EQ Balance is intended to assess body tilt as an indicator of balance. Individual suitability for assessment must be judged on a case by case basis, by a qualified including those certified and/or licensed in their state to prescribe and/or use balance devices such as certified athletic trainers and coaches, physical therapists, nurses and physicians. Interpretation of EQ Balance results should only be made by a healthcare professional, as part of a multifaceted assessment of balance. Conditions affecting postural sway include nausea, headache, orthopedic injury, ear infection, medications, head injury, dehydration and fatigue. EO Balance should be used in an indoor setting free from obstructions and free from excessive noise or visual distractions. EQ Balance should be only be used as directed by your healthcare practitioner. EQ Balance may be used on mobile devices running iOS or Android operating systems.

Device Description

EQ Balance is a mobile balance test to be used on mobile phone and tablet devices with iOS version 10.3 or later, or Android OS version 6 or later. EQ Balance measures balance using the accelerometer within the device.

EQ Balance utilizes an algorithm that calculates a balance score based on the analysis of subject movements detected by the device's internal accelerometer. Balance is measured during a series of stances with the mobile device held to the chest by the user. Users follow the step-by-step voice guidance that runs after launching the app during the entirety of the test to ensure consistency in obtaining balance measures. EQ Balance does not function as a diagnostic test, and EQ Balance results should be interpreted by qualified individuals only.

AI/ML Overview

The provided text details the 510(k) summary for the EQ Balance device, which is intended to assess body tilt as an indicator of balance. The study's primary goal was to demonstrate substantial equivalence to the predicate device, Sway Balance.

Here's an analysis of the acceptance criteria and study information:

1. Table of Acceptance Criteria and Reported Device Performance

The document states that the performance testing verified that "EQ Balance and the Sway™ Balance System (Sway) are in statistical agreement." The agreement was primarily assessed using Spearman's analysis and Deming Regression Model.

Acceptance Criteria / Performance Metric	Acceptance Criteria	Reported Device Performance	Comments
Statistical Agreement (3-pose average) with Predicate (Sway Balance)	Not explicitly stated, implied to be demonstrable statistical agreement	Spearman's analysis: "the 3-pose average measures calculated by EQ Balance were in statistical agreement with the 3-pose average obtained with Sway Balance for both normal and balance-impaired groups, and for all three stances (double leg, tandem right and left)."Deming Regression Model: "showed agreement between the 3-pose average balance measures (the primary device output), as well as 23 of the 27 additional analyses that were conducted."	The study aimed to show agreement rather than a specific statistical threshold for acceptance.
Intraclass Correlation (ICC) for consistency of EQ Balance measure	Not explicitly stated. Implied to be strong consistency.	ICC for the cohort was 0.75 (p<0.001)	This indicates strong consistency of the task output between test sessions.
Poorer balance scores for subjects with balance impairments	Not explicitly stated, but expected for clinical relevance.	"Poorer balance scores were observed for subjects with balance impairments."	This demonstrates the device's ability to differentiate between healthy and impaired balance.
Conformance to product specification (Nonclinical/Bench Testing)	Met specification	"EQ Balance met specification."	Verified accuracy of tilt angles from the accelerometer.

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

Sample Size for Test Set: 70 subjects (25 males; 45 females).
Data Provenance: Prospective. The clinical testing was conducted under an IRB-approved study at a "sports medicine and concussion clinic in Mississauga, Ontario." Mississauga is in Canada.

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

Number of Experts: Not explicitly stated for specific ground truth establishment. However, the study was conducted under the "oversight of a principle investigator from the Department of Neurosurgery at the University of Toronto."
Qualifications of Experts: The ground truth for balance impairment was "determined by failure of the modified Balance Error Scoring System (mBESS) test." The mBESS test itself is administered by trained individuals, implying expert involvement in the assessment that defined the ground truth. While explicit expert count or detailed qualifications for establishing mBESS ground truth aren't given, the involvement of a "principle investigator from the Department of Neurosurgery" suggests qualified oversight.

4. Adjudication Method for the Test Set

The adjudication method is not explicitly described as a multi-reader adjudication process (e.g., 2+1, 3+1). The balance impairment ground truth was determined by the "failure of the modified Balance Error Scoring System (mBESS) test," implying a standardized test administered and interpreted by trained personnel. The simultaneous testing of EQ Balance and Sway Balance on the same subjects suggests a direct comparison where each device's output was against the other and against the mBESS-determined impairment status, rather than a multi-expert adjudication of the device outputs themselves.

