GENESEEQPRIME NGS Tumor Profiling Assay (FFPE) (GS6005)

K250003

Geneseeq Technology Inc. · cleared 2025-08-29 · product code PZM · Pathology

Premarket evidence — what FDA accepted

Device typehardware with ml
source quote (p.5)
“The GENESEEQPRIME NGS Tumor Profiling Assay (FFPE) is a qualitative in vitro diagnostic test kit that uses next generation sequencing of DNA isolated from formalin-fixed paraffin-embedded tumor tissue from previously diagnosed patients with solid malignant neoplasms to detect tumor gene alterations in a broad multi gene panel. This test is intended to provide tumor mutation profiling information on somatic variants, including single nucleotide variants (SNVs), insertions and deletions (indels), one amplification, four translocations, microsatellite instability (MSI), and tumor mutation burden (TMB). The GENESIS by GENESEEQ™™ (hereafter referred to as “GENESIS") software necessary for the GENESEEQPRIME assay (software version is displayed on the user interface and on reports) is provided by Geneseeq Technology Inc. (Geneseeq) to perform sample information management, sequencing data analysis and test report generation.”
Algorithmmachine learning module, ToSeq, which uses a Distributed Random Forest model
source quote (p.19)
“The GENESIS software includes a machine learning module, ToSeq, which distinguishes somatic from germline SNVs and indels without matched normal samples by evaluating features related to variant location, frequency, pathogenicity, and database presence. Trained on 3,189 tumor-normal pairs and tested on 4,781 independent pairs (7,970 total), ToSeq uses a Distributed Random Forest model that achieved high performance (SNV AUC = 0.9867; indel AUC = 0.9818).”
Adaptive (vs locked)No
PCCPNo
Cybersecurity addressedYes
source quote (p.22)
“Guidance for Industry Cybersecurity for Networked Medical Devices Containing Off-the-Shelf (OTS) Software (January 14, 2005), Content of Premarket Submissions for Management of Cybersecurity in Medical Devices Guidance for Industry and Food and Drug Administration Staff (October 2, 2014), Postmarket Management of Cybersecurity in Medical Devices Guidance for Industry and Food and Drug Administration Staff (December 28, 2016)”

Validation studies (9)

Retrospective clinical

n=503 cases

endpoints: Positive Percent Agreement (PPA); Negative Percent Agreement (NPA)

Bench

n=28 cases · 3 site(s)

endpoints: average positive agreement; average negative agreement; coefficient of variance of TMB score; concordance of MSI status calls; positive call rate (Modal PCR); negative call rate (NCR)

Bench

n=10 cases

endpoints: Limit of Detection (LoD) for SNVs, insertions, deletions; LoD for ERBB2 amplification; LoD for MSI calls; LoD for TMB calls

Bench

n=43 cases

endpoints: Limit of Blank (LoB) for SNVs, Indels, ERBB2 amplifications, gene translocations, MSI; False positive rate

Bench

n=108 cases

endpoints: Positive Percent Agreement (PPA); Negative Percent Agreement (NPA); Mean Absolute Percentage Error (MAPE) for TMB calls

Bench

n=21 cases

endpoints: Positive Percent Agreement (PPA); Negative Percent Agreement (NPA)

Bench

n=10 cases

endpoints: concordance rate for detected variants; coefficient of variance of TMB score; concordance of MSI status; Positive Percent Agreement (PPA)

Bench

n=7 cases

endpoints: Positive Percent Agreement (PPA); Negative Percent Agreement (NPA); Mean Absolute Percent Error (MAPE) for TMB

Bench

n=8 cases

endpoints: Positive Percent Agreement (PPA); Negative Percent Agreement (NPA); Coefficient of variation for mutational burden

Reported performance (3 observations)

sensitivity92.44CI 91.45%-93.33%
source quote (p.25)
“92.44% (91.45%, 93.33%)”
specificity99.99CI 99.99%, 99.99%
source quote (p.25)
“99.99% (99.99%, 99.99%)”
agreement_kappaas written: “Overall Percent Agreement (OPA) for MSI status”93.48CI 86.49%, 96.98%
source quote (p.37)
“93.48% (86.49%, 96.98%)”

Each value carries its own analysis unit and task — never compare or pool across devices. Source: 510(k) summary PDF.

Predicate network

Postmarket — what happened after clearance

0
recalls in product code, 24mo
0
MAUDE reports in code, 12mo
—
vs code's own 3-yr baseline
0
drift signals on this device

Recall and MAUDE counts are product-code-level (reports aren't reliably attributable to one device); a recall is shown as device-attributed only when the recall record itself lists this clearance number. Signals are descriptive observables with sources — never a judgment that the device is unsafe or drifting. Snapshot 2026-07-08.

Reimbursement — how devices like this got paid

Not yet tracked — no payment pathway indexed for this clearance (the reimbursement corpus is a growing seed set).

Applicable FDA guidance — what the submission is measured against

FDA guidance documents and guiding principles applicable to 510(k) AI/ML devices in the Pathology panel. A curated reference index, not legal or regulatory advice — each item states its own status, and a draft is never binding.

Applicability is derived from the device's FDA advisory panel and pathway — cross-cutting guidances apply to every AI/ML device; panel-specific ones are flagged. Titles, dates, and links verified against fda.gov as of July 2026.

Constat Precedent · public FDA/CMS data · descriptive decision-support, not regulatory or reimbursement advice. Share this page: constat.dev/precedent/device/K250003