Rapid LVO is a radiological computer aided triage and notification software indicated for use in the analysis of CTA head images. The device is intended to assist hospital networks and trained radiologists in workflow triage by flagging and communication of suspected positive Large Vessel Occlusion (LVO) findings in head CTA images.

Rapid LVO uses a software algorithm to analyze images and highlight cases with suspected LVO on a server or standalone desktop application in parallel to the ongoing standard of care image interpretation. The user is presented with notifications for cases with suspected LVO findings. Notifications include compressed preview images, that are meant for informational purposes only and not intended for diagnostic use beyond notification. The device does not alter the original medical image and is not intended to be used as a diagnostic device.

The results of Rapid LVO 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 responsible for viewing full images per the standard of care.

Device Description

Rapid LVO 1.0 is a clinical module which operates within the integrated Rapid Platform to provide triage and notification of suspected Large Vessel Occlusion (LVO). The Rapid LVO module consists of the core Rapid Platform software which provides the administration and services for the Rapid image processing modules; and the Rapid LVO module which functions as one of many image processing modules hosted by the platform.

Rapid LVO acquires (DICOM compliant) medical image data from CTA scanners through the Rapid Platform interface.

The Rapid platform is a software package that provides for the visualization and study of changes in tissue using digital images captured by diagnostic imaging systems including CT (Computed Tomography), CTA, XA and MRI (Magnetic Image Resonance), as an aid to physician diagnosis. Rapid can be installed on a customer's Server or it can be accessed online as virtual system. It provides viewing, quantification, analysis and reporting capabilities. The Rapid platform has multiple modules a clinician may elect to run and provide analysis for decision making. The basic architecture supports the general functionality to support the Rapid LVO imaging module such as DICOM interfaces, job management, data base functions and communications. The Rapid Platform and base functions are not under review for this submission.

AI/ML Overview

The provided document (K200941) describes the 510(k) premarket notification for the iSchemaView Rapid LVO 1.0 device. Here's a breakdown of the acceptance criteria and the study proving the device meets them:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria for standalone performance were specified as exceeding an 80% goal for both Sensitivity (Se) and Specificity (Sp) using the lower bound of the 95% Confidence Interval. Additionally, a time-to-notification goal of less than 3.5 minutes was established based on the predicate device.

Acceptance Criterion	Reported Device Performance
Sensitivity (Se) > 80% (lower bound of 95% CI)	0.970 (95% CI: 0.933, 0.987)
Specificity (Sp) > 80% (lower bound of 95% CI)	0.956 (95% CI: 0.919, 0.977)
ROC AUC	0.99 (95% CI: 0.972, 0.995)
Time to Notification < 3.5 minutes	2.86 min (95% CI: 2.79, 2.92)
PPV (at 45% prevalence)	0.95 (95% CI: 0.90, 0.97)
NPV (at 45% prevalence)	0.98 (95% CI: 0.94, 0.99)

As shown in the table, all reported performance metrics exceeded the specified acceptance criteria.

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

The document mentions that iSchemaView performed "standalone performance in accordance with the 892.2080 special controls to show acceptance of the clinical performance of the Rapid LVO module." However, the exact sample size used for this test set is not explicitly stated in the provided text.

Regarding data provenance, the document does not specify the country of origin for the clinical data used in the performance validation. It only broadly states that the Rapid System performance "has been validated through the use of phantoms (Rapid core indications) and clinical data (Rapid LVO)." It is retrospective data, as it was used for validation after development, rather than prospectively collected for the clinical trial.

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

The document does not explicitly state the number of experts used to establish the ground truth for the test set or their specific qualifications (e.g., "radiologist with 10 years of experience").

4. Adjudication Method for the Test Set

The document does not describe any specific adjudication method (e.g., 2+1, 3+1, none) used for establishing the ground truth of the test set. It implies that the "clinical data" was used for validation, but the process of expert consensus or adjudication is not detailed.

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

A Multi-Reader Multi-Case (MRMC) comparative effectiveness study was NOT done according to the provided text. The study described is a "standalone performance" evaluation, meaning it assesses the algorithm's performance independent of human readers. Therefore, there is no information about how human readers improve with or without AI assistance in this document.

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

Yes, a standalone performance study was done. The document explicitly states: "iSchemaView performed standalone performance in accordance with the 892.2080 special controls to show acceptance of the clinical performance of the Rapid LVO module." The reported Sensitivity, Specificity, and ROC AUC are metrics of this standalone performance.

