a model for the judge's ruling.  See my December 2024 blog here.   Going back to December, see the mockup ruling here.   See my summary (including AI) of the February 2025 oral hearing here.

Below, AI analyzes the case, projects the odds the government will appeal (versus fold its cards), and writes a strategic memo for labs.  Finally, at bottom, AI compares its December 2024 position, with the final position of the judge in March 2025, and finds its predictions had "remarkable accuracy."

###
AI CORNER
###

In December, I gave you final memoranda in the case of ACLA/AMP versus FDA, where laboratories argued that an FDA regulation about LDT regulation should be struck down.  After reading those memoranda, you argued that FDA would lose, and you even gave a mock-up judge's ruling in which FDA lost.

DISCUSS

Discuss the 51-page decision and 2-page ruling.  Your readers have been watching the case very closely.   You can write at the college or law school level.
###

The March 31, 2025 decision by Judge Sean D. Jordan of the U.S. District Court for the Eastern District of Texas is a watershed ruling in the battle over FDA’s authority to regulate Laboratory-Developed Tests (LDTs). In ACLA et al. v. FDA and AMP et al. v. FDA, the court struck down the FDA's 2024 Final Rule that sought to classify and regulate all LDTs as medical devices under the Federal Food, Drug, and Cosmetic Act (FDCA). This 51-page opinion—accompanied by a 2-page final judgment—delivers a forceful rebuke to FDA’s regulatory overreach and represents a resounding victory for the laboratory plaintiffs.

⚖️ Key Holdings:

  1. FDA's Final Rule is Vacated in Full
    The Court vacated and set aside the FDA's final rule in its entirety: Medical Devices; Laboratory Developed Tests, 89 Fed. Reg. 37,286 (May 6, 2024).

  2. FDA Lacks Statutory Authority under the FDCA
    The court held that LDTs are not “devices” under the FDCA and thus fall outside the FDA’s statutory jurisdiction. The ruling is grounded in the text, structure, and history of both the FDCA and the Clinical Laboratory Improvement Amendments (CLIA) of 1988, which Congress specifically enacted to govern laboratory testing.

  3. FDA’s Interpretation Was Not Merely Overbroad—It Was Legally Unsupportable
    The Court found that FDA was attempting to redefine intangible professional laboratory services as physical medical devices, which it described as a category error. The judge emphasized that terms like "instrument," "machine," and "in vitro reagent" in the FDCA unambiguously refer to tangible articles, not in-house testing services conducted by trained lab professionals.

  4. FDA Ignored Legislative Intent and Agency History
    The decision meticulously catalogs FDA’s historical abstention from regulating LDTs as devices, noting that for decades FDA exercised “enforcement discretion” but did not assert jurisdiction. That restraint was consistent with Congress’s clear intent that CMS—not FDA—should oversee laboratory services under CLIA.

  5. Recent FDA Rule Contradicted Past Agency and Congressional Actions
    The Court found persuasive evidence that Congress repeatedly declined to legislate FDA authority over LDTs, including bills like the VALID Act and VITAL Act. FDA’s attempt to impose sweeping new requirements without statutory change represented an administrative power grab.

  6. Enforcement Discretion Offers No Legal Shield
    Although FDA promised not to enforce its rule against many labs immediately, the Court held that this non-binding discretion did not cure the underlying illegality. Agencies cannot regulate beyond their statutory limits and then invoke prosecutorial discretion to downplay the impact.

🧪 Who Won and Why?

  • Plaintiffs:

    • American Clinical Laboratory Association (ACLA)

    • HealthTrackRX

    • Association for Molecular Pathology (AMP)

    • Dr. Michael Laposata

    These plaintiffs succeeded in arguing that LDTs are professional services, not commercial devices. The court emphasized that no article of personal property changes hands in an LDT service, and there is no manufactured product to regulate under the FDCA.

