Lunit INSIGHT CXR Triage is a radiological computer-assisted triage and notification software that analyzes adult chest X-ray images for the presence of pre-specified suspected critical findings (pleural effusion and/or pneumothorax). Lunit INSIGHT CXR Triage uses an artificial intelligence algorithm to analyze images for features suggestive of critical findings and provides case-level output available in the PACS/workstation for worklist prioritization or triage.

As a passive notification for prioritization-only software tool within standard of care workflow, Lunit INSIGHT CXR Triage does not send a proactive alert directly to the appropriately trained medical specialists. Lunit INSIGHT CXR Triage is not intended to direct attention to specific portions of an image. Its results are not intended to be used on a standalone basis for clinical decision-making.

Device Description

Lunit INSIGHT CXR Triage is a radiological computer-assisted prioritization software that utilizes AI-based image analysis algorithms to identify pre-specified critical findings (pleural effusion and/or pneumothorax) on frontal chest X-ray images and flag the images in the PACS/workstation to enable prioritized review by the appropriately trained medical specialists who are qualified to interpret chest radiographs. The software does not alter the order or remove cases from the reading queue.

Chest radiographs are automatically received from the user's image system (e.g. Picture Archiving and Communication System (PACS)) or other radiological imaging equipment (e.g. X-ray systems) and processed by the Lunit INSIGHT CXR Triage for analysis. Following receipt of chest radiographs, the software device de-identifies a copy of each chest radiographs in DICOM format (.dcm) and automatically analyzes each image to identify features suggestive of pleural effusion and/or pneumothorax. Based on the analysis result, the software notifies PACS/workstation for the presence of the critical findings as indicating either "flag" or "(blank)". This would allow the appropriately trained medical specialists to group suspicious exams together that may potentially benefit for their prioritization. Chest radiographs without an identified anomaly are placed in the worklist for routine review, which is the current standard of care. Lunit INSIGHT CXR Triage can flag more than one critical finding per radiograph and the user may select the option to turn on and off notification of critical findings (pleural effusion and pneumothorax).

When deployed on other radiological imaging equipment, Lunit INSIGHT CXR Triage automatically runs after image acquisition. It prioritizes and displays the analysis result through the worklist interface of PACS/workstation. Moreover, the analysis result can also be provided in the form of DICOM files containing information on the presence of suspicious radiologic findings. In parallel, the algorithms produce an on-device notification indicating which cases were prioritized by Lunit INSIGHT CXR Triage in PACS. The on-device notification does not provide any diagnostic information and it is not intended to inform any clinical decision, prioritization, or action to the technologist.

Lunit INSIGHT CXR Triage works in parallel to and in conjunction with the standard care of workflow; therefore, the user enables to review the study containing critical findings earlier than others. As a passive notification for prioritization-only software tool within standard of care workflow, the software does not send a proactive alert directly to the appropriately trained medical specialists who are qualified to interpret chest radiographs. Lunit INSIGHT CXR Triage is not intended to direct attention to specific portions or anomalies of an image and it should not be used on a stand-alone basis for clinical decision-making.

In parallel, an on-device, technologist notification is generated 15 minutes after interpretation by the user, indicating which cases were prioritized by Lunit INSIGHT CXR Triage in PACS. The technologist notification is contextual and does not provides any diagnostic information. The ondevice, technologist notification is not intended to inform any clinical decision, prioritization, or action.

