healthcarebriefing.com

Category: Opinion

  • Hospitals Can No Longer Afford to Manage Revenue Cycle After the Fact

    Hospitals Can No Longer Afford to Manage Revenue Cycle After the Fact

    Hospitals Can No Longer Afford to Manage Revenue Cycle After the Fact
    Noah Breslow, CEO, Revecore

    For years, hospital finance teams have run revenue cycle on a familiar loop: a claim goes out, a claim comes back denied or underpaid, and staff spend the next several weeks working it back. That loop was manageable when denial rates held fairly steady and reimbursement was reasonably predictable. Neither of those things is true anymore, and the gap between how revenue cycle is typically run and what today’s payer environment actually demands is widening fast.

    Denials are climbing, and they are climbing for reasons that have little to do with how hard revenue cycle teams are working. The pressure showing up in the numbers is driven by shifts in payer behavior, patient mix, and administrative complexity that no amount of appeals staffing can fully offset. A reactive model for denials is no longer enough. 

    The Reactive Model Is Running Out of Room

    The numbers make the case on their own. Kodiak Solutions, which benchmarks revenue cycle performance across more than 2,300 hospitals, found that providers on its platform lost more than $48 billion in 2025 to final denials and uncollected patient balances, a 25% increase over 2024. Clinical denials tied to prior authorization and medical necessity accounted for nearly all of that jump, and initial denial rates have now risen for five straight years.

    Experian Health’s 2025 State of Claims survey tells a similar story. Forty-one percent of providers now report denial rates above 10%, a figure that has climbed every year since the survey began in 2022, well past the 5% to 10% range HFMA considers a healthy benchmark.

    Payers have grown faster, more automated, and more willing to deny first and let providers make their case on appeal later. Reactive revenue cycle management was built for a world where denials were infrequent, and that world has disappeared.

    Complexity Is Coming From Every Direction

    Payer mix is a large part of why. Fitch Ratings expects the nonprofit hospital sector to keep shifting toward government payers as the population ages. As more claims run through Medicare and Medicaid, more of a hospital’s revenue becomes subject to rules that change frequently and get enforced unevenly across regions and plans.

    At the same time, prior authorization requirements have tightened across commercial and Medicare Advantage plans, and payers are increasingly relying on automated systems to flag claims before a human ever reviews them. Documentation gaps that used to slide through review now get caught immediately, often before a claim leaves the payer’s system.

    Increased prior authorization requirements and the shifting payer mix (including more Medicare Advantage plans) multiply the places where a claim can be delayed, denied, or underpaid. A process built to react to one denial at a time will not keep pace. 

    The Cost of Fixing Problems After They Happen

    Working a denial after the fact is costly. The American Hospital Association estimates that hospitals spent $43 billion in 2025 simply trying to collect payments insurers already owed them for care that had already been delivered. The average hospital now employs roughly 64 administrative and billing staff, about 6.5% of total hospital employment, largely to manage prior authorization, denials, and repeated documentation requests — staff time that goes toward chasing revenue that should have arrived the first time around.

    Some of that revenue never comes back at all. Claims that go unappealed or unresubmitted become permanent losses rather than delayed ones. Kodiak’s analysis of its top-performing organizations recommends directing more resources toward preventing clinical denials rather than just appealing them after the fact. That shift in orientation only works if an organization can see the patterns behind its denials rather than just the individual claims in front of it.

    What a Proactive Revenue Cycle Actually Looks Like

    Proactive revenue cycle management starts when you look at patterns of claim denials vs. the individual claims themselves. That requires analyzing denials and underpayments at the root cause level, tracing a problem back to the payer, the service line, the documentation gap, or the workflow step that keeps generating it, and fixing that step before claims go out the door instead of fighting each one after it comes back.

    Most revenue cycle teams were not built to operate this way. Treating denial and underpayment data as a feedback loop into clinical documentation, coding, scheduling, and patient access is a different discipline than working a queue of appeals, and it gives finance leaders visibility into where revenue is at risk before it turns into a write-off, rather than after. It also changes what success looks like. Recovered revenue still matters, but the number worth watching more closely is how much denial volume never happens in the first place.

    Revenue Cycle Belongs in the Strategic Conversation

    Hospital leaders can control how quickly their organization identifies the root cause of a reimbursement problem and closes it, regardless of demographic shifts, payer mix, or how aggressively insurers adjudicate claims. With costs rising and margins remaining thin across much of the sector, that capability may be the difference between a hospital making or losing money. Health systems that rapidly detect denial patterns and address root causes through operational improvements are the ones most likely to protect their margins over the next several years. These organizations will hold their footing while others spend the next few years chasing revenue they should have collected the first time.

    About Noah Breslow

    As CEO of Revecore, Noah Breslow brings more than 20 years of executive leadership experience, with a focus on driving growth, innovation, and transformation in complex, highly regulated industries. Most recently, Breslow was a Partner at Bain Capital Ventures (BCV), where he led their portfolio support team, built out data-driven investment tooling, and helped incubate two startups at the forefront of applying AI in the insurance claims processing and wealth management industries.

    Prior to BCV, Breslow served as Chairman and CEO of OnDeck, a pioneering online small business lender, where he built the business from its earliest stages, took it public and ultimately facilitated its acquisition. OnDeck used data and analytics to effectively deliver capital at scale to businesses historically underserved by banks. Earlier in his career, Breslow held leadership roles in product, engineering and marketing. He holds a Bachelor of Science in Computer Science and Engineering from MIT and an MBA from Harvard Business School.

  • Pharma’s Billion-Dollar AI Bets May Be Chasing the Wrong Advantage

    Pharma’s Billion-Dollar AI Bets May Be Chasing the Wrong Advantage

    Pharma's Billion-Dollar AI Bets May Be Chasing the Wrong Advantage
    Shashi Shankar, Co-Founder and CEO, Novellia

    2026 will be remembered as the year pharma went all in on AI.

    Since January, nearly every major pharmaceutical company has announced some version of the same thing. GSK signed a five-year foundation-model deal with Noetik. Eli Lilly built a co-innovation lab with NVIDIA. Merck committed a billion dollars to Google Cloud. This month, Novo Nordisk named Amazon Web Services its preferred AI partner. The dollar figures are staggering. And the messaging has been almost identical across all of them: get access to the right model, the right compute, the right discovery platform, and you’ll win the next decade of drug development.

    Then Q2 earnings calls wrapped, and almost no one could point to a measurable return. A faster trial. A failure caught earlier. A drug that reached folks sooner because of what they’d invested. Executives talked about pilots and roadmaps. The announcements are loud but the silence on results is the real story.

    I get why these deals get announced the way they do. The models are really incredible. But when everyone has access to roughly the same model capability, the model stops being an advantage. It becomes table stakes, like electricity. Nobody wins on having electricity. They win on what they build with it.

