The Screening Gap
Status: concept — the problem PRISM exists to address.
Millions of people live for years with conditions that an established, inexpensive test could identify, because no one is systematically watching for the moment when testing would pay off. That missing piece — not new science, not new tests, not new treatments — is the gap PRISM exists to close.
A solved problem that keeps not being solved
For a substantial class of conditions, medicine already has everything it needs. The disease mechanism is understood. A reliable, non-invasive diagnostic test exists and is routinely performed — once someone thinks to order it. Effective treatment exists, and it works far better started early than started after complications. The knowledge exists. The tests exist. The treatments exist. What is missing is systematic identification of which patients would benefit from which test, and when.
Patients with these conditions are not undiagnosable in principle; they are undiagnosable in practice. The failure is not one of diagnostic capability but of attention: nothing in the ordinary operation of the healthcare system is responsible for noticing that this particular patient, right now, has drifted into the population for whom that particular test is worth running. So the diagnosis waits — often for years — until the condition announces itself through damage that early treatment would have prevented.
The stakes run in both human and financial terms, and they point the same direction. For the patient, a missed underlying condition means years of symptoms treated one at a time, each managed plausibly on its own while the cause goes unaddressed — and the eventual complications can be permanent. For the system that pays for care, waiting for complications is the most expensive possible way to discover a disease: the diagnostic test costs a tiny fraction of the emergency admissions, procedures, and chronic-damage care that follow a late diagnosis. Early detection is one of the rare places in healthcare where better outcomes and lower cost are the same intervention.
Each provider sees a slice
The root cause is fragmentation. A developing condition rarely presents as one dramatic event; it leaves a trail — an escalating prescription pattern at a primary-care office, an emergency visit across town, a specialist consultation for one symptom in isolation, a mildly abnormal lab at yet another facility. Each provider sees only the slice of that trail that passes through their own doors, usually inside a visit measured in minutes, and each slice looks unremarkable on its own.
The pattern is legible only across the whole journey, and the whole journey is precisely what no single point of care possesses. It is no one's job to sit down with years of a patient's complete history and ask what it adds up to — and even a diligent physician who wanted to could not, because the record is scattered across systems that do not talk to each other. This is not a failing of individual clinicians. It is the predictable output of a system in which longitudinal attention is nobody's assigned role.
One real-world illustration
Primary aldosteronism, a hormonal driver of high blood pressure, is a fair stand-in for the whole class. It is common among people with hard-to-control hypertension, it is identified with a simple blood test, and targeted treatment for it works — yet the large majority of people who have it, by most estimates well over ninety percent, are never diagnosed until complications develop. The typical trajectory is years of escalating blood-pressure medications, repeat visits, and accumulating cardiovascular and kidney strain before anyone orders the one inexpensive test that would have named the problem near the start. Nothing about that trajectory needed new medicine to change; it needed someone, or something, to notice sooner. In this documentation the condition appears only as an illustration — PRISM's actual evidence comes from the 2026 synthetic proof of concept, not from any real disease.
What a fix has to look like
The shape of any real fix follows directly from the shape of the failure:
| requirement | why |
|---|---|
| Population-scale | Each condition is uncommon enough that you must look at everyone to find anyone. A process that depends on someone deciding a patient merits a closer look has already failed the undiagnosed majority. |
| Longitudinal | The evidence is a pattern spread across years of encounters, not a single alarming value. Anything built on snapshots recreates the fragmentation it is meant to repair. |
| Automatic | It has to run continuously in the background, over the whole population, without waiting for a trigger — the trigger not firing is the very problem being solved. |
There is exactly one vantage point in the existing system that already holds population-scale, longitudinal records of every patient's journey across every provider: the insurer's claims stream. Why that view — and not hospital records — is the workable foundation is the subject of The Insurance Vantage Point. How PRISM turns it into early-screening suggestions is laid out in What is PRISM.
One honest caveat belongs here: none of this presumes that every under-diagnosed condition leaves a readable trail in billing data. Whether a given condition does is an empirical question, and PRISM's condition-selection criteria treat it as one — the method is only claimed for conditions where such a precursor pattern exists to be found.