AI/ML Overview

Here's a summary of the acceptance criteria and study details for the Lunit INSIGHT CXR Triage device:

1. Table of Acceptance Criteria and Reported Device Performance

| Feature/Metric | Acceptance Criteria | Reported Device Performance (Clinical Study) |
|------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Pleural Effusion Detection | | |
| ROC AUC | > 0.95 | 0.9686 (95% CI: 0.9547 - 0.9824) |
| Sensitivity (Lower Bound) | > 0.85 | 89.86% (95% CI: 86.72 - 93.00) |
| Specificity (Lower Bound) | > 0.85 | 93.48% (95% CI: 91.06 - 95.91) |
| Pneumothorax Detection | | |
| ROC AUC | > 0.95 | 0.9630 (95% CI: 0.9521 - 0.9739) |
| Sensitivity (Lower Bound) | > 0.85 | 88.92% (95% CI: 85.60 - 92.24) |
| Specificity (Lower Bound) | > 0.85 | 90.51% (95% CI: 88.18 - 92.83) |
| Device Performance Time (average) | Comparable to cleared commercial products (HealthCXR (Zebra, K192320) and red dot™ (Behold.AI, K161556)) Considering the primary predicate (HealthCXR) had a delay of ~22 seconds for image transfer, computation, and results transfer, and Critical Care Suite had an average of 42 seconds for acquisition, annotation, processing, and transfer, comparably shorter times would be favorable. | Pleural Effusion: 20.76 seconds (95% CI: 20.23 - 21.28) |
| | | Pneumothorax: 20.45 seconds (95% CI: 19.99 - 20.92) |
| Nonclinical Testing (Standalone Performance) | ROC AUC > 0.95, Sensitivity > 0.80, Specificity > 0.80 | Pleural Effusion: ROC AUC: 0.9864 (95% CI: 0.9815 - 0.9913), Sensitivity: 94.29%, Specificity: 95.72% |
| | | Pneumothorax: ROC AUC: 0.9973 (95% CI: 0.9955 - 0.9992), Sensitivity: 96.08%, Specificity: 99.14% |

2. Sample Size Used for the Test Set and Data Provenance

Clinical Studies (Pivotal Studies):
- Total Sample Size: 1,708 anonymized chest radiographs.
  - 754 cases for pleural effusion.
  - 954 cases for pneumothorax.
- Data Provenance:
  - NIH chest X-ray dataset (represents the US population).
  - India dataset collected from multiple institutions in India (6 sites for pleural effusion and 3 sites for pneumothorax).
- Type: Retrospective (implied by "anonymized chest radiographs collected from datasets").
Nonclinical Internal Validation Test (for standalone performance validation):
- Total Sample Size: 1,385 images.
- Data Provenance: Not explicitly stated, but performed "internally" by the company. It's likely a mix of internal data or data acquired for internal development.
- Type: Retrospective (implied by "images were collected").

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications

Clinical Studies (Pivotal Studies): Not explicitly stated how many experts established the ground truth for the clinical pivotal studies.
Nonclinical Internal Validation Test: "highly experienced board-certified radiologists" were used to classify images into positive and negative groups. The specific number of radiologists is not mentioned.

4. Adjudication Method for the Test Set

The document does not explicitly describe an adjudication method (e.g., 2+1, 3+1). For the Nonclinical Internal Validation Test, it states "classified into positive and negative groups by highly experienced board-certified radiologists," which might imply a consensus or single-reader approach, but an explicit adjudication method is not detailed.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not done or reported in this document. The studies primarily focused on the standalone performance of the Lunit INSIGHT CXR Triage device and comparison to predicate device performance metrics rather than human reader improvement with AI assistance.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

Yes, standalone performance was evaluated:
- An internal nonclinical validation test was conducted specifically "to assess the standalone performance of Lunit INSIGHT CXR Triage."
- The clinical pivotal studies also reported standalone performance metrics (ROC AUC, sensitivity, specificity) for the device.

7. The Type of Ground Truth Used

For both the nonclinical internal validation test and the clinical pivotal studies, the ground truth was established by expert consensus/interpretation, specifically by "highly experienced board-certified radiologists" for the internal validation. For the clinical studies, "positive" cases contained at least one target finding, and "negative" cases did not.

8. The Sample Size for the Training Set

The document does not provide the sample size for the training set. It only discusses the validation/test sets used for performance evaluation.