5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

MRMC Study: No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not explicitly described.
Effect Size of Human Reader Improvement: This study focused on the statistical agreement between two device outputs (EQ Balance and Sway Balance) and their ability to correlate with balance impairment as determined by mBESS. It did not involve comparing human reader performance with and without AI assistance.

6. If a Standalone (i.e. algorithm only without human-in-the-loop performance) was done

Yes, a standalone performance evaluation was done. The study "Performance testing verified that EQ Balance and the Sway™ Balance System (Sway) are in statistical agreement." Both EQ Balance and Sway Balance are described as software applications that "utilizes an algorithm that calculates a balance score based on the analysis of subject movements detected by the device's internal accelerometer." The clinical study involved subjects holding the mobile device and the applications calculating scores; there's no mention of a human-in-the-loop directly interpreting the raw accelerometer data or refining the algorithm's scores for the purpose of the study.

7. The Type of Ground Truth Used

The ground truth for balance impairment in the clinical study was established by the "failure of the modified Balance Error Scoring System (mBESS) test." This is a clinical assessment method.

8. The Sample Size for the Training Set

The document does not provide information about the sample size used for the training set for the EQ Balance algorithm. The provided clinical study appears to be solely for validation/performance testing.

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

As no information is provided regarding a specific training set or its sample size, details on how its ground truth was established are also not available in the provided text.

Summary

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

Image /page/0/Picture/0 description: The image shows 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.

August 16, 2019

Highmark Innovations Inc. DBA Highmark Interactive % E.J. Smith Consultant Smith Associates 1468 Harwell Avenue Crofton, Maryland 21114

Re: K190735

Trade/Device Name: EQ Balance Regulation Name: Vestibular Analysis Apparatus Regulatory Class: Unclassified Product Code: LXV Dated: July 12, 2019 Received: July 18, 2019

Dear E.J. 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

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

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-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 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.

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

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

Sincerely,

Srinivas Nandkumar, Ph.D. Assistant Director DHT1C: Division of ENT, Sleep Disordered Breathing, Respiratory and Anesthesia Devices OHT1: Office of Ophthalmic, Anesthesia, Respiratory, ENT and Dental Devices Office of Product Evaluation and Ouality Center for Devices and Radiological Health

Enclosure

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

Indications for Use

510(k) Number (if known) K190735

Device Name EQ Balance

Indications for Use (Describe)

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

Prescription Use (Part 21 CFR 801 Subpart D)

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

CONTINUE ON A SEPARATE PAGE IF NEEDED.

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

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

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

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

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

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

Image /page/3/Picture/1 description: The image is a logo for Highmark Interactive. The logo features a blue graphic above the words "HIGHMARK interactive". The graphic is a stylized representation of two hemispheres, possibly representing a brain, with lines dividing each hemisphere into sections.

510(k) Summary

Trade Name	EQ Balance
Common Name	Balance Test Application
Classification	Unclassified
Product Code	LXV
Predicate Device	Sway Balance™ by Capacity Sports, LLC (K121590)
Company Name:	Highmark Interactive
Company Address:	1 University Avenue, 3rd FloorToronto, Ontario, Canada M5J 2P1
Telephone:	416.320.0286
email:	david@highmark.tech
Contact Person:	David Crane, Senior Product Manager
Summary Preparation Date:	August 14, 2019

PREDICATE DEVICE:

Manufacturer	Brand Name	510(k) Number
Capacity Sports, LLC	Sway BalanceTM	K121590

DEVICE DESRIPTION:

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

INDICATIONS FOR USE:

EQ Balance is intended to assess body tilt as an indicator of balance. Individual suitability for assessment must be judged on a case by case basis, by a qualified individual including those certified and/or licensed in their state to prescribe and/or use balance devices such as certified athletic trainers and coaches, physical therapists, nurses and physicians. Interpretation of EQ Balance results should only be made by a healthcare professional, as part of a multifaceted assessment of balance. Conditions affecting postural sway include nausea, headache, orthopedic injury, ear infection, medications, head injury, dehydration and fatigue. EQ Balance should be used in an indoor setting free from obstructions and free from excessive noise or visual distractions. EQ Balance should be only be used as directed by your healthcare practitioner. EQ Balance may be used on mobile devices running iOS or Android operating systems.

