Annalise Enterprise
K250831Annalise-AI · cleared 2025-04-23 · product code QFM · Radiology
Premarket evidence — what FDA accepted
Device typesamd
source quote (p.7)
“Annalise Enterprise is a software workflow tool which uses an artificial intelligence (AI) algorithm to identify suspected findings on chest X-ray studies in the medical care environment.”
AlgorithmAI algorithm a convolutional neural network trained using deep-learning techniques
source quote (p.7)
“Radiological findings are identified by the device using an AI algorithm a convolutional neural network trained using deep-learning techniques.”
Adaptive (vs locked)FDA source did not state this
PCCPFDA source did not state this
Cybersecurity addressedFDA source did not state this
Validation studies (2)
Retrospective clinical
n=3,252 cases · 4 site(s)
endpoints: AUC; Sensitivity; Specificity
Bench
n=303 cases
endpoints: Triage turn-around time
Reported performance (16 observations)
aurocas written: “AUC (Pneumothorax)”0.984CI 0.976, 0.990
source quote (p.11)
“0.984 (0.976, 0.990)”
aurocas written: “AUC (Tension pneumothorax)”0.989CI 0.984, 0.994
source quote (p.11)
“0.989 (0.984, 0.994)”
aurocas written: “AUC (Pneumoperitoneum)”0.987CI 0.976, 0.994
source quote (p.11)
“0.987 (0.976, 0.994)”
aurocas written: “AUC (Pleural effusion)”0.977CI 0.969, 0.984
source quote (p.11)
“0.977 (0.969, 0.984)”
aurocas written: “AUC (Vertebral compression fracture)”0.972CI 0.960, 0.982
source quote (p.11)
“0.972 (0.960, 0.982)”
sensitivityas written: “Sensitivity (Pneumothorax) at Operating Point 0.200”97.1CI 95.5,98.6
source quote (p.12)
“0.200 97.1 (95.5,98.6) 88.2 (85.4,90.8)”
specificityas written: “Specificity (Pneumothorax) at Operating Point 0.200”88.2CI 85.4,90.8
source quote (p.12)
“0.200 97.1 (95.5,98.6) 88.2 (85.4,90.8)”
sensitivityas written: “Sensitivity (Tension pneumothorax) at Operating Point 0.225”96CI 92.0,99.2
source quote (p.12)
“0.225 96.0 (92.0,99.2) 94.0 (92.3,95.6)”
specificityas written: “Specificity (Tension pneumothorax) at Operating Point 0.225”94CI 92.3,95.6
source quote (p.12)
“0.225 96.0 (92.0,99.2) 94.0 (92.3,95.6)”
sensitivityas written: “Sensitivity (Pneumoperitoneum) at Operating Point 0.250”96.2CI 92.4,99.0
source quote (p.12)
“0.250 96.2 (92.4,99.0) 87.9 (83.2,92.1)”
specificityas written: “Specificity (Pneumoperitoneum) at Operating Point 0.250”87.9CI 83.2,92.1
source quote (p.12)
“0.250 96.2 (92.4,99.0) 87.9 (83.2,92.1)”
sensitivityas written: “Sensitivity (Pleural effusion) at Operating Point 0.380”96.7CI 95.0,98.1
source quote (p.12)
“0.380 96.7 (95.0,98.1) 86.8 (83.6,89.5)”
specificityas written: “Specificity (Pleural effusion) at Operating Point 0.380”86.8CI 83.6,89.5
source quote (p.12)
“0.380 96.7 (95.0,98.1) 86.8 (83.6,89.5)”
sensitivityas written: “Sensitivity (Vertebral compression fracture) at Operating Point 0.460”93.4CI 90.1,96.0
source quote (p.12)
“0.460 93.4 (90.1,96.0) 85.8 (82.1,89.6)”
specificityas written: “Specificity (Vertebral compression fracture) at Operating Point 0.460”85.8CI 82.1,89.6
source quote (p.12)
“0.460 93.4 (90.1,96.0) 85.8 (82.1,89.6)”
time_to_resultas written: “Triage turn-around time”42.3CI 41.2, 43.4
source quote (p.12)
“The results demonstrated a triage turn-around time of 42.3 (95% CI: 41.2, 43.4) seconds, which is substantially equivalent to the total performance time published for the predicate device.”
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). 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).