9. How the Ground Truth for the Training Set Was Established

The document does not specify how the ground truth for the training set was established, as it does not detail the training process or dataset.

Summary

{0}------------------------------------------------

Image /page/0/Picture/0 description: The image shows the logo of the U.S. Food & Drug Administration (FDA). On the left is the Department of Health & Human Services logo. To the right of that is the FDA logo, which is a blue square with the letters "FDA" in white. To the right of the blue square is the text "U.S. FOOD & DRUG ADMINISTRATION" in blue.

Lunit Inc. % Colin Jacob 15th Floor, 27 Teheran-ro 2-gil Gangnam-gu, Seoul REPUBLIC OF KOREA

Re: K211733

November 10, 2021

Trade/Device Name: Lunit INSIGHT CXR Triage Regulation Number: 21 CFR 892.2080 Regulation Name: Radiological computer aided triage and notification software Regulatory Class: Class II Product Code: QFM Dated: October 1, 2021 Received: October 1, 2021

Dear Colin Jacob:

We have reviewed your Section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database located at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmp/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.

If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.

Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801; medical device reporting (reporting of medical device-related adverse events) (21 CFR 803) for devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see

{1}------------------------------------------------

https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.

Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.

For comprehensive regulatory information about medical devices and radiation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-device-advice-comprehensive-regulatoryassistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).

Sincerely,

For

Thalia T. Mills, Ph.D. Director Division of Radiological Health OHT7: Office of In Vitro Diagnostics and Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health

Enclosure

{2}------------------------------------------------

Indications for Use

510(k) Number (if known) K211733

Device Name Lunit INSIGHT CXR Triage

Indications for Use (Describe)

Type of Use (Select one or both, as applicable)
-------------------------------------------------	--

× | Prescription Use (Part 21 CFR 801 Subpart D)

| Over-The-Counter Use (21 CFR 801 Subpart C)

CONTINUE ON A SEPARATE PAGE IF NEEDED.

This section applies only to requirements of the Paperwork Reduction Act of 1995.

DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.

The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:

Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff(@fda.hhs.gov

"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."

{3}------------------------------------------------

510(k) Summary

K211733

This summary of safety and effectiveness information is submitted in accordance with 21 CFR § 807.92.

Date Prepared: November 3, 2021

Submitter Lunit Inc., 15th Floor, 27 Teheran-ro 2-gil, Gangnam-gu, Seoul, Republic of Korea Phone: +82 2 2138 0827 Facsimile: +82 2 6969 5116 Contact Person: Colin S. Jacob

Name of Device:	Lunit INSIGHT CXR Triage
Common or Usual Name:	Lunit INSIGHT CXR Triage
Classification Name:	Radiological Computer-Assisted Prioritization Software for Lesions
Classification Regulation:	21 CFR 892.2080
Regulatory Class:	Class II
Product Code:	QFM

Predicate Device

The Lunit INSIGHT CXR Triage is substantially equivalent to the following devices:

Primary Predicate Device

Manufacturer Name	Zebra Medical Vision, Ltd.
Device Trade Name	HealthCXR
510(k) Number	K192320

Secondary Predicate Device

Manufacturer Name	GE Medical Systems, LLC
Device Trade Name	Critical Care Suite
510(k) Number	K183182

{4}------------------------------------------------

Device Description

{5}------------------------------------------------

Intended Use / Indications for Use

There is a minor difference between the subject and primary predicate device HealthCXR (K192320) in their indications for use. The primary predicate device is indicated for use to analyze chest X-ray images for the presence of pleural effusion, while Lunit INSIGHT CXR Triage detects pleural effusion as well as pneumothorax. While the specific clinical finding differs, the intended use of the device which is to provide passive notification for triage and prioritization for time sensitive radiologic findings in the chest X-ray is the same. Additionally, the time sensitivity of additional potential finding of pneumothorax has been already established in a secondary predicate device; Critical Care Suite (K183182) and the detection of such potential finding in Lunit INSIGHT CXR Triage is supported by performance testing.

