In July rulemaking, in both OPPS (hospital outpatient) and Physician (aka Part B) proposed rules, CMS announced it will evict digital pathology / computational pathology services from CLIA services, and therefore strip them of their position on the Clinical Laboratory Fee Schedule.
Whether you love or hate CLIA, love or hat the CLFS, my reading of the SSA 1834A PAMA statute is that "clinical laboratory tests" go on the CLFS, and there is no mention of exceptions. On the other hand, if a service is not a clinical laboratory service (the CL in CLIA), it can't go on the CLFS.
So, as far as I can tell, the only way CMS can reach its goal of tossing digital pathology out of CLFS, is to toss it out of CLIA.
But this is 180 degrees opposite CAP and CPT. CAP and CPT are looking to have MORE CLIA requirements for computational pathology - copies of CLIA licenses, special letters from CLIA lab director to CPT, etc.
On this theme, I asked Chat GPT if it could find documentation where CAP clearly places computational pathology under CLIA (and CAP-CLIA inspections, etc.
AI came back with alot. If you want to comment to CMS, that computational pathology is a CLIA service, which CMS is directly denying, here are some bricks and stones you can throw.
This blog concludes with a model letter -- though too long -- to CMS about SaMS and CLIA and digital pathology.
##
Prompt
In proposed rulemaking for a new category called Software as a Medical Service (SaMS), CMS would remove certain computational pathology tests—such as AI-based prognostic recurrence tests performed on H&E whole-slide images—from the Clinical Laboratory Fee Schedule. CMS reasons that these analyses need not be performed by a CLIA-regulated laboratory and may instead be classified and paid as SaMS.
CAP and the AMA CPT process appear to be moving in precisely the opposite direction. When the same computational pathology test applies for a CPT code, the applicant may be asked to provide CLIA certificates, documentation from the CLIA laboratory director, and other evidence that the test is performed within a regulated clinical laboratory. It is difficult to imagine two more nearly opposite conceptions of the same service.
Are there CAP documents that clearly place clinical digital and computational pathology within the CLIA regulatory framework, including oversight through CAP’s role as a federally deemed CLIA accrediting organization?
##
Yes. The CAP record is unusually clear—and it directly conflicts with CMS’s categorical premise that these computational-pathology analyses “do not require” a CLIA laboratory and may be performed by “any non-regulated entity.”
Strongest CAP authority
The most useful document is CAP’s February 23, 2026 response to the HHS Health Sector AI RFI. It is recent, formal, addressed to HHS, and explicit:
CAP identifies itself as a CLIA-deemed accrediting organization that accredits more than 8,300 laboratories.
CAP states that its accreditation checklists require laboratory-director validation or verification before patient testing, “including AI and machine learning algorithms.”
CAP describes FDA regulation and CLIA oversight as “complementary and necessary” for clinical AI.
CAP says laboratories must validate or verify local AI performance under CLIA before implementation.
Later in the letter, CAP states directly that CLIA requires pathologists, acting as laboratory directors, to assess AI systems before local implementation.
CAP recommends using its accreditation and proficiency-testing infrastructure to evaluate, monitor, and safely deploy AI tools.
This is not an inference from general laboratory principles. CAP expressly places clinical AI under CLIA laboratory-director oversight and CAP accreditation requirements.
CAP’s actual inspection checklist
CAP’s 2025 accreditation checklist edition is described in detail in the February 2026 CAP TODAY article, “Digital path practices reflected in latest checklist changes”.
The Laboratory General Checklist now contains a section expressly titled:
Digital Pathology Including Remote Data Assessment
CAP explains that it revised this section specifically to encompass developments in digital algorithms and artificial intelligence. Its definition expressly includes pathologists’ review and diagnostic interpretation of tissue using digital pathology and whole-slide images. It also ties the activity to the laboratory’s CLIA address and explains when a remote interpreting location becomes a separate referral laboratory.
Page two of the CAP article identifies particularly useful checklist requirements:
Inspectors sample digital-pathology policies and procedures.
Inspectors sample reports generated through digital pathology.
Inspectors review digital-pathology validation and verification records.
