The Sway System Sports Plus is intended for use as a computerized cognitive assessment and management of concussion in individuals ages 18-24. The Sway System Sports Plus is indicated for use when there is a suspected concussion or head injury.

Device Description

Sway Sports Plus (referred to as Sway Sports+) is a licensed variant of the Device Sway System and is a software solution (SaMD) that provides a computerized cognitive assessment aid for concussion. This prescription device uses an individual's score(s) on a battery of cognitive tasks to provide an indication of the current level of cognitive function in response to a suspected concussion. The computerized cognitive assessment aid for concussion is used only as an assessment aid in the management of concussion to determine cognitive function for patients after a potential concussive event where other diagnostic tools are available and does not identify the presence or absence of concussion. The examiner may have the patient complete the Sway Balance test to provide an additional indicator in their assessment of concussion. The Sway System is not intended as a stand-alone diagnostic device. After the patient completes the Sway Sports+ test(s), the examiner can view the summary statistics for each test such as mean reaction time (speed). Sway Sports+ does not create new information through analysis or interpretation, nor does it offer any diagnostic or treatment recommendations. The Sway Sports+ is not intended to be used as a standalone diagnostic device. Sway Sports+ operates in the Apple iOS or Android operating systems, enabling it to be used on the hardware of Apple iPhone. iPad, and iPod Touch. or Android mobile devices. The internal accelerometer is accessed to analyze motion of the device in response to stimuli during testing. The mobile device hardware is not provided by Sway Medical. Environments where Sway Sports+ may be used may include both clinical and non-clinical settings. Clinical settings may include physician offices, hospitals, physical or occupational therapy clinics, skilled nursing facilities, assisted living centers and other healthcare facilities where cognitive tests may be evaluated. In addition, non-clinical environments may include sports team's locations where the application may be used on the sideline to perform a cognitive assessment, e.g., fitness centers, gymnasiums, or stadiums. It is recommended that the tests be taken in a supervised environment for baseline and post-injury testing. Sway Sports+ consists of the Sway Balance (K121590) and the Sway Computerized Cognitive Assessment Aid. The Sway Computerized Cognitive Assessment Aid (PTY) is exempt from 510(k).

AI/ML Overview

Here's a breakdown of the acceptance criteria and the study information for the Sway System Sports Plus, based on the provided text:

Acceptance Criteria and Device Performance

The provided text details the non-clinical and clinical performance testing results, and how they relate to the substantial equivalence claim rather than explicit "acceptance criteria" in a pass/fail table format. However, we can infer the acceptance criteria from the reported performance results and the comparison to predicate devices.

Table 1: Inferred Acceptance Criteria and Reported Device Performance

Performance Metric	Inferred Acceptance Criteria (Based on Predicate/Reference Equivalence & Clinical Utility)	Reported Device Performance (Sway Sports Plus)
Software Validation	Compliance with IEC 62304 and FDA guidance for software V&V. Meeting predetermined specifications.	Designed and developed according to Sway Medical, Inc.'s internal software development process in accordance with IEC 62304. Tested using verification and validation methods. Results indicate compliance with specifications. All tests passed with no exceptions.
Construct Validity	Demonstrates construct validity with traditional neuropsychological tests and similar correlations to predicate devices.	VanRavenhorst-Bell et al., 2021: Sway Reaction Time, Impulse Control, and Inspection Time módulos correlated significantly (r = -0.46 to 0.22, p ≤ 0.05) with ImPACT QT reaction time measures. Clark & VanRavenhorst-Bell, 2022: Sway Sports+ modules exhibited correlation values ranging from 0.22 to 0.42 with traditional neurocognitive tests (WAIS-IV, WMS-IV, D-KEFS, CVLT-III). Demonstrated stronger correlation strengths with traditional neurocognitive tests compared to ImPACT. Significant correlations with ImPACT and traditional tests (p < 0.001 and p < 0.05).
Test-Retest Reliability	Adequate or better test-retest reliability (e.g., ICC values generally ≥ 0.60 or similar to predicate devices).	Van Patten et al., 2021: ICC values for weeks 1-2 ranged from 0.60 to 0.8; weeks 1-3 ranged from 0.68 to 0.88. ANOVA showed non-significant differences over three weeks. Caccese et al., 2022: For Sway Balance, ICC for Weeks 1 & 2 was 0.82, Weeks 1 & 3 was 0.88. ANOVA showed no significant differences. Additional Study (healthy adults 18-35): ICC values ranged between 0.82 and 0.92 for all Sway Sports+ modules with a one-week interval. No statistically significant differences between test and retest. Additional Study (concussed individuals): Robust level of reliability during post-concussion testing, comparable to baseline evaluations (within-session design).
Sensitivity	Ability to effectively identify concussed individuals, comparable to predicate devices.	Chikar & Curtiss, 2023: Sensitivity of 69.6% (32/46) for predicting concussion group membership, outperforming ImPACT (58.7% at 80% CI). McNemar's test showed no significant difference (p=0.383). Additional Study: High sensitivity.
Specificity	Ability to correctly identify non-concussed individuals, avoiding excessive false positives, or acceptable levels given the clinical context.	Additional Study: Moderate specificity, suggesting a tendency to over-identify concussed individuals (potential false positives). However, in a clinical context with healthcare professionals, such false positives can be eliminated. Very low rate of false negatives.
Normative Data	Establishment of a robust normative database
to aid in clinical interpretation, stratified by relevant demographics (e.g., age, gender).	De-identified baseline test data from over 126,000 users aged 18 to 24 years old (US, English speakers, no recent concussion/neurological conditions/learning disability, valid scores). Data stratified across age and gender. Age/gender groups required a minimal size of 50 profiles. Results indicate increased performance with age (peaking early to mid-20s) and gender-based differences, leading to age/gender-specific normative values.

