Some Validation Criteria that MolDx Needs to See

 Short "intelligent lay person's" definitons of some of the performance factors that MolDx looks at.

Explanation of Validation Metrics for Molecular Lab Developed Tests (LDTs) Required by MOLDX

1. Sensitivity: This measures the test's ability to correctly identify those with the disease (true positives). It's determined by comparing the test results with a known gold standard of diagnosed positive cases.

2. Specificity: This assesses the test's ability to correctly identify those without the disease (true negatives). It's also compared against a gold standard of diagnosed negative cases.

3. Accuracy: This refers to the test's overall ability to correctly identify both positive and negative cases. It combines the data from sensitivity and specificity to provide a comprehensive measure of test performance.

• I believe it's similar to 100% minus the FP and minus the FN.   For example, if the FP is 5% and the FN is 5% [for a popularion] then the running accuracy is 90%. (BQ)
• While SENS and SPEC should be absolute (from 100 gold standard true positives, etc), the ACCURACY (and PPV NPV) will vary on the population, base rate, etc. (BQ)

4. Precision: This metric evaluates the reproducibility of the test results under the same conditions. It's divided into:

• Repeatability: Consistency of results when the same sample is tested multiple times within a short period.
• Reproducibility: Consistency of results when the same sample is tested across different days, operators, and equipment.

5. Limit of Detection (LOD): This is the lowest concentration of the target analyte that the test can reliably detect, but not necessarily quantify. It indicates the analytical sensitivity of the test.

6. Limit of Quantitation (LOQ): This is the lowest concentration at which the test can not only detect but also quantify the analyte with acceptable precision and accuracy. It represents a higher threshold than LOD and is crucial for quantitative assays.

7. Interference: This involves testing the assay's performance in the presence of potential contaminants or substances that could affect the results, such as hemoglobin, lipids, or other common biological substances.

8. Cross-Reactivity: This measures whether the assay mistakenly identifies non-target substances as the target analyte, ensuring the test's specificity in complex biological samples.

9. Reportable Range: This defines the span of analyte concentrations over which the test can accurately measure and report results. It ensures that the test is reliable across a clinically relevant range of concentrations.

10. Reference Interval/Range: This establishes the normal range of analyte levels in a healthy population, providing a benchmark against which patient results can be compared.

Understanding these metrics helps a genomic lab scientist ensure that their LDTs meet regulatory standards for reliability, accuracy, and clinical utility, essential for MOLDX approval.

##

Limit of Blank.

Limit of Blank (LoB)

Definition: The Limit of Blank (LoB) is the highest measurement result that is likely to be observed for a sample that does not contain the analyte of interest. It represents the upper threshold of background noise in a blank sample, which theoretically should not contain any analyte.

Context and Importance

• Purpose: The LoB helps distinguish between true low-level signals and the noise inherent in the assay. It sets a baseline to ensure that any measurement above this threshold can be attributed to the presence of the analyte rather than random fluctuations or background interference.
• Calculation: The LoB is typically calculated by repeatedly measuring blank samples and determining the value below which a certain percentage (commonly 95%) of the measurements fall. This involves statistical analysis of the blank sample measurements.
• Application: In clinical and laboratory settings, knowing the LoB is crucial for determining the Limit of Detection (LoD). The LoD is derived from the LoB and represents the lowest concentration of the analyte that can be reliably detected above the LoB.

Example

• Suppose an assay measures a blank sample (containing no analyte) multiple times, and the highest measurement observed from these replicates is 0.02 units. This value is determined to be the LoB.
• Any measurement above 0.02 units in test samples can be considered to potentially indicate the presence of the analyte, as values below this are likely due to background noise.

Understanding the LoB helps ensure the reliability and accuracy of assays, particularly when working with low concentrations of analytes. It is a foundational metric for establishing the sensitivity of a test.

Blog Ordered Points

 In a blog about a CMS meeting, I noted that experts had opined on 9 points.   I gave Chat GPT the 9 points in my own typing, but asked Chat GPT to reorder the points.

Here's how it answered when I asked "WHY" it had done so.

##

Sure! Here's a detailed explanation of how I made the decisions to reorder the points logically:

1. The public comment presentations in June are very helpful – it’s frustrating that “half” of codes lack a presentation in that forum.

   • This sets the stage by highlighting a major issue: the lack of presentations for half of the codes, which impacts the panel's ability to make informed decisions.