7. The Type of Ground Truth Used

The document refers to "clinical data" as the basis for the Rapid LVO performance validation. While it doesn't explicitly state "expert consensus" or "pathology" as the ground truth method, for radiological computer-aided triage software, the ground truth is typically established by expert consensus (e.g., multiple expert radiologists reviewing cases and reaching a consensus on the presence or absence of LVO) or by clinical outcomes data (e.g., confirmation of LVO through other gold standard diagnostics or surgical findings). Given the nature of the device for triage and notification, it is highly likely that the ground truth was established by expert consensus of radiologists or neurologists, possibly combined with clinical follow-up data to confirm true LVO. However, the document does not definitively specify which.

8. The Sample Size for the Training Set

The document does not specify the sample size for the training set. It only mentions that the device uses "a software algorithm to analyze images."

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

The document does not describe how the ground truth for the training set was established. It briefly mentions that the predicate device (Rapid ICH) uses "machine learning software implementations," while Rapid LVO uses "traditional algorithms," but it does not detail the training data or its annotation process for either.

Summary

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

Image /page/0/Picture/0 description: The image shows the logo for the U.S. Food and Drug Administration (FDA). The logo consists of two parts: the Department of Health and Human Services seal on the left and the FDA acronym and name on the right. The seal features an eagle with outstretched wings, and the FDA part includes the acronym in a blue square and the full name "U.S. Food & Drug Administration" in blue text.

July 9, 2020

iSchemaView, Inc. % Mr. James Rosa VP Quality and Regulatory 433 Park Point Drive, Suite 220 GOLDEN CO 80401

Re: K200941

Trade/Device Name: Rapid LVO 1.0 Regulation Number: 21 CFR 892.2080 Regulation Name: Radiological computer aided triage and notification software Regulatory Class: Class II Product Code: QAS Dated: June 8, 2020 Received: June 9, 2020

Dear Mr. Rosa:

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 and Part 809); medical device 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

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

Indications for Use

510(k) Number (if known) K200941

Device Name Rapid LVO 1.0

Indications for Use (Describe)

Rapid LVO uses a software algorithm to analyze images and highlight cases with suspected LVO on a server or

standalone desktop application in parallel to the ongoing standard of care image interpretation. The user is presented with notifications for cases with suspected LVO findings. Notifications include compressed preview images, that are meant for informational purposes only and not intended for diagnostic use beyond notification. The device does not alter the original medical image and is not intended to be used as a diagnostic device.

Contraindications/Exclusions/Cautions:

· Rapid LVO is one input to physician diagnosis for patients undergoing screening for acute ischemic stroke.

· Excessive patient motion may lead to artifacts that make the scan technically inadequate.

• Identification of suspected findings is not for diagnostic use beyond notification. Images that are previewed through email and the mobile application are compressed and are for informational purposes only and not intended for diagnostic use beyond notification.

· Notified clinicians are responsible for viewing non-compressed images on a diagnostic viewer and engaging in appropriate patient evaluation and relevant discussion with a treating physician before making care-related decisions or requests.

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

iSchemaView, Inc.'s Rapid LVO 1.0

This document contains the 510(k) summary for the iSchemaView Rapid LVO. The content of this summary is based on the requirements of 21 CFR Section 807.92(c).

Applicant Name and Address:

Name:	iSchemaView, Inc.
Address:	433 Park Point DriveSte. 220Golden, CO 80401
Official Contact:	Jim RosaPhone: (303) 704-3374Email: rosa@ischemaview.com

Summary Preparation Date: June 29, 2020

Device Name and Classification:

Trade Name:	iSchemaView Rapid LVO 1.0
Common Name:	Radiological computer aided triage andnotification software
Classification:	II
Product Code:	QAS
Regulation No:	21 C.F.R. §892.2080
Classification Panel:	Radiology Devices

Predicate Devices:

The iSchemaView Rapid LVO is claimed to be substantially equivalent to the following legally marketed predicate device:

iSchemaView Rapid ICH (K193087)

Device Description:

Rapid LVO acquires (DICOM compliant) medical image data from CTA scanners through the Rapid Platform interface:

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

Rapid Platform

Indications for Use:

Contraindications/Exclusions/Cautions:

. Rapid LVO is one input to physician diagnosis for patients undergoing screening for acute ischemic stroke.
Excessive patient motion may lead to artifacts that make the scan technically inadequate.
. Identification of suspected findings is not for diagnostic use beyond notification. Images that are previewed through email and the mobile application are compressed and are for informational purposes only and not intended for diagnostic use beyond notification.
Notified clinicians are responsible for viewing non-compressed images on a diagnostic viewer ● and engaging in appropriate patient evaluation and relevant discussion with a treating physician before making care-related decisions or requests.

