The comparison is explicit
For level of consciousness, output is designed to be framed as departure from this patient’s established state rather than as a percentile, so the clinician can see what the comparison set is.
Clinicians & health systems
The reference range is the patient.
Built by a registered nurse with about ten years at the bedside, for people who have watched a patient deteriorate inside a normal range. Here is what changes, what the regulatory status actually is, and what we will not claim.
Regulatory status, before anything else
Pathos Vigil is an investigational medical device. It has not been cleared or approved by the U.S. Food and Drug Administration or any other regulatory authority, and it is not available for sale or clinical use. Nothing on this page is a claim of clinical performance, safety or efficacy.
We put this first rather than in a footnote because clinicians are entitled to know the stage of a thing before they read a word about what it might do.
The clinical problem
Deterioration inside a normal range.
You have seen this. A patient whose observations sit inside every threshold on the chart, whose trend is unmistakably wrong, and whose deterioration is obvious to the nurse who has been with them for six hours and invisible to the scoring system that has been with them the whole time.
The scoring system is not broken. It is answering the question it was built to answer: is this observation abnormal for people in general? The question that matters is whether it is abnormal for this patient, now, compared to this patient, earlier.
The gap between those two questions is time. It is the interval in which a change is real, may be measurable, and is not yet visible to any instrument comparing the patient to a population. For Pathos Vigil, the within-subject comparison is made for level of consciousness.
The asymmetry
The direction that gets missed.
Level of consciousness is the clearest example. Agitation is documented, escalated and responded to. Its opposite is the patient becoming quieter, slower, less engaged, less present. That generates no disruption, and in a system whose attention is allocated by disruption, that is a hazard.
The populations who experience the quiet failure mode are not random. They are the sedated, the delirious-hypoactive, the non-verbal, the cognitively impaired, the patients whose first language is not the ward’s, and the patients who have learned that speaking up does not improve their care.
Symmetric treatment is a design response to a directional gap that is well described in the literature on hypoactive delirium and unrecognized deterioration; see the hypoactive-delirium citation, a gap you can go and check rather than take from us.
At the bedside
What a per-subject baseline changes in practice.
Change over time
Designed to track change over time, continuously, rather than only when someone next has a hand free.
Direction is preserved, not ranked
Elevated and suppressed departures are designed to be reported distinctly, because the clinical response differs.
Absence of baseline is stated
A newly admitted patient has no baseline yet. The system is designed to say so, rather than silently substituting a population range and presenting the result with the same confidence.
What it is not
Not a replacement for clinical assessment, and not designed to be. Not an autonomous alarm system. Not a diagnosis. The intended role is to make a change visible earlier to the person who is going to make the decision, who remains the clinician.
The patient who stops making noise is the one to look at hardest.
Attention in a busy unit is allocated by disruption. Deterioration is not obliged to be disruptive.
Evidence
Where the evidence stands.
The underlying mathematics is not ours and is not new. Critical slowing down as an early-warning signature of state transition in complex dynamical systems is an established body of work spanning ecology, climate science and physiology. We set out the published lineage on the evidence page. What we are doing is applying it under a per-subject baseline and a symmetry constraint, in monitoring contexts.
The application is what requires evidence, and that evidence is what a regulatory pathway exists to establish. We are in development. We have not published clinical performance data, and we will not describe performance we have not demonstrated.
If you would find this useful, the most valuable thing you can offer us is a hard question about where it would fail in your unit, not enthusiasm.
What we will claim
- The framework and how it is constructed.
- The mathematical basis and its published lineage.
- The architectural design constraints, as documented.
What we will not claim
- Clinical performance, sensitivity or specificity.
- Improved outcomes, length of stay, or mortality.
- Regulatory status we do not have.
- Comparative superiority over any existing tool.
Safety, quality and data
How the regulated part is kept separate.
- Software lifecycle
- A software lifecycle appropriate to its intended classification is planned and documented for the clinical decision logic, which is kept inside the regulated product. It is never moved into the shared substrate that non-clinical products consume.
- Non-clinical products cannot reach it
- The wellness, veterinary and defense products have no dependency on the clinical decision logic. A wellness product emitting a clinical conclusion would be a program that does not exist, not a compliance failure we watch for.
- Patient data
- Identifiable physiology and per-subject baselines are designed not to cross the federation boundary. The restriction is designed into the type system rather than a setting, so a deployment would have no option that turns it off. Data handling for any specific deployment is governed by the applicable agreement and by the institution’s own requirements.
- Human decision authority
- The intended use is to surface a change to a clinician. Autonomous clinical action is outside the scope of the design.
Nursing leadership
What it would ask of your nurses.
Nurses would carry whatever this becomes at the bedside. We would like nursing leaders to tell us early what a shift can absorb, and what it cannot.
- What would this add to my nurses’ work?
- The first study we propose would record its output for later analysis without showing it to the care team. A study would ask time of your staff, including research assessments that are not part of usual care, and the study agreement would set that scope. That scope is not set yet, and neither is what any later use would ask of a shift.
- Will it add alarms, or second-guess nursing assessment?