2. Companies present elaborate and useful info packets to AMA, but they dead-end there and are not part of the crosswalk process. Could the companies/AMA/CMS facilitate sharing, at least as an option?

   • Following the initial point, this highlights a related issue: the detailed information packets that are not shared with CMS, suggesting a potential area for improvement.

3. The panelists would like to have patient result reports for each test.

   • Building on the need for more information, this point specifies a particular type of useful information that the panelists need.

4. Inclusion of an FDA instructions for use would help.

   • This continues the theme of needing more detailed information, specifically mentioning FDA instructions as another helpful resource.

5. One frustrating scenario is when a test in one year (000XU) is sent to gapfill, and the next summer a very similar code is created (00XXU). The new code can’t be crosswalked to 000XU, but it’s a similar code and for consistency the price should be the same. Under today’s rules, 00XXU will get sent to gapfill in the next year, a waste of gapfill resources and potentially a source of price inconsistency.

   • This point transitions to specific procedural issues, illustrating a scenario where the current rules lead to inefficiencies and inconsistencies.

6. It seems unfair to price two tests differently, one with 10 markers, one with 20, when they output the same result with the same accuracy.

   • Continuing with procedural issues, this highlights a fairness concern in pricing, which builds on the previous point about consistency.

7. There was discussion that the PLA codebook has no structure, and with >500 codes, that’s confusing and makes crosswalk searches unreliable.

   • This point addresses the structural issues in the PLA codebook, adding to the theme of procedural and organizational challenges.

8. What does “appropriate crosswalk” mean? Intended use? Method? Number of analytes? CMS noted that both creating such rules – and the lack of the rules – is problematic.

   • This follows logically from the previous point by questioning the criteria for crosswalking, a core issue in the pricing process.

9. When public stakeholders align on a pricing proposal, that’s impressive and helpful.

   • Ending on a positive note, this acknowledges the benefits of stakeholder alignment, suggesting that collaboration and agreement can lead to successful outcomes.

The reordered points follow a logical flow from identifying the problem, detailing specific issues and needs, discussing procedural challenges, and concluding with a note on potential solutions and positive aspects.

AI Summarizes my new White Paper on MRD (Minimal Residual Disease Testing) - Draft

 DRAFT - GPT 4 summarizes my own white paper.

##

Summary of the White Paper: 

Minimal Residual Disease Testing: A Case Study for Policy Reforms

Introduction and Key Findings The white paper delves into Minimal Residual Disease (MRD) testing, emphasizing its critical role in detecting cancer recurrence, monitoring therapy response, and assessing the completeness of cancer resection. It highlights the transformative potential of MRD tests, particularly those based on circulating tumor DNA (ctDNA), over traditional imaging methods like CT and MRI. The paper reviews current MRD technologies, their applications, and the need for policy reforms to support their broader adoption.

Technologies for MRD MRD tests have evolved significantly, with key players like Adaptive Biotechnologies' ClonoSEQ, Natera's Signatera, and Guardant Health's Reveal leading the field. These tests use various technologies, from bespoke sequencing approaches to standardized tests for specific cancers. The paper discusses the diverse applications of MRD, including:

• Detecting cancer recurrence earlier than imaging.
• Monitoring therapy response.
• Assessing the completeness of cancer resection.

Insurance Coverage and Policy Issues Insurance coverage for MRD testing varies widely. The paper outlines the discrepancies in Medicare coverage across different regions, highlighting the advanced policies of the MolDx program and the lack of systematic policies in other Medicare regions. Key policy issues include:

• The restrictive national coverage decision (NCD) for NGS-based testing, which limits serial testing and coverage for early-stage cancers.
• The 14-day rule for inpatient services, causing delays in test availability post-surgery.
• The complex and fragmented coding system, with a proliferation of PLA codes that are not widely accepted.
• Slow and non-transparent pricing processes for new tests.

Stakeholder Analysis The white paper examines the perspectives of various stakeholders:

• Payers: MRD can reduce costs and improve patient outcomes by enabling more precise treatment decisions.
• Diagnostic labs: Leading labs like Natera emphasize the importance of reimbursement dynamics and intellectual property positioning.
• Biopharma: MRD tests offer new surrogate markers for clinical trials, particularly in adjuvant and neoadjuvant therapy.
• FDA: The regulatory landscape is evolving, with new guidelines and approvals for MRD tests expected to impact the market.