GEN.50630 requires the laboratory to validate or verify digital-pathology systems used for clinical diagnostic purposes, with approval by the laboratory director or a qualified designee.
GEN.52860 requires digital-pathology services to be included in the laboratory’s quality-management system.
CAP inspectors may examine scan-failure rates, image-quality criteria, risk-mitigation procedures, discordance reconciliation, and other ongoing performance measures.
That is probably the best operational evidence for your letter. CAP is not merely saying that a pathologist should use good judgment when purchasing software. CAP has placed clinical digital pathology inside the inspection checklist used to determine continuing laboratory accreditation.
CAP’s specific AI-validation guidance
CAP’s educational guidance, “How to Validate AI Algorithms in Anatomic Pathology”, is also remarkably direct:
Both CLIA and CAP require validation of a new test, device, or diagnostic aid before reporting patient results.
CAP applies its whole-slide-imaging validation principles to image-analysis algorithms.
CAP states that any image-analysis or image-recognition system—FDA-authorized or not—must be validated before clinical use.
Validation occurs in the laboratory, using cases representative of the laboratory’s intended clinical use and patient population.
The medical director establishes acceptance criteria and approves implementation.
CAP even supplies suggested report language for a non-FDA-authorized AI system treated as a laboratory-developed test.
Although this is educational guidance rather than the checklist itself, it demonstrates how CAP interprets and operationalizes CLIA and CAP requirements for H&E-based AI.
Second formal CAP policy letter
CAP made essentially the same point in its December 1, 2025 comments to FDA on measuring and evaluating AI performance.
CAP states that:
CAP is a federally deemed CLIA laboratory accrediting organization.
CAP checklist validation and verification requirements expressly include AI and machine-learning algorithms.
AI represents a new component of pathologists’ responsibilities as CLIA laboratory directors and section directors.
CLIA and CAP impose quality requirements beyond the manufacturer’s FDA-authorized operating instructions.
Laboratories should establish controls, performance metrics, corrective actions, and procedures addressing AI performance drift.
Again, CAP treats AI applied in clinical pathology as part of the laboratory test system—not as an unregulated computer transaction detached from the laboratory.
CMS’s own CLIA guidance
There is also an apparent inconsistency within CMS itself. In its May 11, 2023 CLIA Post-PHE Guidance, CMS treated the remote review of digital laboratory data, results, and images as testing performed under a primary laboratory’s CLIA certificate:
The remote work must fall within the specialties or subspecialties on the primary laboratory’s certificate.
The laboratory director remains responsible.
Records are retained by the primary laboratory.
Survey findings and enforcement actions attach to that laboratory’s CLIA certificate.
Digital proficiency-testing review is treated as occurring under the primary site’s CLIA number.
This does not decide every possible algorithm-only service, but it refutes any general theory that converting tissue information into digital images automatically removes subsequent clinical interpretation from the CLIA framework.
The precise conflict with the OPPS proposal
CMS states in the CY 2027 OPPS proposed rule that stand-alone algorithmic analyses are separate from a CLIA laboratory’s examination of human material. CMS then concludes that they:
do not require CLIA-regulated laboratory services or entities;
can be performed by any “non-regulated entity” possessing the software;
are “other diagnostic tests,” rather than clinical diagnostic laboratory tests; and
should therefore be removed from the CLFS and paid as SaMS under OPPS.
For a purely secondary calculation performed on a finalized laboratory result, CMS’s distinction may sometimes be defensible. It is much less persuasive for computational pathology applied to an H&E whole-slide image. The WSI is a direct digital representation of the patient’s tissue specimen, and the algorithm produces a patient-specific diagnostic, prognostic, or predictive result. CAP expressly subjects that clinical process to laboratory validation, laboratory-director oversight, quality management, reporting requirements, and inspection.
Payment classification and regulatory classification need not always be identical. But CMS’s proposal does not merely select a different payment system. It makes the broader factual and regulatory assertion that no CLIA entity is needed. That is where the collision becomes unavoidable.
