Retrospective study of 394 brain CT images from 13 clinical sites in the U.S.
>1 (trained neuro-radiologists)
Indications for Use
Hyper Insight - ICH is a notification-only workflow tool for trained clinicians to identify patients' brain CT images and share them with medical specialists in parallel with standard patient care workflow. Hyper Insight - ICH uses deep learning-based AI algorithms to analyze images to find suspected intracranial hemorrhage and notifies and shares the findings to medical specialists. Identification of images with suspected intracranial hemorrhage is for notification purposes only, not diagnostic purposes. In particular, this medical device analyzes non-contrast brain CT images, and if a suspected intracranial hemorrhage is identified, it sends a notification to medical specialists, who are advised to review these images. Images may be previewed through the mobile app but are for informational purposes only and are not intended to be used for diagnostic purposes other than notifications and previews. The medical specialist who received the notification is responsible for reading the image in a diagnostic viewer. Hyper Insight - ICH is limited to the purpose of analysis of image data and should not be used as a substitute for a full patient assessment or relied upon to make or confirm a diagnosis.
Device Story
Software as a medical device (SaMD) for triage of non-contrast head CT scans; integrates with third-party worklist applications to receive DICOM images. Uses deep learning AI to detect acute intracranial hemorrhage (ICH); provides binary prediction (suspected ICH found/not found). Operates in clinical/hospital environments; used by radiologists, emergency physicians, neurosurgeons, and neurologists. Sends notifications to specialists via mobile app; allows image previewing for informational purposes. Does not alter images; does not replace diagnostic viewing. Benefits include rapid triage and prioritization of emergency ICH cases, potentially reducing time to specialist intervention.
Clinical Evidence
Retrospective study of 394 non-contrast head CT images from 13 U.S. sites (198 positive, 196 negative for ICH). Reference standard established by trained neuro-radiologists. Sensitivity 95.45% [91.55, 97.90], specificity 98.47% [95.59, 99.68], AUC 0.9864. Average notification time 16.39 ± 5.46 seconds. Performance stratified by age, gender, race, ICH subtype, slice thickness, and scanner manufacturer.
Technological Characteristics
SaMD; deep learning-based AI algorithm. Inputs: DICOM non-contrast head CT images. Outputs: Binary notification of suspected ICH. Connectivity: Integrates with third-party worklist/PACS. No image marking or alteration. Standalone software deployment.
Indications for Use
Indicated for trained clinicians to identify suspected intracranial hemorrhage (ICH) in non-contrast brain CT images. Used as a notification-only workflow tool to alert medical specialists in parallel with standard care. Not for diagnostic use; not a substitute for full patient assessment.
Regulatory Classification
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.
Special Controls
Radiological computer aided triage and notification software must comply with the following special controls: 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. Standalone 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. 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.
*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.
{0}------------------------------------------------
Image /page/0/Picture/0 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 is a blue square with the letters "FDA" in white. To the right of the blue square is the text "U.S. FOOD & DRUG ADMINISTRATION" in blue.
SK Inc. % Hannah Taggart Regulatory Associate Empirical Technologies 4628 Northpark Drive Colorado Springs, Colorado 80918
July 1, 2024
#### Re: K240353
Trade/Device Name: Hyper Insight - ICH Regulation Number: 21 CFR 892.2080 Regulation Name: Radiological Computer Aided Triage And Notification Software Regulatory Class: Class II Product Code: QAS Dated: May 30, 2024 Received: May 30, 2024
#### Dear Hannah Taggart:
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 (the 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 available 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.
Additional information about changes that may require a new premarket notification are provided in the FDA guidance documents entitled "Deciding When to Submit a 510(k) for a Change to an Existing Device" (https://www.fda.gov/media/99812/download) and "Deciding When to Submit a 510(k) for a Software Change to an Existing Device" (https://www.fda.gov/media/99785/download).
{1}------------------------------------------------
Your device is also subject to, among other requirements, the Quality System (QS) regulation (21 CFR Part 820), which includes, but is not limited to, 21 CFR 820.30, Design controls; 21 CFR 820.90, Nonconforming product; and 21 CFR 820.100, Corrective and preventive action. Please note that regardless of whether a change requires premarket review, the QS regulation requires device manufacturers to review and approve changes to device design and production (21 CFR 820.30 and 21 CFR 820.70) and document changes and approvals in the device master record (21 CFR 820.181).
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 Part 803) for devices or postmarketing safety reporting (21 CFR Part 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 (OS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR Part 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR Parts 1000-1050.
Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR 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,
Jessica Lamb
Jessica Lamb, Ph.D. Assistant Director Imaging Software Team DHT8B: Division of Radiologic Imaging Devices and Electronic Products OHT8: Office of Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health
{2}------------------------------------------------
## Indications for Use
510(k) Number (if known) K240353
Device Name Hyper Insight - ICH
#### Indications for Use (Describe)
Hyper Insight - ICH is a notification-only workflow tool for trained clinicians to identify patients' brain CT images and share them with medical specialists in parallel with standard patient care workflow. Hyper Insight - ICH uses deep learning-based Al algorithms to analyze images to find suspected intracranial hemorrhage and notifies and shares the findings to medical specialists. Identification of images with suspected intracranial hemorrhage is for notification purposes only, not diagnostic purposes.
In particular, this medical device analyzes non-contrast brain CT images, and if a suspected intracranial hemorrhage is identified, it sends a notification to medical specialists, who are advised to review these images may be previewed through the mobile app but are for informational purposes only and are not intended to be used for diagnostic purposes other than notifications and previews. The medical specialist who received the notification is responsible for reading the image in a diagnostic viewer.
Hyper Insight - ICH is limited to the purpose of analysis of image data and should not be used as a substitute for a full patient assessment or relied upon to make or confirm a diagnosis.
| Type of Use (Select one or both, as applicable) | |
|-------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------|
| <div> <span> <span style="font-size:16px">☑</span> Prescription Use (Part 21 CFR 801 Subpart D) </span> </div> | <div> <span> <span style="font-size:16px">☐</span> Over-The-Counter Use (21 CFR 801 Subpart C) </span> </div> |
#### 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}------------------------------------------------
# K240353 510(K) SUMMARY
| Submitter's Name: | SK Inc. |
|------------------------------------|------------------------------------------------------------------------------------------------|
| Submitter's Address: | SK U-Tower, 9 Seongnam-daero, Bundang-gu, Seongnam-si, Gyeonggi-do, 13558<br>Republic of Korea |
| Submitter's Telephone: | +82-2-6400-0114 |
| Contact Person: | Hannah Taggart, MS<br>Empirical Technologies<br>1-719-457-1152<br>htaggart@empiricaltech.com |
| Image: Empirical Technologies logo | |
| Date Summary was Prepared: | June 25, 2024 |
| Trade or Proprietary Name: | Hyper Insight - ICH |
| Device Classification Name: | Radiological Computer-Assisted Triage And Notification Software |
| Classification & Regulation #: | Class II per 21 CFR §892.2080 |
| Product Code: | QAS |
| Classification Panel: | Radiology |
## DESCRIPTION OF THE DEVICE SUBJECT TO PREMARKET NOTIFICATION:
Hyper Insight - ICH is software as a medical device (SaMD) that detects intracranial hemorrhage (ICH) condition by analyzing non-contrast CT images. The software needs to be integrated with a third-party worklist application to receive analysis requests and the corresponding DICOM images and return the ICH findings (whether suspected ICH is found) to the worklist to alert the radiologists.
For ICH patients, immediate emergency diagnosis and treatment is critical for saving their lives and later recovery. Thus, it is very important to triage and identify ICH patients in a speedy manner to prioritize their treatment. Computed tomography (CT) is a non-invasive and effective diagnosis imaging approach to detect ICH. Acute Intracranial hemorrhage can be recognized on non-contrast CT scans since blood has higher density (Hounsfield unit, HU) than other brain tissues but lower than that of bones. Radiologists can identify ICH and determine the location and severity of any such bleeding from the intensity patterns presented in the images.
To help radiologists triage and prioritize reading of images for patients with ICH, Hyper Insight - ICH uses deep learning methods to automatically detect acute ICH in non-contrast head CT scans.
The software analyzes the input image and returns a binary prediction as to whether the exam suggests the presence of acute ICH. The Hyper Insight-ICH device is for notification purposes only and should be not used for final diagnosis.
## INDICATIONS FOR USE
Hyper Insight - ICH is a notification-only workflow tool for trained clinicians to identify patients' brain CT images and share them with medical specialists in parallel with standard patient care workflow. Hyper Insight - ICH uses deep learning-based AI algorithms to analyze images to find suspected intracranial hemorrhage and notifies and shares the findings to medical specialists. Identification of images with suspected intracranial hemorrhage is for notification purposes only, not diagnostic purposes.