Technological Characteristics:

Rapid Platform performs the following functions in support of Rapid LVO:

processes DICOM images from multiple sources to provide visualization of changes . of tissue perfusion, diffusion and change.

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

. receives DICOM images from external DICOM image providers (modalities (CT/MRI Scanners), PACS and Workstations) and sends DICOM images to external image consumers.
. processes requests, statuses and results, and references therein, which are stored in a searchable database
processing status is available through a web browser using HTTP. HTML and PHP. ●
. can send summary results to the user over email and mobile application. For this, Rapid generally connects to the infrastructure of the medical partner (e.g., the hospital). In particular, Rapid uses a SMTP protocol with security extensions to provide secure emailing.

Rapid is available in the following configurations:

Standard Rapid, which is installed directly on a customer's Linux-based server and . integrated with medical image processing software such as commercial PACS.
. Virtual Rapid, wherein the user accesses Rapid online and uses it to process DICOM images otherwise available on his/her computer.

Rapid Platform is a DICOM-compliant PACS software that provides comprehensive functionality to transfer, process, and display modality specific imaging data. Rapid runs on standard "off-the- shelf" computer and networking hardware. Rapid is entirely independent from CT, XA, MRI, or PACS platforms. It supports secure VPN (Virtual Private Network) networking or encapsulated Secure Shell (SSH), and seamlessly integrates into an existing radiological data network.

The primary users of Rapid PACS software are medical imaging professionals who analyze tissue using CT or MRI images.

Performance Standards:

Rapid has been developed in conformance with the following standards, as applicable:

ISO 14971:2019	Application of Risk Management to Medical Devices
IEC 62304:2015	Medical device software – Software lifecycle processes
IEC 62366:2015	Application of Usability Engineering to Medical Devices
NEMA PS 3.1 - 3.20	Digital Imaging and Communications in Medicine (DICOM

Performance Data:

Rapid complies with DICOM (Digital Imaging and Communications in Medicine) - Developed by the American College of Radiology and the National Electrical Manufacturers Association. NEMA PS 3.1 - 3.20.

Additionally, iSchemaView conducted extensive performance validation testing and software verification and validation testing of the Rapid system. This performance validation testing demonstrated that the Rapid system provides accurate representation of key processing parameters under a range of clinically relevant parameters and perturbations associated with the intended use of the software. Software performance, validation and verification testing demonstrated that the Rapid system met all design requirements and specifications.

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

iSchemaView performed standalone performance in accordance with the 892.2080 special controls to show acceptance of the clinical performance of the Rapid LVO module. The Standalone Performance exceeded the 80% Goal using the lower bound of the 95% Confidence Interval for Sensitivity (Se) and Specificity (Sp). The observed results are Se: Sensitivity (Se) of 0.970 (95% CI: 0.933.0.987) and Specificity (Sp) 0.956 (95% CI: 0.919, 0.977) with a ROC AUC of 0.99 (95% CI:0.972, 0.995). Additionally, at a prevalence of 45%, PPV = 0.95 (95% CI: 0.90, 0.97) and NPV = 0.98 (95% CI 0.94, 0.99)

In addition, an analysis on time to notification using Rapid LVO to notify of suspicion/nonsuspicion as 2.86 min (95% CI: 2.79. 2.92) was achieved meeting the goal of < 3.5min established by the predicate. The Rapid LVO time-to-notification includes the time to get the DICOM exam, de-identify it (if required), analyze and send a notification to the attending physician(s) email and mobile. The time to notification consists primarily of the processing time, as the notification time via electronic transmission is considered in seconds via email and mobile.

Prescriptive Statement:

Caution: Federal law restricts this device to sale by or on the order of a physician.

Safety & Effectiveness:

Rapid has been designed, verified and validated in compliance with 21 CFR, Part 820.30 requirements. The device has been designed to meet the requirements associated with ISO 14971:2019 (risk management). The Rapid System performance has been validated through the use of phantoms (Rapid core indications) and clinical data (Rapid LVO).

Substantial Equivalence:

Rapid LVO is as safe and effective as the previously cleared Rapid ICH (K193087). The subject and predicate devices are radiological computer-assisted triage and notification software programs. Both devices are implemented in software algorithms, LVO using traditional and ICH using machine learning software implementations for use with CTA scanners, PACS, and workstations. Both devices process images intended to aid in prioritization and triage of radiological medical images. The subject and predicate differ in imaging input, the subject device process CTA images and the predicate NCCT images for indication. Both devices are intended to provide notifications and preview head images of potential findings to radiologists and other clinicians for the purpose of treatment planning and follow up.