Suggested comment-letter language
CMS’s proposed treatment of computational pathology as Software as a Medical Service creates a direct conflict with the existing federal laboratory-quality framework. CMS states that these algorithmic analyses do not require a CLIA-certified laboratory and may be performed by an otherwise unregulated entity. In contrast, the College of American Pathologists—the nation’s largest federally deemed CLIA accrediting organization—expressly applies its laboratory accreditation requirements to artificial intelligence and machine-learning algorithms used for patient testing. CAP requires laboratory-director validation or verification before implementation, and its 2025 Laboratory General Checklist includes a dedicated section entitled “Digital Pathology Including Remote Data Assessment.” CAP inspectors review digital-pathology policies, patient reports, validation records, and quality-management activities; checklist requirements GEN.50630 and GEN.52860 specifically address laboratory validation, laboratory-director approval, and continuing quality management of digital-pathology systems.
This conflict is especially pronounced for computational-pathology tests that apply an algorithm to an H&E whole-slide image to produce a patient-specific diagnostic, prognostic, or predictive result. Such a service is not simply an arithmetic calculation performed on a previously reported laboratory value. It is the clinical examination and interpretation of a digital representation of human tissue. CAP’s current accreditation framework treats that activity as patient testing conducted under the responsibility of the CLIA laboratory director.
CMS should therefore withdraw or qualify its categorical conclusion that SaMS analyses performed on laboratory-test data require no CLIA-regulated entity. At minimum, CMS should clarify that classification and payment of a service under OPPS does not displace otherwise applicable CLIA requirements; distinguish purely secondary analysis of finalized data from computational examination of whole-slide tissue images; and consult with CMS’s CLIA program and federally deemed accrediting organizations before finalizing the regulatory status of computational-pathology services.
One terminology refinement: CAP is not universally “CLIA’s inspection body.” The technically exact phrase is “a CMS-approved, federally deemed CLIA accrediting organization.” CAP states that, for CAP-accredited laboratories, a CAP inspection occurs in lieu of a CMS inspection. That wording will be harder for CMS to evade.
###
WRITE A FORMAL COMMENT LETTER WITH CITATIONS
###
[DATE]
Administrator
Centers for Medicare & Medicaid Services
Department of Health and Human Services
7500 Security Boulevard
Baltimore, Maryland 21244
Re: CY 2027 Hospital Outpatient Prospective Payment System Proposed Rule, CMS-1850-P; CY 2027 Medicare Physician Fee Schedule Proposed Rule, CMS-1848-P—Software as a Medical Service and Computational Pathology
Dear Administrator:
[ORGANIZATION] appreciates the opportunity to comment on the Centers for Medicare & Medicaid Services’ proposed policies for Software as a Medical Service (SaMS) in the CY 2027 Hospital Outpatient Prospective Payment System (OPPS) and Medicare Physician Fee Schedule (PFS) proposed rules.
We support CMS’s broader effort to develop coherent and predictable payment policies for software-based medical technologies. However, we urge CMS not to finalize its proposal to remove clinical computational pathology tests from the Clinical Laboratory Fee Schedule (CLFS) based solely on the absence of a conventional laboratory method in the CPT descriptor. In particular, CMS should not conclude categorically that an artificial intelligence algorithm applied to an H&E whole-slide image to produce a patient-specific diagnostic, prognostic, or predictive result requires no CLIA-regulated laboratory.
This conclusion conflicts with the existing laboratory-quality framework established by the Clinical Laboratory Improvement Amendments (CLIA), CMS’s own CLIA guidance, the accreditation requirements of the College of American Pathologists (CAP), and the laboratory requirements applied through the AMA CPT process. CAP expressly treats artificial intelligence, machine-learning algorithms, whole-slide imaging, and clinical digital pathology as activities subject to laboratory-director oversight, laboratory validation and verification, continuing quality management, and CAP inspection.
We therefore recommend that CMS:
Retain CLFS treatment for computational pathology tests performed by a CLIA-certified laboratory on whole-slide images or other data directly derived from a patient specimen when the algorithm generates a patient-specific diagnostic, prognostic, or predictive result.
Exclude such computational pathology tests from the proposed SaMS reassignment under both OPPS and the PFS unless and until CMS completes a coordinated review with its CLIA program and federally deemed CLIA accrediting organizations.