    A lot of the conversation this year has moved toward the discovery platform or the algorithm on top of the model as the real differentiator. That’s closer. But I’d push it one level further. The real edge is the data the platform is trained and run on. A world-class algorithm trained on incomplete, fragmented, clinically thin data will still give you incomplete, fragmented, thin answers. That’s the layer none of these mega-deals have actually touched.

    To understand why, think about what it actually looks like when a real person tries to navigate serious illness in this country.

    Take someone managing a rare condition who sees six different specialists over four years. Her rheumatologist is in one system. Her neurologist is in another. Two of her earlier records exist at  community clinics she stopped going to. By the time anyone tries to assemble a complete picture of what’s happened to her, half the story is missing or inaccessible. And she’s one of the simpler cases.

    The US has no unique patient identifier. Providers have little regulatory incentive to share records across systems. A single person’s health history can be scattered across every hospital, lab, specialist, and health system they’ve ever seen. Insurance coverage varies by state and plan. Hospitals and their clinics inside the same health system often run on different EHR platforms that don’t talk to each other. Nobody has a complete picture of the folks these drugs are actually designed to serve.

    Claims-based real-world data, the first data type I ever worked with as an intern at Genentech well over a decade ago, are still the primary input for most pharma real-world evidence work and inherit all of that fragmentation. Claims were designed for billing. They can tell you a treatment happened. They can’t tell you what led to it or why. The clinical context lives in physician notes, which are unstructured, inconsistent, and scattered across decades of care. Basic social factors like housing, income, and smoking status are frequently missing. Seventy-eight percent of health organizations say they can’t even locate social-determinant data in a patient’s record after it’s been collected.

    Clinical trials are rigorous by design, and that rigor is also what limits them. They’re built around selected populations, defined observation windows, and specific endpoints. A person enrolled in a six-month trial doesn’t stop being a patient after month six. They get new conditions. They switch doctors. They move. With many rare diseases, patients might see seven different physicians before anyone lands on the right diagnosis. None of that shows up in a trial dataset. Most of it doesn’t show up cleanly in claims either.

    The folks who are hardest to capture accurately in current datasets are usually the people a drug needs to work for the most. Complex conditions. Multiple diagnoses. Long, difficult care journeys. That’s where the data falls shortest, and that’s where the AI answers will be weakest.

    I spent over a decade inside biopharma. I watched incredibly talented teams work hard with an incomplete picture of the people they were trying to help. That gap was always there. What’s new is the scale of investment now being built on top of it.

    The next real competitive edge in this industry will come from the less glamorous work of actually fixing the data. Connecting fragmented records. Capturing the clinical detail sitting in unstructured notes. Building datasets that reflect the full reality of the folks who will rely on a new medicine to save their lives, including the ones that don’t fit neatly into a trial population.

    That work is harder to announce. It doesn’t generate the same headlines. It’s also what determines whether these AI investments eventually deliver.

    The only thread that runs through every part of the care journey is the patient. Every physician visit, every lab, every specialist, every prescription. When you stitch the data around that reality, with the patient’s knowledge and consent, the fragmentation starts to resolve itself. That’s a fundamentally different starting point than what most of the industry is working from today.

    There are real people on the other side of this. A father whose daughter just got a life-changing diagnosis that should have come four years earlier, and has to reckon with what those four years might have cost her. A family sitting in a waiting room, wondering whether the new drug their mom just started is actually working. These are the people whose care journeys are scattered across systems. Getting the data piece right is how the industry actually reaches them, in time, with the right answer.

    About Shashi Shankar

    Shashi Shankar is Co-Founder and CEO of Novellia. He spent over a decade at Genentech and Roche in medical affairs, health economics, and digital health innovation.

  • Medicare Policy Shouldn’t Be Made in the Shadows

    Medicare Policy Shouldn’t Be Made in the Shadows

    As a rheumatologist, I treat rheumatoid arthritis (RA) and other complex autoimmune diseases. If you have or happen to develop one of these diseases, I am thankful that science has delivered amazingly effective targeted therapeutics and biologics in recent decades. While highly effective, these treatments come with a high economic cost, so I have grown accustomed to daily battles with commercial insurance plans to get working-age patients the treatments they need. While horror stories abound regarding commercial insurers, Medicare has traditionally been a more predictable partner for my older patients. Medicare reimbursement is low — an issue worthy of a separate commentary piece — but comes on time, typically without the hassle and administrative delays of prior authorizations, assuming we use our therapeutics within FDA-approved dosing and indications.

    On top of these existing challenges here in the Midwest, providers recently won a battle we did not expect to have to fight with a Medicare administrative contractor (MAC). The story deserves scrutiny from legislators and regulators nationwide. 

    Medicare beneficiaries rightly assume, as have I, that policy spells out the services they are entitled to receive. Lawmakers in Congress establish patients’ benefits in law, while the Centers for Medicare & Medicaid Services (CMS) develops the national rules and policies to implement them. MACs fit into this process by administering those rules regionally (with some discretion), but they are not supposed to privately create new substantive conditions of payment.

    Recently, the MAC overseeing Kentucky and Ohio began auditing and denying claims for intravenous Orencia, a biologic drug used to treat RA, citing a “lack of medical necessity.” The policy affected more than a hundred patients who had mostly been on Orencia for a decade or more. These patients were forced to stop or delay treatment or switch therapies, which resulted in serious RA flares. MAC administrators had decided that most patients on intravenous Orencia, covered under Medicare Part B, should instead receive subcutaneous Orencia, covered under Medicare Part D and often at substantially higher out-of-pocket cost. 

    The decision was made without a formal notice-and-comment process. In fact, this requirement does not even appear in the Medicare guidance cited for this decision. Worst of all, it effectively forced dozens of patients off a life-changing therapy.

    Thanks to outreach from clinicians, national advocacy organizations, angry patients, and congressional representatives, this policy was walked back. Or at least, we think so. There was no announcement of a reversal. Instead, the MAC covering Kentucky and Ohio quietly revised a fact sheet on its website, removing language that preferred subcutaneous over intravenous dosing. 

    This whiplash has been devastating to my own small clinic, however, as the MAC continues to withhold the equivalent of roughly three payrolls’ worth of payments for treatments we rendered in good faith during this period. They have also not answered repeated inquiries about whether denials issued under the now-removed standard will be reversed. 

    This situation exposed several problems that need to be addressed before this happens to other MACs, Medicare beneficiaries and clinicians:

    1. The current system allowed one medical director’s opinion to acquire the force of Medicare policy without an effective check. This violates the Supreme Court’s decision in Azar v. Allina, which limits the government’s ability to create substantive Medicare payment standards through informal guidance. Yet it still took months of work, worry, and countless hours distracted from providing clinical care to get the issue elevated to a level where the policy was reconsidered. 