In particular, this medical device analyzes non-contrast brain CT images, and if a suspected intracranial hemorrhage is identified, it sends a notification to medical specialists, who are advised to review these images. Images may be previewed through the mobile app but are for informational purposes only and are not intended to be used for diagnostic purposes other than notifications and previews. The medical specialist who received the notification is responsible for reading the image in a diagnostic viewer.
Hyper Insight - ICH is limited to the purpose of analysis of image data and should not be used as a substitute for
{4}------------------------------------------------
a full patient assessment or relied upon to make or confirm a diagnosis.
## TECHNOLOGICAL CHARACTERISTICS
The predicates included in this submission were selected based on the best practices described in the FDA Draft Guidance document Best Practices for Selecting a Predicate Device to Support a Premarket Notification [510(k)] Submission. The subject and predicate devices have nearly identical technological characteristics and the minor differences do not raise any new issues of safety and effectiveness. Specifically, the following characteristics are identical between the subject and predicates:
- Indications for Use ●
- Intended End User .
- Input/Output of Software ●
- . Performance Data
| 510k Number | Trade or Proprietary or Model Name | Manufacturer | Product Code | Predicate Type |
|-------------|------------------------------------|--------------|--------------|----------------|
| K193658 | Viz ICH | Viz.ai, Inc. | QAS | Primary |
#### Predicate Device Comparison
| | Subject Name<br>(Subject Device) | Viz.ai, Inc. Viz ICH<br>(K193658) |
|---------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Indications for Use | Hyper Insight - ICH is a notification-only workflo<br>w tool for trained clinicians to identify patients' br<br>ain CT images and share them with medical speci<br>alists in parallel with standard patient care workflo<br>w. Hyper Insight - ICH uses deep learning-based<br>AI algorithms to analyze images to find suspected<br>intracranial hemorrhage and notifies and shares the<br>findings to medical specialists. Identification of im<br>ages with suspected intracranial hemorrhage is for<br>notification purposes only, not diagnostic purposes.<br>In particular, this medical device analyzes non-cont<br>rast brain CT images, and if a suspected intracrani<br>al hemorrhage is identified, it sends a notification<br>to medical specialists, who are advised to review t<br>hese images. Images may be previewed through th<br>e mobile app but are for informational purposes o<br>nly and are not intended to be used for diagnostic<br>purposes other than notifications and previews. T<br>he medical specialist who received the notification<br>is responsible for reading the image in a diagnosti<br>c viewer.<br>Hyper Insight - ICH is limited to the purpose of<br>analysis of image data and should not be used as<br>a substitute for a full patient assessment or relied<br>upon to make or confirm a diagnosis. | Viz ICH is a notification-only, parallel workflow tool f<br>or use by hospital networks and trained clinicians to id<br>entify and communicate images of specific patients to a<br>specialist, independent of standard of care workflow.<br>Viz ICH uses an artificial intelligence algorithm to anal<br>yze images for findings suggestive of a prespecified cli<br>nical condition and to notify an appropriate medical spe<br>cialist of these findings in parallel to standard of care i<br>mage interpretation. Identification of suspected findings<br>is not for diagnostic use beyond notification. Specificall<br>y, the device analyzes non-contrast CT images of the b<br>rain acquired in the acute setting and sends notification<br>s to a neurovascular or neurosurgical specialist that a s<br>uspected intracranial hemorrhage has been identified and<br>recommends review of those images. Images can be p<br>reviewed through a mobile application. Images that are<br>previewed through