Clarify that payment classification under OPPS or the PFS does not displace otherwise applicable CLIA requirements.
Distinguish computational examination of whole-slide tissue images from genuinely stand-alone secondary calculations performed on previously finalized laboratory results.
Refrain from using the absence of a conventional laboratory method in a CPT descriptor as the dispositive test for whether a service is clinical laboratory testing.
CMS’s SaMS proposal
In the CY 2027 OPPS proposed rule, CMS proposes to classify certain software-based technologies as SaMS and assign them to New Technology Ambulatory Payment Classifications. CMS also proposes to remove ten algorithmic-analysis codes from the CLFS and pay for them under OPPS as SaMS. CMS proposes a parallel policy under the PFS: the same ten codes would be removed from the CLFS and contractor priced when furnished outside the hospital outpatient setting. CMS further proposes that future codes describing SaMS analyses performed on laboratory-test data generally follow these pathways rather than the CLFS.[1,2]
CMS offers several arguments for this policy.
First, CMS characterizes these services as downstream analyses of data generated by an earlier laboratory test. CMS distinguishes the algorithmic analysis from the CLIA-certified laboratory’s examination of human material and reasons that an entity performing only the subsequent software analysis may neither qualify as a laboratory under 42 CFR 493.2 nor require CLIA certification.
Second, CMS states that a subsequent algorithmic analysis can be performed by any otherwise unregulated entity possessing the necessary software. CMS therefore proposes to classify the analysis as an “other diagnostic test” under section 1861(s)(3) of the Social Security Act rather than as a clinical diagnostic laboratory test.
Third, CMS reasons that algorithmic analysis of laboratory-derived data is substantively similar to algorithmic analysis of a radiological image, such as a CT scan. CMS seeks to place both within a uniform SaMS payment framework.
Fourth, CMS expresses concern that traditional CLFS crosswalking and gapfilling methodologies are not well suited to computer-based services whose proprietary algorithms and development costs may not be reflected in conventional laboratory methods. CMS notes that laboratories have sometimes been unable or unwilling to disclose detailed information about proprietary algorithms and their costs.
Finally, CMS raises program-integrity and payment-policy concerns. The agency observes that CLFS services are not subject to beneficiary cost sharing or budget neutrality and suggests that the resulting payment framework may create vulnerabilities. CMS believes that shifting the services to OPPS or contractor pricing under the PFS could improve consistency and facilitate development of a more comprehensive payment approach.[1,2]
These are legitimate payment-policy questions. They do not, however, establish that clinical computational pathology lies outside the CLIA laboratory-quality framework. Whether a payment system produces sufficient cost information is analytically distinct from whether a patient-specific clinical test is performed under CLIA laboratory oversight.
Section 1834A makes the CLFS the default for separately payable clinical laboratory tests
Section 1834A is unambiguous about the default payment pathway. For a clinical diagnostic laboratory test furnished under Medicare Part B, the payment amount is established under the CLFS using the PAMA methodology. For a new test, section 1834A(c) directs CMS to establish the initial CLFS payment through crosswalking or gapfilling. Once a service is recognized as a separately payable clinical diagnostic laboratory test performed under CLIA, CMS ordinarily does not have an unrestricted choice among the CLFS, OPPS, and the PFS.[13]
This does not mean that every activity regulated under CLIA must always receive a separate CLFS payment. Congress and CMS have established particular exceptions and alternative payment arrangements. Most prominently, section 1834A(b)(1)(B) expressly recognizes that a hospital laboratory test may be bundled into an OPPS payment rather than paid separately under the CLFS. Certain anatomic pathology services are paid under the PFS, and laboratory services may also be incorporated into inpatient or other bundled payments. These are identifiable exceptions to the general payment structure.
CMS therefore may have authority to carve particular classes of CLIA-regulated services out of separate CLFS payment. But that is very different from concluding that the service is not laboratory testing and requires no CLIA-regulated entity. If CMS intends to create a new exception for computational pathology, it should identify the statutory authority for that exception, define its boundaries, and preserve applicable CLIA quality requirements. Concerns about proprietary cost information, beneficiary cost sharing, budget neutrality, or the limitations of crosswalking and gapfilling do not themselves convert a CLIA-regulated patient test into a nonlaboratory service.
