Annalise Enterprise CXR Triage Trauma

K222179

Annalise-AI Pty Ltd · cleared 2023-03-28 · product code QFM · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.5)

“Annalise Enterprise CXR Triage Trauma is a software workflow tool which uses an artificial intelligence (AI) algorithm to identify suspected findings on chest X-ray (CXR) studies in the medical care environment. The subject device and the predicate device are both software only packages”

Algorithmconvolutional neural network trained using deep-learning techniques

source quote (p.5)

“Radiological findings are identified by the device using an AI algorithm – a convolutional neural network trained using deep-learning techniques.”

Adaptive (vs locked)No

PCCPNo

Cybersecurity addressedFDA source did not state this

Validation studies (2)

Bench

sample size not stated

standards: FDA's Guidance for Industry and FDA Staff, “Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices”, May 11, 2005.

Retrospective clinical

n=1,269 cases · 4 site(s)

endpoints: AUC; Sensitivity; Specificity

Reported performance (14 observations)

sensitivity0.96CI 94.2,97.7

source quote (p.8)

“96.0 (94.2,97.7)”

specificity0.883CI 85.3,91.1

source quote (p.8)

“88.3 (85.3,91.1)”

aurocas written: “auc”0.98CI 0.972-0.986

source quote (p.8)

“0.980 (0.972-0.986)”

aurocas written: “AUC (Pneumoperitoneum)”0.969CI 0.950-0.984

source quote (p.8)

“0.969 (0.950-0.984)”

sensitivityas written: “Sensitivity (Pleural effusion) at 0.2990 operating point”0.938CI 91.5,95.8

source quote (p.8)

“93.8 (91.5,95.8)”

specificityas written: “Specificity (Pleural effusion) at 0.2990 operating point”0.917CI 89.3,94.1

source quote (p.8)

“91.7 (89.3,94.1)”

sensitivityas written: “Sensitivity (Pleural effusion) at 0.4355 operating point”0.863CI 83.0,89.4

source quote (p.8)

“86.3 (83.0,89.4)”

specificityas written: “Specificity (Pleural effusion) at 0.4355 operating point”0.956CI 93.7,97.2

source quote (p.8)

“95.6 (93.7,97.2)”

sensitivityas written: “Sensitivity (Pneumoperitoneum) at 0.0322 operating point”0.901CI 84.2,95.0

source quote (p.8)

“90.1 (84.2,95.0)”

specificityas written: “Specificity (Pneumoperitoneum) at 0.0322 operating point”0.874CI 82.4,92.3

source quote (p.8)

“87.4 (82.4,92.3)”

sensitivityas written: “Sensitivity (Pneumoperitoneum) at 0.0484 operating point”0.861CI 79.2,92.1

source quote (p.8)

“86.1 (79.2,92.1)”

specificityas written: “Specificity (Pneumoperitoneum) at 0.0484 operating point”0.896CI 85.2,94.0

source quote (p.8)

“89.6 (85.2,94.0)”

sensitivityas written: “Sensitivity (Pneumoperitoneum) at 0.2266 operating point”0.822CI 75.2,89.1

source quote (p.8)

“82.2 (75.2,89.1)”

specificityas written: “Specificity (Pneumoperitoneum) at 0.2266 operating point”0.962CI 93.4, 98.9

source quote (p.8)

“96.2 (93.4, 98.9)”

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

recalls in product code, 24mo

MAUDE reports in code, 12mo

—

vs code's own 3-yr baseline

drift signals on this device

Recall and MAUDE counts are product-code-level (reports aren't reliably attributable to one device). 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).