Study Details

Sample size used for the test set and the data provenance:
- Validity Studies:
  - VanRavenhorst-Bell et al., 2021: 88 healthy adults aged 18 to 48 years (mean 22.09 ± 4.47 years). Data provenance not explicitly stated, but implies U.S. based on the context of FDA submission. Retrospective as it compares existing tools.
  - Clark & VanRavenhorst-Bell, 2022: 85 adults (mean age 23.1 years; 68% female). Data provenance not explicitly stated, but implies U.S. based on the context of FDA submission. Prospective (all tests administered in one session by trained professionals).
- Reliability Studies:
  - Van Patten et al., 2021: 55 adults (69% women) with a mean age of 26.69 years (± 9.89; range = 18-58). Data provenance not explicitly stated, but implies U.S. based on the context of FDA submission. Prospective (assessed remotely over 3 subsequent weeks).
  - Caccese et al., 2022: 55 healthy adults (69% women) with a mean age of 26.69 years (SD = 9.89; range = 18-58). Data provenance not explicitly stated, but implies U.S. based on the context of FDA submission. Prospective (assessed remotely over 3 subsequent weeks).
  - Additional study (healthy adults): 97 participants initially recruited, with 56 completing all test and retest sessions (one-week interval). Data provenance not explicitly stated, but implies U.S. based on the context of FDA submission. Prospective.
  - Additional study (concussed individuals): Utilized a dataset derived from NCAA member schools. Data provenance implies U.S. Retrospective (analyzing existing NCAA data for a within-session design).
- Sensitivity & Specificity Studies:
  - Chikar & Curtiss, 2023: 46 athletes (mean age 19.6, SD=1.4; 59% male) with confirmed concussions. Data from athletic organizations that conducted both ImPACT and Sway assessments. Data provenance implies U.S. and likely retrospective.
  - Additional study (sensitivity/specificity): No explicit sample size given, describes "high sensitivity but moderate specificity." Data provenance not explicitly stated, but implies U.S. based on the context of FDA submission. Likely retrospective analysis of existing data.
  - Additional pilot study (ImPACT vs. Sway): 24 high school and college-aged participants. Data provenance implies U.S. Prospective (underwent baseline and post-injury testing with both tools).
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- The document primarily relies on comparisons to established and FDA-cleared devices (ImPACT QT, ImPACT, traditional neurocognitive assessments) and clinical standards for concussion diagnosis (NCAA Concussion Safety Protocol guidelines).
- For the Clark & VanRavenhorst-Bell, 2022 validity study, "all tests administered by trained professionals." Specific number or qualifications of these professionals (e.g., neuropsychologists, physicians) are not detailed.
- For the concussed individuals reliability study and the sensitivity/specificity pilot study, the "clinical standards for concussion diagnosis were strictly followed according to NCAA Concussion Safety Protocol guidelines" or involved "athletic organizations that conducted both ImPACT and Sway assessments." This implies diagnosis by medical professionals (e.g., team physicians, athletic trainers) adhering to established protocols, but no specific number or detailed qualifications of these "experts" is provided.
Adjudication method for the test set:
- No explicit adjudication method (e.g., 2+1, 3+1) is described for establishing ground truth within the provided studies. The ground truth often relies on the established scores/diagnoses from predicate devices or clinical protocols.
If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:
- No MRMC comparative effectiveness study involving human readers' improvement with AI vs. without AI assistance is described. The device is a "computerized cognitive assessment aid," meaning it provides data, but does not inherently involve human "readers" interpreting images (as would be common in diagnostic imaging MRMC studies). The studies focus on the device's measurement properties and its correlation with other assessment tools.
If a standalone (i.e. algorithm only without human-in-the loop performance) was done:
- Yes, the studies evaluate the Sway Sports+ system (algorithm/software) primarily in a standalone capacity, assessing its internal consistency (reliability), its correlation with established cognitive tests (validity), and its ability to distinguish between concussed and non-concussed states (sensitivity/specificity) based on its output.
- The document states, "While Sway Sports+ is not intended to be used to classify a patient as having a concussion, it may be useful to create criteria based on the device's output to classify a patient as concussion positive or negative, to allow comparison to predicate devices..." and "Sway Sports+ does not create new information through analysis or interpretation, nor does it offer any diagnostic or treatment recommendations. The Sway Sports+ is not intended to be used as a standalone diagnostic device." However, the performance studies themselves are evaluating the device's output directly. The implication is that a human still needs to interpret these outputs in the broader clinical context. The sensitivity/specificity studies show how well the device's output alone, when used to classify, performs.
The type of ground truth used:
- Comparison to predicate devices: ImPACT QT, ImPACT, traditional neurocognitive assessments (Wechsler Adult Memory Scale-IV (WMS-IV), Wechsler Adult Intelligence Scale-IV (WAIS-IV), Delis-Kaplan Executive Function System (D-KEFS), and California Verbal Learning Test – 3rd Edition (CVLT-III)).
- Clinical Diagnosis: Concussion diagnosis confirmed by medical professionals following NCAA Concussion Safety Protocol guidelines.
- Healthy Controls: Participants recruited as "healthy adults" or "healthy controls."
The sample size for the training set:
- Normative Database: Over 126,000 de-identified baseline test data records from users aged 18 to 24 years old were used to establish the normative database. This effectively serves as a large training/reference set for individual score comparison.
- No specific "training set" size for the AI algorithm itself (if applicable, as it's a "computerized cognitive assessment aid" not explicitly framed as deep learning AI) is provided beyond the normative data.
How the ground truth for the training set was established:
- For the normative database (126,000+ users), the ground truth was established by:
  - Self-reported health status: Users "did not report a concussion within the last 6 months, did not report neurological conditions, did not report learning disability."
  - Behavioral criteria: "Completed a baseline test in English, completed a baseline test in the United States of America, primary language was English, had valid scores on all tests."
  - This establishes a "healthy, non-concussed baseline" for reference rather than a diagnostic ground truth.

