Common questions

Filos makes technology that helps hospital nutrition teams deliver better care to patients. Our enterprise-grade tools help identify and monitor patients at risk of malnutrition.

We build around the needs of clinical dietitians, nutrition leaders, and the care teams working alongside them.

Filos helps hospital nutrition teams identify patients at risk of malnutrition and monitor their status throughout their stays. Our EHR-based risk scores help dietitians prioritize patients for assessment, with supporting information from the clinical record available for review.

Our technology works alongside your existing EHR, documentation, and CDI tools. We tailor implementation to your team’s workflow, while assessment, diagnosis, and treatment decisions remain with clinicians.

A screening system needs to identify patients who may benefit from a closer look without creating an unmanageable review burden. We approach that as a tradeoff between sensitivity and precision: how many relevant cases are identified, and how many flagged cases merit the team’s attention. Rather than offering only a binary flag, Filos provides a scaled risk score to help dietitians prioritize patients for review.

Our founders’ experience building AI systems that flag potential problems for human review informs how we evaluate malnutrition screening. We consider missed cases (false negatives), false alarms (false positives), and the review workload created for dietitians.

For each hospital, we’ll work with the team to evaluate missed cases alongside the volume and usefulness of flagged cases. The aim is to identify the right balance for the hospital’s workflow, so dietitians can focus their time where it matters.

Filos analyzes patient history and clinical information recorded during a hospital stay for signals that brief admission questionnaires can miss. Risk scores update as new clinical information becomes available throughout the stay.

We scope the specific data elements and interfaces with each hospital during evaluation.

We’ve built technology to help hospital nutrition teams identify malnutrition risk and monitor patients throughout their stays. Our capabilities extend beyond risk scores derived from existing EHR data.

We’d be happy to demonstrate the technology and discuss its fit for your hospital in a confidential conversation.

Timothée Kampouris and Zuntue Pommerich met at Blue Sky Robotics (BSR).

They bonded early in their tenure at BSR when they were put in charge of rescuing a failing pilot, putting in about 440 hours over three weeks. They worked day and night alongside frontline staff, learned what was working, and listened carefully so feedback shaped the solution. By the end of that stretch, the client’s executives had regained confidence in the project.

After that success, Timothée was promoted to Director of Solutions, leading as many as five client projects at once and managing other external-facing efforts. Zuntue was promoted to Director of Engineering and later to CTO, building and leading a team of about fifteen engineers and interns and managing internal company priorities.

Learn more about the founders →

Before starting Filos, Timothée and Zuntue led hospital food service technology projects at Mayo Clinic and UNC Health. They spent substantial time onsite at both locations, working directly with hospital food service teams.

Their computer vision work verified meal trays against printed diet orders before trays left the kitchen. The projects included onsite evaluation, image data collection, model development, and pilot preparation.

At Mayo Clinic, they worked through the hospital’s third-party risk management (TPRM) process. At UNC Health, they completed an evaluation-stage business associate agreement (BAA) and received clearance to use protected health information (PHI) for that evaluation.

Filos is designed to work alongside your hospital’s EHR, documentation, and CDI systems. Our technology integrates with Epic and has been tested in that environment.

For hospitals using other EHR systems, we work with your IT team to scope the appropriate connection. Connection details are agreed during evaluation to match your institution’s systems and security requirements.

We were inspired to start Filos after learning how big a problem malnutrition is while working on food service technology projects at Mayo Clinic and UNC Health.

We also noticed that hospital systems have recently reported significant financial results after implementing another startup’s EHR-based malnutrition risk scores alone. We expect that our proprietary technology could meaningfully improve those risk scores and deliver even better results.

A month after we started Filos, a close family member experienced severe malnutrition, leading to a hospital stay lasting over two weeks. The problem we were working to address was now affecting someone we loved. That experience strengthened our commitment to helping hospital nutrition teams deliver better care to patients.

Filos means “friend” in Greek. At our previous company, a client told us he saw us as partners rather than vendors—and the way he worked with us made that clear.

His approach left a lasting impression on us. When we started our own company, we wanted to carry that same spirit into how we treated people and built relationships. We chose the name Filos as a daily reminder of the kind of business we want to run.

Filos was founded in September 2026.

Yes. All of Filos’s proprietary technology and intellectual property were developed independently, from scratch, after the company was founded in September 2026.

Filos Technologies, Inc. is our legal entity. We are a Delaware corporation in good standing.