Summary of Technological Characteristics

Both the Lunit INSIGHT CXR Triage and the predicate devices are software only devices that use Artificial intelligence (AI) algorithms and are intended to aid in triage and prioritization of radiological images. At a high level, the subject and the predicate devices are based on the following same technological elements:

· Artificial Intelligence Algorithm(s)
· Triage and prioritization software

The following technological differences exist between the subject and predicate devices:

· Clinical condition(s)
Lunit INSIGHT CXR Triage detects suspected findings, pleural effusion as well as pneumothorax. In comparison, the primary predicate device detects suspected findings of pleural effusion alone. However, both devices identify time sensitive findings and provide passive notification and pleural effusion as well as pneumothorax have been accepted by FDA as appropriate for regulation as CAD t devices.

Comparison of the key features of the subject, and predicate devices is provided in Table 1.

{6}------------------------------------------------

Performance Data

The performance of Lunit INSIGHT CXR Triage was validated by clinical and nonclinical tests. All verification testing met the acceptance criteria (passed), demonstrating that the software fulfills its requirement specifications.

Nonclinical Tests

The company conducted an internal validation test to assess the standalone performance of Lunit INSIGHT CXR Triage. The validation was completed to determine whether a distinction between target findings is properly completed by the subject device. A total of 1,385 images were collected according to the inclusion and exclusion criteria and classified into positive and negative groups by highly experienced board-certified radiologists. For each target finding, positive includes any case that contains at least one target finding in the image and negative represents the case that does not have the target finding, which includes cases without any findings and cases that contain findings other than the target radiologic finding.

Summary of results: ROC AUC was 0.9864 (95% CI: 0.9815 - 0.9913) with 94.29% sensitivity and 95.72% specificity for pleural effusion. For pneumothorax, 0.9973 ROC AUC (95% CI: 0.9955 -0.9992), 96.08% sensitivity, and 99.14% specificity were reported. By confirming that the lower bound of ROC AUC exceeds 0.95 and the sensitivity and specificity for both target radiologic findings are above 0.80, the performance of the algorithm of Lunit INSIGHT CXR Triage is validated to demonstrate that the prespecified target performance is satisfied.

Clinical Tests

Two individual clinical pivotal studies were conducted to evaluate the effectiveness of the Lunit INSIGHT CXR Triage. The studies were conducted with NIH chest X-ray dataset that represents the US population and India dataset collected respectively from multiple institutions in India (6 sites for pleural effusion and 3 sites for pneumothorax).

A total of 1,708 anonymized chest radiographs (754 cases for pleural effusion and 954 cases for pneumothorax) collected from NIH chest X-ray dataset and multiple institutions in India were enrolled in the validation dataset for the standalone performance test and device performance time estimation. For pleural effusion, the results are as follow: ROC AUC 0.9686 (95% CI: 0.9547 - 0.9824), sensitivity 89.86% (95% CI: 86.72 - 93.00) and specificity 93.48% (95% CI: 91.06 - 95.91). For pneumothorax, the results are as follows: ROC AUC 0.9630 (95% CI: 0.9521 - 0.9739), Sensitivity 88.92% (95% CI: 85.60 - 92.24) and Specificity 90.51% (95% CI: 88.18 - 92.83). The performance for the primary predicate device indicated for pleural effusion (Zebra Medical Vision, HealthCXR) are as follows: ROC AUC was 0.9885 (95% CI: 0.9815 - 0.9956) with sensitivity 96.74% (95% CI: 92.79 -96.48) and specificity 93.17% (95% CI: 89.57 – 95.58). The performance data show that the lower bound of ROC AUC exceeds 0.95 and the lower bounds of both sensitivity and specificity are above

Image /page/6/Picture/11 description: The image shows the word "Lunit" in a simple, sans-serif font. To the left of the word is a small, stylized graphic consisting of two circles connected by a diagonal line. The graphic is in a light blue color, while the text is in a darker shade of blue or black. The overall design is clean and modern.

