NeuroRPM

K221772 · New Touch Digital, Inc. · GYD · Mar 17, 2023 · Neurology

Device Facts

• Record ID: K221772
• Device Name: NeuroRPM
• Applicant: New Touch Digital, Inc.
• Product Code: GYD · Neurology
• Decision Date: Mar 17, 2023
• Decision: SESE
• Submission Type: Traditional
• Regulation: 21 CFR 882.1950
• Device Class: Class 2
• Attributes: AI/ML, Software as a Medical Device

Intended Use

NeuroRPM is intended to quantify movement disorder symptoms during wake periods in adult patients 46 to 85 years of age with Parkinson's disease. These symptoms include tremor, bradykinesia, and dyskinesia. NeuroRPM is intended for clinic and home environments.

Device Story

NeuroRPM is a software application for Apple Watch; collects accelerometer and gyroscope data from wrist-worn device. Motion data transmitted to cloud servers; analyzed via machine learning models to generate binary symptom classifications every 15 minutes. Outputs include tremor, bradykinesia, and dyskinesia status. Used in clinic and home environments; prescribed by health professionals. Healthcare providers review PDF reports containing daily graphs and summary statistics to assess motor symptoms. Device aids clinical decision-making by quantifying symptom presence/absence, potentially benefiting patient management of Parkinson's disease.

Clinical Evidence

Observational, non-intervention study (n=36) of Parkinson's patients. Ground truth established by expert rater panel (3 movement disorder specialists) using UPDRS and AIMS scales. Primary endpoints: sensitivity and specificity. Results: Tremor (Sens: 0.7176, Spec: 0.9508), Bradykinesia (Sens: 0.7143, Spec: 0.7740), Dyskinesia (Sens: 0.7123, Spec: 0.9466). 95% CIs calculated via cluster bootstrap. Bench testing verified motion data consistency.

Technological Characteristics

Software application for Apple Watch (triaxial inertial measurement unit). Data transmission to cloud server. Analysis via machine learning models. Outputs: binary symptom classification (tremor, bradykinesia, dyskinesia) every 15 minutes. PDF report generation.

Indications for Use

Indicated for adult patients 46 to 85 years of age with Parkinson's disease to quantify movement disorder symptoms (tremor, bradykinesia, dyskinesia) during wake periods in clinic and home settings.

Regulatory Classification

Identification

A tremor transducer is a device used to measure the degree of tremor caused by certain diseases.

Predicate Devices

• Personal Kinetigraph (PKG) System Model GKC-2000 (K161717)

Submission Summary (Full Text)

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

Image /page/0/Picture/0 description: The image shows the logo of the U.S. Food & Drug Administration (FDA). The logo consists of two parts: the Department of Health & Human Services logo on the left and the FDA logo on the right. The FDA logo is a blue square with the letters "FDA" in white, followed by the words "U.S. FOOD & DRUG ADMINISTRATION" in blue.

March 17, 2023

New Touch Digital Inc. Chan Lee Chief Operating Officer 3124 Dumbarton Street NW Washington, District of Columbia 20007

Re: K221772

Trade/Device Name: NeuroRPM Regulation Number: 21 CFR 882.1950 Regulation Name: Tremor Transducer Regulatory Class: Class II Product Code: GYD, ISD Dated: February 15, 2023 Received: February 15, 2023

Dear Chan Lee:

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

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

statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting of medical device-related adverse events) (21 CFR 803) for devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.

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

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

Sincerely,

# Patrick Antkowiak -S

for

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

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

# Indications for Use

510(k) Number (if known) K221772

Device Name NeuroRPM

Indications for Use (Describe)

NeuroRPM is intended to quantify movement disorder symptoms during wake periods in adult patients 46 to 85 years of age with Parkinson's disease. These symptoms include tremor, bradykinesia. NeuroRPM is intended for clinic and home environments.

| Type of Use (Select one or both, as applicable) | |
|---------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------|
| <div> <span> Prescription Use (Part 21 CFR 801 Subpart D) </span> </div> | <div> <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}------------------------------------------------

# K221772 Traditional 510(k) SUMMARY New Touch Digital Inc.'s NeuroRPM

#### Submitter:

New Touch Digital Inc. 3124 Dumbarton Street NW Washington, DC 20007

Contact Person: Chan Lee Phone: [phone] Email: [e-mail]

March 17, 2023 Date Prepared: Name of Device: NeuroRPM K221772 Common or Usual Name: NeuroRPM Classification Name: Tremor Transducer 21 CFR 882.1950 Regulatory Class: Class II Primary Product Code: GYD Secondary Product Code: ISD

## Predicate Device:

| Manufacturer: | GKC Manufacturing Pty Ltd. |
|--------------------|--------------------------------------------------|
| Trade/Device Name: | Personal Kinetigraph (PKG) System Model GKC-2000 |
| 510(K) Number: | K161717 |
| Decision Date: | September 20, 2016 |

### Device Description:

NeuroRPM is a software application for the Apple Watch that is prescribed by a health professional to quantify motor symptoms of Parkinson's disease including bradykinesia, dyskinesia, and tremor. NeuroRPM collects accelerometer and gyroscope data from the Apple Watch. The motion data are transmitted to cloud servers and analyzed using machine learning models developed to generate binary symptom classifications. Binary symptom classification output is generated every 15-minutes. A description of the NeuroRPM outputs is provided in Table 1.