the mobile application may be comp<br>ressed and are for informational purposes only and not<br>intended for diagnostic use beyond notification. Notified<br>clinicians are responsible for viewing non-compressed i<br>mages on a diagnostic viewer and engaging in appropri<br>ate patient evaluation and relevant discussion with a tre<br>ating physician before making care-related decisions or<br>requests. Viz ICH is limited to analysis of imaging dat<br>a and should not be used in-lieu of full patient evaluati<br>on or relied upon to make or confirm diagnosis. Viz I<br>CH is contraindicated for analyzing non-contrast CT sca<br>ns that are acquired on scanners from manufacturers ot<br>her than General Electric (GE) or its subsidiaries (i.e.<br>GE Healthcare). This contraindication applies to NCCT<br>scans that conform to all applicable Patient Inclusion C<br>riteria, are of adequate technical image quality, and wo<br>uld otherwise be expected to be analyzed by the device<br>for a suspected ICH. |
| Product Code | QAS | QAS |
| Environment of use | Clinical/Hospital Environment | Clinical/Hospital Environment |
| Intended Clinical | Radiologist, emergency medicine physicians, neuros | Radiologist, emergency medicine physicians, neurosurge |
| End User | urgeons, neurologist | ons, neurologist |
| Anatomical Region | Head | Head |
| Clinical Condition | Acute Intercranial Hemorrhage (ICH) | Intercranial Hemorrhage (ICH) |
{5}------------------------------------------------
| | Subject Name<br>(Subject Device) | Viz.ai, Inc. Viz ICH<br>(K193658) |
|--------------------------------------------------------|--------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------|
| Independent of<br>standard of care<br>workflow | Yes, No cases are removed from worklist | Yes |
| | | |
| | | |
| AI Used | Yes | Yes |
| Input Image<br>Modality | Non-Contrast Head CT | Non-Contrast Head CT |
| | | |
| Alteration of Image | No | No |
| DICOM Compatible | Yes | Yes |
| Transfer, store, and<br>process DICOM im<br>ages | Yes | Yes |
| | | |
| | | |
| Data Acquisition | Acquires medical image data from DICOM compli<br>ant imaging devices and modalities. | Acquires medical image data from DICOM compliant i<br>maging devices and modalities. |
| | | |
| Results of Image<br>Analysis | Internal, no image marking | Internal, no image marking |
| | | |
| Preview Images | Initial assessment; non-diagnostic | Initial assessment; non-diagnostic |
| View DICOM Data | DICOM Information about the patient, study and c<br>urrent image. | DICOM Information about the patient, study and curren<br>t image. |
| | | |
| Image viewing and<br>manipulation<br>(window,pan,zoom) | Yes | Yes |
| | | |
| | | |
| Output | AI findings (Suspected ICH or Case Processed) | Suspected ICH (Yes or No) |
| Clinical SoC<br>Workflow | In parallel to | In parallel to |
| | | |
| Results Receiver | PACS/Workstation | PACS/Workstation |
## Overall Performance Data Comparison
| Performance | Subject Device | K193658 |
|---------------------------------------|-------------------------|-------------------|
| Sensitivity (%) | 95.45 | 93 |
| 95% Confidence Interval | [91.55, 97.90] | [87, 97] |
| Specificity (%) | 98.47 | 90 |
| 95% Confidence Interval | [95.59, 99.68] | [84, 94] |
| AUC of ROC | 0.9864 [0.9738, 0.9989] | 0.96 |
| Average time to alerting a specialist | 16.39±5.46 seconds | 0.49±0.15 minutes |
# Age Subgroup Performance Data Comparison
| | Subject Device | | K193658 | |
|-------------------|-------------------------|---------------------------|-------------------------|-------------------------|
| Age Range (years) | Sensitivity<br>[95% CI] | Specificity<br>[95% CI] | Sensitivity<br>[95% CI] | Specificity<br>[95% CI] |
| <50 | 95.35<br>[84.19, 99.43] | 96.94<br>[91.31, 99.36] | 0.89<br>[0.52, 1.0] | 0.95<br>[0.76, 1.0] |
| 50 - 70 | 97.92<br>[88.93, 99.95] | 100.00<br>[94.04, 100.00] | 0.92<br>[0.82, 0.97] | 0.9<br>[0.8, 0.96] |
| >70 | 94.39<br>[88.19, 97.91] | 100.00<br>[90.75, 100.00] | 0.94<br>[0.84, 0.99] | 0.88<br>[0.76, 0.95] |
{6}------------------------------------------------