The proposed SaMS policy obscures this distinction. CMS appears to reason backward from its preferred payment system to the regulatory nature of the service: because CMS considers OPPS or PFS payment more appropriate, it concludes that the analysis is not a clinical laboratory test and can be performed by an unregulated entity. CMS should instead determine first whether the service constitutes clinical laboratory testing under CLIA. If it does, section 1834A supplies the ordinary payment pathway unless CMS can identify and lawfully apply a specific exception.
Accordingly, CMS should retain CLFS payment for clinical computational pathology tests. At an absolute minimum, if CMS elects to place some of these tests under OPPS or the PFS, it should describe that action as a limited payment exception and expressly state that the payment classification does not eliminate CLIA certification, laboratory-director oversight, validation, quality management, or accreditation requirements.
#
Our Response
Computational pathology is not merely a calculation performed on a finalized laboratory result
CMS’s genomic-sequencing example does not adequately describe many computational pathology tests. A whole-slide image is not simply a previously reported laboratory value. It is a high-resolution digital representation of the patient’s tissue specimen. An AI algorithm that examines cellular morphology, tissue architecture, tumor-stroma relationships, spatial patterns, or other features within that image is performing a computational examination of information derived directly from human tissue.
When that examination produces a patient-specific diagnosis, recurrence score, risk classification, predicted therapeutic response, or other result used in clinical management, the algorithm is functioning as part of the clinical test system. Its performance can be affected by tissue preparation, staining, slide quality, scanning equipment, image resolution, file compression, image-management software, local patient characteristics, workflow configuration, algorithm version, and performance drift. These are precisely the kinds of preanalytic, analytic, and postanalytic variables addressed through CLIA laboratory-director oversight and CAP accreditation.
The fact that software technically can be run by an unregulated entity does not demonstrate that a patient-specific computational pathology test should be furnished outside a regulated clinical laboratory. Nor does it eliminate the need for validation, correct patient identification, report integrity, quality management, proficiency assessment, corrective action, and accountable medical oversight.
CAP expressly places clinical AI under CLIA laboratory oversight
CAP’s position is unusually clear. In February 2026, CAP submitted formal comments to HHS concerning the adoption of AI in clinical care. CAP identified itself as a CLIA-deemed accrediting organization overseeing more than 8,300 laboratories. It stated that CAP accreditation requirements require laboratory directors to ensure that new tests, instruments, and methods are validated or verified before patient testing, expressly “including AI and machine learning algorithms.”[3]
CAP further stated that FDA review and CLIA oversight serve complementary and necessary roles in clinical AI. According to CAP, FDA evaluates the safety and effectiveness of the device, while the clinical laboratory must verify or validate performance in its local environment before using the device to report patient results. CAP also stated directly that CLIA requires pathologists, acting as laboratory directors, to assess AI systems before implementation.[3]
CAP made the same point in its December 2025 comments to FDA on the real-world performance of AI-enabled medical devices. CAP explained that AI has become an important new element of the pathologist’s responsibilities as a CLIA laboratory director or section director. CAP emphasized that CLIA and CAP accreditation requirements impose quality practices extending beyond the manufacturer’s operating instructions and FDA authorization. Those practices include local validation or verification, controls, performance monitoring, corrective actions, and procedures addressing changes or drift that may affect clinical results.[4]
CAP’s inspection checklist now expressly covers digital pathology
CAP’s 2025 Laboratory General Checklist contains a dedicated section titled “Digital Pathology Including Remote Data Assessment.” CAP explained that this section was revised specifically to address developments in digital algorithms and artificial intelligence.[5]
The checklist’s definition of remote assessment expressly includes pathologists’ review and diagnostic interpretation of tissue using digital pathology and whole-slide images. It connects the activity to the laboratory’s CLIA address and explains when a separate interpreting site may constitute a referral laboratory operating under its own CLIA certificate.[5]
CAP has also described what its inspectors evaluate. Inspectors may review:
Digital pathology policies and procedures;
Patient reports generated through digital pathology;