  • Defendants:

    • FDA

    • HHS

    • Robert F. Kennedy, Jr. (as HHS Secretary)

    • Dr. Sara Brenner (Acting FDA Commissioner)

    FDA's arguments were found unconvincing and contrary to both law and history.

🧵 Implications:

  • Legal Precedent:
    This case will likely become the seminal case on FDA’s limits under the FDCA, especially when it comes to regulating intangible services.

  • Regulatory Strategy:
    The court signaled that FDA must wait for clear congressional authorization before it can impose sweeping rules on LDTs. Agencies can no longer assume that enforcement discretion or policy shifts suffice.

  • CLIA Reaffirmed:
    This decision fortifies CMS’s exclusive authority over LDT oversight, ensuring that professional laboratories are regulated as healthcare providers, not device manufacturers.

Would you like a summarized 1-pager or a slide for stakeholder communication?


###'
WHAT CAN THE FDA DO NOW?

Given this devastating loss, is there much to do by way of appeal to the 5th circuit?   Does the government have many arrows in its quiver besides its prior arguments?  I have argued that while the new administration continued to support this case (for example, by showing up at an oral hearing shortly after inauguration day), the government might fold its cards at this point.  But I'm not certain.
###

Your instincts are sound, and your analysis touches the key tension. While the legal basis for appeal is narrow after such a comprehensive loss on statutory grounds, the government may still appeal for strategic or political reasons, particularly if it wants to preserve long-term regulatory authority over LDTs. Let’s break it down:

🔍 What Can FDA Do on Appeal?

1. Reframe the Statutory Interpretation
FDA could attempt a narrower statutory reading argument, claiming that the trial court overly formalized the distinction between devices and services, and that some LDTs involve tangible reagents or instruments developed in-house. But:

  • The district court thoroughly dismissed that idea (e.g., distinguishing LDTs from “test kits” and noting that no article of commerce changes hands).

  • FDA’s historic position was not consistent on this point, and that inconsistency undermines its deference argument.

2. Argue Congressional Silence Isn’t Prohibitive
FDA might argue that Congress’s failure to act (e.g., not passing VALID or VITAL) doesn't prove prohibition, and try to invoke a more functionalist statutory interpretation. But the Supreme Court’s recent Loper Bright decision cuts that off at the knees—Chevron deference is gone, and courts must now interpret statutes independently.

3. Try to Reframe the “Service vs. Device” Issue as a Mixed Question
FDA may argue that the case turns on a mixed question of law and fact, and therefore some factual deference is warranted. But Judge Jordan wrote a pure statutory interpretation opinion: no factual ambiguity, no APA “arbitrary and capricious” wiggle room. [He could have called FDA arbitrary and capricious, but, it would have thereby opened an appeal window.]

4. Lean Into the Major Questions Doctrine (In Reverse)
Unusually, FDA could try to argue that this isn’t a “major question”—just routine device regulation. That’s a hard sell given the court’s emphasis on multibillion-dollar impacts, decades of FDA restraint, and explicit congressional debate. The major questions framework works against FDA.

🎯 Strategic Considerations: Why Might FDA Appeal Anyway?

  1. Preserve Institutional Authority
    Even if they expect to lose again, the FDA may want to signal that it’s not giving up its turf without a fight. The jurisdictional line between FDA and CMS is still in flux, and this case could define it nationally.

  2. Avoid Circuit Splits
    By appealing, FDA could try to avoid future rulings in other circuits that further fracture the legal landscape. Or—less likely—it may gamble on reversing in the Supreme Court.

  3. Change of Administration in 2025
    If the current administration appeals and stays in office, it can continue pursuing the appeal. If there's a change in administration, an appeal could preserve the rule on life support until the FDA under new leadership potentially withdraws or modifies it, rather than losing outright in court.

  4. Buy Time and Keep Pressure on Labs
    Even a losing appeal could delay finality for a year or more, during which time labs may hesitate to launch high-risk tests or expand LDT services.