{7}------------------------------------------------

0.85 for both pleural effusion and pneumothorax. Accordingly, the Lunit INSIGHT CXR Triage is demonstrated to achieve effective image analysis and triage capabilities.

With regards to the device performance time, the company assessed the performance time of the Lunit INSIGHT CXR Triage that reflects the time it takes for the device to analyze the study and send a notification to the worklist. The performance time of the Lunit INSIGHT CXR Triage was 20.76 seconds (95% CI: 20.23 - 21.28) for pleural effusion and 20.45 seconds (95% CI: 19.99 - 20.92) for pneumothorax. As compared the device performance time of the Lunit INSIGHT CXR Triage with cleared commercial products (HealthCXR (Zebra, K192320) and red dot™ (Behold.AI, K161556)), the result was comparable with the primary predicate device and other 510(k) cleared products.

In summary, the Lunit INSIGHT CXR Triage performed successfully in the clinical pivotal studies. The Lunit INSIGHT CXR Triage established standalone adequate detection performance and device performance time for pleural effusion and pneumothorax as compared to the primary predicate device.

Conclusions

The Lunit INSIGHT CXR Triage is as safe and effective as the predicate devices. The Lunit INSIGHT CXR Triage has the same intended uses and similar indications, technological characteristics, and principles of operation as its predicate devices. The minor differences in indications do not alter the intended use of the device and do not affect its safety and effectiveness when used as labeled. In addition, the minor technological differences between the Lunit INSIGHT CXR Triage and its predicate devices raise no new issues of safety or effectiveness. The clinical and non-clinical performance data demonstrates that the Lunit INSIGHT CXR Triage is as safe and effective as the predicate devices. Thus, the Lunit INSIGHT CXR Triage support a decision is substantially equivalent to its predicate devices for triage and notification.

{8}------------------------------------------------

Lunit, Inc.
15 Floor, 27 Teheran-ro 2-gil, Gangnam-gu, Seoul, 06241, Republic of Korea