Summary

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

February 15, 2025

Image /page/0/Picture/1 description: The image shows the logo of the U.S. Food and Drug Administration (FDA). On the left is the Department of Health and 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.

Sway Medical, Inc. % Robert Steurer Consultant Steurer Consulting Group, LLC 800 Blue Quail Rd Keller, Texas 76248

Re: K241737

Trade/Device Name: Sway System Sports Plus Regulation Number: 21 CFR 882.1471 Regulation Name: Computerized Cognitive Assessment Aid For Concussion Regulatory Class: Class II Product Code: POM Dated: January 15, 2025 Received: January 15, 2025

Dear Robert Steurer:

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.

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

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).

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 (QS) 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.

All medical devices, including Class I and unclassified devices and combination product device constituent parts are required to be in compliance with the final Unique Device Identification System rule ("UDI Rule"). The UDI Rule requires, among other things, that a device bear a unique device identifier (UDI) on its label and package (21 CFR 801.20(a)) unless an exception or alternative applies (21 CFR 801.20(b)) and that the dates on the device label be formatted in accordance with 21 CFR 801.18. The UDI Rule (21 CFR 830.300(a) and 830.320(b)) also requires that certain information be submitted to the Global Unique Device Identification Database (GUDID) (21 CFR Part 830 Subpart E). For additional information on these requirements, please see the UDI System webpage at https://www.fda.gov/medical-device-advicecomprehensive-regulatory-assistance/unique-device-identification-system-udi-system.

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 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-regulatory

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

assistance/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,

Jay R. Gupta -S

Jay Gupta Assistant Director DHT5A: Division of Neurosurgical, Neurointerventional, and Neurodiagnostic Devices OHT5: Office of Neurological and Physical Medicine Devices Office of Product Evaluation and Quality Center for Devices and Radiological Health

Enclosure

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

Indications for Use

510(k) Number (if known)

Device Name Sway System Sports Plus

Indications for Use (Describe)

The Sway System Sports Plus is intended for use as a computerized cognitive assessment and management of concussion in individuals ages 18-24.

The Sway System Sports Plus is indicated for use when there is a suspected concussion or head injury.

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."

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

Date Prepared:	February 12, 2025
Submitter:	Sway Medical, Inc.32 S. Lewis Ave.Tulsa, OK 74101
Submitter Contact:	Sway Medical, Inc.32 S. Lewis Ave.Tulsa, OK 74101Name: Alex PettigrewSway Medical IncPhone: (281) 726-3820Email: alex.pettigrew@swaymedical.com
ApplicationCorrespondent:	Robert SteurerPrincipal ConsultantSteurer Consulting Group800 Blue Quail Rd.Keller, TX 76248steurerbob@gmail.com+1 (425) 358-1072
ManufacturingSite:	Sway Medical, Inc.32 S. Lewis Ave.Tulsa, OK 74101
Trade Name:	Sway Sports+
Common Name:	Neurological Diagnostic Device
ClassificationName:Device Class:	Computerized Cognitive Assessment Aid for ConcussionClass II
PrimaryClassificationRegulation:	21 CFR §882.1471

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

Primary Product Code:

POM

Predicate Device: Impact Applications, Inc. ImPACT Quick Test, K170551

Reference

Predicate Device: Impact Version 4, K202485

SubstantiallyEquivalentDevices:	New Device	PredicateDevice	Reference PredicateDevice
	Sway Sports Plus (Sports+)Sway Medical, Inc.	ImPACT Quick TestK170551Impact Applications, Inc.	ImPACT Version 4K202485ImPACT Applications, Inc.

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

Sway Sports Plus (referred to as Sway Sports+) is a licensed variant of the Device Sway System and is a software solution (SaMD) that provides a computerized Description: cognitive assessment aid for concussion. This prescription device uses an individual's score(s) on a batterv of cognitive tasks to provide an indication of the current level of cognitive function in response to a suspected concussion. The computerized cognitive assessment aid for concussion is used only as an assessment aid in the management of concussion to determine cognitive function for patients after a potential concussive event where other diagnostic tools are available and does not identify the presence or absence of concussion. The examiner may have the patient complete the Sway Balance test to provide an additional indicator in their assessment of concussion. The Sway System is not intended as a stand-alone diagnostic device. After the patient completes the Sway Sports+ test(s), the examiner can view the summary statistics for each test such as mean reaction time (speed).

Sway Sports+ does not create new information through analysis or interpretation, nor does it offer any diagnostic or treatment recommendations. The Sway Sports+ is not intended to be used as a standalone diagnostic device.

