Sepsis ImmunoScore

DEN230036

Prenosis, Inc. · granted 2024-04-02 · product code SAK · General Hospital

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.1)
“The Sepsis ImmunoScore is an Artificial Intelligence/Machine Learning (AI/ML)-Based Software that identifies patients at risk for having or developing sepsis.”
Algorithmartificial intelligence/machine learning (AI/ML) based algorithm; fixed machine learning model (probability random forest model) trained to identify sepsis in patients; uses 1000 decision trees as the base model
source quote (p.3)
“The device uses an artificial intelligence/machine learning (AI/ML) based algorithm that is locked to compute the risk score and place the patient in a risk category. The core of the algorithm is a fixed machine learning model (probability random forest model) trained to identify sepsis in patients. A probability random forest calculates the mean predicted class probabilities from multiple simple models. Probability random forest performs bagging, a method of sampling a dataset with replacement. An individual simple model is trained on this sampled dataset. This sampling with replacement followed by training is performed many times to generate an ensemble, or forest, of simple models. The probability random forest used for the development of the ImmunoScore algorithm used 1000 decision trees as the base model to generate the forest.”
Adaptive (vs locked)No
source quote (p.3)
“The device uses an artificial intelligence/machine learning (AI/ML) based algorithm that is locked to compute the risk score and place the patient in a risk category.”
PCCPYes
source quote (p.43)
“The device manufacturer must develop and implement a post-market performance management plan that ensures regular assessment of the generalizability and device performance in the intended patient population in real-world use.”
Cybersecurity addressedYes
source quote (p.41)
“For cybersecurity, the recommended information from FDA guidance document "Content of Premarket Submissions for Management of Cybersecurity in Medical Devices" was provided. This includes a threat model, software bill of materials, data security training, validation and mitigation of adversarial examples, cyber risk management, labeling, cyber testing, and post market cyber vulnerabilities and exploits and other information for safeguarding the algorithms.”

Validation studies (2)

Retrospective clinical

n=746 patients · 3 site(s)

endpoints: monotonic increase in sepsis diagnostic predictive value and risk stratification category; in-hospital mortality; ICU admission; mechanical ventilation usage; vasopressor usage within 24 hours of patient assessment; median length of stay

Bench

n=746 patients

endpoints: Sepsis Risk Score Imprecision; Sepsis Risk Score Reproducibility; Impact of Input Parameter Bias on Device Performance; Diagnostic Accuracy; Primary Endpoint Acceptance Criteria

standards: CLIA 1988

Reported performance (1 observation)

aurocas written: “auc”0.81CI [0.76, 0.86]
source quote (p.15)
“An estimate of the AUROC for 95% confidence intervals was calculated for both the forced majority and forced unanimous adjudication schemes. There was a pre-specified performance goal of 0.75, which was achieved for both schemes: Adjudicated Forced Majority 0.81 [0.76, 0.86] Adjudicated Forced Unanimous 0.84 (0.78, 0.90]”

Each value carries its own analysis unit and task — never compare or pool across devices. Source: De Novo decision summary PDF.

Predicate network

Postmarket — what happened after clearance

Not yet tracked — the weekly postmarket refresh hasn't snapshotted this device.

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 De Novo AI/ML devices in the General Hospital 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/DEN230036