#### Gender Subgroup Performance Data Comparison
| Gender | Subject Device | | K193658 | |
|--------|----------------|-----------------|--------------|-------------|
| | Sensitivity | Specificity | Sensitivity | Specificity |
| | [95% Cl] | [95% Cl] | [95% Cl] | [95% Cl] |
| Male | 97.25 | 100.00 | 0.9 | 0.9 |
| | [92.17, 99.43] | [95.55, 100.00] | [0.8, 0.96] | [0.8, 0.96] |
| Female | 93.26 | 97.39 | 0.95 | 0.89 |
| | [85.90, 97.49] | [92.57, 99.46] | [0.86, 0.99] | [0.8, 0.95] |
#### ICH Subtype Performance Data Comparison
| ICH Subtype | Subject Device | K193658 |
|--------------------------------------|---------------------------|-------------------------|
| | Sensitivity<br>[95% CI] | Sensitivity<br>[95% CI] |
| Intraparenchymal Hemorrhage<br>(IPH) | 97.30<br>[90.58, 99.67] | 0.98<br>[0.91, 1.0] |
| Intraventricular Hemorrhage (I VH) | 97.67<br>[87.71, 99.94] | 1.00<br>[0.74, 1.0] |
| Subarachnoid Hemorrhage (SA H) | 97.65<br>[91.76, 99.71] | 0.60<br>[0.26, 0.88] |
| Subdural Hemorrhage (SDH) | 94.69<br>[88.80, 98.03] | 0.85<br>[0.62, 0.97] |
| Extradural Hemorrhage (EDH) | 100.00<br>[80.49, 100.00] | N/A |
| SDH or EDH | 97.30<br>[90.58, 99.67] | 0.85<br>[0.62, 0.97] |
#### Slice Thickness Subgroup Performance Data Comparison
| | Subject Device | | K193658 | |
|-------------------------------------|-------------------------|---------------------------|-------------------------|-------------------------|
| Slice Thickness | Sensitivity<br>[95% CI] | Specificity<br>[95% CI] | Sensitivity<br>[95% CI] | Specificity<br>[95% CI] |
| 2.5mm <= Slice Thickness<br>3.5mm | 96.67<br>[88.47, 99.59] | 94.00<br>[83.45, 98.75] | 0.93<br>[0.85, 0.98] | 0.92<br>[0.83, 0.97] |
| 3.5mm <= Slice Thickness<br>= 5.0mm | 94.78<br>[89.53, 97.87] | 100.00<br>[97.45, 100.00] | 0.92<br>[0.81, 0.98] | 0.88<br>[0.77, 0.95] |
## PERFORMANCE DATA
SK Inc. conducted a retrospective study to evaluate the efficacy of radiological computer aided triage and notification software (CADt), which supports medical specialist to promptly diagnose and treat with suspected intracranial hemorrhage by providing notification, when analyzed as a patient with suspected intracranial hemorrhage. To this study, the clinical sensitivity of the investigational medical device "Hyper Insight-ICH' was evaluated against the reading results of intracranial hemorrhage from brain CT images by the Reference Standard Establishment Committee. The results of this non-clinical testing show that the strength of the Hyper Insight-ICH is sufficient for its intended use and is substantially equivalent to legally marketed predicate device.
394 brain Computed Tomography images were obtained from 13 clinical sites in the U.S. There were approximately equal numbers of 'yes' or 'no' analysis results (198 with intracranial hemorrhage and 196 without intracranial hemorrhage). Sensitivity and specificity were calculated in the image database, comparing the Viz ICH's output to ground truth as established by trained neuro-radiologists. Sensitivity and specificity were 95.45% (95% CI) and 98.47% (95% CI), respectively. Because the lower bound of each confidence interval exceeded 80%, the study met the pre-specified performance goals of 80% for sensitivity and specificity.
In addition, the area under the receiver operating characteristic curve (AUC) was 0.9864 demonstrating the
{7}------------------------------------------------
clinical utility and potential benefits of the Hyper Insight - ICH based on the imaging study results.
In the study, the average time to analyzing the brain CT image and notify the result of the intracranial hemorthage identification to the mobile (DICOM VIEWER) was analyzed was 16.39 ± 5.46 seconds (0.27 ± 0.091 minutes), which is lower than the average time to notification seen in the predicate device of 0.49 ± 0.15 minutes. This data will allow medical personnel to quickly and accurately identify patients suspected of intracranial hemorthage through notifications and determine priority triage, providing them an opportunity to participate early in the clinical workflow.