Sway Sports+ operates in the Apple iOS or Android operating systems, enabling it to be used on the hardware of Apple iPhone. iPad, and iPod Touch. or Android mobile devices. The internal accelerometer is accessed to analyze motion of the device in response to stimuli during testing. The mobile device hardware is not provided by Sway Medical.

Environments where Sway Sports+ may be used may include both clinical and non-clinical settings. Clinical settings may include physician offices, hospitals, physical or occupational therapy clinics, skilled nursing facilities, assisted living centers and other healthcare facilities where cognitive tests may be evaluated. In addition, non-clinical environments may include sports team's locations where the application may be used on the sideline to perform a cognitive assessment, e.g., fitness centers, gymnasiums, or stadiums. It is recommended that the tests be taken in a supervised environment for baseline and post-injury testing.

Sway Sports+ consists of the Sway Balance (K121590) and the Sway Computerized Cognitive Assessment Aid. The Sway Computerized Cognitive Assessment Aid (PTY) is exempt from 510(k).

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

Intended Use:	The Sway System Sports Plus is intended for use as a computerized cognitive assessment test to aid in the assessment and management of concussion in individuals ages 18-24. The Sway System Sports Plus is indicated for use when there is a suspected concussion or head injury
Summary of Substantial Equivalence:	The Intended Use of Sway Sports+ is the same as the predicate device, ImPACT QT, and the reference predicate device, ImPACT. The patient age range for Sway Sports+ is contained within that of the predicate and reference devices. Sway Sports+ and the predicate device function on mobile devices incorporating Apple iOS; Sway Sports+ also functions on Android OS devices.Sway Sports+, the predicate device, and the reference device all enable the administration of neuropsychological tests to evaluate a test taker's cognitive state. All devices are similar in terms of technological characteristics, as they administer neurocognitive test modules using standard off-the-shelf computing devices and record objective cognitive performance measurements as the test taker responds to stimuli presented on the screen. Sway Sports+ also includes balance assessments; balance has been documented in the scientific literature as a potential indicator of the effects of concussion.Sway Sports+ differs from the predicate and reference devices in the content and design of the cognitive tasks. However, both Sway Sports+ and the predicate device provide the same reporting on the mobile application, on a web portal, and in .pdf format. The reference device also has reporting available on a web portal and in .pdf format. Both summary and raw data are available as an export for all devices.Sway Sports+ uses internal accelerometer and gyroscope data from mobile devices as well as touch input to record patient responses. The predicate device relies solely on touch input, and the reference device uses input from computer peripherals. This is not a significant difference, as all devices include a response signal to the underlying operating system as part of their algorithms.
Technology Comparison:	The Sway Sports+ employs the same technological characteristics as the predicate device and the reference device.

Intended Use:

The Sway System Sports Plus is intended for use as a computerized cognitive assessment test to aid in the assessment and management of concussion in individuals ages 18-24. The Sway System Sports Plus is indicated for use when there is a suspected concussion or head injury

Summary of Substantial Equivalence:

The Intended Use of Sway Sports+ is the same as the predicate device, ImPACT QT, and the reference predicate device, ImPACT. The patient age range for Sway Sports+ is contained within that of the predicate and reference devices. Sway Sports+ and the predicate device function on mobile devices incorporating Apple iOS; Sway Sports+ also functions on Android OS devices.Sway Sports+, the predicate device, and the reference device all enable the administration of neuropsychological tests to evaluate a test taker's cognitive state. All devices are similar in terms of technological characteristics, as they administer neurocognitive test modules using standard off-the-shelf computing devices and record objective cognitive performance measurements as the test taker responds to stimuli presented on the screen. Sway Sports+ also includes balance assessments; balance has been documented in the scientific literature as a potential indicator of the effects of concussion.Sway Sports+ differs from the predicate and reference devices in the content and design of the cognitive tasks. However, both Sway Sports+ and the predicate device provide the same reporting on the mobile application, on a web portal, and in .pdf format. The reference device also has reporting available on a web portal and in .pdf format. Both summary and raw data are available as an export for all devices.Sway Sports+ uses internal accelerometer and gyroscope data from mobile devices as well as touch input to record patient responses. The predicate device relies solely on touch input, and the reference device uses input from computer peripherals. This is not a significant difference, as all devices include a response signal to the underlying operating system as part of their algorithms.

Technology Comparison:

The Sway Sports+ employs the same technological characteristics as the predicate device and the reference device.

