Lung AI (LAI001)
K243239Exo Inc · cleared 2025-04-24 · product code MYN · Radiology
Premarket evidence — what FDA accepted
source quote (p.4)
“Lung AI software device is a Computer-Aided Detection (CADe) tool designed to assist in the detection of consolidation/atelectasis and pleural effusion during the review of lung ultrasound scans.”
source quote (p.8)
“Supervised Deep Learning including Deep Convolutional Neural Networks for Segmentation, Landmark Detection and Classification”
source quote (p.7)
“Artificial intelligence, including non-adaptive machine learning algorithms trained with clinical data”
source quote (p.8)
“Cybersecurity testing was performed in accordance with Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions.”
Validation studies (2)
Retrospective clinical
n=359 patients · 6 site(s)
standards: IEC 62304:2006/AC:2015 - Medical device software – Software life cycle processes, Content of Premarket Submissions for Device Software Functions, Guidance for Industry and Food and Drug Administration Staff, Computer-Assisted Detection Devices Applied to Radiology Images and Radiology Device Data Premarket Notification [510(k)] Submissions, Clinical Performance Assessment: Considerations for Computer-Assisted Detection Devices Applied to Radiology Images and Radiology Device Data in Premarket Notification (510(k)) Submissions
Reader study (MRMC)
n=322 patients
endpoints: improvement of at least 2% in overall reader performance, as measured by AUC-ROC, when aided by the device
Reported performance (20 observations)
source quote (p.9)
“Se = 0.97 (95% CI 0.94 – 0.99)”
source quote (p.9)
“Sp = 0.91 (95% CI 0.87 – 0.96)”
source quote (p.9)
“Se = 0.97 (95% CI 0.94 – 0.99)”
source quote (p.9)
“Sp = 0.94 (95% CI 0.90 – 0.98)”
source quote (p.9)
“Se = 0.85 (95% CI 0.80 – 0.89)”
source quote (p.9)
“Sp = 0.91 (95% CI 0.87 – 0.96)”
source quote (p.9)
“Se = 0.86 (95% CI 0.81 – 0.90)”
source quote (p.9)
“Sp = 0.94 (95% CI 0.90 – 0.98)”
source quote (p.10)
“AUC_unaided = 0.93 (95% CI .92 - .94)”
source quote (p.10)
“AUC_aided = 0.96 (95% CI .95 - .98)”
source quote (p.10)
“Se_unaided = 0.71 (95% CI .68 - .75)”
source quote (p.10)
“Se_aided = 0.88 (95% CI .86 – .92)”
source quote (p.10)
“Sp_unaided = 0.96 (95% CI .95 – .97)”
source quote (p.10)
“Sp_aided = 0.93 (95% CI .88 – .95)”
source quote (p.10)
“AUC_unaided = 0.92 (95% CI .91 - .96)”
source quote (p.10)
“AUC_aided = 0.95 (95% CI .94 - .98)”
source quote (p.10)
“Se_unaided = 0.73 (95% CI .72 - .80)”
source quote (p.10)
“Se_aided = 0.89 (95% CI .88 – .93)”
source quote (p.11)
“Sp_unaided = 0.92 (95% CI .88 – .93)”
source quote (p.11)
“Sp_aided = 0.91 (95% CI .87 – .93)”
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).