    2. There is inadequate accountability and little transparency within MAC operations. After an initial call with the MAC medical director to raise this issue, we went for weeks with response and no clue as to where our appeal stood. Providers didn’t know how to “correctly” care for our affected patients. When the disputed language did quietly disappear from the fact sheet, there was no public explanation, formal announcement, or directive regarding claims already denied. 

    3. There is no clearly identified chain of command to move a critical issue of patient harm from a regional MAC to CMS. As an experienced advocate, I leveraged my relationship with my congressional representative and the American College of Rheumatology to elevate this issue to CMS, but what if I hadn’t had those relationships? Our system should not require physicians to become experts in Medicare law and policy just to ensure the Medicare system follows its own rules.

    Medicare beneficiaries deserve better. While in this case we’ve been able to protect access to intravenous Orencia, this experience exposed flaws that extend far beyond one drug or one MAC contractor. We should all be concerned that MACs are increasingly making unilateral decisions that negatively impact patient access. Medicare policy should be transparent and include appropriate notice and stakeholder input. And when a contractor gets it wrong, there should be a clear and rapid way to stop the harm to patients, their relationship with their doctor and the doctor’s practice. A patient’s access to Medicare-covered care should never depend on whether their physician can find someone in Washington willing to intervene. Something must change.

    Author bio:

    Dr. Chris Phillips is an American College of Rheumatology leading rheumatologist and owner of Paducah Rheumatology.

    Photo: Stas_V, Getty Images

  • Why Calling ICD-10 a Diagnosis Is Healthcare’s Costliest Design Flaw

    Why Calling ICD-10 a Diagnosis Is Healthcare’s Costliest Design Flaw

    Calling ICD-10 a Diagnosis Is Now a Design Flaw
    Jay Anders, MD, Chief Medical Officer at Medicomp Systems

    Healthcare software colleagues of mine often describe a recurring discussion they have with their outsourced development teams. They recount that when they try to explain the difference between a billing diagnosis and a clinical diagnosis, the engineers on the other end deliver a common platitude: “a diagnosis is a diagnosis.” 

    That answer is defensible in ordinary English. In healthcare data, however, it is wrong in a way every team that accepts it inherits. The formal name of the “diagnosis” system is the International Statistical Classification of Diseases and Related Health Problems, Tenth Revision (ICD-10). Statisticians created it in 1893 to count causes of death, and around 1938, leaders suggested that the codes might be useful to health insurers. Medicare then tied hospital reimbursement to those codes in 1983, and the rest is history.

    Accordingly, I have started referring to ICD-10 as a billing category rather than a diagnosis code. Colleagues tell me the phrasing sounds pedantic, but we have all witnessed what has happened due to this lack of differentiation. Software analysts carry the loose usage into product requirements documents, data dictionaries and integration specifications. Developers then build software that treats a category as though it were a clinical finding. We are all suffering the consequences of asking a statistical instrument to carry the complexity and nuance within clinical meaning.

    Grouper or Splitter?

    The vocabulary distinction reminds me of when clinical informaticists once asked each other whether they were groupers or splitters. Groupers gather related conditions under a shared heading, while splitters separate them down to the specific entity. The people who built the ICD chose grouping because a statistical classification exists to produce comparable counts across whole populations. Grouping is what makes an epidemiological instrument work, but a clinical one fail.

    Conversely, clinical care has continued to split because treatment now turns on distinctions a single code cannot carry. One example is ICD-10 code G60.0, hereditary motor and sensory neuropathy. Coders assign that single category to Charcot-Marie-Tooth disease (CMT) and to its near relatives alike. Yet researchers have now linked more than 100 genes to CMT alone, and dozens of clinically distinct diseases are filed under that heading, each with its own inheritance pattern and treatment path. A claim clears on G60.0 without difficulty, while a physician reading G60.0 learns almost nothing.

    Maintainers cannot resolve this by adding codes. They added 487 new diagnosis codes in the fiscal year 2026 update, which all offer important detail. Even so, a larger classification system is still a classification system rather than a clinical vocabulary. 

    Where Therapy Already Split

    Pharmaceutical manufacturers have already committed to the splitter’s position, a decision their product names record. Anyone watching evening television will hear a run of medications ending in -mab or -nib. Chemists apply the first stem to a monoclonal antibody engineered against a single protein, the second to a small molecule built to inhibit a specific kinase. 

    Eventually, however, even these naming conventions were not specific enough. In October 2021, the World Health Organization retired the -mab stem and replaced it with four stems because manufacturers had exhausted the available names. Concurrently, the FDA endorsed greater specificity through new drug approvals. Personalized medicines accounted for roughly 36% of new therapeutic molecular entities in 2025, the sixth consecutive year they exceeded a third of new approvals. Therapy is now chosen at the level of a protein, while the diagnosis pointing toward it is still recorded as a bucket.

    Compiling the Confusion

    AI-software vendors have supercharged the vocabulary problem operationally through ambient documentation. These solutions listen to a visit, infer a diagnosis and produce an ICD-10 code. That code is then treated as the diagnosis because that is the word everyone uses. Independent testers have measured the best general-purpose models at roughly 50% to 59% accuracy on medical coding. Consequently, a model that cannot determine the specific condition selects the broader code, presenting the clinician with a settled answer that is likely less accurate and certainly less informative.

    Unfortunately, many vendors also group the alternate phrasings listed beneath a code as synonyms for it, which might be acceptable for billing, but is misleading for care. Several of those phrasings name distinct diseases with different genetics and different treatment. With only the category recorded, every downstream clinician may need to conduct their own time-consuming and costly investigation to arrive at a real diagnosis.

    Writing the Distinction Into Systems

    On a macro-level, fixing the problem must involve everyone in healthcare consistently differentiating ICD-10 codes as billing categories, both when speaking and writing. On a micro-level, software analysts should also distinguish the billing category and the clinical diagnosis as separate data elements. Similarly, evaluation teams should ensure a clinically specific diagnosis exists alongside the code captured in a way that a downstream platform can access and interpret it. 

    Until then, however, an evidence-based clinical knowledge layer can be integrated into electronic health record systems to import the specific diagnosis in the free text as a computable concept already mapped to its billing category, so both are recorded. 

    As a result, reimbursement is unaffected, but, more importantly, the next clinician then sees the clinical explanation alongside the code. So, in the past, when G60.0 (hereditary motor and sensory neuropathy) alone reported almost nothing, the additional detail now helps the clinician understand the type of hereditary neuropathy present to inform their decisions, potentially avoiding repetitive testing or ineffective therapies. The patient then receives the right treatment sooner, one that may never have been pursued if the condition remained obscured behind a vague label.

