510(k) Report

510(k) · Cleared

Cleared

Bayesian Health Sepsis Flagging Device

K250680510(k) TraditionalCleared Apr 30, 2026420-day reviewClass II21 CFR 880.6316

Data to Oct 25, 2026 (FDA decisions) Oct 12, 2026 (recalls) Sep 30, 2026 (MAUDE) refreshed weekly, last Nov 3, 2026

Bayesian Health, Inc. · SAK Software Device To Aid In The Prediction Or Diagnosis Of Sepsis

Cleared on Apr 30, 2026 as substantially equivalent to DEN230036 (Prenosis, Inc., 2024) after a 420-day review. Its family tree reaches back 1 generation to 2024.

Decided
Apr 30, 2026
Review
420 days
Class
Class II
Product code
SAK
Recalls
None
Predicates
1

Its longest line of descent runs back 1 generation to DEN230036 (2024). No later device cites it as a predicate yet.

DEN230036 · Sepsis ImmunoScore · Prenosis, Inc. · 202420202022202420262028
DEN230036 · Sepsis ImmunoScore · Prenosis, Inc. · 20240
  1. Root · 1 generation backDEN230036 Sepsis ImmunoScorePrenosis, Inc. · 2024
  2. This deviceK250680 Bayesian Health Sepsis Flagging DeviceBayesian Health, Inc. · 2026
View FIG. 1 as a table

Line of descent and top descendants

GenerationNumberDeviceApplicantDecidedRecalls
−1DEN230036Sepsis ImmunoScorePrenosis, Inc.2024—
0 (this device)K250680Bayesian Health Sepsis Flagging DeviceBayesian Health, Inc.2026—
FIG. 1 — Lineage of K250680, 2024–2026Source: FDA 510(k) summaries, read by 510(k) Report · How lineage is built

Get the monthly Device Review Tracker

Notable FDA decisions, review times and new Class I recalls. See an issue.

Sources: FDA 510(k) database (decision fields), the FDA summary (predicates and indications), FDA recall and enforcement reports, and MAUDE; processed by 510(k) Report. Verify on FDA.gov · Methodology and accuracy.

Planning a device in SAK? A 510(k) Report weighs predicate choices, recall history and review times for a new device like this one.

  • Candidate predicates for a device like this, rankedin the report
  • Recall history across each candidate’s familyin the report
Get a 510(k) Report

What was it cleared against? (1)

Devices the submitter claimed this one is substantially equivalent to (*), and reference devices cited for a specific test or feature (†), as written in the FDA summary.

TypeNumberDeviceApplicantDecidedRecalls
*DEN230036Sepsis ImmunoScore
Summary page 5
…e SAK Regulation Number 21 CFR 880.6316 Regulatory Class Class II Review Panel Gastroenterology/Urology Submission Type De Novo De Novo Identifier DEN230036 1…
Prenosis, Inc.2024—

What descends from it?

No later submission names this one as a predicate yet.

Has anything in its family been recalled? (0 Class I)

No FDA recall names this device.

No ancestor or descendant has a Class I recall.

What does this lineage say?

  • Its one ancestor has no recall.

How does its category compare?

All SAK devices

SAK Software Device To Aid In The Prediction Or Diagnosis Of Sepsis: FDA decisions, review times, recalls and adverse event reports over 20 years. 2026, this device’s year, is highlighted.

FDA decisions per year · SAK

1in 2024

2024: 12026 (partial year): 1
2007high 1 (2024) · low 0 (2007)2026

2026 to Oct 25, outlined.

Median 510(k) review, days · SAK

Too few SAK 510(k)s in any year since 2007 to give a median.

Recalls per year · SAK

No recall names SAK since 2007.

Adverse event reports per year · SAK

13in 2025

2024: 32025: 13
2007high 13 (2025) · low 0 (2007)2025

MAUDE reports naming product code SAK, not matched to any one device; reports are not rates.

View these four charts as a table
YearDecisionsMedian 510(k) review, daysRecalls (Class I)MAUDE reports
20070—00
20080—00
20090—00
20100—00
20110—00
20120—00
20130—00
20140—00
20150—00
20160—00
20170—00
20180—00
20190—00
20200—00
20210—00
20220—00
20230—00
20241—03
20250—013
20261—0—

What is it indicated for?

The Bayesian Health Sepsis Flagging Device is a continuously monitoring artificial intelligence and machine learning-based software as a medical device intended for use by Health Care Providers (HCPs) in conjunction with clinical assessments and other laboratory data to aid in the early detection and/or risk prediction of sepsis developing within 24 hours. The Bayesian Health Sepsis Flagging Device uses a machine learning algorithm to analyze patient…

Read the full statement (176 words)

The Bayesian Health Sepsis Flagging Device is a continuously monitoring artificial intelligence and

machine learning-based software as a medical device intended for use by Health Care Providers

(HCPs) in conjunction with clinical assessments and other laboratory data to aid in the early

detection and/or risk prediction of sepsis developing within 24 hours.

The Bayesian Health Sepsis Flagging Device uses a machine learning algorithm to analyze patient

data from the EHR, which includes a combination of patient information, comorbidities, the chief

complaint documented at presentation to the emergency department, laboratory measurements and

vital signs, and procedures, medications, and consult orders. The Bayesian Health Sepsis Flagging

Device outputs a flag ("Sepsis Risk High") that is displayed within the EHR but should not be used

as the sole basis to determine the presence of sepsis or risk of developing sepsis within 24 hours.

The Bayesian Health Sepsis Flagging Device is intended to be used for adult patients (≥18 years

old) upon Emergency Department (ED) presentation or hospital admission throughout the duration

of the patient's stay in acute care settings.

Indications for use as stated in the FDA summary.

Cite this page

510(k) Report. “K250680: Bayesian Health Sepsis Flagging Device.” Lineage record from FDA 510(k) data and the FDA summary. Updated Nov 3, 2026. Accessed Nov 6, 2026. https://510kreport.com/device/K250680

Report an extraction error

Tell us what is wrong; we check it against the FDA summary.

Are you the manufacturer?

Send a correction or an update to this page, for example a newer model or a public statement about a recall.

Record history
  • FDA decision record loaded Oct 30, 2026
  • Summary read Oct 30, 2026 (extraction version 2d9447fa9ea4)
  • Lineage and recalls computed Nov 3, 2026
  • Page last updated Nov 3, 2026