Features	Highmark Interactive	Capacity Sports, LLC	Comments
Identify	EQ Balance	Sway Balance™
Predicate
Device
510(k)	K190735	K121590
Number:
Indicationsfor usestatement	EQ Balance is intended toassess body tilt as anindicator of balance.Individual suitability forassessment must be judgedon a case by case basis, bya qualified individualincluding those certifiedand/or licensed in their stateto prescribe and/or usebalance devices such ascertified athletic trainers andcoaches, physical therapists,nurses and physicians.Interpretation of EQ Balanceresults should only be madeby a healthcare professional,	The Sway™ Balance Systemis intended for use to assesssway as an indicator ofbalance. Individual suitabilityfor assessment must bejudged on a case by casebasis, by a qualified individualincluding those certified and/orlicensed in their state toprescribe and/or use balancedevices such as certifiedathletic trainers and coaches,physical therapists, nurses andphysicians. Conditionsaffecting postural sway includenausea, headache, orthopedicinjury, ear infection,	SubstantiallyEquivalent
Features	Highmark Interactive	Capacity Sports, LLC	Comments
	as part of a multifacetedassessment of balance.Conditions affecting posturalsway include nausea,headache, orthopedic injury,ear infection, medications,head injury, dehydration andfatigue. EQ Balance shouldbe used in an indoor settingfree from obstructions andfree from excessive noise orvisual distractions. EQBalance should be only beused as directed by yourhealthcare practitioner. EQBalance may be used onmobile devices running iOSor Android operatingsystems.	medications, head injury,dehydration and fatigue. TheSway™ Balance System canbe used wherever an iOSmobile operating device isavailable.
UseEnvironment/ Where used	Mobile tablet/phone runningiOS and Android operatingsystems.The testing is intended to bedone on a firm and flatsurface in an area free fromvisual or auditory distraction.	Mobile tablet/phone runningiOS and Android operatingsystems.A controlled environment on aflat, hard surface.(Sway's website:https://swaymedical.com/resources/faqs)	SubstantiallyEquivalent
TargetPopulation	Individual suitability forassessment must be judgedon a case-by-case basis, bya qualified individualincluding those certifiedand/or licensed in their stateto prescribe and/or usebalance devices such ascertified athletic trainers andcoaches, physical therapists,nurses and physicians.	Individual suitability forassessment must be judged ona case-by-case basis, by aqualified individual includingthose certified and/or licensedin their state to prescribeand/or use balance devicessuch as certified athletictrainers and coaches, physicaltherapists, nurses andphysicians.	SubstantiallyEquivalent
Features	Highmark Interactive	Capacity Sports, LLC	Comments
Stand AloneSoftware	Yes	Yes	Same
Electronicallyrecordobjectiveperformancemeasurement(speed andaccuracy)	Yes	Yes	Same
Design	Android and iOS-basedmobile software application	Android and iOS-based mobilesoftware application	Substantiallyequivalent
Materials	EQ Balance is a software-only solution that uses thehardware via the Apple iOSand Android OS mobileoperating systems forproducts.The built-in accelerometer isaccessed to analyze motionduring a balance test.	The Sway BalanceTM Systemis a software only solution thatuses the hardware of the AppleiOS mobile operating systemfor products such as theiPhone 3G, 3GS, 4, 4S, iPad,iPad2 and iPod Touch.The built-in accelerometer isaccessed to analyze motionduring a balance test.Now also compatible withAndroid OS	Substantiallyequivalent

PREDICATE PRODUCT COMPARISON TABLE:

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

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

DISCUSSION OF TECHNOLOGICAL DIFFERENCES:

EQ Balance and Sway Balance both run on iOS and Android mobile devices. EQ Balance is compatible with iPhone, iPad and iPod touch devices running iOS version 10 and up as well as devices using Android OS version 6 and up. EQ Balance will continually update to run on future generations of these mobile devices. Sway Balance functions on iPhone, iPad and iPod touch devices running version iOS 9.3 or later, or Android OS version 6 and up, according to the app store marketplaces where this app is distributed.

Both applications use built-in iOS mobile device accelerometers to calculate the output balance score. The output score reflects how much movement occurred during each assessment. Balance scores are measured on a 0 to 100 scale. Scores closer to 100 are considered closer to normal with 100 being a perfect score. The point spread may vary between EQ Balance and Sway based on differences in algorithms, however the output scores are comparable and repeatable.