    About Jay Anders, MD

    Dr. Jay Anders serves as the Chief Medical Officer of Medicomp Systems, where he plays a pivotal role in product development and acts as a liaison to the healthcare community. He champions the use of technology to empower clinicians, rather than hinder them.

  • When Cybercriminals Impersonate Care: Why Trust Is Part of the Treatment

    When Cybercriminals Impersonate Care: Why Trust Is Part of the Treatment

    When Cybercriminals Impersonate Care: Why Trust Is Part of the Treatment
    Cindi Carter, Global Chief Information Security Officer, Check Point Software

    For years, healthcare organizations have encouraged patients to become more digitally connected to their care.

    Use the patient portal. Check your test results online. Respond to appointment reminders. Communicate electronically with your care team. Use digital tools to take a more active role in managing your health.

    Patients listened.

    That progress has made digital engagement an important part of the healthcare experience. Unfortunately, cybercriminals understand that relationship, too.

    Recent phishing campaigns impersonating MyChart demonstrate an important evolution in healthcare cyber risk. Attackers are using fraudulent emails, text messages, phone calls, and websites designed to look like familiar healthcare communications. Some promise free Medicare kits or health-related products. More concerning schemes have used fake MyChart websites and fabricated medical information to create urgency around supposedly critical test results.

    The technology may be fraudulent, but the emotion it creates is very real.

    Imagine receiving a notification that appears to come from your healthcare provider telling you that abnormal laboratory results require immediate attention. In that moment, most patients aren’t thinking like cybersecurity professionals. They’re thinking like patients.

    What did they find? Is something wrong? What do I need to do?

    That is precisely what makes these attacks so effective.

    Cybercriminals Aren’t Just Exploiting Technology. They’re Exploiting Trust.

    Healthcare has always operated on trust. Patients trust clinicians with deeply personal information and life-changing decisions. Increasingly, they must also trust the digital systems through which healthcare is delivered.

    That makes cybersecurity part of the patient experience.

    When an attacker impersonates a patient portal, the immediate objective may be to steal credentials or financial information, or to install malware. But there is another consequence healthcare leaders should consider: every convincing impersonation can make patients a little less certain about whether the next legitimate communication can be trusted.

    That matters.

    If patients become afraid to click an authentic appointment notification, access a test result, or respond to a message from their care team, the consequences move beyond information security. Security friction can become healthcare friction.

    Trust is part of the treatment.

    Protecting it requires healthcare organizations to think beyond defending their own infrastructure. The organization’s digital identity, and the communications patients associate with it, must also be protected.

    Healthcare Organizations Need to Protect the Digital Relationship

    The first priority is prevention. Healthcare organizations should continue strengthening email security, identity protections, multifactor authentication, domain protections, and monitoring for brand impersonation and lookalike domains. But technology alone is not enough.

    Organizations should establish recognizable and consistent patterns for patient communications. Patients should know how their healthcare organization communicates, which domains and phone numbers it uses, what information it will request electronically, and, equally important, what it will never request.

    Healthcare organizations should also make the trusted path easy to find.

    Instead of asking patients to determine whether every link is authentic, teach a simpler behavior: when something feels unexpected, urgent, or unusual, leave the message and access the patient portal through the healthcare organization’s official app or known website.

    Security, communications, digital health, patient experience, and clinical leadership should also have a coordinated response plan for patient-targeted impersonation campaigns. When a campaign emerges, organizations need to communicate quickly and consistently across their websites, patient portals, call centers, clinical practices, and other trusted channels.

    This is an important distinction: an organization does not need to have suffered a breach for a cyberattack to affect its patients. Someone impersonating your organization can create risk for the people you serve even when your own systems remain secure.

    Patients Have a Role, Too

    Patients should approach unexpected healthcare messages with healthy skepticism, particularly those that create urgency, offer free products, or request personal, insurance, financial, or login information.

    A few habits can dramatically reduce risk:

    • Access MyChart through the official mobile application or the healthcare provider’s known website rather than through an unexpected message.
    • Never provide passwords or verification codes by email, text, or phone. Legitimate MyChart support will not request them through those channels.
    • Be suspicious of unexpected offers for free healthcare products, Medicare kits, prizes, or rewards.
    • Never follow instructions from a website telling you to run commands, install software, or bypass a computer security warning.
    • If a message involves an alarming diagnosis or unexpected medical result, verify it through the official patient portal or contact the healthcare provider directly.

    Patients who believe they interacted with a fraudulent message should change their portal credentials, review their contact information and account activity, and contact their healthcare organization’s support team.

    But we should be careful not to place the entire burden on patients.

    Modern phishing attacks are becoming increasingly sophisticated. Generative AI makes it easier to produce convincing language, personalize messages, and replicate trusted communications at scale. “Look for spelling mistakes” is no longer an adequate cybersecurity strategy.

    The safer approach is to make verification habitual and simple.

    Protecting Confidence in Digital Care

    Healthcare’s digital transformation depends on patients being willing to engage with technology.

    We want patients checking their records. We want them communicating with clinicians. We want them using digital tools to schedule appointments, manage medications, review test results, and participate more actively in their care.

    Cybersecurity therefore has a responsibility beyond protecting systems and data. It must help preserve patients’ confidence in those interactions.

    The MyChart phishing campaigns offer an important reminder for healthcare leaders: cybercriminals will exploit not only our vulnerabilities, but also the relationships and trusted brands we have worked for years to build.

    The answer isn’t to make patients afraid of digital healthcare.

    It’s to make trustworthy digital healthcare easier to recognize and harder to impersonate.

    Because in an increasingly connected healthcare ecosystem, protecting the patient means protecting the technology, the communication, and the confidence that connects them.

    Trust is part of the treatment.

    About Cindi Carter 

    Cindi Carter is a global, multi-industry Cybersecurity and Information Technology Executive who consistently delivers the optimal outcome. As a transformational leader from startups to enterprises she excels at building cybersecurity practices in highly regulated industries, turning strategic goals into action, and highly collaborative engagement to lead the organization in managing cyber risk. At Check Point Software Technologies, Cindi is a Global Chief Information Security Officer in the Office of the CISO, leading Check Point’s Healthcare Center of Excellence where human safety is essential to care. With over two decades in the healthcare and financial industries, Cindi’s purpose is deeply rooted in human safety, bringing together the capabilities that protect the security and privacy of each individual.

  • Telehealth Was Built for Two. Interpreted Care Requires Three

    Telehealth Was Built for Two. Interpreted Care Requires Three

    Philip Rosen, Founder and Managing Director of Capital Linguists

    Telehealth was supposed to widen access. For patients who do not speak English, it narrowed access.