Traditional 510(k) Lunit INSIGHT CXR Triage

Page 6 of 10

Table 1 Substantial Equivalence Table

TechnologicalCharacteristics	Proposed Device:Lunit INSIGHT CXR Triage	Primary Predicate Device:HealthCXR (K192320)	Secondary Predicate Device:Critical Care Suite (K183182)
Deviceclassification	Radiological Computer AssistedPrioritization Software Class II,QFM	Radiological Computer AssistedPrioritization Software Class II,QFM	Radiological Computer AssistedPrioritization Software Class II,QFM
Indication forUse/IntendedUse	Lunit INSIGHT CXR Triage is aradiological computer-assisted triageand notification software thatanalyzes adult chest X-ray images forthe presence of pre-specifiedsuspected critical findings (pleuraleffusion and/or pneumothorax).Lunit INSIGHT CXR Triage uses anartificial intelligence algorithm toanalyze images for featuressuggestive of critical findings andprovides case-level output availablein the PACS/workstation forworklist prioritization or triage.As a passive notification forprioritization-only software toolwithin standard of care workflow,Lunit INSIGHT CXR Triage doesnot send a proactive alert directly tothe appropriately trained medicalspecialists. Lunit INSIGHT CXRTriage is not intended to directattention to specific portions of animage or to anomalies other than	The Zebra HealthCXR device is asoftware workflow tool designed toaid the clinical assessment of adultChest X-Ray cases with featuressuggestive of pleural effusion in themedical care environment.HealthCXR analyzes cases using anartificial intelligence algorithm toidentify suspected findings. It makescase-level output available to aPACS/workstation for worklistprioritization or triage. HealthCXR isnot intended to direct attention tospecific portions or anomalies of animage. Its results are not intended tobe used on a stand-alone basis forclinical decision-making nor is itintended to rule out Pleural Effusionor otherwise preclude clinicalassessment of X-Ray cases.	Critical Care Suite is a computeraided triage and notification devicethat analyzes frontal chest x-rayimages for the presence of pre-specified critical findings(pneumothorax). Critical Care Suiteidentifies images with critical findingto enable case prioritization or triagein the PACS/workstation.Critical Care Suite is intended fornotification only and does notprovide diagnostic informationbeyond the notification. Critical CareSuite should not be used in-lieu offull patient evaluation or solely reliedupon to make or confirm a diagnosis.It is not intended to replace thereview of the x-ray image by aqualified physician.Critical Care Suite is indicated foradult-size patients.
TechnologicalCharacteristics	Proposed Device:Lunit INSIGHT CXR Triage	Primary Predicate Device:HealthCXR (K192320)	Secondary Predicate Device:Critical Care Suite (K183182)
	pleural effusion and/orpneumothorax. Its results are notintended to be used on a stand-alonebasis for clinical decision-making.
Notification-only, parallelworkflow tool	Yes	Yes	Yes
User	Appropriately trained medicalspecialists who are qualified tointerpret chest radiographs.	Radiologist	Radiologist
Targetedclinicalcondition,anatomy, andmodality	Pleural effusion, pneumothoraxChest/LungFrontal Chest X-ray	Pleural effusionChest/LungFrontal Chest X-ray	PneumothoraxChest/LungFrontal Chest X-ray
Algorithm forpre-specifiedcritical findingsdetection	AI algorithm designed to detectpleural effusion and pneumothoraxin chest X-ray images.Lunit INSIGHT CXR Triage uses avendor agnostic algorithmcompatible with DICOM chest X-rayimages.	AI algorithm designed to detectpleural effusion in chest X-rayimages.HealthCXR employs a vendoragnostic algorithm compatible withDICOM chest X-ray images.	AI algorithm designed to detectpneumothorax in frontal chest X-rayimages.Critical Care Suite uses a vendoragnostic algorithm compatible withDICOM frontal chest X-ray images.
Radiologicalimages format	DICOM	DICOM	DICOM
ComputationalPlatform	Lunit INSIGHT CXR Triage isdesigned as a software module thatcan be deployed on several	HealthCXR is designed as a softwaremodule that can be deployed on	Critical Care Suite is designed as asoftware module that can bedeployed on several computing and
TechnologicalCharacteristics	Proposed Device:Lunit INSIGHT CXR Triage	Primary Predicate Device:HealthCXR (K192320)	Secondary Predicate Device:Critical Care Suite (K183182)