Regulatory and Legislative Uncertainties Two significant areas of uncertainty are highlighted:

• The impact of new FDA regulations bringing lab-developed tests under FDA control by 2027.
• The influence of state biomarker coverage laws, which mandate coverage for biomarker tests by commercial insurers in some states.

Future Directions and Recommendations The white paper concludes with several recommendations to improve MRD testing policies:

• Reopen NCD 90.2 to enhance coverage for early-stage cancers and serial testing.
• Revise the 14-day rule to allow immediate testing post-discharge.
• Develop general CPT codes for major types of MRD testing.
• Increase transparency in coverage decisions, particularly within the MolDx program.

The paper underscores the importance of adapting policies to keep pace with technological advancements in MRD testing, ensuring broader access and better patient outcomes in clinical genomics.

###

My working title was, "Minimal Residual Disease Testing: Case Study for Policy Reforms."  Provide 20 alternatives.

1. "Reforming Policies for Minimal Residual Disease Testing"
2. "Advancing MRD Testing: Policy Challenges and Solutions"
3. "Innovations in MRD Testing: A Policy Framework"
4. "Transforming Cancer Detection: Policy Insights for MRD"
5. "Navigating Policy Barriers in Minimal Residual Disease Testing"
6. "MRD Testing and Policy Reform: A Path Forward"
7. "Policy Evolution in Minimal Residual Disease Diagnostics"
8. "Modernizing Cancer Detection: MRD Testing and Policy"
9. "The Future of MRD Testing: Policy Recommendations"
10. "Clinical Genomics and MRD Testing: Bridging the Policy Gap"
11. "Unlocking the Potential of MRD Testing: Policy Reforms Needed"
12. "Revisiting Policy for Advanced MRD Testing"
13. "From Lab to Clinic: Policy Reforms for MRD Testing"
14. "Enhancing Cancer Detection: Policy Approaches to MRD Testing"
15. "Policy Innovations for Effective MRD Testing"
16. "Optimizing MRD Testing: Policy Perspectives and Reforms"
17. "MRD Testing in Cancer: Policy Gaps and Solutions"
18. "Comprehensive Policy Reforms for MRD Testing"
19. "MRD Testing and Healthcare Policy: A Comprehensive Review"
20. "Charting a New Course for MRD Testing: Policy Recommendations"

Sidebar: Castle Protests MolDx Overlooked 2 Papers (Coverage of Squamous Test)

 Main Blog

https://www.360dx.com/reimbursement-news/palmetto-declines-cover-molecular-risk-stratification-tests-cutaneous-squamous

Quote:

In an email, a spokesperson for Castle Biosciences said its DecisionDx-SCC test is supported by "robust validation data in the intended use population," and since draft decision was posted last year, the firm has published "additional peer-reviewed papers addressing the perceived gaps in data that appear to have been overlooked by Palmetto."

She pointed to a study demonstrating the ability of the test to identify patients at the highest risk of metastasis who will benefift the most from adjuvant radiation therapy, and high-risk patients identified to be at lower risk of metastasis who could choose to defer treatment. 

She also mentioned a separate study that demonstrated that wen used with traditional clinicopathologic staging factors, DecisionDx-SCC "engendered significant improvement in accuracy for the prediction of metastatic events..

##

The papers are ARRON 2024 and WYSONG 2024.  Both are open access.

https://www.sciencedirect.com/science/article/pii/S0360301624006850

Arron et al., Online 27 May 2024

Purpose

Adjuvant radiation therapy (ART) for cutaneous squamous cell carcinoma (cSCC) is recommended based on a number of wide-ranging clinicopathologic features, which encompass a broad array of patients. The 40-gene expression profile (40-GEP) test classifies cSCC tumors into low (Class 1) or higher (Class 2A) or highest (Class 2B) risk of nodal and/or distant metastasis. This study's hypotheses are 1) local recurrence is associated with metastatic disease progression, and 2) 40-GEP, by identifying high risk for metastasis, could predict a metastasis-specific benefit from ART.

