Medscape Medical NewsAll articles

AIMI-Triage CXR PTX

RADLogics, Inc. • Radiology • 04/08/2020

510(k)IEC 62304 Class B
FDA Summary PDF

Device Purpose

The AIMI-Triage CXR PTX employs an artificial intelligence algorithm, developed through pattern recognition, to analyze adult digital chest X-rays for features suggestive of moderate to large sized pneumothorax. Its primary function is to serve as a notification-only triage tool that integrates with PACS/workstations to flag potential positive cases, thereby aiding radiologists in prioritizing their review workflow in acute care settings without providing a diagnosis.

Summary

The AIMI-Triage CXR PTX is a radiological computer-aided triage and notification software designed for hospital networks and clinics. Its purpose is to assist radiologists by identifying and helping to prioritize adult chest X-rays, acquired in acute settings, that exhibit features suggestive of moderate to large sized pneumothorax. The system utilizes an artificial intelligence algorithm, trained through pattern recognition on a database of images, to analyze these X-rays. It operates independently and in parallel with the standard image interpretation workflow, flagging suspected cases at a case-level within the Picture Archiving and Communication System (PACS) or workstation to facilitate worklist prioritization or triage. Importantly, the device does not alter original images or provide diagnoses; its function is strictly for notification to guide the urgency of review. The performance of the AIMI-Triage CXR PTX was assessed in a blinded, retrospective, multi-center study involving 300 frontal chest X-rays from a representative adult patient population, with ground truth established by three independent US-board certified radiologists. The software demonstrated an overall area under the curve (AUC) of 96.7%, a sensitivity of 92%, and a specificity of 90% in detecting moderate to large sized pneumothorax. The average time for the system to analyze an image and send a notification to the PACS worklist was 20.3 seconds. The device's performance was also found to be consistent across different datasets (US and OUS) and varying scanner spatial resolutions. It is critical to note that the AIMI-Triage CXR PTX application is limited to analyzing imaging data for potential urgency and should not replace full patient evaluation or be used to make or confirm diagnoses. Radiologists remain responsible for final interpretation and patient care decisions, and the device is not intended for use with plain film X-rays.

AI Regulatory Concerns

Powered byJev by TypeSafe AI

Jev reads the full FDA letter and returns calibrated concern probabilities per regulatory category. These are AI estimates, not regulatory advice.

Keywords

PneumothoraxChest X-rayArtificial IntelligenceTriageNotification SoftwareRadiologyPACS IntegrationAlgorithmSensitivitySpecificity

Device Metadata

Submission Number
K193300
Company
RADLogics, Inc.
Panel
Radiology
Product Code
N/A
Data Type
Images
Clinical Function
Assessment
AI Function
Analysis
AI Subclass
triage

Relevant Clinical Questions

  • Q1. How does the AI algorithm's performance vary with different sizes of pneumothorax (e.g., small vs. moderate vs. large), and what is the defined threshold for 'moderate to large'?; What were the specific demographics, inclusion/exclusion criteria, and geographical diversity of the patient data used for training and validating the AI algorithm?; How does the AIMI-Triage CXR PTX system differentiate features of pneumothorax from other pulmonary conditions that might present with similar radiographic appearances?; What is the system's robustness to variations in chest X-ray image quality, such as patient positioning, exposure levels, or presence of artifacts?; Are there studies evaluating the real-world impact of AIMI-Triage CXR PTX on radiologist reading times, diagnostic accuracy for non-triaged findings, or patient outcomes in acute care settings?

Risk Classification

ESL Analysis
FDA Device ClassII

FDA Class II via 510(k) pathway; IEC 62304 Class B (software safety classification); Authorized before §524B enforcement

Learn how Parasoft automates IEC 62304 compliance testing →

Cybersecurity Evidence

Powered by SBOMator™

Based on AI-generated device summaries, not the full FDA submission. Items not detected here may still be present in the complete submission package.

Cyber Score25/100
SBOM Evidence⚠ Not mentioned in summary
Cyber Risk Assessment⚠ Not mentioned in summary
Postmarket Plan✓ Detected in Summary
§524B ApplicableNo

Supply Chain BOM Evidence

Based on the CycloneDX / OWASP ECMA-424 xBOM ecosystem. Detection is from the AI-generated summary.

SBOMSoftware Bill of Materials
- Not detected
ML-BOMMachine Learning Bill of Materials(algorithm, dataset, ground truth)
✓ Detected
SaaSBOMSoftware-as-a-Service Bill of Materials(network)
✓ Detected
HBOMHardware Bill of Materials
- Not detected
CBOMCryptography Bill of Materials
- Not detected
VDR/VEXVulnerability Disclosure Report / Vulnerability Exploitability eXchange
- Not detected
OBOMOperations Bill of Materials
- Not detected

Analysis:

• Analysis is based on the AI-generated device summary, not the full FDA submission package. Click "Analyze Full FDA PDF" below to scan the actual submission document.

• Evidence of ML-BOM, SaaSBOM detected in AI-generated device summary.

• This device was authorized before §524B took effect. Cybersecurity evidence requirements were less prescriptive at the time.

• Not detected in AI-generated device summary: SBOM, HBOM, CBOM, VDR/VEX, OBOM. These may be present in the full FDA submission.

Preparing a similar submission?

ESL takes complete ownership of your software evidence work - SBOM & CVE remediation with SBOMator™, static analysis & unit testing with Parasoft, traceability, and full IEC 62304 lifecycle support.

Assess Your Readiness →Or contact ESL directly
AIMI-Triage CXR PTX - RADLogics, Inc. | ESL FDA AI Device Intelligence