CINA CHEST is a radiological computer aided triage and notification software indicated for use in the analysis of Chest and Thoraco-abdominal CT angiography. The device is intended to assist hospital networks and trained radiologists in workflow triage by flagging and communicating suspected positive findings of (1) Chest CT angiography for Pulmonary Embolism (PE) and (2) Chest or Thoraco-abdominal CT angiography for Aortic Dissection (AD).

CINA CHEST uses an artificial intelligence algorithm to analyze images and highlight cases with detected PE and AD on a standalone Web application in parallel to the ongoing standard of care image interpretation. The user is presented with notifications for cases with suspected PE or AD findings. Notifications include compressed preview images that are meant for informational purposes only, and are not intended for diagnostic use beyond notification. The device does not alter the original medical image, and it is not intended to be used as a diagnostic device.

The results of CINA CHEST are intended to be used in conjunction with other patient information and based on professional judgment to assist with triage/prioritization of medical images. Notified clinicians are ultimately responsible for reviewing full images per the standard of care.

Device Description

CINA CHEST is a radiological computer-assisted triage and notification software device.

The software system is based on algorithm-programmed components and is comprised of a standard off-the-shelf operating system and additional image processing applications.

DICOM images are received, recorded and filtered before processing. The series are processed chronologically by running algorithms on each series to detect suspected positive findings of a pulmonary embolism (PE) or an aortic dissection (AD), then notifications on the flagged series are sent to the Worklist Application.

The Worklist Application (on premise) displays the pop-up notifications of new studies with suspected findings when they come in, and provides both active and passive notifications. Active notifications are in the form of a small pop-up containing patient name, accession number and the type of suspected findings (PE or AD). All the chest and thoraco-abdominal CT angiography studies received by CINA CHEST device are displayed in the worklist and those on which the algorithms have detected a suspected finding (PE or AD) are marked with an icon (i.e., passive notification). In addition, a compressed, small black and white image that is marked "not for diagnostic use" is displayed as a preview function. This compressed preview is meant for informational purposes only, does not contain any marking of the findings, and is not intended for primary diagnosis beyond notification. Presenting the radiologist with notification facilitates earlier triage by allowing one to prioritize images in the PACS. Thus, the suspect case receives attention earlier than would have been the case in the standard of care practice alone.

AI/ML Overview

Here's a detailed breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided FDA 510(k) summary for CINA CHEST:

Acceptance Criteria and Reported Device Performance

Parameter	Acceptance Criteria (Performance Goal)	Reported Device Performance (CINA CHEST)	Comparison to Predicate (BriefCase)
Pulmonary Embolism (PE) Detection
Sensitivity	≥ 80%	91.1% [95% CI: 86.1% - 94.7%]	Predicate: 90.6% [95% CI: 82.2% - 95.9%]
Specificity	≥ 80%	91.8% [95% CI: 87.1% - 95.1%]	Predicate: 89.9% [95% CI: 82.2% - 95.1%]
Accuracy	Not explicitly stated as a minimum goal, but reported.	91.4%	Not explicitly stated for predicate.
Time-to-Notification (PE)	Not explicitly stated as a minimum/maximum goal, but comparable to predicate.	63 ± 16.1 seconds (Mean) 60.8 seconds (Median) [95% CI: 61.5 – 64.6] seconds	Predicate: 3.9 [95% CI: 3.7 - 4.1] minutes (234 seconds)
Aortic Dissection (AD) Detection
Sensitivity	≥ 80%	96.4% [95% CI: 91.7% - 98.8%]	Not applicable (Predicate is for PE/ICH, not AD)
Specificity	≥ 80%	97.5% [95% CI: 93.8% - 99.3%]	Not applicable
Accuracy	Not explicitly stated as a minimum goal, but reported.	97%	Not applicable
Time-to-Notification (AD)	Not explicitly stated as a minimum/maximum goal, but comparable to reference.	36.5 ± 9.1 seconds (Mean) 34.1 seconds (Median) [95% CI: 35.4 – 37.5] seconds	Reference (CINA, ICH/LVO): 21.6 ± 4.4 sec (ICH), 34.7 ± 10.7 sec (LVO)