Methods

Samples were obtained from 920 patients (ART-untreated: 496 Class 1, 335 Class 2A, 33 Class 2B; ART-treated: 11 Class 1, 35 Class 2A, 10 Class 2B) who were matched on clinical risk factors and stratified by ART status, to create 49 matched patient strata. To control for the variety of characteristics and treatment selection bias, randomly sampled pairs of matched ART and non-ART patients comprising 10,000 resampled cohorts were each analyzed for 5-year metastasis-free survival and predicted time to metastatic event.

Results

Of 96 patients experiencing local recurrence, 56.3% experienced metastasis; of those experiencing both, 88.9% had local recurrence before (75.9%) or concurrently (13.0%) with metastasis. After matching for clinicopathological risk, median 5-year disease progression rates for resampled cohorts demonstrated approximately 50% improvement for Class 2B ART-treated as compared to ART-untreated cohorts. Class 2B ART-treated cohorts had a 5-fold delay in predicted time to metastatic event and deceleration of disease progression as compared to ART-untreated cohorts (Kolmogorov-Smirnov test, p<0.01); this was not observed for Class 1 or 2A patients (p>0.05 for each). No risk factor or staging system combined with ART status identified groups that would benefit from ART as well as 40-GEP.

Conclusion

40-GEP identifies patients at highest risk of nodal/distant metastasis who may derive greatest benefit from ART, as well as patients who may have clinical indications for ART but are at low risk of metastasis. Compared to current guidelines, 40-GEP could provide greater specificity concerning the benefit of ART in individual patients.

##

##

https://pubmed.ncbi.nlm.nih.gov/38424384/

Wysong, Epub March 1 2024

Introduction: The validated 40-gene expression profile (40-GEP) test independently stratifies risk of regional or distant metastasis for cutaneous squamous cell carcinoma (cSCC) tumors with high-risk clinicopathologic features. This study evaluated the stratification of risk by the 40-GEP test in a large cohort of tumors with one or more high-risk factors and in clinically relevant subgroups, including tumors within National Comprehensive Cancer Network (NCCN) high- and very-high-risk groups, lower-stage BWH T1 and T2a tumors, and patients > 65 years old.

Methods: This multicenter (n = 58) performance study of the 40-GEP included 897 patients. Kaplan-Meier analyses were performed to assess risk stratification profiles for 40-GEP Class 1 (low), Class 2A (higher) and Class 2B (highest) risk groups, while nested Cox regression models were used to compare risk prediction of clinicopathologic risk classification systems versus risk classification systems in combination with 40-GEP.

Results: Patients classified as 40-GEP Class 1, Class 2A, or Class 2B had significantly different metastatic risk profiles (p < 0.0001). Integrating 40-GEP results into models with individual clinicopathologic risk factors or risk classification systems (Brigham and Women's Hospital, American Joint Committee on Cancer Staging Manual, 8th Edition) and NCCN demonstrated significant improvement in accuracy for prediction of metastatic events (ANOVA for model deviance, p < 0.0001 for all models).

Conclusion: The 40-GEP test demonstrates accurate, independent, clinically actionable stratification of metastatic risk and improves predictive accuracy when integrated into risk classification systems. The improved accuracy of risk assessment when including tumor biology via the 40-GEP test ensures more risk-aligned, personalized patient management decisions.

Chat GPT 4 Assesses a Table of 54 Line Item Z Codes for "MRD" Tests at MOLDX

Using companies like Natera and Inivata, I assembled a 54-row table of Z codes for Minimal Residual Disease tests at MolDx.   (Codes ranged from about 30 to 130 words long).   I asked Chat GPT 4 to assess what's going on.

See master blog here:

https://www.discoveriesinhealthpolicy.com/2024/07/is-moldx-doing-amazing-new-things-with.html

### [Start Chat GPT 4]

The table you've provided lists molecular tests for minimal residual disease (MRD) in oncology, indicating whether they are covered by Medicare (MolDx program). The descriptors for each test are quite extensive and variable. Here's an analysis of what MolDx might be aiming to achieve with these detailed, yet inconsistent descriptors:

Goals of MolDx with Detailed Test Descriptors

1. Precise Identification:

   • Unique Test Characteristics: Each test descriptor includes specific details about the test's methodology, target biomarkers, patient population, and intended use. This level of detail helps in precisely identifying what each test does, which is crucial for coverage decisions.
   • Differentiation: By providing detailed descriptions, MolDx ensures that each test can be clearly distinguished from others, even if they target similar conditions. This differentiation is essential for evaluating the uniqueness and potential value of each test.