Filos’s EHR-based malnutrition risk scoring is informed by peer-reviewed research on using hospital records to identify malnutrition risk, including a 2022 PLOS ONE study of malnutrition trajectories ↗.

We’ve built on that foundation with advances from AI research and developed our own model. Our Results page describes its evaluation and performance.

Our research model achieved 0.93 AUROC on a held-out test set of 65,688 adult non-ICU hospital admissions from MIMIC-IV. The full study included 326,222 admissions.

The model used patient history and information from the first 24 hours of care to distinguish admissions with and without documented malnutrition.

See the results →

Filos organizes the evidence—why a patient was flagged and what chart support was gathered—so dietitians and the care team can act with clearer information. They stay in the driver’s seat for assessment and care decisions, including when documentation conflicts or information is incomplete. Diagnosis and treatment orders stay with the care team.

We take that concern seriously. Our goal is not to maximize diagnosis rates or assign a billing code based on an AI prediction. It is to help care teams find patients who may have been missed, assess them, and document diagnoses that are clinically supported.

The evidence shows why both sides matter. In a 2024 study by Aktas and colleagues of hospitalized patients with cancer, 197 of 420 patients identified as malnourished by a dietitian did not have a corresponding physician-coded diagnosis. That is evidence of a documentation gap in one clinical population, not a national missed-diagnosis rate. Separately, a 2020 federal audit found substantial overbilling in a targeted group of historical severe-malnutrition claims, including cases where the record did not support the severity or effect on patient care.

Our approach separates screening, clinical assessment, diagnosis, and coding. A risk score is a prompt for review, not a diagnosis. We intend for the clinical evidence behind a recommendation to be traceable to the patient record, for dietitians and the responsible provider to exercise independent judgment, and for coding decisions to remain subject to the hospital’s CDI and compliance processes. Unsupported diagnoses or severity should be corrected, not carried forward to increase reimbursement.

We plan to evaluate clinical validity and documentation quality alongside identification rates, including cases that should not be diagnosed or coded. Success means helping the right patients receive appropriate care, with documentation that accurately reflects their condition.

Our current product is designed to meet FDA’s criteria for non-device clinical decision support—a category of software that does not require FDA device clearance or approval (FDA guidance ↗).

Filos helps hospital dietitians prioritize patients for assessment using existing health-record information. Our design makes the supporting information and reasoning available for independent clinical review, while assessment, diagnosis and treatment decisions remain with the care team.

As Filos and FDA guidance evolve, we will review changes in functionality and intended use, seek appropriate regulatory expertise, and obtain any required clearance or approval before introducing capabilities that require it.

For a hospital evaluation, Filos uses clinical data the partner approves for that purpose, under the agreements and controls that partner requires. Public demos use synthetic inputs. Retention, deletion, and model-improvement terms are set with the partner in those agreements.

Website visitor privacy (contact email, no ad trackers) is described on Privacy. Hospital product controls are summarized on Security.

Filos is built for hospital security reviews from the start, with HIPAA-oriented controls, encrypted transit, secure cloud environments, and support for hospital access requirements, including single sign-on (SSO).

Before Filos, our founders completed third-party risk management (TPRM) review with Mayo Clinic and an evaluation-stage business associate agreement (BAA) with UNC Health. That experience informs how we prepare for partner reviews today.

We maintain vendor BAA relationships with major cloud and productivity providers under each provider’s stated scope. See our Security page for our current controls.

Filos’s technology integrates with Epic and has been tested in that environment. Implementation at your hospital is scoped with your IT, security, and clinical teams to fit your systems and workflows.

Together, we agree on the data sources, interfaces, access requirements, and initial evaluation scope. The interface approach, whether FHIR, HL7, or another route, is selected with your team before a live connection is established.

You’ll work directly with Filos’s founders, Timothée and Zuntue. We love spending time on site, getting to know people and learning from the teams who have been doing this for years.

We tailor the technology to your existing tools and workflows, and your feedback helps us make it more useful for your team. As an early partner, you have a direct line to the founders who built the technology.

We want to become familiar faces—people you feel comfortable telling what’s helpful, what’s frustrating, and what could work better.

We start by learning your nutrition workflow and goals, demonstrating the technology, and agreeing on what success would look like at your hospital.