🃏 Will They Fold?

You noted that the Trump administration showed up for oral arguments after inauguration and continued backing the case. That's important—it wasn’t a passive handoff.

But now that:

  • Chevron is gone, and

  • The court vacated the rule in its entirety, and

  • CMS's CLIA role has been reaffirmed,

the case has lost most of its strategic high ground. Unless the DOJ is being directed to litigate this as a signal case for FDA authority across domains, folding is a rational option.

Still, FDA may file a notice of appeal to preserve the option, then decide whether to pursue or narrow the appeal after internal consultation—especially after April/May public reaction and political input.

🎬 Summary:

  • Legal outlook for appeal: very poor—this was a categorical statutory ruling, not a discretionary one.

  • Tactical options: limited and made worse by recent Supreme Court decisions.

  • Government behavior: may still appeal to delay, preserve options, or protect institutional authority—but could fold quietly midstream.

  • Your prediction (that they might walk away): increasingly likely, unless they're playing a long game on FDA power in diagnostics more generally.

Would you like a mock-up of what a DOJ statement withdrawing the appeal might look like—or alternatively, a concise explainer on the implications for labs in light of this ruling?

###

WILL THE GOVERNMENT FOLD ITS CARDS?  40%.  

CAN GOVERNMENT WIN?  10%

Given the appeal pathway is via the conservative 5th Circuit, which often agrees with its underlying district judges in this nature of case, what are the odds of the government appealing? (Use a percent). And, if the government appeals, what are the odds of winning at the Fifth Circuit? (Use a percent.)

###

Odds of appeal: 60%.   [This 60% includes, merely filing an intent to appeal, to buy time.]
Odds of a 5th Circuit win: 10%.  Timeline: 60 days.
_____

Based on the strength of the district court's statutory analysis, the conservative lean of the Fifth Circuit, and the Supreme Court’s recent dismantling of Chevron deference (Loper Bright), here is a reasoned estimate of the government’s likely behavior:

🎯 Odds the Government Appeals:

60%

  • In favor of appeal:

    • Institutional interest in defending FDA's jurisdictional reach.

    • Delay as a strategic tool—buying time, especially in light of pending elections and possibly shifting political control in 2025.

    • Preserving optionality: DOJ may file a Notice of Appeal (low cost) even if unsure about pursuing the full appeal.

  • Against appeal:

    • High likelihood of loss, especially in the Fifth Circuit.

    • Supreme Court precedent (Loper Bright) directly undermines FDA's basis.

    • No meaningful Chevron wiggle room, and weak fallback arguments.

    • A loss at the Fifth Circuit could worsen the precedent nationally.

Bottom line: The government may file a placeholder appeal to preserve options, even if it ultimately chooses to withdraw or not press it fully. Hence, ~60%.

⚖️ Odds the Government Wins on Appeal in the Fifth Circuit:

10%

  • The Fifth Circuit has:

    • Repeatedly curtailed agency overreach.

    • Explicitly cited the “major questions” doctrine to strike rules down.

    • Supported the logic used by Judge Jordan in other administrative law cases.

  • Judge Jordan’s ruling is:

    • Deeply rooted in the statutory text and structure.

    • Supported by historical context and decades of FDA/CMS practice.

    • Entirely unaffected by Chevron (even if it were still in place).

  • An FDA win would require:

    • Reversal on statutory grounds, despite clear textual limitations.

    • Acceptance of the idea that a professional service (not a product) is a regulated "device."

    • Fifth Circuit willingness to side with agency logic over structural separation of powers.

Bottom line: Almost no path to win in the 5th Circuit. A 10% estimate is generous and assumes an unexpected panel composition or unusual deference to agency history—neither of which is likely post-Loper Bright.

Let me know if you’d like visuals (charts, timelines) or a strategic memo version of this for broader distribution.