| | Subject Device | K193658 |
|---------------------------------|---------------------------------------------------------|-----------------------|
| Average time to<br>notification | $16.39 \pm 5.46$ seconds<br>( $0.27 \pm 0.091$ minutes) | $0.49\pm0.15$ minutes |
As part of a secondary analysis, the company stratified the device performance by various confounding variables:
| Performance Stratified by Clinical Site | | |
|-----------------------------------------|---------------------------|---------------------------|
| Clinical Site | Sensitivity [95% Cl] | Specificity [95% Cl] |
| Clinical Site 1 | 100.00<br>[59.04, 100.00] | 100.00<br>[59.04, 100.00] |
| Clinical Site 2 | 92.86<br>[66.13, 99.82] | 50.00<br>[1.26, 98.74] |
| Clinical Site 3 | 100.00<br>[2.50, 100.00] | [-, -] |
| Clinical Site 4 | 100.00<br>[15.81, 100.00] | 90.00<br>[55.50, 99.75] |
| Clinical Site 5 | 100.00<br>[59.04, 100.00] | 94.12<br>[71.31, 99.85] |
| Clinical Site 6 | 100.00<br>[2.50, 100.00] | [-, -] |
| Clinical Site 7 | 100.00<br>[47.82, 100.00] | 100.00<br>[15.81, 100.00] |
| Clinical Site 8 | 100.00<br>[2.50, 100.00] | 100.00<br>[2.50, 100.00] |
| Clinical Site 9 | 100.00<br>[69.15, 100.00] | 100.00<br>[59.04, 100.00] |
| Clinical Site 10 | 83.33<br>[35.88, 99.58] | 100.00<br>[39.76, 100.00] |
| Clinical Site 11 | 92.59<br>[75.71, 99.09] | 100.00<br>[94.72, 100.00] |
| Clinical Site 12 | 92.00<br>[80.77, 97.78] | 100.00<br>[92.75, 100.00] |
| Clinical Site 13 | 98.51<br>[91.96, 99.96] | 100.00<br>[88.06, 100.00] |
| Performance Stratified by Age | | |
|-------------------------------|-------------------------|---------------------------|
| Age Range (years) | Sensitivity [95% Cl] | Specificity [95% Cl] |
| ≤50 | 95.35<br>[84.19, 99.43] | 96.94<br>[91.31, 99.36] |
| 50 - 70 | 97.92<br>[88.93, 99.95] | 100.00<br>[94.04, 100.00] |
| ≥70 | 94.39<br>[88.19, 97.91] | 100.00<br>[90.75, 100.00] |
{8}------------------------------------------------
| Performance Stratified by Gender | | |
|----------------------------------|-------------------------|---------------------------|
| Gender | Sensitivity [95% CI] | Specificity [95% CI] |
| Male | 97.25<br>[92.17, 99.43] | 100.00<br>[95.55, 100.00] |
| Female | 93.26<br>[85.90, 97.49] | 97.39<br>[92.57, 99.46] |
| Performance Stratified by Race | | |
|----------------------------------------------------|---------------------------|---------------------------|
| Race | Sensitivity [95% CI] | Specificity [95% CI] |
| American<br>Indian or<br>Alaskan Native | 100.00<br>[2.50, 100.00] | [-, -] |
| Asian | 100.00<br>[59.04, 100.00] | 100.00<br>[29.24, 100.00] |
| Black or<br>African<br>American | 100.00<br>[85.18, 100.00] | 100.00<br>[90.00, 100.00] |
| Native<br>Hawaiian or<br>Other Pacific<br>Islander | 100.00<br>[15.81, 100.00] | [-, -] |
| White | 95.21<br>[90.37, 98.05] | 97.79<br>[93.69, 99.54] |
| Two or more<br>races | [-, -] | [-, -] |
| Unknown | 89.47<br>[66.86, 98.70] | 100.00<br>[84.56, 100.00] |
| Performance Stratified by ICH Subtype | |
|---------------------------------------|---------------------------|
| ICH Subtype | Sensitivity [95% CI] |
| Intraparenchymal Hemorrhage (IPH) | 97.30<br>[90.58, 99.67] |
| Intraventricular Hemorrhage (IVH) | 97.67<br>[87.71, 99.94] |
| Subarachnoid Hemorrhage (SAH) | 97.65<br>[91.76, 99.71] |
| Subdural Hemorrhage (SDH) | 94.69<br>[88.80, 98.03] |
| Epidural Hemorrhage (EDH) | 100.00<br>[80.49, 100.00] |
| Performance Stratified by Slice Thickness | | |
|---------------------------------------------------------------------|---------------------------|---------------------------|
| Slice Thickness | Sensitivity [95% CI] | Specificity [95% CI] |
| $0.5 \text{ mm } \leq \text{ slice thickness } < 2.5 \text{ mm}$ | 100.00<br>[39.76, 100.00] | 100.00<br>[29.24, 100.00] |
| $2.5 \text{ mm } \leq \text{ slice thickness } < 3.5 \text{ mm}$ | 96.67<br>[88.47, 99.59] | 94.00<br>[83.45, 98.75] |
| $3.5 \text{ mm } \leq \text{ slice thickness } \leq 5.0 \text{ mm}$ | 94.78<br>[89.53, 97.87] | 100.00<br>[97.45, 100.00] |
| Performance Stratified by CT scanner's manufacturer | | |
|-----------------------------------------------------|---------------------------|-------------------------|
| CT scanner's manufacturer | Sensitivity [95% CI] | Specificity [95% CI] |
| Canon Medical Systems | 100.00<br>[66.37, 100.00] | -<br>[-, -] |
| GE MEDICAL SYSTEMS | 96.77<br>[83.30, 99.92] | 90.91<br>[70.84, 98.88] |