    An analysis of California Health Interview Survey data published in Health Affairs found that patients with limited English proficiency used telehealth at a rate of 4.8 percent, against 12.3 percent among proficient English speakers, roughly half the odds even after adjusting for other sociodemographic factors. 

    A systematic review by researchers at the University of North Carolina’s Sheps Center for Health Services Research reached a starker finding: every one of the seven studies examining telehealth by modality reported significantly lower video use among patients with limited English proficiency. Of the roughly 25.6 million people in the United States with limited English proficiency, those who do connect are disproportionately routed to audio-only care, the modality where interpretation is hardest and clinical observation is weakest.

    Here is what competence looks like in practice.

    Book the language, not just the appointment

    Language needs must be captured as a structured field at scheduling and must carry an interpreter reservation with it. Two failures are near-universal. First, preferred language is recorded but never triggers anything downstream. Second, the language is recorded too coarsely  “Chinese” instead of Cantonese or Mandarin, “Arabic” without dialect, “Spanish” without noting an Indigenous first language behind it. A mismatched interpreter burns the appointment slot as thoroughly as no interpreter at all.

    Book by encounter type as well as language. A 15-minute medication check and a 45-minute oncology consult are different assignments, and rare languages need lead time that on-demand queues cannot always deliver.

    The interpreter needs a dedicated participant link not the patient’s link forwarded, and not a phone line bridged into a video visit. Bridging is where three-way encounters most often collapse: the interpreter cannot see the patient, and roughly half of what an interpreter relies on disappears.

    That is not only a quality problem. The technical standards carried into Section 1557 require a sharply delineated image large enough to show the faces of both the interpreter and the person being served, along with real-time video free of lags or irregular pauses. The rule explicitly bars reliance on low-quality video remote interpreting, and OCR’s December 2024 Dear Colleague letter signaled that these obligations are active and enforceable. An interpreter on a phone line is a compliance exposure, not a workaround.

    Where the platform allows it, pin the interpreter’s video so the patient can see them throughout, and confirm the connection before the patient joins.

    Spend sixty seconds on the pre-session

    The single highest-yield habit in interpreted care costs one minute. Before the clinical conversation begins, the clinician and interpreter align on the encounter: the visit’s purpose, any specialized terminology likely to come up, whether difficult news is expected, and how the interpreter should signal a need to pause.

    This is also where the interpreter states the ground rules to the patient  that everything said will be interpreted, that nothing will be omitted or added, and that the encounter is confidential. Patients who understand this speak more freely. Patients who do not tend to compress their answers.

    Run the visit in the first person

    Speak directly to the patient, not to the interpreter. “Where does it hurt?” not “Ask her where it hurts.” The interpreter renders in the first person. This is standard practice, and it is not a stylistic nicety: third-person framing pushes the patient out of their own encounter and invites the clinician to build rapport with the wrong person.

    Deliver one or two sentences at a time and pause. Long uninterrupted passages force the interpreter to summarize, and summarization is where clinical detail is lost. Expect the interpretation to take longer than the original. Build the extra time into the slot rather than accelerating to recover it.

    Two habits matter especially on video. Silence carries no visual explanation, so narrate what you are doing when you turn to the chart. And when the interpreter requests a clarification, treating it as a quality signal rather than an interruption  it usually means a term has no clean equivalent, which is precisely the moment a misunderstanding would otherwise pass unnoticed.

    Document the interpretation, not just the visit

    Record the interpreter’s name or ID, the language and dialect, the modality, and the duration. Most organizations cannot currently stratify outcomes by language because this data never reaches the chart, which makes a known disparity invisible to the quality committee that is accountable for it.

    Teach-back is where a language-discordant visit is verified or lost. Ask the patient to explain the plan in their own words, through the interpreter, before anyone disconnects. Written follow-up should be reviewed by a qualified human, the 2024 rule requires exactly that for critical communications produced with machine translation.

    The system-level point

    None of this is difficult. It is unassigned. Interpreter integration usually belongs to no one: not the telehealth platform team, not the clinical informatics group, not the compliance office that owns the language access plan on paper.

    Health systems now buying ambient documentation, AI translation, and virtual-first care are making architectural decisions about a population that is already using video least. Deciding who owns the three-way visit before those tools are configured rather than after is the cheapest equity investment on the roadmap.

    About Philip Rosen

    About Philip Rosen

    Philip Rosen is the Founder and Managing Director of Capital Linguists, a US-based language services firm providing certified interpreting and translation across more than 210 languages. He works with healthcare systems, government agencies, and academic institutions on language access in high-stakes settings.

  • Health Systems Can’t Optimize What They Can’t See: TeleTracking on Ambulatory Capacity, Leakage, and Operational AI

    Health Systems Can’t Optimize What They Can’t See: TeleTracking on Ambulatory Capacity, Leakage, and Operational AI

    Health Systems Can’t Optimize What They Can’t See: TeleTracking on Ambulatory Capacity, Leakage, and Operational AI
    Michelle Skinner, MBA, BSN, RN, Chief Clinical Executive, TeleTracking

    For decades, health systems have invested in creating operational visibility inside the hospital. Leaders are accustomed to tracking bed capacity, anticipating demand, identifying bottlenecks and coordinating the movement of patients and resources within the four walls of the hospital.

    But healthcare no longer begins and ends at the hospital doors.

    Care continues to move into physician practices, specialty clinics, imaging centers, ambulatory surgery centers, and at home with virtual care. Yet many health systems still lack the same enterprise-level operational visibility at these settings as they do inside the hospital. The result is a gap in ambulatory visibility that limits patient access, threatens network integrity, and stifles revenue growth.

    Research has shown that missed appointments alone cost the U.S. healthcare system approximately $150 billion annually. At the same time, McKinsey has found substantial unused capacity within employed physician networks, and demonstrated the financial value health systems can realize by improving access and utilization.

    The challenge is not necessarily a lack of capacity. Often, it’s a lack of visibility to where that capacity exists and the operational ability to act on it.

    The patient journey has changed. The operating model must follow.

    Historically, inpatient and ambulatory care developed as distinct operating environments. Physician practices were often independent organizations with their own technology, workflows and processes. As health systems acquired practices and expanded their outpatient footprints, many of those operations remained relatively independent.

    The result today can be an enormous network of care supported by fragmented operational systems.

    A scheduler may need to navigate multiple platforms to determine where a patient can be seen. An executive looking at an access KPI may have to ask analysts or operational leaders to determine which region, location, specialty or provider is causing the problem. A referral coordinator may know a patient needs specialty care but lack visibility into availability across the entire network.

    The information exists. It simply exists in too many places.