###
ADVICE TO LAB INDUSTRY

What can the litigants - ACLA, AMP, etc - do to strengthen the chance the government folds its hand?  in the form of a strategic memo, as you mention.
###

Certainly — here's a concise strategic memo tailored for ACLA, AMP, and allied stakeholders. It focuses on legal, political, and public messaging strategies to increase the likelihood the government opts not to pursue an appeal of the recent district court decision striking down the FDA’s LDT rule.

Strategic Memo: 

Increasing the Likelihood of Government Non-Appeal in ACLA et al. v. FDA

To: Leadership at ACLA, AMP, HealthTrackRX, and aligned stakeholders
From: Strategy Counsel
Date: March 31, 2025
Re: Action Plan to Encourage Government Non-Appeal of FDA LDT Rule Decision

Objective

To increase the probability that DOJ/FDA declines to appeal the March 31 ruling vacating FDA’s final LDT rule by applying legal, political, and public relations pressure in a coordinated and timely manner.

I. Legal Pressure Points

1. Highlight Futility of Appeal Under Current Law

  • Submit or coordinate letters from respected legal scholars (including administrative law and health law experts) explaining that:

    • The decision aligns with Loper Bright and other post-Chevron precedents.

    • The Fifth Circuit is unlikely to reverse on statutory grounds.

    • An appeal would risk enshrining unfavorable national precedent for FDA.

2. Quiet Amicus Campaign

  • Encourage amicus letters to DOJ or HHS General Counsel (not the court), outlining the strategic hazards of appealing a losing case with high visibility and a poor legal footing.

  • Focus on institutional legitimacy, not political confrontation.

II. Political and Interagency Pressure

3. Leverage CMS and Capitol Hill Allies

  • Engage CMS career and political leadership to reaffirm CLIA as the rightful regulatory home for LDT oversight.

  • Work with bipartisan congressional offices (especially from health committees or oversight) to:

    • Send oversight inquiries or letters to HHS urging restraint.

    • Remind the administration of congressional intent: Congress has repeatedly declined to give FDA this authority.

4. Coordinate a Senate “Soft-Landing” Narrative

  • Reach out to Senate HELP and House Energy & Commerce contacts to suggest that future LDT oversight reform should be legislative, not judicially or bureaucratically imposed.

  • Offer to support hearings or roundtables that pull FDA back toward a VALID/VITAL compromise without litigation.

III. Public Messaging and Reputational Framing

5. Shape the Narrative Around Patient Access and Innovation

  • Launch op-eds, white papers, and patient stories (especially from rare disease and oncology communities) emphasizing:

    • The district court ruling preserves patient access to cutting-edge diagnostics.

    • FDA’s rule would have created a multi-billion-dollar regulatory burden with no evidence of improved safety.

    • Congress already empowered CLIA to ensure lab quality.

6. Appeal to Fiscal Moderates

  • Use think tanks (e.g., AEI, Manhattan Institute, Brookings) to publish quick analyses showing:

    • FDA’s appeal would be an expensive regulatory escalation.

    • DOJ/FDA should not spend taxpayer money defending a regulation projected to cost $113B (FDA’s own estimate) with minimal benefit.

IV. Tactical Timing

  • Act before the 60-day appeal window expires (i.e., before May 30, 2025).

  • Target internal deliberation windows at DOJ Office of the Solicitor General and HHS General Counsel by mid-April.

  • Prepare for a “win by default” if DOJ files a notice of appeal but then quietly lets it lapse or withdraws.

Conclusion

While DOJ may reflexively file a notice of appeal, the odds of ultimate pursuit can be reduced by sustained, multi-pronged messaging focused on legal futility, political overreach, and practical cost. Lining up stakeholders from both industry and patient advocacy sectors will bolster the case for a graceful government exit and refocus oversight debates in Congress, where they belong.

Let me know if you'd like a version of this formatted as a Word/PDF briefing memo, or expanded sections on talking points, press strategy, or Hill outreach targets.