Study Details

Sample sizes used for the test set and the data provenance:
- Pulmonary Embolism (PE): 396 clinical anonymized cases.
- Aortic Dissection (AD): 298 clinical anonymized cases.
- Data Provenance: Retrospective, multicenter study. Data was provided from multiple US clinical sites (230 US cities for PE, and 200 US cities for AD).
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Number of Experts: "Several US-board-certified radiologist readers." The exact number is not specified beyond "several".
- Qualifications: US-board-certified radiologists. No specific years of experience are mentioned.
Adjudication method for the test set:
- The ground truth was established by "concurrence of several US-board-certified radiologist readers." This implies a consensus-based adjudication, but the specific method (e.g., majority vote, unanimous agreement, or an independent adjudicator in case of disagreement) is not explicitly detailed.
If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:
- No, an MRMC comparative effectiveness study was not reported. The study described is a standalone performance evaluation of the CINA CHEST software against a ground truth. It assesses the device's ability to identify PE and AD cases for triage, not the improvement of human readers with AI assistance.
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Yes, a standalone study was done. The document explicitly states: "Avicenna.Al conducted a retrospective, multicenter and blinded study with the CINA CHEST software with the primary endpoint to evaluate the software's performance..." and later refers to "The results of the standalone assessment study demonstrated an overall agreement (Accuracy)..." This confirms the study evaluated the algorithm's performance in isolation.
The type of ground truth used:
- Expert Consensus. The ground truth was "established by concurrence of several US-board-certified radiologist readers."
The sample size for the training set:
- The document does not specify the sample size for the training set. It only details the test set used for performance evaluation.
How the ground truth for the training set was established:
- Since the training set sample size is not provided, the method for establishing its ground truth is also not detailed in this document. It is common for AI algorithms to be trained on data with ground truth established by expert radiologists or pathology, but this specific information is absent here.

Summary

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

May 19, 2021

Image /page/0/Picture/1 description: The image contains the logo of the U.S. Food and Drug Administration (FDA). On the left is the Department of Health & Human Services logo. To the right of that is the FDA logo, which consists of the letters "FDA" in a blue square, followed by the words "U.S. FOOD & DRUG" in blue, with the word "ADMINISTRATION" underneath.

Avicenna.AI % John J. Smith, M.D., Ph.D. Partner Hogan Lovells US LLP 555 13th St. NW WASHINGTON DC 20004

Re: K210237

Trade/Device Name: CINA CHEST Regulation Number: 21 CFR 892.2080 Regulation Name: Radiological Computer aided triage and notification software Regulatory Class: Class II Product Code: QAS Dated: April 23, 2021 Received: April 23, 2021

Dear Dr. Smith:

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/cfpmn/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 and Part 809); medical device reporting of medical device-related adverse events) (21 CFR

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

for devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see 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 mediation-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}------------------------------------------------

DEPARTMENT OF HEALTH AND HUMAN SERVICES Food and Drug Administration Indications for Use

Form Approved: OMB No. 0910-0120 Expiration Date: 06/30/2023 See PRA Statement below

510(k) Number (if known)

K210237

Device Name

CINA CHEST

Indications for Use (Describe)

CINA CHEST uses an artificial intelligence algorithm to analyze images and highlight cases with detected PE and AD on a standalone Web application in parallel to the ongoing standard of care image interpretation. The user is presented with notifications for cases with suspected PE or AD findings. Notifications include compressed preview images that are meant for informational purposes only, and are not intended for diagnostic use bevond notification. The device does not alter the original medical image, and it is not intended to be used as a diagnostic device.

The results of CINA CHEST are intended to be used in conjunction with other patient information and based on professional judgment to assist with triage/prioritization of medical images. Notfiled clinicians are ultimately responsible for reviewing full images per the standard of care.