	computing and X-ray imagingplatforms such as radiologicalimaging equipment, PACS, OnPremise or On Cloud.	PACS and Standalone desktopapplication, Zebra Worklist.	X-ray imaging platforms such asDigital Projection RadiographicSystems, PACS, On Premise or OnCloud.
	When deployed on other radiologicalimaging equipment, Lunit INSIGHTCXR Triage automatically runs afterimage acquisition and prioritizes anddisplays the analysis result throughthe worklist interface ofPACS/workstation.	Integration module notifies thePACS/workstation for prioritizationthrough the worklist interface.	Critical Care Suite enables caseprioritization or triage through directcommunication of the Critical CareSuite notification during imagetransfer to the PACS.
Device outputin case ofpositivedetection	No markup on original image.	No markup on original image.	No markup on original image
	Secondary capture of the finding.
	Upon image acquisition from otherradiological imaging equipment (e.g.X-ray systems), an on-device,technologist notification indicatingwhich cases were flagged by LunitINSIGHT CXR Triage in PACS, isgenerated 15 minutes afterinterpretation by the user. The on-device notification is contextual anddoes not provide any diagnosticinformation. It is not intended to		Upon image acquisition on a DigitalProjection Radiographic System, anon-device, technologist notification isgenerated 15 minutes after examclosure, indicating which cases wereprioritized by Critical Care Suite inPACS. The technologist notificationis contextual and does not providesany diagnostic information. The on-device, technologist notification isnot intended to inform any clinicaldecision, prioritization, or action.
Republic of Korea
TechnologicalCharacteristics	Proposed Device:Lunit INSIGHT CXR Triage	Primary Predicate Device:HealthCXR (K192320)	Secondary Predicate Device:Critical Care Suite (K183182)
	inform any clinical decision,prioritization, or action to thetechnologist.
Notification(i.e., recipient,timing andmeans ofnotification)	Passive notification.Images with suspicion of pleuraleffusion and/or pneumothorax areflagged in PACS/workstation.	Passive notification.Images with suspicion of pleuraleffusion are flagged inPACS/workstation.	Passive notification.Images with suspicion ofpneumothorax are flagged inPACS/workstation.
Wheregeneratedresults (i.e.,DICOM files)are stored	PACS/Workstation	PACS/Workstation	PACS/Workstation
Performancelevel –Timing ofnotification	The average time taken for thenotification to travel from the LunitINSIGHT CXR Triage to the pointat which the result is displayed in thedestination PACS/RIS/EPR worklistis 14.66 seconds.	Passive notification is visible upontransfer to the PACS with a delay ofabout 22 seconds for image transferto the cloud, computation, andresults transfer.	The average time to acquire,annotate, process and transfer animage from the x-ray system toPACS was measured and found totake 42 seconds on average. Examsarrive on PACS with the passivenotification already incorporated,therefore there is no delay for imagetransfer or computation. Theworklist prioritization happensimmediately once the exam isreceived on the PACS.
TechnologicalCharacteristics	Proposed Device:Lunit INSIGHT CXR Triage	Primary Predicate Device:HealthCXR (K192320)	Secondary Predicate Device:Critical Care Suite (K183182)
Performancelevel –accuracy ofclassification	Pleural Effusion	ROC AUC > 0.95	ROC AUC > 0.95
	ROC AUC > 0.95	AUC: 0.9885 (95% CI: [0.9815, 0.9956])	AUC: 0.9607 (95% CI [0.9491, 0.9724])
	AUC: 0.9686 (95% CI: [0.9547, 0.9824])	First operating point	Specificity 93.5% (95% CI [91.1%, 95.8%])
	Sensitivity 89.86% (95% CI: [86.72, 93.00])	Sensitivity 96.74% (95% CI: [92.79; 96.48])	Sensitivity 84.3% (95% CI [80.6%, 88.0%])
	Specificity 93.48% (95% CI: [91.06, 95.91])	Specificity 93.17% (95% CI: [89.57; 95.58])	AUC on large pneumothorax 0.9888 (95% CI [0.9810, 0.9965])
	Pneumothorax	"High-specificity" operatingpoint	Sensitivity on large pneumothorax96.3% (95% CI [93.3%, 99.2%])
	ROC AUC > 0.95	Sensitivity 93.84% (95% CI:[90.36;96.12])	AUC on small pneumothorax 0.9389(95% CI [0.9209, 0.9570])
	AUC: 0.9630 (95% CI: [0.9521, 0.9739])	Specificity 97.12% (95% CI:[94.43;98.53])	Sensitivity on small pneumothorax75% (95% CI [69.2%, 80.8%])
Sensitivity 88.92% (95% CI: [85.60, 92.24])
Specificity 90.51% (95% CI: [88.18, 92.83])

