NinesAl is a parallel workflow tool indicated for use by hospital networks and trained clinicians to identify images of specific patients to a radiologist, independent of standard of care workflow, to aid in prioritizing and performing the radiological review. NinesAl uses artificial intelligence algorithms to analyze head CT images for findings suggestive of a pre-specified emergent clinical condition.

The software automatically analyzes Digital Imaging and Communications in Medicine (DICOM) images as they arrive in the Picture Archive and Communication System (PACS) using machine learning algorithms. Identification of suspected findings is not for diagnostic use beyond notification. Specifically, the software analyzes head CT images of the brain to assess the suspected presence of intracranial hemorrhage and/or mass effect and identifies images with potential emergent findings in a radiologist's worklist.

NinesAl is intended to be used as a triage tool limited to analysis of imaging data and should not be used in-lieu of full patient evaluation or relied upon to make or confirm a diagnosis. Additionally, preview images displayed to the radiologist outside of the DICOM viewer are non-diagnostic quality and should only be used for informational purposes.

Device Description

NinesAl notifies a radiologist of the presence of a suspected critical abnormality in a radiological image. The software system is a complete package comprised of image analysis software and a workstation module that is used to alert the radiologist. The image analysis can also be configured to send HL7 messages and DICOM secondary series.

The image analysis uses Artificial Intelligence (AI) technology to analyze non contrast CT Head scans for the presence of Intracranial Hemorrhage and/or Mass Effect. More specifically, the device utilizes two machine learning (ML) algorithms to detect each finding respectively.

NinesAl is a software device and does not come into contact with patients. All radiological studies are still reviewed by trained radiologists. NinesAl is meant to be used as an aid for case prioritization.

AI/ML Overview

Here's a summary of the acceptance criteria and study details for the NinesAI device, based on the provided text:

Acceptance Criteria and Device Performance

The acceptance criteria are derived from the observed performance of the predicate device (Aidoc's BriefCase) and a baseline of 0.80 for both sensitivity and specificity for general emergent findings.

Finding	Acceptance Criteria (Sensitivity)	Reported Device Performance (Sensitivity) [95% CI]	Acceptance Criteria (Specificity)	Reported Device Performance (Specificity) [95% CI]
Intracranial Hemorrhage	>= 0.80	0.899 [0.837, 0.940]	>= 0.80	0.974 [0.974, 0.992]
Mass Effect	>= 0.80	0.964 [0.916, 0.987]	>= 0.80	0.911 [0.856, 0.948]

Time Benefit Analysis:

Metric	NinesAI Time-to-Notification (Mean [min] / Median [min])	Standard of Care Time-to-Open-Dictation (Mean [min] / Median [min])
Intracranial Hemorrhage (Time-Savings)	0.23 [0.23, 0.24] / 0.24	159.4 [67.07, 251.7] / 6.0
Mass Effect (Time-Savings)	0.23 [0.23, 0.24] / 0.24	28.5 [14.1, 42.8] / 7.5

Study Details

Sample Size and Data Provenance (Test Set):
- Sample Size: Not explicitly stated as a single number, but the text mentions "Head CT studies included in each of the test datasets were obtained from over 20 clinical sites."
- Data Provenance: Retrospective. The studies were obtained from "over 20 clinical sites" and included "a minimum of 3 scanner manufacturers and over 20 scanner models, and also reflected broad patient demographics," suggesting a diverse dataset. The country of origin for the data is not specified.
Number of Experts and Qualifications (Ground Truth for Test Set):
- Number of Experts: Not explicitly stated. The text mentions "agreement rate between labelers who determined ground truth for the test dataset studies." This implies multiple experts were involved in establishing the ground truth.
- Qualifications of Experts: Not explicitly stated, but the term "labelers" typically refers to trained medical professionals who are qualified to interpret medical images, such as radiologists.
Adjudication Method (Test Set):
- Not explicitly stated. The mention of "agreement rate between labelers who determined ground truth" suggests some form of consensus or agreement process, but the specific method (e.g., 2+1, 3+1) is not detailed.
Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:
- No, a specific MRMC comparative effectiveness study is not explicitly mentioned. The study focuses on the standalone performance of the AI algorithm and a time benefit analysis, which compares AI notification time to standard-of-care time-to-open-dictation, rather than comparing human reader performance with and without AI assistance.
Standalone Performance Study:
- Yes, a standalone (algorithm only) performance study was conducted. The algorithms were evaluated independently, and primary endpoints like sensitivity and specificity were measured for each algorithm.
Type of Ground Truth Used (Test Set):
- Expert Consensus: The text states, "agreement rate between labelers who determined ground truth for the test dataset studies." This indicates that human expert consensus was used to establish the ground truth.
Sample Size for Training Set:
- Not explicitly stated in the provided text. The text mentions, "The algorithms are trained using a database of radiological images," but does not give a specific number for the training set size.
How Ground Truth for Training Set was Established:
- Not explicitly stated in the provided text. It is generally inferred that similar expert labeling methods would be used for training data, but the document does not detail this.