###

AI LOOKS BACK TO DECEMBER 2024

Compare your December 2024 prediction of the outcome, and your mockup ruling, with the ACTUAL ruling today.

###

Here is a comparison of the December 2024 AI "mock-up ruling" with the actual federal court decision issued on March 31, 2025 in ACLA et al. v. FDA. This side-by-side assessment focuses on key structural, legal, and rhetorical elements.

🔍 OVERALL STRUCTURE & STYLE

Feature AI Mock-Up (Dec 2024) Actual Ruling (Mar 2025)
Length ~5 pages 51-page opinion + 2-page judgment
Tone Concise and explanatory Formal, detailed, and judicial
Remedy Summary judgment for plaintiffs, rule vacated and remanded Same: Rule vacated in full, summary judgment for plaintiffs, remanded to HHS
Framing High-level summary of arguments and conclusions Detailed statutory history, legislative record, agency behavior, and administrative law doctrine

⚖️ CORE LEGAL HOLDINGS

Legal Point AI Mock-Up Actual Ruling
FDA lacks statutory authority to regulate LDTs as devices YES — devices are tangible articles, not professional services YES — extensive statutory and historical analysis showing LDTs are not devices under FDCA
Major Questions Doctrine applies YES — regulating LDTs is a major economic/political question requiring clear Congressional authorization IMPLIED but not decided — Court notes the doctrine but rules solely on statutory grounds (p. 23)
APA violation: arbitrary and capricious YES — FDA failed to account for reliance interests and overstated benefits NOT REACHED — the court vacated the rule solely on jurisdictional/statutory grounds
Remedy: Vacatur and remand YES YES (Final Rule vacated in its entirety, remanded to HHS)

🧠 ANALYTICAL DEPTH

Category AI Mock-Up Actual Ruling
Statutory Analysis (FDCA vs. CLIA) Explained but brief Very deep dive into legislative history from 1938 to 2024, contrasting FDCA (devices) and CLIA (services)
FDA Historical Behavior Noted: 30 years of non-enforcement Extensive documentation of shifting FDA positions, Congressional inaction, and reliance interests (1992–2024)
CLIA Oversight Role Described as the rightful regulator Affirmed and detailed across multiple pages; CLIA framed as the sole proper framework for LDT oversight
Enforcement Discretion Criticized as unpredictable Dismissed as legally inadequate — discretionary policies cannot compensate for lack of jurisdiction

🗣️ RHETORICAL STYLE

Style Feature Mock-Up Actual Ruling
Judicial Voice Modeled tone, but simplified Authentic and authoritative, citing 5th Circuit and Supreme Court precedents
Examples/Imagery General analogies (e.g., contrast with kits) Concrete examples (e.g., 79,000 existing tests, CMS role, training requirements, AMA comments)
Conclusion "FDA lacks authority, acted arbitrarily, rule vacated" "FDA lacks authority under FDCA, vacatur required under APA and 5th Circuit precedent"

🧾 FINAL ORDERS: IDENTICAL

Both the mock-up and actual ruling conclude with:

  • Summary judgment for ACLA, AMP, and other plaintiffs

  • Denial of FDA's cross-motion

  • Vacatur of the FDA's May 2024 Final Rule

  • Remand to HHS for further proceedings

🎯 Bottom Line

The December mock ruling anticipated the outcome with remarkable accuracy, both legally and structurally. The actual ruling, however, surpasses it in:

  • Depth of legislative and administrative law reasoning

  • Documentation of FDA’s shifting policy stance

  • Use of APA and FDCA statutory structure to decide the case without invoking the major questions doctrine directly

Would you like a PDF one-pager comparing the two, or a version of this formatted as a press release or advisory memo?

3 New Views of AI in Healthcare (Consolidated View)

 In the last couple days I ran across 3 views of AI in healthcare, from current trade journals.