2. Clinical Context:

   • Clinical Application: Descriptions often include the clinical context in which the test is used, such as monitoring specific types of cancer. This helps in assessing the test's relevance and utility in clinical practice, which is critical for coverage decisions.
   • Intended Use: Clearly stating the intended use helps determine if the test is appropriate for the intended patient population and if it addresses an unmet medical need.

3. Regulatory and Reimbursement Clarity:

   • Compliance: Detailed descriptors ensure that the tests meet regulatory requirements and provide the necessary information for reimbursement processes.
   • Documentation: Comprehensive descriptions serve as thorough documentation for coverage decisions, providing a clear rationale for why a test is covered or not.

4. Evidence and Validation:

   • Scientific Validity: Detailed descriptions often include the technological basis and the scientific evidence supporting the test. This information is crucial for evaluating the test’s validity and reliability.
   • Outcomes: Including information on the test's impact on patient outcomes helps in assessing its clinical utility and cost-effectiveness.

Issues with Non-Systematic Descriptors

1. Lack of Consistency:

   • The variability in descriptors makes it challenging to compare tests directly. A more standardized approach could improve clarity and facilitate easier comparisons.

2. Complexity:

   • Lengthy and complex descriptions may obscure key information. Simplified, yet comprehensive, descriptors might improve understanding and accessibility for decision-makers and other stakeholders.

3. Potential for Misinterpretation:

   • Inconsistent terminology and structure can lead to misinterpretation of the test’s purpose and utility, potentially affecting coverage decisions.

Conclusion

MolDx appears to be aiming for a comprehensive and detailed documentation of MRD tests to support precise, evidence-based coverage decisions. However, the non-systematic nature of the descriptors might hinder clarity and comparability. Standardizing the format and simplifying the language could enhance the effectiveness of these descriptions. ​

HR 1691 Passes Committee, July 2024, Breakthrough Device Coverage

HR 1691 passess committee.

Budget cut, per trade journals.

https://www.fiercehealthcare.com/regulatory/four-year-coverage-breakthrough-medical-devices-passes-ways-and-means-heavy-discount

https://www.congress.gov/118/bills/hr1691/BILLS-118hr1691ih.pdf

### PRESS:

The House Ways and Means Committee advanced bipartisan legislation on Thursday that would grant Medicare coverage to novel medical technologies for four years while the Centers for Medicare & Medicaid Services (CMS) makes a national coverage determination. 

The new version of the bill that was voted on by Ways and Means reduces the cost of the bill by 75% of the version that the House Energy and Commerce Committee voted favorably on back in November. It allocates $10 million per year over five years to CMS for the project. 

CHAT GPT 4 READS BILL:

The Ensuring Patient Access to Critical Breakthrough Products Act of 2024, if passed, would give any device designated as “breakthrough” from the Food and Drug Administration (FDA) four years of Medicare coverage. Co-sponsor of the bill Rep. Susan DelBene, R-Washington, said during the hearing that it takes CMS an average of more than five years to make a national coverage determination for FDA breakthrough devices.

The proposed Medicare coverage for breakthrough devices under HR 1691, known as the “Ensuring Patient Access to Critical Breakthrough Products Act of 2023,” aims to ensure that innovative medical devices receive prompt coverage. Here are the key aspects and implications of the bill, with a particular focus on the budget allowance:

1. Definition of Breakthrough Devices:

   • The bill defines "breakthrough devices" as those given priority review by the FDA and approved or cleared for use after March 15, 2021.

2. Transitional Coverage Period:

   • Breakthrough devices will be provided with transitional coverage for four years from the date of FDA approval or clearance.
   • During this period, these devices will be deemed reasonable and necessary for Medicare coverage purposes and will be eligible for additional and pass-through payments under various Medicare payment systems.

3. Payment Systems and Additional Payments:

   • The bill specifies that the Secretary of Health and Human Services will assign unique codes for these devices within three months of FDA approval, ensuring they are recognized in relevant Medicare payment systems.
   • These systems include inpatient hospital services, outpatient hospital services, ambulatory surgical center services, physicians' services, durable medical equipment, diagnostic laboratory tests, and others.
   • There will be additional payments or adjustments made to cover the costs of these breakthrough devices during the transitional period.