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

NONCLINICAL TESTING:

Device testing was conducted to evaluate conformance to product specification. EQ Balance met specification. Nonclinical ("bench") testing analyzed the accuracy of the tilt angles coming from the accelerometer in the mobile devices that are compatible with the EQ Balance application. Accuracy with EQ Balance were comparable. Testing was conducted using a sample of Apple device models running the iOS operating system and sample of Samsung device models running the Android operating system.

Test documentation has been provided according to the FDA Guidance for the Content of Premarket Submissions for Software, including software Verification and Validation reports and Bench Testing. The design and testing was conducted according to IEC 62304 Medical Device Software –Software Life Cycle Processes and ISO 14971 Medical Device -Application of Risk Management to Medical Devices.

CLINICAL STUDY:

Performance testing verified that EQ Balance and the Sway™ Balance System (Sway) are in statistical agreement.

Clinical testing was completed under an IRB-approved study at a sports medicine and concussion clinic in Mississauga, Ontario under the oversight of a principle investigator from the Department of Neurosurgery at the University of Toronto. EQ Balance and Sway Balance testing were performed simultaneously (two trials) for a total of 70 male and female subjects (25 males; 45 females; mean age: 37.8 ± 14.8, range: 13-65) with and without balance impairment, determined by failure of the modified Balance Error Scoring System (mBESS) test (26 balance-impaired). Participants performed three postures, that were analyzed, while holding the mobile device aqainst their chest. Balance measures were then obtained simultaneously with Sway Balance and EQ Balance during each of the stances, which included the double leg stance, right tandem stance, and left tandem stance. Participants held a device holder that secured two devices: one iPhone 6s (Apple, Cupertino, CA, USA) with EQ Balance and a second iPhone 6s with Sway Balance. The amount of movement was calculated by each balance test application algorithm using data generated by the mobile device accelerometer. The primary output ("3-pose average") was calculated as the average of the balance performance on the 3 stances.

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

The following table summarizes EQ Balance scores by pose and by group: Healthy vs. Impaired balance

	Healthy balance (N=44)
Pose:	Feettogether	Tandem left	Tandem right	3-poseaverage
Minimum	87.7	40.7	62.5	70.5
5th percentile	87.8	74.4	68.0	83.0
Median	94.0	90.0	91.4	91.0
95th percentile	96.2	95.2	94.8	94.3
Max	96.7	96.4	95.0	95.4

Impaired balance (N=26)

Pose:	Feettogether	Tandem left	Tandem right	3-poseaverage
Minimum	78.8	42.6	28.0	49.8
5th percentile	79.2	42.7	31.2	51.2
Median	89.4	75.5	73.3	78.9
95th percentile	97.5	94.0	92.8	93.0
Max	98.0	95.0	93.2	93.1

5% percentile means 5% of the data is below this value; 95% percentile means 95% of the data below this value

According to the Spearman's analysis, the 3-pose average measures calculated by EQ Balance were in statistical agreement with the 3-pose average obtained with Sway Balance for both normal and balance-impaired groups, and for all three stances (double leg, tandem right and left). The Deming Regression Model showed agreement between the 3-pose average balance measures (the primary device output), as well as 23 of the 27 additional analyses that were conducted . The statistical agreement between the two tests supports substantial equivalence of EQ Balance to Sway Balance. Poorer balance scores were observed for subjects with balance impairments. No adverse effects or complications were encountered during or after performance testing.

Consistency of the EQ Balance measure was conducted by calculating the intra-class correlation (ICC) on two consecutive EQ Balance tests. The ICC for the cohort was ICC=0.75 (p<0.001). This analysis demonstrates strong consistency of the task output between test sessions.

SUMMARY OF SUBSTANTIAL EQUIVALENCE:

EQ Balance is based on the legally market predicate device Sway Balance (K121590), with the same intended use. There are some differences in technological characteristics which do

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

510(k) Summary (K190735)

not raise different questions of safety and effectiveness, such as different proprietary algorithms used in the software for calculation of output balance score. Through clinical testing and other information (e.g. software, cybersecurity) according the agency's guidance document, we have demonstrated that the subject device EQ Balance is substantially equivalent to the predicate device Sway Balance.

Regulation Number and Section

N/A