  • A California company is letting AI run medical visits, from intake to diagnosis.  Endpoints.
  • Crisis in healthcare administration; Can AI be the solution?  Healthcare Dive.
  • In clinical pathology, generative AI has many uses.  CAP Today.

As an experiment, I wondered how Chat GPT 4o could consolidate these three news items.

###
AI CORNER
###

Here is a consolidated article that synthesizes the three AI developments—office visits, hospital administration, and clinical pathology—into a single cohesive narrative, tailored to inform healthcare industry readers and connect the dots:

AI Is Quietly Reshaping the Foundations of Healthcare: 

Three Case Studies from the Clinic, the Hospital, and the Lab


Artificial intelligence is no longer an emergent technology poised on the horizon of healthcare—it is threading itself into the fabric of how we deliver, manage, and interpret care. From front-line medical visits to back-office hospital workflows and the cerebral realm of clinical pathology, AI is not just accelerating efficiency—it’s redefining the roles of clinicians and reengineering the architecture of health systems. Three recent case studies underscore this transformation.

AI in the Exam Room: Akido’s ScopeAI and the Future of Scalable Clinical Visits

At Akido Labs in California, AI is being trialed not merely as an assistant, but as a co-pilot during entire patient visits. Their ScopeAI platform, built on Meta’s LLaMA large language model, empowers medical assistants to gather data, synthesize differential diagnoses, and propose treatment plans—all before a physician enters the room. The goal is clear: expand physician reach, reduce burnout, and improve access to care.

By enabling non-physicians to manage intake and history-taking through conversational AI, Akido allows clinicians to focus on the 20% of patients who truly need their expertise, reserving their cognitive bandwidth for the most complex cases. According to Akido co-founder Prashant Samant, this model can increase visit capacity five- to tenfold, improving outcomes for patients with chronic diseases through more frequent and informed care encounters.

Administrative AI: A Lifeline for Hospital Operations

While AI in the clinic aims to extend the physician's reach, AI in hospital administration is addressing an equally urgent crisis: an overwhelmed, understaffed, and financially strained hospital system. With over 13% of U.S. hospitals critically understaffed and administrative costs consuming nearly a quarter of hospital budgets, the stakes are high.

AI-powered assistants are already proving their worth. Automated scheduling systems are reducing patient wait times and no-show rates—together responsible for billions in annual losses. Meanwhile, AI tools that streamline billing and documentation are reducing denied claims and accelerating revenue cycles. Estimates suggest these tools could save administrators 870 hours annually while improving coding accuracy to 97%.

Perhaps most significantly, AI enables smarter resource allocation. By analyzing underutilized data from EHRs and operational metrics, hospital leaders are uncovering patterns and inefficiencies previously buried in data silos. The result? A blueprint for cost-effective strategic planning grounded in real-time insights rather than retrospective guesswork.

Generative AI in the Clinical Path Lab: A New Era of Interpretive Medicine

If the exam room and front office are seeing tangible gains from AI, the clinical pathology lab is arguably where AI’s cognitive potential shines brightest. As Dr. Rama Gullapalli and Dr. Peter McCaffrey note in Archives of Pathology & Laboratory Medicine, clinical pathology is uniquely suited to benefit from generative AI due to its vast, structured data sets—and its deep tradition of interpretive inference.  Open access / Arch Path Lab Med, McCaffrey 149:130-141.

Large language models are now being applied to everything from SOP auditing and instrument selection to complex multimodal report generation. Tasks that once required weeks of expert labor—like evaluating new lab platforms or comparing vendor performance—can now be initiated with well-formed prompts and validated in hours. And in fields like molecular pathology, AI is beginning to surface subtle patterns across massive datasets that would otherwise go unnoticed, such as early anemia trends suggesting undiagnosed malignancy.