Image /page/8/Picture/5 description: The image contains the word "Lunit" in a sans-serif font. To the left of the word is a teal-colored graphic that resembles a network connection or a molecule. A thin teal line is above the word.

{9}------------------------------------------------

Lunit, Inc.
15 Floor, 27 Teheran-ro 2-gil, Gangnam-gu, Seoul, 06241,
Republic of Korea

Traditional 510(k) Lunit INSIGHT CXR Triage

Page 7 of 10

Image /page/9/Picture/4 description: The image shows the word "Lunit" in a sans-serif font. The "L" is in black, while the rest of the word is in a lighter shade of gray. To the left of the word is a blue graphic consisting of two circles connected by a line, positioned above a blue line that extends over the word.

{10}------------------------------------------------

Lunit, Inc.
15 Floor, 27 Teheran-ro 2-gil,
Gangnam-gu, Seoul, 06241,
Republic of Korea

Traditional 510(k) Lunit INSIGHT CXR Triage

Page 8 of 10

{11}------------------------------------------------

Lunit, Inc.
15 Floor, 27 Teheran-ro 2-gil, Gangnam-gu, Seoul, 06241,
Republic of Korea

Traditional 510(k) Lunit INSIGHT CXR Triage

Page 9 of 10

{12}------------------------------------------------

Lunit, Inc.
15 Floor, 27 Teheran-ro 2-gil, Gangnam-gu, Seoul, 06241,
Republic of Korea

Traditional 510(k) Lunit INSIGHT CXR Triage

Page 10 of 10

Regulation Number and Section

§ 892.2080 Radiological computer aided triage and notification software.

(a)
Identification. Radiological computer aided triage and notification software is an image processing prescription device intended to aid in prioritization and triage of radiological medical images. The device notifies a designated list of clinicians of the availability of time sensitive radiological medical images for review based on computer aided image analysis of those images performed by the device. The device does not mark, highlight, or direct users' attention to a specific location in the original image. The device does not remove cases from a reading queue. The device operates in parallel with the standard of care, which remains the default option for all cases.(b)
Classification. Class II (special controls). The special controls for this device are:(1) Design verification and validation must include:
(i) A detailed description of the notification and triage algorithms and all underlying image analysis algorithms including, but not limited to, a detailed description of the algorithm inputs and outputs, each major component or block, how the algorithm affects or relates to clinical practice or patient care, and any algorithm limitations.
(ii) A detailed description of pre-specified performance testing protocols and dataset(s) used to assess whether the device will provide effective triage (
e.g., improved time to review of prioritized images for pre-specified clinicians).(iii) Results from performance testing that demonstrate that the device will provide effective triage. The performance assessment must be based on an appropriate measure to estimate the clinical effectiveness. The test dataset must contain sufficient numbers of cases from important cohorts (
e.g., subsets defined by clinically relevant confounders, effect modifiers, associated diseases, and subsets defined by image acquisition characteristics) such that the performance estimates and confidence intervals for these individual subsets can be characterized with the device for the intended use population and imaging equipment.(iv) Stand-alone performance testing protocols and results of the device.
(v) Appropriate software documentation (
e.g., device hazard analysis; software requirements specification document; software design specification document; traceability analysis; description of verification and validation activities including system level test protocol, pass/fail criteria, and results).(2) Labeling must include the following:
(i) A detailed description of the patient population for which the device is indicated for use;
(ii) A detailed description of the intended user and user training that addresses appropriate use protocols for the device;
(iii) Discussion of warnings, precautions, and limitations must include situations in which the device may fail or may not operate at its expected performance level (
e.g., poor image quality for certain subpopulations), as applicable;(iv) A detailed description of compatible imaging hardware, imaging protocols, and requirements for input images;
(v) Device operating instructions; and
(vi) A detailed summary of the performance testing, including: test methods, dataset characteristics, triage effectiveness (
e.g., improved time to review of prioritized images for pre-specified clinicians), diagnostic accuracy of algorithms informing triage decision, and results with associated statistical uncertainty (e.g., confidence intervals), including a summary of subanalyses on case distributions stratified by relevant confounders, such as lesion and organ characteristics, disease stages, and imaging equipment.