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

Table 1 - Substantial Equivalence Comparison
Characteristic	Sway Sports Plus(Sports+)	Predicate DeviceImPACT Quick Test(K170551)	Reference DeviceImPACT Version 4(K202485)
Operating System	Apple iOS and Androidmobile devices	Apple iOS mobiledevices	Desktop/laptopcomputers
Use Cases	Measures change overtime	Same	Same
Patient Population	18-24 years old	12-70 years old	12-80 years old
How Provided	Software only	Same	Same
Reporting Features	Report viewable on theSway Mobile Applicationand on the Sway WebPortal and in .pdfformat. Summary andRaw Data is available ascsv export from the webportal data.	Report viewable in PDFformat. Summary andRaw Data available incsv, xml, and html fileformats.	Same
Technology	Stand-alone softwareapplication	Same	Same
Stimulus Presentation	Mobile device screen	Same	Desktop or laptop screen
Stimulus Capture(test taker response)	User input (motionresponse) via mobiledevice motion sensorsand via touch screen	User input (finger touch)via mobile device touchscreen	User input via computerperipherals.
Cognitive TasksAdministered	Test battery consisting ofmultiple test modules:-Module 1: ReactionTime-Module 2: ImpulseControl-Module 3: InspectionTime-Module 4: Memory Test,including three letterdelayed recall andworking memory	Test battery consisting ofmultiple test modules:-Module 1: SymbolMatch-Module 2: Three lettermemory and reversenumber counting-Module 3: AttentionTracker	Test battery consistingof multiple test modules:-Module 1: WordMemory and DelayedMemory Recognition-Module 2: DesignMemory and DelayedDesign Recognition-Module 3: X's and O's-Module 4: SymbolMatching-Module 5: Color MatchModule 6: Three LetterMemory
Additional Tests/Input	Balance Test; SymptomTracker; PatientDemographics	Symptom Tracker;Patient Demographics	Same as predicatedevice
Results Interpretation	The Sway System doesnot provide arecommendation thatthe patient is impairedvs. unimpaired. Clinicalinterpretation of theresults includes anormative database forClinical comparison.	Same	Same
PsychometricProperties	Demonstrates constructvalidity with traditionalneuropsychological testand test-retest reliability	Same	Same
Standards Used	ISO 14971IEC 62304IEC 62366	ISO 14971IEC 62304	Same
Key Clinical Outcomes	Validity: r values rangefrom 0.22 to 0.42 whencompared to traditionalneuropsychologicaltesting; similar small tomoderate correlationswhen compared to thepredicate device.Reliability: ICC valuesrange from 0.68 to 0.92for one-week test-retests intervals	Validity: r values rangefrom 0.28 to 0.61 whencompared to traditionalneuropsychologicaltesting.Reliability: r valuesrange from 0.18 to 0.83	Validity: r values rangefrom 0.37 to 0.70 whencompared to traditionalneuropsychologicaltesting.Reliability: ICC valuesrange from 0.50 to 0.88for test-retest intervalsless than 30 days

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

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

Sterilization andShelf-life	Sway Sports+ is a software product. Sway Sports+ does not have a shelf-life. Therefore, this section is not applicable.
Biocompatibility	Sway Sports+ is a software product and does not directly nor indirectly contactthe patient. Therefore, this section is not applicable.
Software Testing	Sway Sports+ was designed and developed according to Sway Medical, Inc.'s,internal software development process in accordance with IEC 62304. SwaySports+ was tested using verification and validation methods, the results ofwhich indicate the Sway Sports+ complies with its specifications.
Electrical Safety	Sway Sports+ is a software product. Therefore, this section is not applicable.
ElectromagneticCompatibility Testing	Sway Sports+ is a software product. Therefore, this section is not applicable.

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

Sway Sports+ was developed and validated in accordance with IEC 62304, Medical Performance Devices – Software Life Cycle and the FDA Guidance documents "General Principles Testing — Bench of Software Validation" and "Applying Human Factors and Usability Engineering to Optimize Medical Device Design" that are appropriate for software development. Software verification and validation activities, including design phase reviews, risk management, traceability and software testing for performance, were all executed to demonstrate compliance with predetermined specifications.

Non-Clinical A summary of the Non-Clinical Performance Bench Testing is included in Table 2.

Table 2 - Summary of Non-Clinical Performance Testing Documents: Software Testing as part of Verification and Validation; Documents: Test PRJ-2303-02 Verification and Validation Report . Performed PRJ-2211-04 Usability Validation Protocol ● . PRJ-2303-03 Usability Validation Results Device The Sway Sports+ is a software product capable of running on Android v9.0 Description or later and Apple iOS v13 or later. The software was tested on both platforms. The Sway Sports+ was tested per Verification and Validation protocol and Test Method/ criteria to ensure product meets product requirements. The results of the Applicable testing are included in PRJ-22303-02 Verification and Validation Report Standards along with Usability Testing Acceptance The actual (observed) results conform to the specified expected results. Criteria Unexpected Results/ None Significant Deviations Results All tests pass with no exceptions. System meets requirements specifications.

Testing

{12}------------------------------------------------

Performance Testing

– Clinical

This 510(k) submission includes a literature review of studies that demonstrate the validity, reliability, normative data, and clinical use of Sway Sports+. Data was collected to examine test-reliability in healthy controls, test-retest reliability in concussed patients, and the sensitivity & specificity of the product in the concussed population.

While Sway Sports+ is not intended to be used to classify a patient as having a concussion, it may be useful to create criteria based on the device's output to classify a patient as concussion positive or negative, to allow comparison to predicate devices to support a substantial equivalence determination. This information, along with additional data that demonstrate the device's test-reliability, construct validity, and reliability of outputs in patients with concussion, was used to support a determination of substantial equivalence.

Summary of Clinical Testing:

Normative Database

De-identified baseline test data was collected from over 126,000 users aged 18 to 24 years old. Subjects were selected based on the following inclusion criteria: Completed a baseline test in English, completed a baseline test in the United States of America, primary language was English, did not report a concussion within the last 6 months, did not report neurological conditions, did not report learning disability, had valid scores on all tests. Data were stratified across age and gender. Mann-Whitney U statistical tests were used to assess inter- and intra-sex and age differences in Sway balance and cognitive test module scores. Descriptive statistics (mean, standard deviation, median, and interquartile range [10th, 25th, 75th, and 90th]) were calculated for all Sway tests. Statistical significance was set a priori at a p-value of 0.05. Age/gender group samples were required to have a minimal size of 50 profiles to be considered for normative analysis. Results indicate an increase in performance in Sway Sports+ modules with age, with scores peaking in the early to mid-20's. Specific tests also show gender-based normative value differences. Thus, Sway Sports+ is designed to use both age and gender when relating individual scores to normative values.