4. Regular Coverage Process:

   • After the transitional period, the Secretary must establish a process for regular coverage of these devices, considering any additional evidence or data required.
   • This process should avoid duplicating FDA data requests, minimize administrative burdens, and not be unnecessary or redundant.

5. Special Rules for Certain Breakthrough Devices:

   • The bill also addresses "specified breakthrough devices" for which no Medicare benefit category exists, ensuring they receive coverage and payment similar to other breakthrough devices.

6. Budget Allocation:

   • Although the bill does not specify a precise budget allocation for the coverage of these devices, it implies that Medicare will ensure the necessary funds are allocated to cover the costs associated with the transitional and regular coverage periods.
   • There is no direct mention of a $10 million budget cap within the provided sections of the bill. The bill outlines mechanisms for covering the costs but does not limit the total budget.

In summary, HR 1691 seeks to streamline the coverage and payment process for breakthrough medical devices under Medicare, ensuring prompt access and appropriate reimbursement to foster innovation and improve patient care. The focus is on facilitating a smooth transition from FDA approval to Medicare coverage, with specific provisions to support the financial aspects through additional payments and adjustments across different Medicare payment systems.

Sen Cassidy Chevron LDT Letter

Senator Cassidy's letter to FDA (6/30/2024) re CHEVRON decision, including impact on FDA-LDT regulation.   Link to original 5p PDF and to Dr Stanley Lo's posting, at bottom.

### Chat GPT 4:

Senator Bill Cassidy's letter to the FDA, dated June 30, 2024, addresses significant changes resulting from the Supreme Court's decision in Loper Bright Enterprises v. Raimondo, which overturned the Chevron deference. This decision mandates that courts no longer defer to federal agencies' interpretations of ambiguous statutory provisions, thereby restoring Congress's and the courts' roles in writing and interpreting laws.

Senator Cassidy urges the FDA to reassess its role in light of this ruling, emphasizing that agencies should not exceed their authority granted by Congress. He highlights specific concerns regarding the FDA's unilateral assertion of jurisdiction over laboratory-developed tests (LDTs) without clear congressional authorization and its disregard for court rulings on the Orphan Drug Act.

The letter calls for the FDA to answer several questions by July 19, 2024, detailing how it plans to adjust its practices to comply with the new legal framework, facilitate greater congressional involvement, and improve responsiveness to oversight and technical assistance requests. Senator Cassidy stresses the importance of the FDA adhering strictly to the laws enacted by Congress and not overstepping its regulatory authority.

Senator Cassidy asks the FDA the following questions in his letter:

1. Compliance with Congressional Laws: How will the FDA adjust its practices to enforce laws as written by Congress, avoiding improper legislation through agency action?

   • Will there be a systematic review of ongoing activities to identify necessary changes?
   • Will any rulemaking activities be paused or stopped in light of the Supreme Court's decision?

2. Congressional Involvement: How does the FDA plan to enhance congressional involvement in policy issues under its jurisdiction? Please specify plans for oversight, briefings, trainings, seminars, and other actions.

3. Briefing Policies: What are the FDA’s current policies on when staff may or may not provide briefings to congressional staff? Under what circumstances would the FDA refuse a briefing request, and where are these policies codified?

4. Responsiveness to Oversight: How will the FDA improve its responsiveness to oversight and technical assistance requests from Congress?

   • How will the process for clearing technical assistance be streamlined to reduce response times?

5. Substantive Responses: Will the FDA commit to providing substantive responses to congressional oversight requests within 30 days of receipt? If not, why?

6. LDT Regulation: How will the FDA apply the Supreme Court’s decision to its actions related to the regulation of laboratory-developed tests (LDTs), given the lack of clear congressional authority?

7. Court Decision Compliance: Following the Catalyst decision regarding orphan drug exclusivity, what criteria does the FDA use to determine when it will follow or ignore a court decision? Include details on how the status of the deciding court (district vs. appellate) and any relevant congressional legislation are considered.

 https://media.licdn.com/dms/document/media/D561FAQGVrwGelokQMg/feedshare-document-pdf-analyzed/0/1719928583497?e=1720656000&v=beta&t=cgoyIsCKdDfzCIpU4BOhipFi-3k7AVT1MrNi5soel-M

https://www.linkedin.com/posts/stanley-lo-a234a05_senator-cassidy-letter-activity-7213903933205827585-Ul1X?utm_source=share&utm_medium=member_desktop