Both software devices notify a designated list of clinicians of the availability of time sensitive radiological medical images for review based on computer aided image analysis performed by the device's algorithm. The subject and predicate device sends notifications and compressed previews to the workstations' desktop. Additionally, the subject device sends an email (normal processing within Rapid Platform and previously cleared and mobile notification (similar to the predicate's predicate device. Those notifications work in parallel to the standard of care. They prompt the clinician to start preemptive triage of a flagged case, upon which they may decide after observing the preview, to turn to the local PACS/Workstation to perform the evaluation. If a notification is found to be non-suspicious of LVO, the case still remains in the queue to be handled per the standard of care.

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

As a system, the Rapid LVO raises the same types of safety and effectiveness questions as the predicate; namely, accurate detection of findings within the reviewed and processed study on which a clinician can base a clinically useful triage/prioritization assessment considering all available clinical information.

It is important to note that, like the predicate, the device does not remove cases from a reading queue. Again, both devices operate in parallel with the standard of care, which remains the default option for all cases.

A table comparing the key features of the subject and predicate devices is provided below.

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

Substantial Equivalence Discussion:

Parameter	Rapid ICH (K193087)	Rapid LVO (K200941)
Product Code	QAS	QAS
Regulation	21 CFR §892.2080	21 CFR §892.2080
Intended Use/ Indicationsfor Use	Rapid ICH is a radiological computer aidedtriage and notification software indicated for usein the analysis of non-enhanced head CT images.The device is intended to assist hospital networksand trained radiologists in workflow triage byflagging and communication of suspectedpositive Intracranial Hemorrhage (ICH) findingsin head CT images, namely IntracranialHemorrhage (ICH).Rapid ICH uses an artificial intelligencealgorithm to analyze images and highlight caseswith suspected ICH on a server or standalonedesktop application in parallel to the ongoingstandard of care image interpretation. The user ispresented with notifications for cases withsuspected ICH findings. Notifications includecompressed preview images, that are meant forinformational purposes only and not intended fordiagnostic use beyond notification. The devicedoes not alter the original medical image and isnot intended to be used as a diagnostic device.The results of Rapid ICH are intended to be usedin conjunction with other patient information andbased on professional judgment, to assist withtriage/prioritization of medical images. Notifiedclinicians are responsible for viewing full imagesper the standard of care.	Rapid LVO is a radiological computer aided triageand notification software indicated for use in theanalysis of CTA head images. The device isintended to assist hospital networks and trainedradiologists in workflow triage by flagging andcommunication of suspected positive Large VesselOcclusion (LVO) findings in head CTA images.Rapid LVO uses a software algorithm to analyzeimages and highlight cases with suspected LVO ona server or standalone desktop application inparallel to the ongoing standard of care imageinterpretation. The user is presented withnotifications for cases with suspected LVOfindings. Notifications include compressed previewimages, that are meant for informational purposesonly and not intended for diagnostic use beyondnotification. The device does not alter the originalmedical image and is not intended to be used as adiagnostic device. The results of Rapid LVO areintended to be used in conjunction with otherpatient information and based on professionaljudgment, to assist with triage /prioritization ofmedical images. Notified clinicians are responsiblefor viewing full images per the standard of care.
PACS Functionality
Stroke/Head	Hemorrhagic Stroke/Head	Intracranial Stroke/Head
Parameter	Rapid ICH (K193087)	Rapid LVO (K200941)
Product Code	QAS	QAS
Regulation	21 CFR §892.2080	21 CFR §892.2080
Computer Platform	Standard off-the-shelf PC workstation/serverVirtual platform such as VMware	SameSame
DICOM Compliance	Yes	Yes
Imaging Type	Non-Contrast CT	CT Angiography
Data Acquisition	Acquires medical image data from DICOMcompliant imaging devices and modalities	Same
Technical Implementation
SaMD	Yes - Machine Learning	Yes – Traditional Algorithms
Notification/Workflow
Pathways	PACS, email, mobile	PACS, email, mobile
Preview/Prioritization	Notification Message of Suspected Hemorrhage.Presentation of a preview of the study for initialassessment not meant for diagnostic purposes.The device operates in parallel with the standardof care, which remains.	Notification Message of Suspected LVO.Presentation of a preview of the study forinitial assessment not meant for diagnosticpurposes.The device operates in parallel with thestandard of care, which remains.
SoC Workflow	In parallel to the SoC	In parallel to the SoC
Original Image	No Alteration	No Alteration
Primary Users	Clinician	Clinician

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

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

Conclusion:

In conclusion, the iSchemaView Rapid LVO is substantially equivalent in intended use, technological characteristics, safety, and performance characteristics to the legally marketed predicate device, Rapid ICH (K193087) with a focus on LVO analysis only.

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.