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

### K221772

| Symptom | Output Classification | Output Description | Validated Scale |
|--------------|---------------------------|-------------------------------------------------------------|-------------------------------------------------|
| Tremor | NTD-TR A - No Tremor | No tremor detected. | UPDRS-III TR Score of 0 |
| | NTD-TR B - Tremor | Tremor detected. | UPDRS-III TR Score of 1 and<br>greater |
| Bradykinesia | NTD-BK A - Normal to Low | No, minor or mild bradykinesia<br>detected. | Combined UPDRS-III<br>BK Score of 0, 1, 2, 3 |
| | NTD-BK B - Medium to High | Moderate or greater than<br>moderate bradykinesia detected. | Combined UPDRS-III<br>BK Score of 4 and greater |
| Dyskinesia | NTD-DK A - No Dyskinesia | No dyskinesia detected. | Total AIMS Score of 0, 1 |
| | NTD-DK B - Dyskinesia | Dyskinesia detected. | Total AIMS Score of 2 and<br>greater |

## Table 1 - Description of NeuroRPM Outputs

### Intended Use:

NeuroRPM is intended to quantify movement disorder symptoms during wake periods in adult patients 46 to 85 years of age with Parkinson's disease. These symptoms include tremor, bradykinesia, and dyskinesia. NeuroRPM is intended for clinic and home environments.

### Summary of Technological Characteristics:

The proposed device and the predicate device have similar technological characteristics. Both devices obtain a patient's movement data from a wrist-worn device. Sensor data from both the proposed and predicate wrist-worn devices are transferred to a cloud server and analyzed using algorithms to quantify the movement disorder symptoms. The predicate algorithm uses equations and thresholds, while the proposed algorithm was developed using machine learning. Although the algorithms are different, both devices provide similar quantification of the presence or absence of motor symptoms. In addition, the outputs of both devices indicate the presence of movement disorder symptoms (i.e., bradykinesia, tremor, and dyskinesia) in adult patients diagnosed with Parkinson's disease. The predicate device provides symptom scores every 2 minutes in median and percentiles which are compared to a control group with subjects with no Parkinson's disease. In comparison, NeuroRPM directly outputs the presence of 3 symptom types according to Table 1, without comparison to a control group. Although the output scales and references differ, NeuroRPM outputs were validated in a clinical trial, demonstrating that the device performance is adequate to support the intended use of quantifying movement disorder symptoms. Thus, these differences in technological characteristics do not raise different questions of safety and effectiveness.

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

#### K221772

#### Performance Bench Testing:

Bench testing was conducted to verify that the motion data from the Apple Watch reflected the subject's activities within the expected signal patterns and range of values, and that there were no outliers. Raw motion data from test subjects wearing Apple Watch were collected during UPDRS and AIMS evaluation and analyzed in time and frequency domains. The test results demonstrated that the motion data for all subjects were consistent and reliable.

#### Performance Clinical Testing:

An observational, non-intervention study in 36 subjects was conducted to evaluate NeuroRPM's ability to quantify Parkinson's symptom presence or absence. The primary endpoints for demonstrating the performance of the NeuroRPM outputs were sensitivity and specificity. Subjects who were previously diagnosed with Parkinson's disease were enrolled in the study. Scores for each subject were obtained clinical scales, the Unified Parkinson Disease Rating Scale (UPDRS) and the Abnormal Involuntary Movement Scale (AIMS). The ground truth for each sample was derived based on the majority score of an expert rater panel of 3 board-certified movement disorder specialists.

The summary of subject demographics is provided below and is from a single site with 95.5% Caucasian subjects.

| Demographics | Min | Mean | Max |
|----------------------------------|------|------|------|
| Age | 46 | 67.7 | 85 |
| Approx. Age at Diagnosis | 35.1 | 59.8 | 81.3 |
| Years Since Diagnosis | 0.3 | 7.9 | 19 |
| Average Total UPDRS-III<br>Score | 3.4 | 11.1 | 26.7 |
| Number of Males | - | 18 | - |
| Number of Females | - | 18 | - |

Table 2 - Summary of Subject Demographics

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

Image /page/6/Figure/0 description: The image shows the alphanumeric string "K221772" in a bold, sans-serif font. The characters are arranged horizontally, with the letter "K" followed by the numbers "221772". The text is black against a white background, creating a high contrast and making it easily readable. The overall impression is clean and straightforward.