| Philips | 92.50<br>[79.61, 98.43] | 98.88<br>[93.90, 99.97] |
{9}------------------------------------------------
| PNMS | - | 100.00 |
|---------|----------------|-----------------|
| | [-, -] | [2.50, 100.00] |
| SIEMENS | 93.44 | 100.00 |
| | [84.05, 98.18] | [93.62, 100.00] |
| TOSHIBA | 98.25 | 100.00 |
| | [90.61, 99.96] | [87.66, 100.00] |
| Performance Stratified by ICH Volume | |
|--------------------------------------|--------------------------------------|
| Minimal Volume Threshold (mL) | Sensitivity above Threshold [95% CI] |
| <1 | 90.00<br>[81.24, 95.58] |
| 1≤ ICH volume < 5 | 98.13<br>[93.41, 99.77] |
| 5≤ ICH volume < 10 | 97.37<br>[86.19, 99.93] |
| 10≥ | 100.00<br>[96.61, 100.00] |
#### CONCLUSION
Hyper Insight-ICH is as safe and effective as the predicate, Viz ICH (K193658), in that it has the same indications for use and minor technological differences compared to the predicate. Performance data demonstrate that Hyper Insight-ICH does not raise any new issues regarding safety or efficacy when compared to its predicate device. Thus, Hyper Insight-ICH is substantially equivalent to its predicate device.
Predicate graph will load when search results are available.
Embedding visualization will load when search results are available.
PDF viewer will load when search results are available.
Loading panels...
Select an item from Submissions
Click any panel, subpart, regulation, product code, or device to see details here.
Section Matches
Results will appear here.
Product Code Matches
Results will appear here.
Special Control Matches
Results will appear here.
Loading collections...
Loading
My Alerts
You will receive email notifications based on the filters and frequency you set for each alert.
Sort by:
Create Alert
Search Filters
Agent Token
Create a read-only bearer token for Claude, ChatGPT, or other agents that can call HTTP APIs.
Copy this now. It will not be shown again.
Connected apps
Apps you authorized through browser sign-in. Disconnecting revokes their access immediately.
Learn the FDA Browser
Two short videos show you everything — or skip straight to the written tutorial if you'd rather read. You can reopen this any time from the Tutorial button in the top bar.
Part 1 — Search, results, and everyday workflows 16 min
Part 2 — Embeddings: the galaxy map 3 min
1. Search: exact and fuzzy
Type a phrase like "coronary artery calcification" into the search box. You get two kinds of results. Exact results match the literal phrase — prefix searches work ("coronary artery calcificati") but suffix searches do not. Fuzzy results match on the meaning and intent of your phrase rather than the exact words, and are sorted by relevance score. Hover over the Exact or Fuzzy badge on any row to see exactly why it matched.
Use the checkboxes above the results to narrow: SaMD keeps only software-only devices, AI / ML keeps only devices with AI.
Exact vs. fuzzy search: what's the difference?
Exact matches on the literal phrase (prefix search works, suffix does not). Fuzzy matches on the meaning and intent of the phrase rather than the exact words. Hover over the badge on any row to see why it matched.
You search "coronary artery calcification" and want only software devices with AI. What two filters do you apply?
Narrow by SaMD (software-only devices), then narrow by AI/ML (devices with AI).
2. The results table
Scroll right in the results table. The intended use is extracted for you — no need to open the PDF. The device story gives a high-level snapshot of what the device does and how it's used. The AI Performance sub-table shows each output name, acceptance criteria, observed values, and development/test dataset descriptions — the same format Innolitics uses for regulatory strategy outputs, and the fastest high-level fingerprint of an AI device. It is AI-generated but has been very reliable in practice.
Where do you find a device's intended use without opening the PDF?
Scroll right in the search results table. The intended use column is extracted for you; no need to dig into the 510(k) summary PDF.
What does the AI Performance sub-table show, and why is it useful?
Output name, acceptance criteria, observed values, development dataset description, and test dataset description. It's the same format we use for regulatory strategy output and Fast 510(k) input, and the fastest high-level fingerprint of an AI device. AI-generated but reliable in practice.