Digital pathology validation and verification records;
Processes ensuring correct matching of patients, images, and reports;
Scan-failure rates and image-quality criteria;
Reconciliation of discordant results;
Risk-mitigation procedures; and
Continuing quality-management records.[6]
CAP checklist requirement GEN.50630 requires the laboratory to validate or verify digital pathology systems used for clinical diagnostic purposes through its own studies, including approval by the laboratory director or a qualified designee. GEN.52860 requires digital pathology services to be incorporated into the laboratory’s quality-management system.[6]
These are not aspirational professional recommendations. They are laboratory accreditation requirements used in inspections. CMS has granted CAP deeming authority, meaning that, for CAP-accredited laboratories, the CAP inspection is conducted in lieu of a CMS inspection for CLIA compliance.[7]
CAP applies laboratory validation requirements directly to image-based AI
CAP’s guidance on validating AI algorithms in anatomic pathology is equally explicit. CAP states that both CLIA and CAP require a new test, device, or diagnostic aid to be validated before patient results are reported. CAP applies its whole-slide-imaging validation principles to clinical image-analysis and image-recognition algorithms.[8]
Under CAP’s approach, the laboratory must validate the algorithm for its intended clinical use, using cases representative of the specimen types, diagnoses, complexity, equipment, workflow, and patient population in which the system will operate. The laboratory medical director establishes acceptance criteria and approves implementation. CAP states that any image-analysis or image-recognition system used clinically must be validated, whether or not it has received FDA authorization.[8]
CAP’s separate evidence-based guideline for whole-slide imaging similarly calls for laboratory validation before a WSI system is used for diagnostic purposes. The validation must reflect the intended clinical use and actual practice setting, encompass the complete WSI system, and be repeated when significant changes are made to components that could affect performance.[9]
CMS’s own CLIA guidance treats digital image review as laboratory testing
CMS’s CLIA program has itself treated the clinical review of digital laboratory data, results, and images as work performed under a CLIA certificate. In its May 2023 post-public-health-emergency guidance, CMS allowed remote review of digital laboratory information without requiring an additional certificate at every remote location, but only when the remote activity operated under a designated primary laboratory’s CLIA certificate.[10]
Under that guidance:
The work must fall within the specialties or subspecialties authorized by the primary laboratory’s certificate;
The primary laboratory director remains responsible;
The laboratory must retain documentation of the remotely performed work;
Reports must identify the location where the testing or interpretation occurred;
Survey findings attach to the primary laboratory’s CLIA certificate; and
Enforcement action may affect that certificate.[10]
This guidance does not resolve every possible software application. It nevertheless demonstrates that digitization does not itself remove the clinical examination and interpretation of pathology information from CLIA. CMS should reconcile the proposed SaMS policy with the position already taken by its CLIA program.
The CPT process also treats these services as laboratory testing
The AMA’s publicly available pathology and laboratory CPT application asks whether a proposed test has been classified under CLIA, whether it is high complexity, moderate complexity, or waived, and where the test is performed. It also asks for a standard operating procedure from a licensed, accredited, or certified clinical laboratory. During review, applicants may be asked for CLIA certificates and documentation from the responsible CLIA laboratory director [proposed].[11]
Thus, a developer seeking a CPT code for a clinical computational pathology test may be required to demonstrate that the test is being performed as a regulated laboratory service, while CMS would use the resulting CPT descriptor to conclude that the same service requires no CLIA-regulated laboratory. The two systems are moving in opposite directions.
Published CAP work reaches the same conclusion. A 2025 article in Archives of Pathology & Laboratory Medicine examined the applicability of existing CAP accreditation requirements to machine-learning methods in molecular oncology. The authors concluded that the CAP framework for conventional assay validation and maintenance also applies to clinical machine-learning tests. The examples expressly included prediction from histopathology images.[12]
Requested policy
CMS should distinguish two materially different categories.
The first consists of genuinely stand-alone secondary calculations performed on finalized laboratory results or previously interpreted data. Some of these services may reasonably fall outside the CLFS and be treated as other diagnostic tests or SaMS.