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

X 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

AVICENNA.AI's CINA CHEST

l. Submitter

Applicant:

AVICENNA.AI 93 avenue du Sorbiers, Zone Athelia IV 13600 La Ciotat France

Contact Person:

Stephane Berger Regulatory Manager Phone: +33 6 12 12 28 13 E-mail: stephane.berger@avicenna.ai

Date prepared: January 28, 2021

II. Device Identification

Name of Device:	CINA CHEST
Classification Name:	Radiological Computer-Assisted Triage AndNotification Software
Regulation No:	21 CFR § 892.2080
Product Code:	QAS
Regulatory Class:	Class II
Classification Panel:	Radiology devices

III. Predicate Device

The CINA CHEST device is substantially equivalent to the following predicate device with regard to indications for use, performance, and technological characteristics:

510(k):	K190072
Trade Name:	BriefCase
Manufacturer:	AiDoc Medical, Ltd
Classification Name:	Radiological Computer-Assisted Triage AndNotification Software
Regulation No:	21 CFR § 892.2080
Product Code:	QAS
Regulatory Class:	Class II

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

A reference device is Avicenna.Ai's CINA (K200855), which is a Class II device under the same regulation and product code as above.

IV. Device Description

CINA CHEST is a radiological computer-assisted triage and notification software device.

The software system is based on algorithm-programmed components and is comprised of a standard off-the-shelf operating system and additional image processing applications.

V. Intended Use / Indications for Use

CINA CHEST is a radiological computer aided triage and notification software indicated for use in the analysis of Chest and Thoraco-abdominal CT angiography. The device is intended to assist hospital networks and trained radiologists in workflow triage by flagging and communicating suspected positive findings of (1) Chest CT angiography for Pulmonary Embolism (PE) and (2) Chest or Thoracoabdominal CT angiography for Aortic Dissection (AD).

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

VI. Summary of Technological Characteristics

CINA CHEST runs on a standard "off the shelt" server/workstation and is comprised of PE and AD Image Processing Applications, which can be integrated, deployed and used with the reference device (K200855) or other compatible medical image communications devices. CINA CHEST receives CTA scans identified by the CINA Platform or other compatible medical image communications device. processes them using algorithmic methods involving execution of multiple computational steps to identify suspected presence of PE or AD and generates results files to be transferred by CINA Platform or a similar medical image communications device for output to a PACS system or workstation for worklist prioritization. Each of these components is briefly described below.

VI.1. CINA Platform

The CINA platform is an example of medical image communications platform for integrating and deploying the CINA CHEST PE and AD image processing applications. It provides the necessary requirements for interoperability based on the standardized DICOM protocol and services to communicate with existing systems in the hospital radiology department such as CT modalities or other DICOM nodes (DICOM router or PACS for example). It is responsible for transferring, storing, converting formats, notifying of suspected findings and displaying medical device data such as radiological data. The CINA Platform server includes the Worklist client application in which notifications from the CINA CHEST Image Processing applications (PE and AD) are received. The CINA Platform and base functions were cleared in the reference device (K200855).

VI.2. PE Application

The PE application includes the software algorithm responsible for identifying image characteristics that are consistent with a Pulmonary Embolism (PE). This application reads provided DICOM files, checks the DICOM properties to verify the compatibility with the recommended acquisition protocol, launches the algorithm and provides notification results (when a PE is detected) compatible with the CINA Platform and with DICOM format.

VI.3. AD Application

The AD application includes the software algorithm responsible for identifying and quantifying image characteristics that are consistent with an Aortic Dissection (AD). This application reads provided DICOM files, checks the DICOM properties to verify the compatibility with the recommended acquisition protocol, launches the algorithm part and provides notification results (when an AD is detected) compatible with the CINA Platform and with DICOM format.

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

VII. Summary of Performance Data

The following performance data were provided in support of the substantial equivalence determination.

