Official Press Kit & Media Reference

DeepSensi PBC · Dover, Delaware, USA · [email protected] · www.deepsensi.com

Version 2.0 · September 2026 · Founder: Tomasz Jan Gomoła (ORCID 0009-0001-5222-6154)

This kit is for journalists, editors, and analysts. Everything in it is cleared for

publication and attribution. Quotes may be used verbatim. Numbers are canonical, please

use them exactly as written. For interviews, data, or auditor access to research protocols:

[email protected].

1. One line

DeepSensi is the Difficult Cases Engine: a Cognitive Medical OS that puts the reasoning of an entire university hospital behind every difficult case, in the clinic and, with the DeepSensi Edge Node, at home. Every visit written. Every record private.

2. Boilerplate: "About DeepSensi" (copy-paste ready)

Short (40 words).

DeepSensi is the Difficult Cases Engine: a Cognitive Medical OS for the cases that defeat single-specialty medicine. Precision Suites, RESOLVE registries and the DeepSensi Edge Node bring clinical intelligence to physicians, hospitals and homes worldwide. DeepSensi Public Benefit Corporation, Dover, Delaware.

Long (~135 words).

DeepSensi is the Difficult Cases Engine: a Cognitive Medical OS built for refractory, multi-system illness, the cases that fall into the white space between specialties. Its Inter-Specialty White Space Engine reasons across every organ system at once, with deterministic physiological deduction under the open DSS-001 Platinum standard (the Gomola Framework), and gives the physician every hypothesis with the data and the published sources it rests on.

DeepSensi serves physicians through 11 Precision Medicine Suites, builds evidence through 9 RESOLVE observational registries, and brings clinical intelligence home with the DeepSensi Edge Node: a hospital in every home. Precision Suites launch in the United States in October 2026. The FDA Pre-Submission (Q262487) and the Breakthrough Device designation request (Q262494) were submitted on July 31, 2026 and are pending. DeepSensi Public Benefit Corporation is incorporated in Delaware and operates globally.

3. Fact sheet: canonical numbers

Safety (analytically derived).

• Method: Fault Tree Analysis per IEC 61025, over 23 independent verification barriers in three tiers.
• Safety architecture designed to a SIL-4-class target, quantified by the Company's own fault tree analysis under IEC 61025 across 23 independent barriers. No accredited third party has certified it. The full method: deepsensi.com/safety-architecture.

Accuracy (empirical, development-cohort, double-blinded evaluation).

• Validation set: 301 published NEJM Clinicopathological Conference cases (2014-2023), among the hardest diagnostic cases in medicine.
• Frozen baseline before calibration: 80.1% top-1 / 88.0% top-3.
• Median deliberation time: 14.3 s (benchmark testing mode). Reported as a development-cohort result; a confirmatory study is designated.

Speed & Turnaround.

• Full multi-specialist deliberation completes in ~2 minutes for typical complex cases to a few minutes for complex multi-omic tensors (WGS/WES, OAT, metagenomics), versus the weeks it takes to convene an equivalent human panel by hand.

Clinical Portfolio & Registries.

• 11 Precision Medicine Suites: Dedicated clinical platforms across major intractable disease domains.
• 9 DCT Registries (N = 90,000): Global observational clinical trial registries (EPI, NEURO, IMMUNO, ONCO, METABO, CARDIO, RARE, ENDO, MIND).
• Ward Chief Fast-Track: 1 Case upon evaluation · Identifiers Removed at Source · Zero IT Friction (immediate Shadow Audit for clinical directors).

The standard.

• The DeepSensi Standard (DSS-001 Platinum), also called the Gomola Framework: the first quantitative safety-certification standard for clinical AI. Five auditable pillars, four certification levels with explicit per-assertion hallucination bounds. Open and royalty-free (attribution required). The reference implementation is proprietary.

Company & compliance.

• DeepSensi PBC, a public benefit corporation. 8 The Green STE A, Dover, DE 19901, United States.
• Regulatory Status: Breakthrough Device designation: request submitted July 31, 2026, pending. No designation has been granted. (FDA docket Q262494.) FDA Pre-Submission (Q-Sub) submitted July 31, 2026. (FDA docket Q262487.)
• Identifiers removed on device · built to meet HIPAA · GDPR · EU AI Act (architected to Articles 9-17) · HL7 · FHIR · DICOM.
• Intellectual property: Twelve patent applications filed with the USPTO and twenty-four more prepared.
• Runs in the cloud, on edge nodes ($500+), or entirely offline and air-gapped on-premises.