The second consists of computational examination of whole-slide images, raw molecular data, or other information directly derived from a human specimen to generate a new patient-specific diagnostic, prognostic, predictive, or treatment-selection result. When such a test is performed by a CLIA-certified laboratory under laboratory-director oversight, it should remain eligible for treatment as a clinical diagnostic laboratory test.
The dividing line should turn on the nature of the clinical service, the input being examined, the output being reported, the entity assuming responsibility for the result, and the applicable quality framework. It should not turn solely on whether the CPT descriptor happens to name a wet-laboratory method.
CMS’s concerns about proprietary algorithms, cost transparency, crosswalking, beneficiary cost sharing, and budget neutrality can be addressed through payment policy, data collection, and appropriate ratesetting methods. Those concerns should not be used to declare that an H&E whole-slide-image test producing a clinical result requires no CLIA laboratory.
At minimum, CMS should defer reassignment of computational pathology codes while it consults with the CMS CLIA program, CAP, other federally deemed accrediting organizations, the AMA CPT Editorial Panel, clinical laboratories, pathologists, and developers. Any final policy should expressly preserve applicable CLIA requirements and a workable Medicare enrollment and billing pathway for the CLIA-certified laboratories that currently furnish these tests.
Conclusion
[ORGANIZATION] appreciates CMS’s work to develop a coherent payment framework for innovative software-based medical services. That framework should recognize meaningful differences between generic secondary data analysis and clinical computational pathology performed on patient tissue images.
We respectfully urge CMS not to finalize a categorical policy that removes computational pathology from the CLFS or declares that these tests require no CLIA-regulated entity. Preserving CLIA laboratory oversight for patient-specific computational pathology will support innovation while maintaining the validation, quality management, medical accountability, and patient protections already embedded in the nation’s laboratory regulatory system.
We appreciate your consideration of these comments and would welcome the opportunity to provide additional information or participate in further discussions regarding an appropriate payment and quality framework for computational pathology.
Sincerely,
[NAME]
[TITLE]
[ORGANIZATION]
[ADDRESS]
[EMAIL]
[TELEPHONE]
Endnotes
Centers for Medicare & Medicaid Services. CY 2027 Hospital Outpatient Prospective Payment System and Ambulatory Surgical Center Payment System Proposed Rule, CMS-1850-P, 91 Fed. Reg. 41734, especially 41918–41927.
Centers for Medicare & Medicaid Services. CY 2027 Medicare Physician Fee Schedule Proposed Rule, CMS-1848-P, 91 Fed. Reg. 43842, especially 43910–43912.
College of American Pathologists. Response to the HHS Health Sector AI Request for Information, February 23, 2026.
College of American Pathologists. Response to FDA Request for Information on Measuring and Evaluating Artificial Intelligence-Enabled Medical Device Performance in the Real World, December 1, 2025.
Valerie Neff Newitt. “Digital Path Practices Reflected in Latest Checklist Changes,” page 1, CAP TODAY, February 2026.
Valerie Neff Newitt. “Digital Path Practices Reflected in Latest Checklist Changes,” page 2, CAP TODAY, February 2026.
College of American Pathologists. CAP Laboratory Accreditation Program.
College of American Pathologists. How to Validate AI Algorithms in Anatomic Pathology.
College of American Pathologists. Validating Whole Slide Imaging for Diagnostic Purposes in Pathology: Guideline Update, updated 2022.
Centers for Medicare & Medicaid Services. CLIA Post-Public Health Emergency Guidance—Frequently Asked Questions, May 11, 2023.
American Medical Association. CPT Pathology and Laboratory Coding Change Application.
Furtado LV, Ikemura K, Benkli CY, et al. General Applicability of Existing College of American Pathologists Accreditation Requirements to Clinical Implementation of Machine Learning–Based Methods in Molecular Oncology Testing. Archives of Pathology & Laboratory Medicine. 2025;149(4):319–327. doi:10.5858/arpa.2024-0037-CP. PMID: 38871357.
Social Security Act §1834A, 42 U.S.C. §1395m-1, particularly subsections (b)(1), (b)(1)(B), and (c). Official Social Security Act text; 42 U.S.C. §1395m-1.