Validity

VanRavenhorst-Bell et al., 20214: This work demonstrated the construct validity of Sway Sports+ Reaction Time, Impulse Control, and Inspection Time modules compared to ImPACT QT. The sample included 88 healthy adults aged 18 to 48 years (mean 22.09 ± 4.47 years). Participants completed the ImPACT QT battery and Sway Sports+ tests during the same session, and scores from Sway Sports+ were compared to ImPACT QT composite and sub-test scores. The Sway Reaction Time module was statistically significantly correlated (r = -0.46 to 0.22, p ≤ 0.05) with several ImPACT QT reaction time measures. The Sway Impulse Control and Inspection Time measures were also statistically significantly correlated (r = -0.25 to -0.46, p ≤ 0.05) with five ImPACT QT reaction time measures. Overall, these findings suggest that Sway Sports+ cognitive test battery is clinically comparable to the FDA-cleared concussion management system.
Clark & VanRavenhorst-Bell, 2022-: This study investigated the construct validity ●

{13}------------------------------------------------

of Sway Sports+ in comparison to ImPACT and traditional neurocognitive assessments, including the Wechsler Adult Memory Scale-IV (WMS-IV), Wechsler Adult Intelligence Scale-IV (WAIS-IV), Delis-Kaplan Executive Function System (D-KEFS), and California Verbal Learning Test – 3rd Edition (CVLT-III). A total of 85 adults (mean age 23.1 years; 68% female) participated, with all tests administered by trained professionals in one session. Results indicated significant correlations between Sway Sports+ and both ImPACT and traditional tests, with significance at both p < 0.001 and p < 0.05. The correlation strength between traditional tests served as a benchmark for the Sway Sports+ assessments, showing that correlations varied from weak (0.20) to strong (0.56), particularly between the WAIS-IV Cancellation and WMS-IV Symbol Search tests. Notably, Sway Sports+ modules exhibited correlation values ranging from 0.22 to 0.42 with traditional tests, while also aligning with ImPACT measures. The Reaction Time module, characterized by rapid cognitive processing, did not correlate significantly with traditional tests, consistent with their differing formats. Moreover, Sway Sports+ demonstrated stronger correlation strengths with traditional neurocognitive tests compared to the correlations observed between ImPACT and these tests. Findings support the utility of Sway Sports+ for cognitive assessments, highlighting its robust associations with both traditional neurocognitive tests and the ImPACT system.

Table 3 - Validity between Sway Sports+ and ImPACT QT & ImPACT
	SwayReactionTime	SwayImpulseControl	SwayInspectionTime	SwayMemory
ImPACT QTThree Letter Count Correct	0.22	0.17	0.06
ImPACT QTThree Letter Time First Click	-0.08	-0.01	-0.17
ImPACT QTRectangular Average Time	-0.44	-0.46	-0.19
ImPACT QTFigure Eight Average Time	-0.46	-0.36	-0.29	---
ImPACT QTComplex Average Time	-0.32	-0.31	-0.20
ImPACT QTSymbol Match Correct Visible	-0.27	-0.19	0.04
ImPACT QTSymbol Match Correct Hidden	-0.35	-0.06	-0.05
ImPACT QTSymbol Match Incorrect Hidden	-0.32	-0.10	-0.25
ImPACTVisual Motor Composite Scale	$r_s = 0.26$$p = 0.015 *$	$r_s = 0.43$$p < 0.001 *$
IMPACTReaction Time Composite Scale	$r_s = -0.31$$p = 0.005 *$	$r_s = -0.41$$p < 0.001 *$
IMPACTMemory Composite Verbal			---	$r_s = 0.13$$p = 0.251$
IMPACTMemory Composite Visual				$r_s = 0.26$$p = 0.015 *$
IMPACTDesign Memory				$r_s = 0.24$$p = 0.026 *$
IMPACTSymbol Match				$r_s = -0.22$$p = 0.045 *$
IMPACTXO Memory				$r_s = -0.22$$p = 0.046 *$

{14}------------------------------------------------

ImPACTThree Letters		$r_s = 0.22$$p = 0.041$
Table 4 – Validity between Sway and Traditional Neuropsychological Testing
	SwayReaction Time	SwayImpulseControl	SwayMemory
WAIS-IV Coding	$r_s = 0.13$$p = 0.241$	$r_s = 0.02$$p = 0.840$
WAIS-IV Symbol Search	$r_s = 0.07$$p = 0.504$	$r_s = 0.22$$p = 0.043 *$
WAIS-IV Cancellation	$r_s = 0.10$$p = 0.381$	$r_s = 0.08$$p = 0.501$	---
D-KEFS, Trail Making Condition 1	$r_s = 0.09$$p = 0.437$	$r_s = 0.42$$p < 0.001 *$
D-KEFS, Trail Making Condition 2	$r_s = 0.06$$p = 0.437$	$r_s = 0.20$$p = 0.064$
D-KEFS, Trail Making Condition 3	$r_s = 0.15$$p = 0.170$	$r_s = 0.33$$p = 0.003 *$
WMS-IV Symbol Span			$r_s = 0.00$$p = 0.995$
WAIS-IV Digit Span			$r_s = -0.07$$p = 0.542$
WAIS-IV Letter-Number Sequencing	---	---	$r_s = 0.00$$p = 0.958$
CVLT-III Short Delayed Free Recall			$r_s = 0.07$$p = 0.551$
CVLT-III Short Delayed Cued Recall			$r_s = 0.20$$p = 0.070$