VII.1. Software Verification and Validation Testing

The CINA CHEST device has been evaluated and verified in accordance with software specifications and applicable performance standards through a Software Development and Validation & Verification Process to ensure performance according to specifications, User Requirements and Federal Regulations and Guidance documents, "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices".

The mutual compatibility with the CINA Platform has been verified through the V&V activities that have been conducted at the system level to ensure the safe and proper use of the system. Special attention has been paid to:

. DICOM analysis,
Processing pipeline, ●
Front-end interface, and .
Notifications for suspected findings performances. ●

VII.2. Performance Testing

Avicenna.Al conducted a retrospective, multicenter and blinded study with the CINA CHEST software with the primary endpoint to evaluate the software's performance in 1) Chest CT angiography (CTA) images pertaining to patient with suspected Pulmonary Embolism (PE) findings and 2) Chest or Thoraco-abdominal CT angiography (CTA) images series pertaining to patient with suspected Aortic Dissection (AD) findings, in 396 and 298 clinical anonymized cases, respectively.

The data was provided from multiple US clinical sites: 230 and 200 US cities, for PE and AD, respectively. There were 190 (48%) positive PE (images with PE) cases and 137 (46%) positive AD (images with AD) cases included in the analyses.

Device sensitivities and specificities were compared to ground truth established by concurrence of several US-board-certified radiologist readers.

Sensitivity and Specificity for the "PE" prioritization and triage application were found to be 91.1% [95% CI: 86.1% - 94.7 %] and 91.8% [95% Cl: 87.1% - 95.1%], respectively.

Regarding the "AD" prioritization and triage application, Sensitivity and Specificity of 96.4% (95% Cl: 91.7% - 98.8%] and 97.5% [95% Cl: 93.8% - 99.3%], respectively, were obtained.

All these findings achieved the 80% performance goal and are similar to the results reported for the predicate device BriefCase (Aidoc Medical): Sensitivity and Specificity of 90.6% [95% Cl: 82.2% -95.9%] and 89.9% [95% Cl: 82.2% - 95.1%], respectively.

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

The results of the standalone assessment study demonstrated an overall agreement (Accuracy) of 91.4% and 97% for the "PE" and "AD" tested cases, respectively, when compared to the ground truth (operators' visual assessments).

Regarding Matthews correlation coefficient (MCC), the found values were 0.83 and 0.94, which represent very good predictions.

Additionally, both "PE" and "AD" prioritization and triage effectiveness were evaluated by the standalone per-case processing time of the device (time-to-notification), with the results are presented in Table 1 below:

Time-to-Notification	MEAN ±SD(seconds)	MEDIAN(seconds)	LowerConfidenceLimit(seconds)	UpperConfidenceLimit(seconds)	MIN(seconds)	MAX(seconds)
CINA CHEST -PE(N = 396)	$63 \pm 16.1$	60.8	61.5	64.6	36.6	122.7
CINA CHEST -AD(N = 298)	$36.5 \pm 9.1$	34.1	35.4	37.5	17.8	90.5

Table 1: Time-to-Notification for PE and AD Image Processing Applications

The standalone triage effectiveness assessment demonstrated substantial equivalence of the CINA CHEST triage applications when compared to the predicate (BriefCase) and reference (CINA) devices. Specifically, mean "time-to-notification" were estimated to be 63 [95% Cl: 61.5 – 64.6] seconds and 36.5 [95% Cl: 35.4 – 37.5] seconds for CINA CHEST – PE and CINA CHEST – AD, respectively. This is similar to the times reported by the predicate BriefCase device (mean 3.9 [95% Cl: 3.7 - 4.1] minutes) and the reference CINA device (21.6 ± 4.4 seconds and 34.7 ± 10.7 seconds, for ICH and LVO, respectively).

The performance testing of the CINA CHEST device establishes that the subject device is as safe and effective as the predicate and reference devices. This establishes that the CINA CHEST device meets its intended use and is substantially equivalent to the predicate and reference devices.