- The intended role is to surface a change to the clinician, who decides; it is not designed to replace clinical assessment. The design includes alerting, so any use beyond a shadow-mode study would add signals at the bedside. How many, and how many would be real, is not known, and we make no claim about alarm burden.
- Who built it, and from what kind of practice?
- Matthew Lashomb, RN, BSN, the founder, who leads the company’s technical and clinical direction. He spent about ten years in bedside practice, from 2015 to 2025, most of it on inpatient units. Psychiatric nursing was the largest share, followed by neurology and neuro step-down, where he held SCRN stroke certification (since lapsed). He did not practice in intensive care, and he has not been in bedside practice since 2025.
Intensivists and medical directors
What there is to evaluate, and what a study would have to show.
The founder’s bedside practice did not include intensive care. A study in critical care would need critical-care clinical leadership, and we need you to tell us where a per-subject baseline would mislead in your patients.
- What clinical evidence is there for Pathos Vigil?
- Pathos Vigil has never run on a patient, and no result has been clinically validated, by us or independently. We have published no clinical data on it. The literature on the evidence page is published third-party science the approach draws on, and none of it is a study of an Intuitive Pathos product.
- How is it different from the early-warning score our hospital uses?
- Pathos Vigil is designed to score level of consciousness against each patient’s own earlier state rather than a population threshold. It is not designed to replace the early-warning score your hospital uses, and we claim no better performance than any existing score or model; that would have to be shown in a study.
- How often would it flag, and how many flags would be real?
- We do not claim an alert rate, positive predictive value, sensitivity or specificity. Each would have to be measured in a study, in units like yours.
- What would its status mean for an investigator?
- Pathos Vigil is an investigational medical device. It has not been cleared or approved by the U.S. Food and Drug Administration or any other regulatory authority, and it is not available for sale or clinical use. It is in FDA pre-submission preparation. A study would run under IRB oversight. Whether it would be exempt from the investigational device exemption requirements or subject to them, and if subject, whether as a significant or nonsignificant risk study, has not been assessed; the sponsor, the reviewing IRB and, if asked, the FDA each have a role in that determination.
Quality and patient safety
What a safety program would need to know.
Tell us which deterioration measures you would want a first study to examine, and where you expect per-subject comparison to fail.
- Which of our measures would this touch?
- Which measures a first study should compare its output against is one of the questions we are asking you. We make no claim about outcomes, length of stay, mortality or any other quality measure.
- How would it fit our rapid response system?
- The first study we propose would not show its output to the care team. How any later output would fit an escalation policy, and who would respond to it, is not yet decided, and we would work it out with the physicians and nurses who would carry it. We make no claim about escalation or activation rates.
- Does it perform equally across patient groups, and what are its known limits?
- Whether it performs equally across patient groups is not known, because per-group performance has not been measured. For level of consciousness, the per-subject baseline is designed to reduce bias by construction, pending per-group validation. The framework page sets out some general limits of the approach, including a baseline built during an abnormal period and bias in a sensor itself. They are not a complete list of Pathos Vigil’s known limitations; ask us for those. The disparity literature behind the design is on the evidence page.
IT, security and compliance
What you can review now, and what does not exist yet.
Your review would come before any study starts. The trust page sets out what is in place and what is not, so you can see the gaps before we talk. The security controls it describes cover this website only, because no Intuitive Pathos product is deployed.
- Would any data leave our network?
- In a study, whether any data would leave your network, and in what form, would be set by the study agreement and your institution’s own requirements. Separately, the platform is designed so that identifiable physiology and per-subject baselines do not cross the federation boundary, a restriction designed into the type system rather than a setting; what is designed to federate is described on the platform page.
- What attestations do you have: SOC 2, HITRUST, ISO 27001, a penetration test?
- None. Intuitive Pathos holds no SOC 2 report, no ISO 27001 or ISO 13485 certificate and no HITRUST certification, and no independent penetration test has been done. We do not describe any product as HIPAA compliant.
- What else can our review see?
- Detailed security and data-handling documentation is shared only under a confidentiality agreement, on the terms set out on the trust page. Ask us which of the documents your review needs exist today.
Collaboration
What we are looking for from clinical partners.
-
Clinical input on failure modes
Specifically: where would a per-subject baseline mislead you? Which patients arrive without a usable baseline? Where is the quiet deterioration in your unit?
-
Research collaboration
Retrospective analysis, prospective observational study design, and academic partnership: the work that has to happen before any performance claim is legitimate.
-
Design partnership for workflow
A monitoring output nobody has time to look at is worthless. We want to be told, early and bluntly, what would not survive contact with a real shift.
What a first study would look like
The first study we would propose is observational, under IRB oversight, and run in shadow mode: the system’s output is recorded for analysis and is not shown to the care team or used in any care decision. It would ask time of clinical staff, including research assessments that are not part of usual care. The final protocol, the reviewing IRB, the study agreement and your institution’s own requirements would set the design, that scope and how data is handled.
No such study is running yet. If your unit would be a good place for the first one, or a good place to explain why it would not work, we would like to talk.