Reliability

Van Patten et al., 20213: This work demonstrated both the inter- and intra-. session reliability of Sway Sports+ Reaction Time, Impulse Control, Inspection Time, and Memory modules. Participants were assessed remotely over 3 subsequent weeks. The mean age of the sample was 26.69 years (± 9.89; range = 18-58). Of the 55 adults in the sample, 69% were women and 89% used an iPhone. ANOVA results indicated non-significant differences in scores across all three weeks for all measures. ICC values for weeks 1-2 ranged from 0.60 to 0.8, and ICC values for weeks 1-3 ranged from 0.68 to 0.88, indicating adequate or better test-retest reliability for all tested measures. The authors also established reliable change estimates for the included Sway Sports+ modules.
Caccese et al., 20224: This work demonstrated inter- and intra-session reliability . for Sway Sports+ Balance module using the same sample and test procedure as Van Patten et al., 2021. Participants were assessed remotely over 3 subsequent weeks. The sample included 55 healthy adults (69% women) with a mean age of 26.69 years (SD = 9.89; range = 18-58). The ICC for Weeks 1 & 2 was 0.82, and the ICC for Weeks 1 & 3 was 0.88. ANOVA demonstrated no significant differences between test dates, demonstrating strong reliability between test and retest sessions. The authors also established reliable change estimates for the Sway Sports+ Balance module.
An additional study was undertaken that evaluated the test-retest reliability of ● the Sway Sports+ battery in a sample of healthy adults aged 18-35. This

{15}------------------------------------------------

research included detailed method agreement analyses and established reliable change estimates relevant to the clinical interpretation of test score fluctuations. A total of 97 participants were initially recruited, with 56 completing all test and retest sessions, with a one-week interval. Converging evidence from paired sample comparisons, intraclass correlation coefficients (ICCs), Bland-Altman plots, and Deming regression analyses indicate no statistically significant differences in scores between test and retest sessions for any Sway Sports+ module. ICC values ranged between 0.82 and 0.92. This research demonstrates the reliability of the Sway Sports+ test battery and offers critical insights into the interpretation of score changes associated with external events, thus reinforcing the clinical utility of Sway Sports+ in assessing cognitive and functional performance.

An additional study was undertaken that investigated the test-retest reliability of the Sway Sports+ test battery among concussed individuals, building on prior research that established reliability in healthy adults. Given the challenges in conducting an exact replication of baseline assessments due to variability in postconcussion recovery trajectories, a within-session design was employed. Participants completed multiple trials across different test modules during both baseline and post-concussion assessment sessions. The findings revealed that the Sway Sports+ battery maintains a robust level of reliability during postconcussion testing, comparable to that observed in baseline evaluations. This study utilized a dataset derived from NCAA member schools, ensuring that clinical standards for concussion diagnosis were strictly followed according to NCAA Concussion Safety Protocol guidelines. The results support the application of the Sway Sports+ system as a reliable tool for concussion assessment, contributing to enhanced understanding and management of concussion outcomes in sports.

Table 5 - Test-Retest Reliability of the Sway Sports+ Test Battery
	ICC – 1 week interval	ICC – 1 week interval
	(published, Van Patten et al., 2021 &Caccese et al., 2022)	(510(k) submission studies)
Sway Reaction Time	0.83	0.88
Sway Impulse Control	0.68	0.88
Sway Inspection Time	0.75	0.82
Sway Memory	0.88	0.83
Sway Balance	0.82	0.92

Sensitivity & Specificity

Chikar & Curtiss, 20235: This study evaluated the effectiveness of Sway Sports+ . in classifying individuals with sports-related concussions, demonstrating comparable performance to the ImPACT tool. Presented at the Big Sky Sports Medicine Conference in Big Sky, MT (Jan 29 - Feb 2, 2023), the research utilized data from athletic organizations that conducted both ImPACT and Sway assessments on athletes with confirmed concussions between November 2020 and October 2022. Participants included 46 athletes (mean age 19.6, SD=1.4; 59% male) who completed pre-season baseline and post-injury testing with both tools. The mean interval between injury and post-injury Sway testing was 1.1

{16}------------------------------------------------

days (SD=1.4). While not all schools provided exact timings for ImPACT postinjury tests, they were administered within a week post-injury. Results indicated that Sway testing achieved a sensitivity of 69.6% (32/46) for predicting concussion group membership, outperforming ImPACT, which showed a sensitivity of 58.7% (27/46) at an 80% confidence interval. A McNemar's test revealed no significant difference between these sensitivities (p=0.383). Notably, the sensitivity and specificity of Sway Sports+ tests are strong overall, although they diminish when analyzing individual modules. This research emphasizes the necessity for multi-modal assessments in concussion evaluation and treatment, consistent with the Sway Sports+ test battery.