Summary

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

April 21, 2020

Image /page/0/Picture/1 description: The image contains the logos of the Department of Health & Human Services and the Food and Drug Administration (FDA). The Department of Health & Human Services logo is on the left, featuring a stylized depiction of a human figure. To the right is the FDA logo, with the letters "FDA" in a blue square, followed by the words "U.S. FOOD & DRUG" and "ADMINISTRATION" in blue text.

Nines, Inc. % John J. Smith, M.D., J.D. Regulatory Counsel Hogan Lovells US LLP 555 13th Street. NW WASHINGTON DC 20004

Re: K193351

Trade/Device Name: NinesAI Regulation Number: 21 CFR 892.2080 Regulation Name: Radiological computer aided triage and notification software Regulatory Class: Class II Product Code: QAS Dated: March 30, 2020 Received: March 30, 2020

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); 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 https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reporting

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

combination-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}------------------------------------------------

510(k) Number

K193351

Device Name

NinesAl

Indications for Use (Describe)

NinesAl is a parallel workflow tool indicated for use by hospital networks and trained clinicians to identify images of specific patients to a radiologist, independent of care workflow, to aid in prioritizing and performing the radiological review. Nines Al uses artificial intelligence algorithms to analyze head CT images for findings suggestive of a pre-specified emergent clinical condition.

The software automatically analyzes Digital Imaging and Communications in Medicine (DICOM) images as they arive in the Picture Archive and Communication System (PACS) using machine learning algorithms. Identification of suspected findings is not for diagnostic use beyond notification. Specifically, the software analyzes head CT images of the brain to assess the suspected presence of intracranial hemorrhage and/or mass effect and identifies images with potential emergent findings in a radiologist's worklist.

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 Nines, Inc.'s NinesAl K193351

Submitter:

Nines, Inc. 329 Alma Street Palo Alto, CA 94301

Contact Person:

Dr. Russell Stewart Phone: 650 924 6159 russell@ninesai.com

Date Prepared: April 17, 2020

Name of Device: NinesAl

Classification Name: Radiological Computer-Assisted Triage and Notification Software

Regulatory Class: Class II

Product Code: QAS

Predicate Device: Aidoc Medical's BriefCase (K180647)

Device Description

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

Intended Use / Indications for Use

Summary of Technological Characteristics

The NinesAl indications for use differ slightly from the predicate, but the minor differences do not neqatively impact the safety and effectiveness of the subject device. In sum, the predicate is indicated for use to analyze images for the presence of ICH. NinesAl is indicated for use to analyze ICH, as well as Mass Effect. The additional potential finding of Mass Effect can be seen concomitantly with ICH cases and the detection of such potential pathology is supported by performance testing. All potential findings covered by the predicate and NinesAl are emergent findings in the head.

Artificial intelligence algorithms are the technological principle for both the subject and predicate devices. The algorithms are trained using a database of radiological images. At a high level, the subject and predicate devices are based on the following same technological elements:

· Artificial Intelligence Algorithm(s);
· Notification Technology.