We choose the evaluation approach around the capabilities and goals being assessed. For EHR-based malnutrition risk scoring, this can include a retrospective evaluation using your hospital’s records. Scope, success criteria, data permissions, and security requirements are agreed before kickoff, with your dietitians and nutrition leaders involved throughout.

If the evaluation demonstrates value, we work together toward a pilot and explore opportunities to support other teams across your health system.

What matters most is access to your data and access to the floor—so the founders can observe frontline workers, hear their loudest complaints, and tailor Filos to how your team actually works. A shared commitment to using new technology to improve care is central to that collaboration.

Scope, success measures, and commercial terms are agreed with the partner before work begins. As an early partner, you work directly with the founders; we are open to aligning part of our fee with shared results.

For a benchmark-based view of economic opportunity, use the opportunity calculator on the homepage.

Yes. The calculator is grounded in reported results from AI-assisted malnutrition identification using EHR data at two major hospitals.

Cedars-Sinai reported $10.5 million in total annual financial impact in its 2026 impact report. The Penn Medicine implementation case study reported $23.8 million in annualized financial impact, based on first-quarter results: $6.3 million in additional reimbursement and $17.5 million attributed to shorter hospital stays. The startup behind these implementations reports that Penn Medicine internally validated the financial analysis.

That startup has publicly documented its clinical and technical approach in its research, including the model architecture, clinical inputs, how information is extracted from clinical notes, and validation methods. That published work provides a foundation for researchers developing and evaluating EHR-based malnutrition risk models.

For Filos, EHR-based risk scoring is a starting point. Our own research model achieved 0.93 AUROC on a held-out test set of 65,688 hospital admissions. We’ve also built proprietary technology that extends beyond risk scores based on existing EHR data. We expect that our technology could meaningfully improve those risk scores and deliver even better results.

We use the hospitals’ reported financial outcomes to develop per-admission benchmarks, then scale those benchmarks to your hospital’s annual admissions. The calculator provides a broad, ballpark estimate of the opportunity, grounded in actual hospital implementations. An evaluation with your team would assess that opportunity using your hospital’s own data, patient population, payer mix, and workflows.

Yes. The United States has more than 5,100 community hospitals. We estimate that roughly 125 hospitals currently use dedicated AI-assisted malnutrition identification tools, or about 2–3% of that broad universe.

Our estimate is a bottom-up assessment of publicly reported deployments and inferred adoption across commercial vendors and hospital-built systems. One vendor reported screening patients at more than 50 hospitals; we estimate additional deployments from other vendors and internal hospital programs, with an assumed adjustment for possible overlap. Mount Sinai has reported using its internally developed system across six hospitals.

Public deployment counts are incomplete, and most vendors do not disclose how many hospitals use this specific capability. Our working range is approximately 75–300 hospitals. This is a provisional estimate, not a national census. It covers live AI workflows that identify malnutrition risk and support clinical action, not conventional screening questionnaires or every AI product that can mention malnutrition. The hospital denominator comes from an earlier AHA survey, so the comparison is approximate.

Cedars-Sinai has deployed a specialized AI tool for malnutrition and separately adopted AI-powered diagnostic and documentation support, illustrating that hospitals can use multiple tools for different clinical needs.

Existing deployments demonstrate demand, while the size of the market leaves substantial room for first-time adoption. We’re building Filos to earn that adoption through clinical usefulness, straightforward implementation, and measurable impact.

Yes. Hospitals have already adopted comparable AI-assisted malnutrition screening commercially. One startup in this space has publicly reported closing multiple deals worth more than $500,000 in annual recurring revenue each. Cedars-Sinai has also described a commercial implementation of this type of technology at its hospital.

That gives us evidence that this is a problem hospitals are willing to pay to solve. Filos addresses the same need with technology we’ve already built, including EHR-based malnutrition risk scoring and proprietary capabilities that extend beyond existing EHR data. We pair that technology with implementation tailored to your hospital’s workflows.

We’ve built proprietary technology that extends beyond malnutrition risk scores based on existing EHR data. We expect that our technology could meaningfully improve those risk scores and deliver even better results. We’d be happy to demonstrate it and share more in a confidential conversation.

We combine that technology with direct founder involvement in implementation and close collaboration with your hospital’s nutrition team. Together, we agree on success criteria so an evaluation can establish its value for your hospital.

AI-assisted malnutrition identification using EHR data has already shown promising real-world results for hospitals, while the market remains almost entirely greenfield.