Advanced Medical Strategies - Stacy Borans - Founder of AMS

This podcast episode features Stacy Borans, Co-founder and Chief Medical Officer at Advanced Medical Strategies (AMS), who provides an in-depth look at how technology and clinical expertise are being leveraged to modernize healthcare management, particularly within the self-funded and stop-loss insurance industries. Borans, a former internal medicine physician, details AMS's evolution from a clinical review and denial management service to a software-based platform focused on three core pillars: Payment Accuracy, Risk Assessment, and Business Intelligence. The discussion centers on the need for clinical and financial transparency to manage catastrophic claims effectively, using data-driven tools to assist reinsurers, stop-loss carriers, MGUs, TPAs, and brokers.

AMS’s product suite is designed to address the complexity and high cost of medical care. The foundation includes Predict DX (Diagnosis) and Predict RX (Prescription), which provide cost projections and treatment expectations for over 250 catastrophic diagnoses and expensive drug therapies, respectively. These research directories allow clients to bundle expected costs using a "shopping cart" feature to forecast expenses for an episode of care, typically over 12 months. The more active solutions, Profiler and Census Raider, utilize massive datasets for risk assessment. Profiler ingests client-specific claims data, cleans and sifts it, and ranks members from most to least risky, flagging issues like high-risk maternity or potential gene/CAR T-cell therapy candidates. It also benchmarks client payments against various pricing standards (Medicare, WAC, AWP) and identifies problematic providers or network contracts.

A significant focus of the conversation is achieving true financial transparency. Borans highlights the challenge of synthesizing "dirty data" from over 5,500 hospital charge masters, noting that published charge master prices often differ from the actual billed charges on a claim. AMS standardizes this data to make it intelligible, enabling clients to see where they are overpaying. She advocates for utilizing cash pricing as a strong reference point, noting that while not always the lowest, it is often significantly less than contracted rates. Finally, the discussion touches on the future, emphasizing the immense, though often feared, role of Artificial Intelligence (AI) in providing more robust analytics, looking further down the road than current 12-month projections, and improving diagnostic accuracy, particularly in imaging. Borans stresses that AI should be viewed as a tool to augment human efficiency, not replace it, and calls for the industry to be more proactive in addressing emerging high-cost issues like cell and gene therapies.

Key Takeaways:

• The Marriage of Clinical and Financial Data is Essential: Effective medical cost containment requires combining deep clinical understanding (e.g., standard of care, appropriateness of treatment) with rigorous financial analysis (e.g., benchmarking costs, identifying overcharges) to make informed risk decisions.
• Catastrophic Claim Risk Assessment Requires Specificity: Broad categories like "cancer" are insufficient for accurate risk assessment; tools like Predict DX narrow the focus to catastrophic diagnoses (now 250+) and break down expected treatments and associated costs for precise forecasting.
• Data Cleaning and Standardization is a Core Value Proposition: Raw claims data and published charge master files are often "dirty" and unintelligible; the ability to synthesize, standardize, and present this data in a readable format (as AMS does with its 5,500+ hospital charge master pool) is crucial for actionable business intelligence.
• Charge Master Transparency Reveals Discrepancies: Analysis of hospital charge masters shows that providers sometimes charge more on a claim than their own published, already-inflated charge master price, underscoring the need for continuous auditing and benchmarking.
• Cash Pricing is a Critical Benchmark: While not a universal Panacea, cash pricing offered by providers should be a key jumping-off point for cost negotiations, as payers often reimburse far more than what a patient walking in off the street would pay without coverage.
• Profiler Offers Actionable Intelligence on Group Risk: The Profiler tool allows risk-bearing entities to identify high-risk members and flag potential high-cost events (e.g., gene therapy potential, high-risk maternity) by analyzing historical claims data, enabling proactive underwriting and reserve setting.
• Census Raider Addresses the Small Group Data Gap: For small groups transitioning to self-funding without claims history, Census Raider uses demographic data (age, region, sex) benchmarked against a massive internal database (212 million claimants) to statistically predict the likelihood of various diseases, providing essential directional risk assessment.
• AI's Role in Self-Funding is Strategic and Analytical: AI/Machine Learning will be instrumental in generating more robust analytics, looking beyond 12-month projections, and helping carriers identify which groups will be more profitable, thereby aiding in business acquisition and retention.
• The Industry Must Proactively Address Cell and Gene Therapies (CGTs): The rapid development and high cost of CGTs (especially for prevalent conditions like cancer) require immediate industry solutions beyond temporary coverage exclusions.
• Outcomes-Based Contracts are Necessary for CGTs: To manage the financial risk of multi-million dollar CGTs, the industry must push manufacturers for outcomes-based contracts that include money-back guarantees if the therapy is not durable or fails to achieve promised results.

Tools/Resources Mentioned:

• Predict DX: Software directory for catastrophic diagnosis cost projections.
• Predict RX: Software directory for prescription drug cost projections.
• Profiler: Active software product for claims data analysis, risk ranking, and provider/network benchmarking.
• Census Raider: Software product for small group risk assessment using only census data, benchmarking against historical claimant data.
• Charge Master Data: Pricing data published by hospitals (AMS synthesizes data from 5,500+ hospitals).

Key Concepts:

• Payment Accuracy: Ensuring that the amount paid for a medical service is clinically appropriate and financially justifiable based on benchmarks and contracts.
• Risk Assessment: Evaluating the statistical likelihood and potential cost of catastrophic claims within a self-funded group, crucial for underwriting and setting reserves.
• Business Intelligence (BI): Using data analytics to gain actionable insights into provider performance, network efficiency, and price trends.
• Reference-Based Pricing: A payment model that sets reimbursement rates based on a reference point, often Medicare or a percentage of the cash price, rather than discounted billed charges.
• Cell and Gene Therapies (CGTs): Emerging, high-cost therapies that pose a significant challenge to risk pools due to their price tags and increasing prevalence.