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

	NinesAI (K193351)	AIDoc's BriefCase (K180647)
Indications for Use	NinesAl is a parallel workflow toolindicated for use by hospital networksand trained clinicians to identifyimages of specific patients to aradiologist, independent of standardof care workflow, to aid in prioritizingand performing the radiologicalreview. NinesAl uses artificialintelligence algorithms to analyzehead CT images for findings	BriefCase is a radiological computeraided triage and notification softwareindicated for use in the analysis ofnon-enhanced head CT images.The device is intended to assisthospital networks and trainedradiologists in workflow triage byflagging and communication ofsuspected positive findings ofpathologies in head CT images.
	NinesAI (K193351)	AIDoc's BriefCase (K180647)
	suggestive of a pre-specifiedemergent clinical condition.	namely Intracranial Hemorrhage(ICH).BriefCase uses an artificial
	The software automatically analyzesDigital Imaging and Communicationsin Medicine (DICOM) images as theyarrive in the Picture Archive andCommunication System (PACS)using machine learning algorithms.Identification of suspected findings isnot for diagnostic use beyondnotification. Specifically, the softwareanalyzes head CT images of thebrain to assess the suspectedpresence of intracranial hemorrhageand/or mass effect and identifiesimages with potential emergentfindings in a radiologist's worklist.NinesAl is intended to be used as atriage tool limited to analysis ofimaging data and should not be usedin-lieu of full patient evaluation orrelied upon to make or confirm adiagnosis. Additionally, previewimages displayed to the radiologistoutside of the DICOM viewer are non-diagnostic quality and should only beused for informational purposes.	intelligence algorithm to analyzeimages and highlight cases withdetected ICH on a standalonedesktop application in parallel to theongoing standard of care imageinterpretation. The user is presentedwith notifications for cases withsuspected ICH findings. Notificationsinclude compressed preview imagesthat are meant for informationalpurposes only and not intended fordiagnostic use beyond notification.The device does not alter the originalmedical image and is not intended tobe used as a diagnostic device.The results of BriefCase are intendedto be used in conjunction with otherpatient information and based onprofessional judgment, to assist withtriage/prioritization of medical images.Notified clinicians are responsible forviewing full images per the standardof care.
User Population	used for informational purposes.Radiologists	Radiologists
TechnologicalCharacteristics	Artificial Intelligence algorithmsdetecting emergent findings sendingnotifications to the workstation.	Artificial Intelligence algorithmsdetecting emergent findings sendingnotifications to the workstation.
Components	- Artificial IntelligenceAlgorithm- Notification Technology	- Artificial IntelligenceAlgorithm- Notification Technology
Anatomical Regionof Interest	Head	Head
Findings Covered	Intracranial Hemorrhage and MassEffect	Intracranial Hemorrhage
Data AcquisitionProtocol	Non contrast CT scan of the head	Non contrast CT scan of the head orneck
View DICOM Data	DICOM information about the patient,study and current image	DICOM information about the patient,study and current image
Preview Images	Presentation of notification andpreview of the study for initialassessment not meant for diagnosticpurposes. This is done via desktopnotification or via DICOM series.The device operates in parallel with	Presentation of notification andpreview of the study for initialassessment not meant for diagnosticpurposes. This is done via desktopnotification.The device operates in parallel with
	NinesAI (K193351)	AIDoc's BriefCase (K180647)
	the default option for all cases	the default option for all cases
Alteration ofOriginal Image	No	No
Removal of Casesfrom WorklistQueue	No	No
Triage NotificationTypes	Workstation Application Notification,HL7	Workstation Application Notification

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

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

Performance Testing

Nines performed software verification and validation testing that covers the performance of the algorithms, as well as the performance of the software and its components. In all instances, NinesAl functioned as intended and expected.

The NinesAl device underwent performance testing to verify the efficacy and safety of the machine learning algorithms. Both of the algorithms used in NinesAl were evaluated independently from each other to allow for an individual understanding of each algorithm's respective performance. Each algorithm was tested in a retrospective performance trial, with the primary endpoints of each trial being the respective sensitivity and specificity of the algorithm in question. Other endpoints included: Positive Predictive Value, Negative Predictive Value, ROC AUC, time savings relative to standard of care, and agreement rate between labelers who determined ground truth for the test dataset studies. Head CT studies included in each of the test datasets were obtained from over 20 clinical sites and included a minimum of 3 scanner manufacturers and over 20 scanner models, and also reflected broad patient demographics.

The primary endpoints for each algorithm are listed below:

Finding	Sensitivity[95% confidenceintervals]	Specificity [95% confidenceintervals]
Intracranial Hemorrhage	0.899[0.837, 0.940]	0.974[0.974, 0.992]
Mass Effect	0.964[0.916, 0.987]	0.911[0.856, 0.948]

A time benefit analysis was performed for each algorithm and showed a time-to-notification that is faster than the similar standard of care metric of time-to-open-dictation. These results are summarized below for each algorithm.

The time-savings data for Intracranial Hemorrhage is listed below:
--------------------------------------------------------------------	--	--	--

Metric	Mean (min)	Median (min)
Time-to-open-dictationstandard of care	159.4 [67.07, 251.7]	6.0

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

Metric	Mean (min)	Median (min)
Time-notification ofNinesAl	0.23 [0.23, 0.24]	0.24

The time-savings data for Mass Effect is listed below:

Metric	Mean (min)	Median (min)
Time-to-open-dictationstandard of care	28.5 [14.1, 42.8]	7.5
Time-notification ofNinesAl	0.23 [0.23, 0.24]	0.24

The Intracranial Hemorrhage and Mass Effect algorithms met the performance goal outlined by the predicate device of .80 for both sensitivity and specificity. Additionally, the performance for each algorithm is comparable to the observed performance reported for the predicate device: 93.6% (95% CI: 86.6%-97.6%) sensitivity and 92.3% (95% CI: 85.4%-96.6%) specificity.

Based on the clinical performance as documented in the pivotal clinical study, the subject software has a safety and effectiveness profile that is similar to the predicate device.

Conclusions

NinesAl has the same intended uses and similar indications, technological characteristics, and principles of operation as its predicate device. The minor differences in indication 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 NinesAl and its predicate devices raise no new issues of safety or effectiveness. Performance data demonstrate that NinesAl performs as intended. Thus, NinesAl is substantially equivalent.

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.