This isn’t a vision of AI replacing the clinical pathologist—it’s one where AI acts as an infinite assistant, elevating every team member’s expertise while preserving human oversight. In fact, Dr. McCaffrey argues that the lab’s role may evolve from service to infrastructure, becoming the central “cognitive utility” of the healthcare enterprise.

Connecting the Dots:
AI as Infrastructure, Not Add-On

These three vignettes—from Akido’s clinic-based AI, to hospital admin automation, to cognitive augmentation in pathology—point to a larger transformation: AI is becoming healthcare infrastructure.

Crucially, each use case highlights a different AI strength:

  • In the clinic, AI augments clinical triage and intake to expand access.

  • In administration, AI streamlines logistics and documentation to reduce costs.

  • In the lab, AI enhances pattern recognition and data synthesis to amplify insight.

Together, they form a composite vision of a system where human expertise is redirected from rote tasks to nuanced decision-making—where doctors diagnose the hardest cases, administrators strategize with real-time data, and pathologists provide layered insights across the patient journey.

The risks, of course, remain—hallucinations, automation bias, liability concerns—but with careful governance, pilot testing, and human-in-the-loop validation, these are challenges to be managed, not barriers to adoption.

In short: AI is no longer a tool in the toolbox. It is the foundation of a healthcare model that is leaner, smarter, and more patient-centric. The healthcare leaders who understand this shift—not just as a technical change but as a structural one—will be the ones best positioned to shape its trajectory.


Tell me what's "really novel" in all this.  What's most important?

###

Great question—and one that goes beyond the headlines. Across the three case studies, several novel and important findings stand out as truly surprising and worth deeper attention:

1. AI Is Now Conducting the Medical Visit, Not Just Documenting It

The most unexpected and transformative detail from the Akido Labs case is that AI is not merely supporting clinicians—it is running the entire visit, from intake to preliminary diagnosis, through ScopeAI.

  • Novelty: Medical assistants use AI as an "intelligent teleprompter" that dynamically listens, prompts, and guides a structured medical conversation—all before the physician walks in.

  • Importance: This flips the traditional clinical model. It suggests a division of cognitive labor, where physicians focus on the top 20% of complex patients, while the AI+assistant team handles the rest. That’s an operational redesign, not just a tech upgrade.

2. Hospital Admin AI Can Save Billions and Prevent Burnout Collapse

The scale of AI’s impact on hospital administration is genuinely surprising—and understudied.

  • Novelty: AI isn’t just streamlining tasks—it’s predicted to save up to 47% of administrator time, slash no-show losses (~$150B annually), and improve billing accuracy to 97%, all while reducing clinician burnout, a key driver of attrition.

  • Importance: These are not marginal gains. They touch the very core of hospital solvency and staff retention. AI becomes not just a cost-saver, but a lifeline for workforce sustainability.

3. Clinical Pathology as a “Cognitive Utility”

Perhaps the most conceptually innovative idea is from Dr. McCaffrey’s vision of clinical pathology: “Pathology as infrastructure,” akin to electricity—infused everywhere in EHRs, offering ongoing, real-time inference.

  • Novelty: Clinical pathologists aren’t just reporting test results—they’re becoming AI-augmented advisors, helping predict, contextualize, and even prompt smarter orders before the physician knows what to ask for.

  • Importance: This shifts pathology from a passive service to an active co-pilot of care delivery, leveraging the lab’s privileged position as the first to see the data. It reframes pathology as a key player in preventive inference and operational optimization.

The Common Thread: AI Is Not Just Faster—It’s Restructuring Roles

In all three domains, AI isn’t simply accelerating old workflows. It’s redefining the boundaries between roles:

  • Medical assistants take on structured triage.

  • Administrators become strategists, not schedulers.

  • Pathologists become real-time informatics partners.

That’s the big shift: AI is dissolving old bottlenecks not just by speeding up tasks, but by reassigning cognitive work in a new division of labor.

 


Subscribe to: Posts (Atom)