Critical Care Suite with Pneumothorax Detection AI Algorithm, Critical Care Suite 2.1, Critical Care Suite
K223491GE Medical Systems, LLC · cleared 2023-05-25 · product code QBS · Radiology
Premarket evidence — what FDA accepted
source quote (p.3)
“Critical Care Suite with Pneumothorax Detection AI Algorithm is a computer-aided triage, notification, and diagnostic device that analyzes frontal chest X-ray images for the presence of a pneumothorax. Critical Care Suite is a software module that can be deployed on several computing platforms such as PACS, On Premise, On Cloud or X-ray Imaging Systems.”
source quote (p.6)
“They are all deep learning locked AI algorithms that can be deployed on several computing platforms such as PACS, On Premise, On Cloud or X-ray Imaging Systems.”
source quote (p.6)
“They are all deep learning locked AI algorithms that can be deployed on several computing platforms such as PACS, On Premise, On Cloud or X-ray Imaging Systems.”
Validation studies (2)
Retrospective clinical
n=804 images · 2 site(s)
endpoints: detection of pneumothorax; localization of suspected pneumothorax
Reader study (MRMC)
n=400 images
endpoints: improved reader performance for detection of pneumothorax
Reported performance (7 observations)
source quote (p.8)
“a sensitivity of 84.3% (80.6%, 88.0%)”
source quote (p.8)
“and a specificity of 93.2% (90.8%, 95.6%)”
source quote (p.8)
“The Pneumothorax Detection AI Algorithm achieved an AUC of 96.1% (94.9%, 97.2%)”
source quote (p.8)
“The algorithm also had high sensitivity for detecting large pneumothoraxes with a sensitivity of 96.3% (93.1%, 99.2%)”
source quote (p.8)
“and small pneumothorax with a sensitivity of 75.0% (69.2%, 80.8%).”
source quote (p.8)
“It performed with full agreement between these regions 67.8% (62.7%, 73.0%).”
source quote (p.8)
“It also performed with a DICE Similarity Coefficient of 0.705 (0.683, 0.724) indicating that on average 70.5% of the Pneumothorax Overlay area and the true area of a pneumothorax within an image overlap.”
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
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).