VIII. Substantial Equivalence

The subject CINA CHEST for PE and AD prioritization and triage and the predicate device BriefCase device for PE triage are both intended to aid in prioritization and triage of radiological images of time sensitive findings for patient detection and diagnosis (i.e. Pulmonary Embolism and Aortic Dissection) based on the analysis of medical images acquired from radiological signal acquisition systems. The CINA reference device provides the CINA Platform in which the subject CINA CHEST PE and AD prioritization and triage applications can be integrated, deployed and used. The labeling of the subject and the predicate devices clearly states that the devices are not for diagnostic use. All devices are

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

software packages with similar technological characteristics and principles of operation, and incorporate deep learning Al algorithms that process images, and software to send notifications and to display unannotated preview images. In all three devices, the labeling instructs the user to further evaluate and diagnose based only on the original images in the local PACS.

The subject CINA CHEST, the predicate device BriefCase and the reference device CINA operate in parallel to the standard of care workflow in the sense that they do not change the original image, do not provide any marking on the output preview, and do not remove images from the standard of care FIFO queue, thus not disturbing standard interpretation of the attending radiologists. The subject, predicate and reference devices achieve performance of the time-to-notification metric in similar ranges of time, and thus contribute similarly to effective triage and early involvement of the radiologist in evaluating suspected images of PE and/or AD.

The standalone performance and effectiveness assessment studies demonstrated that the CINA CHEST device performs as intended is therefore substantially equivalent to the BriefCase predicate and CINA reference devices.

Table 2 compares the key features of the subject and the predicate and reference devices.