    A patient leaving the hospital may need primary care, a specialist, imaging, laboratory testing and other services. Each represents another point at which the health system can either maintain that person as a patient or risk losing them.

    In many organizations, schedulers and referral coordinators work across multiple systems simply to find appropriate appointments for a patient. The result is fragmentation that limits the ability to identify the appointment that best meets a patient’s needs based on availability, location and provider type.

    That fragmentation matters because an ambulatory visit can no longer be viewed as separate from the overall patient journey. 

    When patients leave the network, revenue follows

    Consider a patient discharged from the hospital with a referral to a specialist.

    The health system has already invested in that patient’s care. Clinicians understand the patient’s history, records are available, and maintaining continuity within the network benefits both the patient and the health system.

    But what happens when the preferred specialist can’t see the patient for six weeks?

    Without network-wide visibility, a scheduler may not know that another location has an opening next week. The patient only knows that they can’t be seen for six weeks and looks elsewhere to continue their care.

    For patients managing a new diagnosis or recovering from a complex procedure, that gap is not simply inconvenient. It creates clinical risk that the health system is no longer positioned to see or manage.

    Once that happens, the health system risks losing much more than one appointment.

    The specialty visit may generate imaging, procedures, follow-up appointments or additional services. Losing visibility into the patient’s care can also make it harder to manage outcomes under value-based care arrangements.

    The question, therefore, isn’t simply, “Do we have an appointment available?” It should be “Where across our entire network can we best meet this patient’s need?”

    Capacity you can’t see is capacity you can’t use

    One of the problems of ambulatory access is that patients can face long waits for appointments while capacity simultaneously goes unused.

    McKinsey quantified the problem in an analysis of more than 10 health systems with large employed-physician organizations. Across those organizations, actual, or retrospective, appointment-slot utilization ranged from 48% to 93%, with a median of just 70%. McKinsey also found a difference of approximately 20 percentage points between prospective and retrospective fill rates, driven by cancellations that were not backfilled, late cancellations and no-shows.

    That distinction is critical. A schedule may appear full when viewed prospectively, but that doesn’t always mean the available capacity translates into completed patient visits. Without visibility into actual utilization, leaders can overestimate how effectively capacity is being used.

    At enterprise scale, this becomes increasingly important. A health system may have hundreds or thousands of providers spread across dozens of locations. One practice may have a three-week wait while another has appointments available. Without network-wide operational visibility, leaders and schedulers may not recognize that imbalance in time to act.

    The result is more than an efficiency problem. Patients who can’t get timely care are likely to seek it outside the network, taking not only the immediate encounter but the imaging, procedures, specialty care and future services with them.

    Visibility changes the growth equation

    Limited visibility also makes it harder to determine where health systems should invest.

    When access is constrained, the instinct may be to add providers, extend clinic hours or build additional locations. But those decisions should begin with a more fundamental question: Is there truly insufficient capacity, or is existing capacity distributed inefficiently across the network?

    One location may be overwhelmed while another has unused appointments. A specialty may appear constrained across the enterprise when the real bottleneck exists within only a handful of providers or appointment templates.

    The data needed to make those distinctions often already exists, but it may be fragmented across multiple systems, reports and departments. Bringing that information together creates an opportunity not only to identify access and capacity constraints, but also to make better decisions about where service lines should expand, where providers should be deployed and where resources may be underutilized.

    Growth should begin with understanding the capacity you already have.

    From visibility to action

    The next evolution of ambulatory operations is not simply another dashboard, it’s complete operational orchestration.

    Leaders need operational intelligence that allows them to move from seeing a problem to understanding its cause and then being able to act on it.

    Imagine an executive seeing that days to access have increased and immediately drilling down by region, location, department and provider. At the same time, an operator could see that one clinic is approaching capacity while another has availability and redeploy resources accordingly. A scheduler could tell a patient, “This location can’t see you for three weeks, but another location 20 minutes away can see you Tuesday.”

    Today, gathering that level of information can require multiple reports and hours of analysis. The opportunity is to surface that information immediately for executives, managers and schedulers so they can make decisions, open capacity and better navigate patients across the network.

    Artificial intelligence is the next step in this evolution. Rather than simply identifying a capacity constraint, purpose-built operational orchestration platforms can analyze historical and anticipated demand and recommend actions like adjusting templates, shifting resources or adding provider coverage where demand warrants it while keeping the operator in control of the decision.

    That moves ambulatory operations from reporting what happened to helping teams decide what should happen next.

    Building a boundaryless health system

    The opportunity ultimately extends beyond ambulatory care.

    As care continues moving into outpatient, and eventually virtual home settings, health systems need to stop viewing the patient journey through organizational boundaries. The goal should be a truly boundaryless operating model capable of seeing demand, capacity and patient movement wherever care occurs.

    We already understand the value of this kind of visibility inside the hospital. The next challenge is extending it across the rest of the health system.

    That requires more than technology. It requires people, process and technology working together around a shared operational picture. It requires leaders prepared to use real-time data and increasingly AI-driven recommendations to make faster, more informed decisions.

    Most importantly, it requires viewing ambulatory care not as a collection of individual clinics, but as an interconnected enterprise and an integral part of the complete patient journey.

    The billions lost to missed appointments, unused capacity, patient leakage and inefficient utilization are symptoms of a larger challenge: health systems can’t optimize what they can’t see.

    Closing the ambulatory operational visibility gap gives organizations an opportunity to change that equation, connecting patients to the right care at the right time and location, making better use of existing resources, protecting network integrity and building a more sustainable platform for growth.

    As more care moves beyond the hospital, enterprise-wide visibility will no longer be optional. It will be fundamental to how health systems compete, grow and care for their patients.

    About Michelle Skinner

    Michelle Skinner is the Chief Clinical Executive at TeleTracking Technologies, where she brings together clinical insight and operational strategy to help health systems unlock capacity, expand access, and drive scalable growth. A former trauma and critical care nurse, Michelle has led enterprise transformation initiatives across hospital operations, service line development, and patient flow redesign. Her career spans the front lines of care to the executive table—making her a trusted partner to health system leaders navigating complexity and change. She is committed to solving the structural barriers that limit care delivery and believes that rethinking capacity is key to building a more resilient, responsive, and equitable health system.

  • Equitable Care Depends on Intelligent Infrastructure: Actuarial AI and Value-Based Risk Contracts

    Equitable Care Depends on Intelligent Infrastructure: Actuarial AI and Value-Based Risk Contracts

    Najib Jai, MD, Chief Operating Officer, Arbital Health

    Equitable access to health care is more than just about geographical coverage. It depends on the healthcare system’s ability to identify risk early, intervene intelligently, and sustain those interventions across the most clinically and socially complex populations.