3. Judging fuzzy relevance
Fuzzy results trail off in relevance as you scroll. Use three signals to decide how far down to go: the fuzzy badge explanations, the intended use column, and whether your target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, you're past the relevant zone. A top hit with a low score (~0.4) and a stretched explanation is a hint the closest predicates are far away — the project may be headed for De Novo. Note the fuzzy search is a pattern match: it doesn't handle negation ("not") well, and hardware devices can appear — filter by SaMD/AI ML to cut them.
How do you judge how far down fuzzy search results to go?
Use the relevancy signals: the fuzzy badge explanations, the intended use column, and whether the target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, results are trailing off in relevancy.
4. Device detail page: chat and citations
Click a device name to open its detail page: device facts on the left, a chat window on the right. Ask something like "Describe the training data". The answer carries little citation bubbles — click one to jump to the highlighted passage in the source PDF, so you can verify every AI answer against the document. There's also a Download PDF button for sharing.
How do you verify an AI chat answer on the device detail page?
Click the citation bubbles to jump to the relevant highlight in the source document.
Reading rule for every project: how many summaries do you read in full?
At least the three most relevant 510(k) or De Novo summaries, in full. After that, use targeted chat questions to confirm your memory quickly. The tool supports this professional habit — it doesn't replace it.
5. Side-by-side comparison
Select multiple rows in the results table (aim for under ~10), then open the PDF Viewer tab. Ask one question — it goes to all selected devices in parallel, each with citations. This is the fastest way to compare and contrast devices: training data, PCCP scope, how they handled adding new scanners, and so on.
What does the side-by-side PDF viewer mode do?
Select multiple devices, open the PDF viewer tab, and ask one question (e.g., "Describe the training data"). It queries all selected devices simultaneously with citations, so you can compare and contrast quickly.
6. Collections
With rows selected, go to the Collections tab and create a labeled collection (e.g., "Cobb Angle Project"). Reload that selection any time — before a client call, pull up the collection and ask questions across all of its devices at once.
How do you save a set of selected devices for later use?
Select the rows, go to the Collections tab, and create a labeled collection (e.g., "Cobb Angle Project"). You can reload the selection anytime and carry it into the PDF viewer and other tabs that support selections.
7. Product codes and the regulations tree
Click a product code in the results to jump to it in the regulations tree — identification text, sibling product codes, and devices you can open in a PDF viewer on the right. Click a regulation number to see its identification, special controls, and related product codes. You can also search by product code or regulation number at the top of the tree. Always read the special controls if any exist for your device — it broadens your search and sharpens pre-kickoff research.
What can you do from the regulations tree view?
Browse product codes and regulation numbers, read the identification text and special controls, browse sibling product codes, open device PDFs on the right, and search by product code or regulation number at the top of the tree.
8. Chart view
Click Show Chart and segment by regulation number (or product code) to see which regulations dominate your result set. Clicking a regulation takes you into the regulations tree. Great for spotting that most matches are, say, hardware laparoscopic devices — a cue to go back and filter.
How do you see which regulations dominate a search result set?
Click "Show Chart" and segment by Regulation Number. Clicking a regulation takes you to the regulations tree.
9. The predicate graph
Open the Predicates tab for a family-tree view of predicate relationships. Click a node to trace its parents and children; selections from search carry over pre-selected. Commonly predicated devices are worth reading — a lot of people predicated them for a reason. The visual lineage is also handy on client calls, e.g. to show how a predicate family evolved and justify why your predicate still holds.
In the predicate graph, why are commonly predicated devices worth reading?
A lot of people predicated them for a reason. Clicking a node traces parents and children, and selections from search carry over pre-selected.
10. Embeddings: the galaxy map
The Embeddings tab plots every matching document in a 2-D "galaxy map" where semantically similar devices cluster together. Hover or click clusters to explore, and let AI label the clusters for you. Embeddings beat product codes for grouping: two devices can carry different product codes (LLZ vs. QIH) yet do the same thing — the embedding captures the meaning of the intended use and device story. This is also exactly how retrieval-augmented generation (RAG) works under the hood, and it makes a great visual on client calls.
Try it yourself
Head to the search page and work through a few of these AI/ML fuzzy searches to build intuition: perivascular fat on CT · aortic valve calcification opportunistic screening on noncontrast CT · breast cancer prediction on digital pathology slides · autism detection · gestational age prediction · a hearing aid that can also detect a pulse · foundation model based analysis of ECG · large language models · penetration test. Watch how the relevance scores, intended use, and AI Performance tables tell you when results stop being meaningful.