4. The story in one paragraph

Every safety-critical industry measures reliability before deployment: aircraft engines, nuclear reactors, and new drugs must all clear a quantitative bar. Clinical AI, a technology whose errors are counted in human lives, has been required to clear none. DeepSensi closes that gap. It applies aviation's fault-tree mathematics to a 23-barrier verification architecture, producing the first published, quantitative bound on medical-AI hallucination; validates it on the hardest public diagnostic cases in medicine; and publishes the certification standard behind it, open and royalty-free, for the whole industry to adopt or attack.

4a. The benchmark, in context

Exact-diagnosis accuracy on the publicly available NEJM Clinicopathological Conference (CPC) cases, among the hardest diagnostic cases in medicine, the same benchmark used across the field:

Others guess the answer. DeepSensi deduces it, with a Patent Pending anti-hallucination architecture, auditable to every step. A score you cannot audit is still a guess.

4b. What only DeepSensi brings

4c. The human errors that vanish: a panel with no ego

No fatigue, no hierarchy, no memory of a "difficult patient," and a mandatory adversary in every case. The classic human diagnostic biases DeepSensi's architecture is designed to eliminate: anchoring, confirmation, premature closure, availability, base-rate neglect, search satisficing, framing, ascertainment/stereotyping, overconfidence, authority gradient, groupthink, and fatigue. Machine bias is engineered against through cross-vendor independence and deterministic evidence checks.

Benchmark sources: Nori et al., Sequential Diagnosis with Language Models, arXiv:2506.22405 (2025); Kanjee et al., JAMA (2023). DeepSensi figures are development-cohort on 301 NEJM CPC cases; a confirmatory study is designated.

4d. The case that started it: N = 1 in epilepsy

DeepSensi began with one child: three years in hospitals with drug-resistant epilepsy, on polytherapy, with pharmacoresistance growing all the while. The answer lay in the white space between specialties: cross-specialty metabolic findings, acted on by the child's treating clinicians.

Today: more than 1.5 years without a single seizure. The drug resistance has reversed, and the blood levels of every medicine are measurable again.

One child is a case; a registry is how a case becomes evidence. EPI-RESOLVE™ exists to find out how far this result carries, family by family and country by country, under independent ethics review. The complete evidence and timeline are available for review.

Shared with the family's written consent.

5. Key messages

1. A number, not a vibe. DeepSensi gives clinical AI a quantitative safety bound, the way aviation and nuclear engineering have measured reliability for decades.
2. Empowerment, not replacement. DeepSensi makes one clinician stronger: it compresses time-to-diagnosis from days to minutes and hands the physician a defensible, court-grade record of exactly what was checked. The clinician signs, and stays in command.
3. Safety and accuracy are not in tension. Safety-first calibration costs 2.3 additional seconds of median deliberation.
4. The proof is public; the blueprint is not. The papers, the standard, and the audit trail are open. The reference implementation stays proprietary.
5. Honesty is a feature. The system is built to say "I don't know" and to name the single test that would resolve the doubt.
6. A standard, not just a product. The DeepSensi Standard is open and royalty-free, so any vendor, regulator, or health system can use it.

5a. The physician, empowered, not replaced

DeepSensi is built to make one clinician stronger, not to stand in for a department.

• Faster to a verified answer. A deliberation that takes days to convene as a human panel returns in 12 seconds to minutes for complex cases, time-to-diagnosis collapses from days to minutes.
• A defensible record, a first. For the first time, the physician holds a court-grade, cryptographically sealed record of exactly what was checked, by whom, and why, with liability partitioned per decision (AI, physician, or rule). The decision they sign is documented to a standard no chart has offered before.
• The clinician stays in command. DeepSensi is clinical decision support; the treating physician signs every decision. It augments judgment; it does not override it.
• The first Cognitive Engine. Diagnosis, documentation, longitudinal patient memory, and a physician reputation economy on one verified substrate.
• Vendor-agnostic and auditable. Not a wrapper on any single model (a better base model yields a better verified answer), and every step is independently auditable, including against the operator.

The net is empowerment with a safety net: the clinician gains the depth of a full specialist consilium and a record that protects the decision, while remaining, unambiguously, the person in charge.

6. Approved quotes, attributable to Tomasz Jan Gomoła, Founder

"Aviation doesn't ask a jet engine to feel safe. It asks for a number. We gave clinical AI its number."

"We published the standard and kept the implementation. A category belongs to whoever writes its rules, so we wrote them, and gave them away."

"The most dangerous sentence in medicine is a confident mistake. We built a system that is allowed to say 'I don't know', and rewarded for it."

"Every knowledge profession credits its best minds for the reuse of their best ideas. Medicine was simply last, because its attribution problem was the hardest. It isn't anymore."