	Subject device: CINACHEST Software	Predicate device: AidocBriefCase Software(K190072)	Reference device:Avicenna.AI CINAsoftware (K200855)
Intended Use/ Indicationsfor Use	CINA CHEST is aradiological computeraided triage andnotification softwareindicated for use in theanalysis of Chest andThoraco-abdominal CTangiography. The deviceis intended to assisthospital networks andtrained radiologists inworkflow triage byflagging andcommunicatingsuspected positivefindings of (1) Chest CTangiography forPulmonary Embolism(PE) and (2) Chest orThoraco-abdominal CT	BriefCase is aradiological computeraided triage andnotification softwareindicated for use in theanalysis of non-enhancedhead CT and CTPAimages.The device is intended toassist hospital networksand trained radiologists inworkflow triage byflagging andcommunication ofsuspected positivefindings of IntracranialHemorrhage (ICH) andPulmonary Embolism(PE) pathologies. For thePE pathology, the	CINA is a radiologicalcomputer aided triageand notification softwareindicated for use in theanalysis of (1) non-enhanced head CTimages and (2) CTangiographies of thehead.The device is intended toassist hospital networksand trained radiologists inworkflow triage byflagging andcommunicatingsuspected positivefindings of (1) head CTimages for IntracranialHemorrhage (ICH) and(2) CT angiographies of
Subject device: CINACHEST Software	Predicate device: AidocBriefCase Software(K190072)	Reference device:Avicenna.AI CINAsoftware (K200855)
angiography for AorticDissection (AD).CINA CHEST uses anartificial intelligencealgorithm to analyzeimages and highlightcases with detected PEand AD on a standaloneWeb application inparallel to the ongoingstandard of care imageinterpretation. The useris presented withnotifications for caseswith suspected PE or ADfindings. Notificationsinclude compressedpreview images that aremeant for informationalpurposes only, and arenot intended fordiagnostic use beyondnotification. The devicedoes not alter theoriginal medical image,and it is not intended tobe used as a diagnosticdevice.The results of CINACHEST are intended tobe used in conjunctionwith other patientinformation and basedon professional judgmentto assist withtriage/prioritization ofmedical images. Notifiedclinicians are ultimatelyresponsible for reviewing	software is only intendedto be used on single-energy exam.BriefCase uses anartificial intelligencealgorithm to analyzeimages and highlightcases with detectedfindings on a standalonedesktop application inparallel to the ongoingstandard of care imageinterpretation. The user ispresented withnotifications for caseswith suspected findings.Notifications includecompressed previewimages that are meant forinformational purposesonly and not intended fordiagnostic use beyondnotification. The devicedoes not alter the originalmedical image and is notintended to be used as adiagnostic device.The results of BriefCaseare intended to be usedin conjunction with otherpatient information andbased on professionaljudgment, to assist withtriage/prioritization ofmedical images. Notifiedclinicians are responsiblefor viewing full imagesper the standard of care.	the head for large vesselocclusion (LVO).CINA uses an artificialintelligence algorithm toanalyze images andhighlight cases withdetected (1) ICH or (2)LVO on a standaloneWeb application inparallel to the ongoingstandard of care imageinterpretation. The user ispresented withnotifications for caseswith suspected ICH orLVO findings.Notifications includecompressed previewimages that are meant forinformational purposesonly, and are notintended for diagnosticuse beyond notification.The device does not alterthe original medicalimage, and it is notintended to be used as adiagnostic device.The results of CINA areintended to be used inconjunction with otherpatient information andbased on professionaljudgment to assist withtriage/prioritization ofmedical images. Notifiedclinicians are ultimatelyresponsible for reviewingfull images per thestandard of care.
	Subject device: CINACHEST Software	Predicate device: AidocBriefCase Software(K190072)	Reference device:Avicenna.AI CINAsoftware (K200855)
	full images per thestandard of care.
Userpopulation	Radiologist	Radiologist	Radiologist
Anatomicalregion ofinterest	Chest	Head and chest	Head
Dataacquisitionprotocol	Chest and Thoraco-abdominal CTangiography	Non contrast head CTscan and CTPA (singleenergy exams only)	Non contrast CT scan ofthe head or neck and CTangiogram images of thebrain
View DICOMdata	DICOM informationabout the patient, studyand current image	DICOM information aboutthe patient, study andcurrent image	DICOM information aboutthe patient, study andcurrent image
Segmentationof region ofinterest	No; device does notmark, highlight, or directusers' attention to aspecific location in theoriginal image	No; device does notmark, highlight, or directusers' attention to aspecific location in theoriginal image	No; device does notmark, highlight, or directusers' attention to aspecific location in theoriginal image
Algorithm	Artificial intelligencealgorithm with databaseof images	Artificial intelligencealgorithm with databaseof images	Artificial intelligencealgorithm
Notification /Prioritization	Yes	Yes	Yes
Previewimages	Presentation of a small,compressed, black andwhite preview image thatis labeled "not fordiagnostic use";The device operates inparallel with the standardof care, which remainsthe default option for all	Presentation of a small,compressed, black andwhite preview image thatis labeled "not fordiagnostic use";The device operates inparallel with the standardof care, which remainsthe default option for all	Presentation of a previewof the study for initialassessment not meant fordiagnostic purposes.The device operates inparallel with the standardof care, which remainsthe default option for allcases.
	Subject device: CINACHEST Software	Predicate device: AidocBriefCase Software(K190072)	Reference device:Avicenna.AI CINAsoftware (K200855)
	cases.	cases.
Alteration oforiginalimage	No	No	No
Removal ofcases fromworklistqueue	No	No	No
Structure	- PE and AD imageprocessing applications- Compatibility of usewith the CINA Platformreference device(worklist and ImageViewer)	- AHS module (imageacquisition),- ACS module (imageprocessing),- Aidoc Worklistapplication for workflowintegration (worklist andnon-diagnostic basicImage Viewer).	- LVO and ICH imageprocessing applications- CINA Platform (worklistand Image Viewer)

Table 2: Comparison of Key Features between CINA CHEST and Predicate Device (Aidoc BriefCase) and Reference Device (Avicenna.Al CINA)

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

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

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

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.