An additional study was undertaken that evaluated the effectiveness of the Sway Sports+ test battery in distinguishing between concussed and nonconcussed individuals. The sensitivity and specificity of the Sway Sports+ system were assessed based on score changes from initial baseline to subsequent evaluations. Results indicate high sensitivity but moderate specificity, with high negative predictive values (NPVs) and low positive predictive values (PPVs). While the Sway Sports+ system is effective in detecting concussion effects, the moderate specificity suggests a tendency to over-identify concussed individuals, leading to potential false positives. Nevertheless, in a clinical context where Sway is utilized as part of a comprehensive evaluation by healthcare professionals, such false positives can be eliminated. Importantly, the system demonstrates a very low rate of false negatives, thereby mitigating the risk of untreated concussion cases. The findings underscore the utility of Sway Sports+ in concussion management protocols while highlighting areas for further refinement in specificity.
. An additional pilot study was conducted to compare the effectiveness of ImPACT and Sway in the evaluation and management of sports-related concussions in student-athletes. The research involved 24 high school and college-aged participants who underwent baseline and post-injury testing with both tools. This study documented 47 synchronous testing sessions postconcussion (i.e., ImPACT and Sway testing on the same day) and reported concordance rates of 59.6% between the two tools, with discordance rates of 40.4%. Concordance was seen in both flagged and non-flagged scores. ImPACT identified more abnormal results, suggesting greater sensitivity, while SWAY provided critical measures that were missing in ImPACT. On average, recovery to baseline scores occurred in 12.7 days with ImPACT and 9.9 days with SWAY. While the findings support the complementary use of both tools, the limitations include a small sample size and differences in the functional domains assessed. This study underscores the importance of combining objective digital tools to enhance concussion evaluation and management in clinical and athletic settings.

Conclusion: Sway Sports+ falls within the type of device regulated under 21 CFR §882.1471, Computerized Cognitive Assessment Aid for Concussion (product code POM). The differences between Sway Sports+, the predicate device ImPACT QT, and the reference device ImPACT, described above, do not affect the safety or effectiveness of Sway Sports+ for its intended use. The safety and effectiveness of Sway Sports+ have been demonstrated through software verification and validation, non-clinical assessments, and clinical performance testing. Therefore, Sway Sports+ is substantially equivalent to the predicate device.

{17}------------------------------------------------

References:

1. Vanravenhorst-Bell, H. A., Muzeau, M. A., Luinstra, L., Goering, J. & Amick, R. Z. Accuracy of the SWAY Mobile Cognitive Assessment Application. Int J Sports Phys Ther 16, 991 (2021).
1. Clark, C. B. & Vanravenhorst-Bell, H. A. Construct Validity of Sway Mobile Application Cognitive Testing. (2022).
1. Van Patten, R., Iverson, G. L., Muzeau, M. A. & VanRavenhorst-Bell, H. A. Test-Retisbility and Reliable Change Estimates for Four Mobile Cognitive Tests Administered Virtually in Community-Dwelling Adults. Front Psychol 12, (2021).
1. Caccese, J. B. et al. Test-Retest reliability and preliminary reliable change estimates for Sway Balance tests administered remotely in community-dwelling adults. Front Digit Health 4, 217 (2022).
ഗ് Chikar, J. & Curtiss, C. The Use of the Sway Medical Mobile Application in Concussion Management. in Big Sky Athletic Training & Sports Medicine Conference (2023).

Regulation Number and Section

§ 882.1471 Computerized cognitive assessment aid for concussion.

(a)
Identification. The computerized cognitive assessment aid for concussion is a prescription device that uses an individual's score(s) on a battery of cognitive tasks to provide an indication of the current level of cognitive function in response to concussion. The computerized cognitive assessment aid for concussion is used only as an assessment aid in the management of concussion to determine cognitive function for patients after a potential concussive event where other diagnostic tools are available and does not identify the presence or absence of concussion. It is not intended as a stand-alone diagnostic device.(b)
Classification. Class II (special controls). The special controls for this device are:(1) Software, including any proprietary algorithm(s) used by the device to arrive at its interpretation of the patient's cognitive function, must be described in detail in the software requirements specification (SRS) and software design specification (SDS). Software verification, validation, and hazard analysis must be performed.
(2) Clinical performance data must be provided that demonstrates how the device functions as an interpretation of the current level of cognitive function in an individual that has recently received an injury that causes concern about a possible concussion. The testing must:
(i) Evaluate device output and clinical interpretation.
(ii) Evaluate device test-retest reliability of the device output.
(iii) Evaluate construct validity of the device cognitive assessments.
(iv) Describe the construction of the normative database, which includes the following:
(A) How the clinical workup was completed to establish a “normal” population, including the establishment of inclusion and exclusion criteria.
(B) Statistical methods and model assumptions used.
(3) The labeling must include:
(i) A summary of any clinical testing conducted to demonstrate how the device functions as an interpretation of the current level of cognitive function in a patient that has recently received an injury that causes concern about a possible concussion. The summary of testing must include the following:
(A) Device output and clinical interpretation.
(B) Device test-retest reliability of the device output.
(C) Construct validity of the device cognitive assessments.
(D) A description of the normative database, which includes the following:
(
1 ) How the clinical workup was completed to establish a “normal” population, including the establishment of inclusion and exclusion criteria.(
2 ) How normal values will be reported to the user.(
3 ) Representative screen shots and reports that will be generated to provide the user results and normative data.(
4 ) Statistical methods and model assumptions used.(
5 ) Whether or not the normative database was adjusted due to differences in age and gender.(ii) A warning that the device should only be used by health care professionals who are trained in concussion management.
(iii) A warning that the device does not identify the presence or absence of concussion or other clinical diagnoses.
(iv) A warning that the device is not a stand-alone diagnostic.
(v) Any instructions technicians must convey to patients regarding the administration of the test and collection of cognitive test data.