"We report development-cohort results and name the confirmatory study we still owe. The proof travels with the claim. That is the whole point."

"We didn't build an AI to overrule the physician. We built one to give a single clinician the depth of a full specialist panel in minutes, and, for the first time, a record that proves exactly what was checked."

7. Founder bio

Short. Tomasz Jan Gomoła is the Founder of DeepSensi and the author of the DeepSensi Standard (the Gomola Framework), an open safety-certification standard for clinical AI. He designed DeepSensi's 23-barrier verification architecture and its quantitative, fault-tree-derived safety bound. ORCID 0009-0001-5222-6154.

Long. Tomasz Jan Gomoła is the Founder of DeepSensi, a Delaware public benefit corporation building verified clinical intelligence. He is the author of the DeepSensi Standard, also known as the Gomola Framework, the first quantitative safety-certification standard for clinical AI, which he has published open and royalty-free. He architected the system's 23-barrier deterministic verification cascade and the fault-tree reliability analysis that produced its published per-assertion safety bound, and is the corresponding author on the associated body of technical papers (preprints on medRxiv; manuscripts in submission to peer-reviewed venues). His work is covered by twelve patent applications filed with the USPTO and twenty-four more prepared. ORCID 0009-0001-5222-6154.

8. Capabilities glossary (plain-language, public names)

• Difficult Cases Engine: DeepSensi itself, the engine built for the cases that defeat single-specialty medicine, reasoning across every organ system at once.
• Cognitive Medical OS: the operating system that runs the engine for physicians, hospitals, registries and homes, on one verified substrate.
• DeepSensi Edge Node: Clinical Intelligence at Home. The Cognitive Engine in the room, beside the people you care for: a hospital in every home. Clinical monitoring functions require FDA authorization, which DeepSensi will seek.
• Inter-Specialty White Space Engine: DeepSensi's core intelligence layer that bridges the departmental silos of modern medicine, mapping multi-omic tensors (WGS, organic acids, metabolomics, microbiome) to identify the root causes of intractable multi-system illness.
• Ward Chief Fast-Track, 1 case upon evaluation, direct identifiers removed at the source, zero IT friction: provides hospital department heads with an immediate multidisciplinary shadow audit on an unresolved patient without institutional IT integration.
• 11 Precision Medicine Suites: dedicated clinical intelligence platforms spanning 9 major intractable disease domains.
• DeepSensi DCT™ (9 Registries): global decentralized observational clinical trial networks (EPI, NEURO, IMMUNO, ONCO, METABO, CARDIO, RARE, ENDO, MIND) generating Real-World Evidence and Synthetic Control Arms.
• Hyper Consilium: a multi-specialist AI deliberation that reasons like a hospital tumour board, in minutes, with physicians participating as scored contributors.
• LIMBO, the structured "I don't know": when evidence is insufficient, the system declares uncertainty and specifies the exact test required instead of guessing.
• Active Sensing: recommends the single examination or test that would most decisively resolve an ambiguous case.
• GCPS (Global Clinical Performance Score): an objective, bias-resistant measure of physician performance.
• Golden Horizon: DeepSensi PBC's public benefit allocation program providing up to 10,000 subsidized annual allocations for the elite Precision Medicine Suites (standard institutional value $4,850) in chronic and intractable illness, a dedicated 100% full hardship fee waiver pathway for families in acute need, Bring-Your-Own-Diagnostics (BYOD) workflow, and autonomous clinical-trial matching.
• GERN, a privacy-preserving syndromic-surveillance layer: an early-warning signal derived from coded clinical documentation (methods only; no detection results are claimed).
• Retroactive alerting / digital twin: when new medical knowledge changes a past patient's picture, the treating physician is alerted automatically, even years later.

9. The papers (ten)

Preprints headed to medRxiv; manuscripts in submission to peer-reviewed venues (including NEJM AI). Full texts: www.deepsensi.com/papers.

• WP-001: Fault Tree Analysis of multi-layer verification (the safety case)
• WP-002: The Flawed Yardstick (why static benchmarks penalize safety; the Safe Triage Paradox)
• WP-003: The Hyper Consilium (physicians as scored nodes; LIMBO)
• WP-004: The Global Clinical Performance Score (objective physician reputation)
• WP-005: AutoResearcher-HYPO (autonomous hypothesis generation; no biomedical findings claimed)
• Golden Horizon Charter: Autonomous public benefit allocation architecture & PBC-subsidized Precision Suites (Charter)
• WP-007: GERN (privacy-preserving syndromic surveillance; methods only)
• WP-008: The Decentralized Clinical Trials Platform (foundations for global observational registries and synthetic control arms)
• DSS-001: The DeepSensi Standard (the open, royalty-free certification standard, Platinum Level)
• NEJM AI Perspective, why medical AI needs quantitative safety certification