Image /page/6/Figure/1 description: This bar graph shows the number of subjects at each Hoehn and Yahr Stage. The x-axis shows the Hoehn and Yahr Stage from 0 to 5, and the y-axis shows the number of subjects from 0 to 10. The graph shows that the most subjects are at stage 1.5, with 10 subjects.

Figure 1 - Histogram of Hoehn and Yahr Stages (n=36)

The validation study was not specifically tested in the home environment; however, additional supportive data from the clinic, where subjects performed common at-home tasks and observed naturalistic behaviors, were provided to demonstrate the potential for similar performance in the home environment.

Clinical performance testing demonstrated that NeuroRPM is substantially equivalent to the predicate device. 95% confidence intervals were estimated based on the subject cluster bootstrap method.

| NeuroRPM Output | Sensitivity [95% CI] | Specificity [95% CI] |
|-----------------|-------------------------|-------------------------|
| Tremor | 0.7176 [0.6081, 0.8172] | 0.9508 [0.9119, 0.9802] |
| Bradykinesia | 0.7143 [0.5894, 0.8332] | 0.7740 [0.6787, 0.8597] |
| Dyskinesia | 0.7123 [0.5323, 0.8652] | 0.9466 [0.9069, 0.9741] |

Table 3 - NeuroRPM Output Sensitivity and Specificity of the event with 95% Confidence Intervals

Sample size n = 36

The analysis is based on events instead of subjects. There are a total of 36 subjects who may have all the 3 types of events. The total number of events (from truth) for sensitivity evaluation is 170 for Tremor, and 203 for BK and 73 for DK. The number of events (from truth) for specificity evaluation is 325 for Tremor, 292 for BK, and 422 for DK.

### Conclusions:

NeuroRPM is substantially equivalent to GKC's Personal Kinetigraph (PKG) System Model GKC-2000. NeuroRPM has the same intended use, technological characteristics, and principles of operation as the predicate device. The differences in indications for use do not introduce a new intended use. In addition, technological differences between NeuroRPM and the predicate device do not raise different questions of safety or effectiveness.

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

#### K221772

Substantial equivalence comparison of the predicate device and NeuroRPM is provided in Table 2.

| | Predicate Device:<br>GKC PKG System<br>(K161717) | Subject Device:<br>NeuroRPM | Comparison |
|------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Indications for<br>Use | The Personal Kinetigraph<br>(PKG) is intended to quantify<br>kinematics of movement<br>disorder symptoms in<br>conditions such as<br>Parkinson's disease,<br>including tremor,<br>bradykinesia and dyskinesia.<br>It includes a medication<br>reminder, an event marker<br>and is intended to monitor<br>activity associated with<br>movement during sleep. The<br>device is indicated for use in<br>individuals 46 to 83 years of<br>age. | NeuroRPM is intended to<br>quantify movement disorder<br>symptoms during wake<br>periods in adult patients 46<br>to 85 years of age with<br>Parkinson's disease. These<br>symptoms include tremor,<br>bradykinesia, and<br>dyskinesia. NeuroRPM is<br>intended for clinic and<br>home environments. | Same intended use of<br>quantifying movement<br>disorder symptoms. |
| Wearable<br>Device | Proprietary watch with<br>accelerometer. | Apple Watch triaxial inertial<br>measurement unit. | Both use wrist-worn devices<br>to measure movement. |
| Algorithm | Equation with data in<br>frequency domain. | Machine learning model with<br>data in time and frequency<br>domain. | Both algorithms are<br>deterministic and generate<br>classifications. |
| Symptom<br>Measured | Tremor, bradykinesia and<br>dyskinesia. | Tremor, bradykinesia, and<br>dyskinesia. | Same symptom<br>measurements. The subject<br>device produces binary<br>symptom outputs. |
| Outputs | Symptom measurement<br>every 2 minutes in median<br>and percentiles which are<br>compared to a control group<br>with subjects with no<br>Parkison's disease. | Symptom presence or<br>absence levels every 15-<br>minutes. | NeuroRPM provides direct<br>symptom measurement<br>without comparison to a<br>control group. 15-minute<br>intervals provide sufficient<br>characterization of whether a<br>symptom is present. |
| Output Report | PDF report with daily graphs<br>and summary statistics of<br>symptom outputs. | PDF report with daily graphs<br>and summary statistics of<br>symptom outputs. | Same output report formats<br>with similar symptom<br>information and<br>symptom outputs. |

No

Medication

Reminder

Yes

Table 2 - Substantial Equivalence Comparison of Predicate Device and NeuroRPM

visualizations.

Not required for

disorder symptoms.

quantification of movement