    This is why many value-based care (VBC) models struggle. Underserved Medicaid and Medicare populations frequently experience a disproportionate burden of chronic diseases, behavioral health challenges, transportation barriers, food insecurity, language gaps, and disconnected care journeys. Once patients present in the emergency department or experience an avoidable admission, the opportunity for lower-cost, lower-acuity care is often less possible. 

    The challenges are well understood – most organizations are still operating with lagging data, subsequent incomplete visibility into contract performance, and limited ability to connect contractual risk with clinical action in real time. As healthcare continues shifting toward value-oriented reimbursement models, equitable care delivery increasingly depends on infrastructure capable of turning population-level data into timely, actionable clinical and operational decisions.

    One Provider’s Experience

    A large provider organization that serves roughly 141,000 Medicaid and Medicare patients recently confronted this reality. Nearly 45% of its patients managing diabetes were also navigating multiple comorbidities, creating a population vulnerable to acute exacerbations, hospitalizations, and readmissions.

    The organization faced significant operational headwinds common to many serving underserved communities. Payer data often arrived months late, making it difficult to understand why contracts were under-performing or which patients were trending toward acute episodes before costs escalated. The organization was effectively trying to manage complex value-based risk arrangements while looking backward through incomplete data.

    Unfortunately, this dynamic is not unique; across healthcare, providers serving high-risk populations are frequently asked to manage increasingly sophisticated contracts without the same actuarial visibility historically available to payers. The result is reactive care management instead of proactive intervention, particularly for populations where earlier outreach can make the greatest difference. Actuarial AI and predictive intelligence can help alter VBC’s trajectory by offering a more comprehensive, forward-looking framework. 

    Traditional Predictive Models Aren’t Up to the Challenge

    Traditional predictive models often focus narrowly on utilization forecasting or retrospective reporting. The next generation of actuarial AI systems is beginning to amalgamate claims data, contract logic, demographics, utilization trends, and clinical workflows into a more operationally useful framework. Instead of simply identifying what happened, these systems can help organizations understand what is likely to happen next, and where intervention opportunities exist before costs spike.

    The Importance of Operationalizing Insight 

    Risk presents heterogeneously across communities, age groups, languages, comorbidity profiles, and care access patterns; a one-size-fits-all intervention strategy inevitably leaves gaps. Predictive intelligence that can stratify risk dynamically across diverse patient populations allows providers to target outreach more precisely and allocate finite care management resources where they can have the greatest impact. This reduces costs as well as the friction that prevents appropriate care from happening proactively.

    Much like with the technology that has preceded it, we’ve learned that AI adoption in healthcare only succeeds when it streamlines and is integrated into existing workflows rather than creating new administrative burdens. Physicians are not resistant to tools that help them, just to those that add unnecessary steps to already compressed processes and cluttered workdays. Organizations most likely to improve outcomes for vulnerable populations will not necessarily be the ones with the most sophisticated dashboards, but the ones capable of operationalizing insight directly into care delivery. If AI can surface which patients are at risk for avoidable admissions, identify the clinical and social drivers contributing to that risk, and simplify the pathway for intervention, then providers can act earlier and more impactfully.

    Actuarial AI in Action

    The experience of the provider organization mentioned earlier offers a practical example. After implementing actuarial AI tools, they were able to analyze utilization patterns and contract performance in real time, uncovering insights that traditional reporting had obscured. While initial payer data suggested pediatrics and OB were driving readmissions, deeper analysis identified hypertension as a leading root cause of avoidable hospital utilization. That insight materially changed their intervention strategy.

    The system launched a hypertension management initiative specifically targeting Medicaid and Medicare patients with complex comorbidities, embedding prompts into clinical workflows and expanding outreach to previously unengaged patients within its risk contracts. Multi-lingual engagement campaigns helped convert previously disconnected patients back into care.

    The organization moved from reacting to adverse events after they occurred to identifying risk trajectories earlier enough to intervene. That is the promise of combining actuarial AI with VBC infrastructure: strengthening the system’s ability to consistently deliver appropriate care at scale.

    Transparency and Trust Are Critical Ingredients

    There is a growing tension between regulated clinical AI and the informal use of ungoverned AI tools across healthcare environments. Across the industry, leaders agree that black-box outputs cannot become the foundation for clinical, operational, or financial decision-making.

    For AI-driven VBC models to meaningfully support underserved populations, providers must understand how risk is being calculated, how interventions are prioritized, and how recommendations align with real-world patient needs. Otherwise, the industry risks replicating existing inequities inside more sophisticated systems.

    The Future of Equitable Care

    The future of equitable care delivery will depend on whether healthcare organizations can unify clinical intelligence, actuarial rigor, and operational execution into a single framework that supports both outcomes and sustainability. Healthcare already possesses enormous volumes of claims, utilization, demographic, and clinical information. The problem has been the inability to synthesize and operationalize that information quickly enough to change patient trajectories while there is still time to act. Actuarial AI and predictive intelligence are beginning to close that gap.

    As VBC continues to evolve, the organizations best positioned to improve equity may be the ones that can transform data into earlier intervention, precise outreach, and more informed clinical decisions, not just for the easiest patients, but for the populations that healthcare has historically struggled to serve well.

    About Najib Jai, MD,

    Dr. Najib Jai, MD, is the Chief Operating Officer of Arbital Health. His career evolved from supporting value based care (VBC) models through private equity investing to joining Oak Street Health to lead specialty care strategy, improving outcomes for patients with complex, multimorbid conditions. He later co-founded Conduce Health, pioneering the first multi-specialty VBC platforms that match the right specialist with the right patient, considering their social drivers of health. Through predictive modeling and innovative contracting structures, his work improved care coordination and outcomes for high-risk populations. Now at Arbital Health, Dr. Jai continues to influence the industry by embedding clinical and operational insight into its Actuarial AI infrastructure, which enables payers and providers to identify the highest-risk members and their emergent needs to drive positive outcomes at scale.

  • Clinical Trial Site Selection and AI: Look-Alike Modeling Across Real-World Data and Care Delivery Signals

    Clinical Trial Site Selection and AI: Look-Alike Modeling Across Real-World Data and Care Delivery Signals

    Clinical Trial Site Selection and AI: Look-Alike Modeling Across Real-World Data and Care Delivery Signals
    Aaron Cohen, Vice President, Data Strategy at Definitive Healthcare

    Site selection and enrollment failures are persistent challenges for life sciences organizations. A Tufts Center for the Study of Drug Development analysis of nearly 16,000 investigative sites across 151 Phase II and III global trials found that nearly half of all selected sites either failed to enroll a patient or under-enrolled.1 Site-selection decisions commonly draw on historical performance indicators like prior trial participation and past enrollment, typically favoring sites with an established track record over fresh site opportunities. This creates a sampling problem: if the pool of potential sites is largely composed of those selected in previous trials, analyses of that pool will naturally favor characteristics associated with prior selection. When sponsors draw candidates from a pool shaped by prior selection decisions, established sites are more likely to be selected again and trial speed, diversity, and overall quality are potentially impacted.   