10. Regulatory status and evidence

• Regulatory status. DeepSensi Precision Suite is clinical decision support for licensed physicians; the treating physician signs every decision. FDA Pre-Submission (Q-Sub) submitted July 31, 2026 (FDA docket Q262487). Breakthrough Device designation request submitted July 31, 2026, pending (FDA docket Q262494). Functions that require FDA authorization are offered in the United States only upon it.
• Evidence. The accuracy figures are development-cohort results on 301 NEJM CPC cases. The confirmatory study is designated, and the case-level protocol is open to auditors.
• Safety bound. The bound is analytical, derived by fault tree analysis; accuracy studies validate deployability. Certification is two-dimensional: architecture and probability.
• GERN. WP-007 is a methods paper with a pre-registered prospective evaluation.
• The physician. DeepSensi gives the treating clinician the depth of a full specialist panel and a defensible record; the clinician signs every decision and stays in command.

11. FAQ

What is DeepSensi's regulatory status with the US FDA?

Breakthrough Device designation: request submitted July 31, 2026, pending. No designation has been granted. (FDA docket Q262494.) FDA Pre-Submission (Q-Sub) submitted July 31, 2026. (FDA docket Q262487.) DeepSensi is architected for dual SaMD Class IIb and De Novo regulatory pathways.

Are the accuracy numbers peer-reviewed? Preprints are being deposited on medRxiv and manuscripts are in submission to peer-reviewed venues, including NEJM AI. The N = 301 figures are development-cohort estimates with a designated confirmatory study; auditors may request the case-level protocol.

What does “SIL-4-class” mean here? Safety architecture designed to a SIL-4-class target, quantified by the Company's own fault tree analysis under IEC 61025 across 23 independent barriers. No accredited third party has certified it. The full method: deepsensi.com/safety-architecture.

Does it replace doctors? No: it empowers them. DeepSensi compresses time-to-diagnosis from days or weeks to approximately 2 minutes and gives the clinician a court-grade, auditable record (with liability partitioned per decision) of exactly what was checked and why. It is clinical decision support: the physician signs and remains in command.

Which AI models does it use? DeepSensi is model-agnostic and cross-vendor by design; it is not a wrapper on any single model, and a better base model yields a better verified answer. Specific vendors are not disclosed.

Is the standard really free? Yes. The DeepSensi Standard (DSS-001 Platinum) is open and royalty-free (attribution required). Only the reference implementation is proprietary.

How is patient privacy handled? Direct identifiers are removed at the source, before ingestion, and the key that links a case to a person stays with the user; built to meet HIPAA and GDPR. For hospitals, fully air-gapped on-premises edge nodes ensure zero patient bytes ever leave the hospital facility.

Where is the company based? DeepSensi PBC, a Delaware public benefit corporation, 8 The Green STE A, Dover, DE 19901, United States.

12. Assets in this kit

Download the press kit (.zip): logo, mark and wordmark files, three founder photographs of Tomasz Jan Gomoła in JPEG, AVIF and WebP, with `images/README_IMAGES.txt`, and the official SILENT-DS Hospital Site Application & Clinical Onboarding Dossier (PDF, Document ID: DS-INST-2026-SILENT-HOSPITAL). You can also download the clinical dossier individually: SILENT-DS Hospital Site Application Packet (PDF). The photographs are below as well, cleared for editorial use with the credit “DeepSensi”.

13. Usage, trademark & licensing

• Text in this kit (boilerplate, quotes, fact sheet, bios) may be reproduced freely in editorial coverage.
• The DeepSensi Standard / Gomola Framework is open and royalty-free; attribution required. The reference implementation (DeepSensi Cognitive Engine) is proprietary.
• "DeepSensi" and the DeepSensi mark are trademarks of DeepSensi PBC; please do not alter the mark's proportions or colours, or imply endorsement or partnership without written agreement.
• Numbers are canonical, please reproduce them as written, with the development-cohort qualifier where relevant.

14. Contact & embargo policy

• Press, interviews, auditor access: [email protected]
• Partnerships & institutions: [email protected]
• Author / corresponding (papers): [email protected]
• Materials shared "under embargo" may not be published before the stated date. Once preprints are live on medRxiv, DOIs will be circulated and the embargo lifts.

DeepSensi PBC is a Public Benefit Corporation. Up to 10,000 annual subsidized Precision Suite allocations under Golden Horizon, free clinical-trial matching for patients, open research, and the open DSS safety standard are written into its charter. We publish the proof, the standard, and the audit. We do not publish the blueprint.