    AI can help organizations identify new clinical trial sites by evaluating a broader range of characteristics to inform site selection so that appropriate candidates are not overlooked. Using predictive algorithms to target new research characteristics including suitable patient populations, investigators, and clinical capabilities, among other data points, sponsors can potentially identify sites that are a unique fit, expanding their approach to site selection.

    Basing site selection on trial history

    Sponsors commonly evaluate sites across four broad categories: likely eligible-patient volume, clinical capability, investigator availability, and prior-trial performance. Problematically, these criteria are frequently measured using historical proxies, with past trial participation among the most readily available. As a result, these screens tend to return sites that already have a research history; they also fail to address the highly protocol-specific nature of enrollment.

    By leveraging different data points for site selection, sponsors can identify the next generation of capable clinical trial sites. The key to tapping into new opportunities is broadening sponsors’ traditional searches to include specific characteristics of a particular trial. 

    Further informing a sponsor’s site selection approach, data shows that trial participation varies sharply by care setting. For example, across Commission on Cancer programs from 2013 to 2017, the overall adult cancer treatment trial participation rate was 7.1%.2 

    Participation rates varied significantly by program type:

    • 21.6% at NCI-designated comprehensive cancer centers
    • 4.1% at community programs
    • 5.4% at academic, non-NCI-designated programs
    • 5.7% at integrated network programs

    While these NCI findings reflect data from several years ago, little suggests that site selection practices have changed meaningfully in the interim. This noted variation is impactful because a site with a strong trial participation history is likely to appear more attractive in a selection process than those with little or none. Prior participation is a real signal. The problem is that it is also a filter, and using it as a primary screen ensures the pool never expands.

    Selecting the next generation of sites with AI

    By identifying specific characteristics related to clinical capability, patient population, investigator or site capability, and data visibility, AI-enabled tools can perform a look-alike analysis to find sites that resemble other ones that have successfully conducted a very similar trial, potentially surfacing new sites that are an appropriate match but lack a trial track record.

    Using real-world patient claims data, procedure volumes, investigators’ expertise, and capabilities to perform specific services and procedures, AI can evaluate broader signals unrelated to trial history. This can be particularly important in the rare disease space, where diagnosis codes are often not specific enough to identify the patients who meet a study’s criteria. By incorporating broader clinical and longitudinal signals, AI can estimate which patients are likely affected by the disease of interest and, by extension, where those patients are receiving care. This can help sponsors identify qualified sites that may be overlooked by diagnosis-code- or trial-performance-based approaches alone. 

    Although these models rely on prior data, they can use care-delivery and patient-level signals to estimate future suitability without requiring prior performance in a similar trial. AI is not a shortcut around the limitations of the underlying data, but rather a tool that can evaluate more data at scale. The opportunity comes from evaluating different signals, such as patient populations, care-delivery patterns, investigator expertise, and protocol-specific capabilities that can help identify qualified sites traditional approaches may overlook.  

    The foundation of any analysis is and always will be the quality of the input data. AI makes it possible to evaluate larger and more complex datasets. Where data capture can be reliably estimated, it may also help differentiate genuinely low patient volume from limited data visibility.

    It can be effective at extracting variables from clinical text where appropriately governed data are available to supplement site validation. AI can also be used for modeling across full feature sets at scale, beyond manual feasibility capabilities, to screen large numbers of sites that lack prior trial experience.

    While AI cannot fully resolve trial eligibility from claims data, determine site selection, or directly recruit appropriate patients, it can quickly provide valuable estimates, helping sponsors better understand the patient population that is likely to meet treatment criteria. Of course, sponsors will still need to thoroughly assess the capabilities of sites and investigators, and consider the primary factors for managing and running the trial.

    A practical way to evaluate these approaches is through a controlled exploration cohort. Sponsors could reserve a defined percentage of candidate sites for model-identified, trial-naïve organizations and subject them to the same readiness assessments and operational reviews as traditional candidates. Enrollment and study performance could then be measured against established benchmarks. This allows organizations to test whether expanding the candidate pool improves recruitment and site performance without abandoning proven site-selection practices.

    Life sciences organizations don’t need to abandon their current site-selection approach entirely, but they should recognize that relying too heavily on past enrollment performance can create a self-reinforcing system in which the sites selected yesterday become the sites considered tomorrow. This approach comes at a cost: a smaller and less diverse enrollment pool, limited geographic and demographic representation, overlooked patient populations, slower recruitment, and higher costs. By incorporating AI-enabled approaches into site selection, sponsors can base decisions on capabilities and patient populations in addition to prior trial experience, broadening the candidate pool, expanding potential matches, and reaching more patients.

    References

    1. Getz, K. “Enrollment Performance: Weighing the ‘Facts’.” Applied Clinical Trials, May 2012, Vol. 21, Issue 5. Tufts CSDD study of nearly 16,000 investigative sites across 151 Phase II and III global trials conducted 2008–2010, with performance data supplied by 10 pharmaceutical companies and two CROs; typical trial ran in 11 countries among adult patients. Enrollment activation rate is defined as the percentage of sites ready to enroll that enroll at least one patient. Findings: 11 percent of ready-to-recruit sites enrolled no patient; 41 percent of activated sites did not achieve the target enrollment number, defined as a band from sites enrolling only one patient through those missing target by 10 percent or more; 40 percent hit target and 15 percent exceeded it; sites enrolling at least one patient reached 85 percent of target on average; and 48 percent of all selected sites enrolled nobody or under-enrolled.
    2. National Estimates of the Participation of Patients With Cancer in Clinical Research Studies Based on Commission on Cancer Accreditation Data,’ Journal of Clinical Oncology, 2024, doi:10.1200/JCO.23.01030 (covering 2013-2017).

    About Aaron Cohenthe Author: 

    Aaron Cohen is Director of Life Sciences Solutions Consulting at Definitive Healthcare. He specializes in healthcare claims data and real-world data, with deep expertise in claims analytics, provider reference data, patient tokenization and linkage, and cloud analytics. In his more than seven years at Definitive, Aaron has worked in Customer Success, Solutions Consulting, and leadership roles. He leads a team of subject matter experts supporting biopharma, diagnostics, and medical device customers, and is a co-author on a conference poster analyzing Medicare claims data.

    Prior to joining Definitive, Aaron focused on patients’ access to novel medical devices at a reimbursement consulting firm, where he was a Definitive Healthcare customer. Aaron is completing an MS in Data Science at the University of Colorado Boulder.