The Parky App is intended to quantify kinematics of movement disorder symptoms including tremor and dyskinesia, in adults (45 years of age or older) with mild to moderate Parkinson's disease.

Device Description

Parky App is a symptom tracker mobile app for Parkinson's Disease patients. It collects motion data through Apple Watch continuously and quantifies tremor and dyskinesia episodes based on clinically validated MM4PD algorithm. Tracked symptoms are reported as daily, weekly and monthly. Each report is shared with the prescribing healthcare professional through email. The mobile app has a medication reminder module which the patients can manually enter their medication schedule, receive on-time reminder notifications on Apple Watch and iPhone and can respond to them as "taken" or "not yet taken". Parky also reports daily step counts provided by Apple Services - HealthKit.

AI/ML Overview

Acceptance Criteria and Device Performance Study for Parky App

The Parky App utilizes the MM4PD (Mobile Movement for Parkinson's Disease) algorithm to quantify movement disorder symptoms in adults with mild to moderate Parkinson's disease. The following details outline the acceptance criteria and the study proving the device meets them, based on the provided FDA 510(k) summary.

1. Table of Acceptance Criteria and Reported Device Performance

Acceptance Criteria / Performance Metric	Reported Device Performance
Correlation with clinical evaluations of tremor severity (MDS-UPDRS tremor constancy)	Rank Correlation Coefficient (ρ) = 0.72
Differentiation of dyskinesia presence (from no dyskinesia)	Statistically significant difference (P = 0.027) with Wilcoxon rank sum test between "No DK" and "Chorea" groups
Smartwatch captured symptom changes matching clinician expectations	94% of cases with full patient history (blinded: 87.5% correct classifications by 3 experts)
Likelihood of dyskinesia mapped to expert ratings	P < 0.001 during in-clinic tasks

2. Sample Size and Data Provenance

Test Set Sample Size:
- Tremor Algorithm Test (Hold-out data): n = 43 (patients from the longitudinal patient study)
- Dyskinesia Algorithm Test (Hold-out dataset): n = 57 (from the longitudinal patient study), specifically n = 47 for "No DK" group and n = 10 for "Chorea" group.
- Clinician Evaluation (full patient history): 112 subjects (from the longitudinal patient study)
- Blinded Clinician Classification: 10 sets of profiles (cases)
Data Provenance: The studies were conducted by Powers et al. (2021), a publication referenced multiple times. While the specific country of origin is not explicitly stated in the provided text, the use of "MDS-UPDRS" (Movement Disorder Society-Unified Parkinson's Disease Rating Scale) suggests a globally recognized clinical standard. The studies are described as both retrospective (designing algorithms with existing in-clinic and all-day data) and prospective (longitudinal studies, evaluation of symptom changes in response to treatment).

3. Number of Experts and Qualifications

Number of Experts: 3 expert raters were used for the blinded classification task.
Qualifications of Experts: They are described as "blinded movement disorder specialists." Specific years of experience or board certifications are not provided.

4. Adjudication Method

Blinded Clinician Classification: The method used for the 10 cases evaluated by 3 blind clinicians resulted in "87.5% of classifications were correct." This suggests a consensus or majority vote approach, but the exact adjudication method (e.g., 2+1, 3+1) is not explicitly detailed. It's mentioned that "three misclassifications occurred because raters presumed that an alternate medication had a dominant effect. Six cases were deemed inconclusive and were excluded." This implies a form of expert review and selection of cases for evaluation.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

Yes, a form of MRMC study was done, but not explicitly framed as "AI vs. Human with AI assistance." The study assessed clinician performance with and without full patient history, effectively comparing clinical judgment with the aid of the smartwatch symptom profiles.
Effect Size:
- When clinicians had full patient history and reviewed smartwatch symptom profiles, "symptom changes matched the clinician's expectation of the prescribed medication change in 94% of cases."
- When 3 blinded movement disorder specialists classified symptom profiles (without full patient history, but with medication schedule and MDS-UPDRS tremor/dyskinesia ratings from intake), "87.5% of classifications were correct."
- This indicates that the smartwatch-generated symptom profiles (AI-generated data) significantly aided clinicians in affirming or understanding treatment effects, achieving high agreement rates, even when blinded. The direct "improvement with AI vs. without AI" is not quantified as a direct comparative effectiveness study in the traditional sense of reader performance metrics but rather as the utility of the AI-generated profiles in supporting clinical assessment.

6. Standalone (Algorithm Only) Performance

Yes, standalone performance was done for the core algorithms.
- "MM4PD measurements correlated to clinical evaluations of tremor severity (Rank Correlation Coefficient=0.80) and mapped to expert ratings of dyskinesia presence (P<0.001) during in-clinic tasks." (This refers to the algorithm's direct measurement and correlation).
- "The ability of MM4PD to identify tremors and the likelihood of dyskinesia was tested with the final algorithm in holdout sets."
- Specifically, Fig. 3E (Tremor algorithm test with hold-out data) and Fig. 4E (Dyskinesia algorithm test with hold-out data) demonstrate stand-alone algorithm performance against clinical ground truth.

7. Type of Ground Truth Used

Expert Consensus / Clinical Evaluations:
- MDS-UPDRS ratings: Used for tremor severity correlation.
- Expert ratings of dyskinesia presence: Used for mapping dyskinesia likelihood.
- Clinician's expectations: Used as ground truth for evaluating how well the symptom changes matched expected treatment responses.
- Movement disorder specialists' classifications: Used as ground truth for the blinded classification task.

8. Sample Size for Training Set

The training set sample sizes are implicitly provided through the "MM4PD development and validation" overview (Figure S1) and "Study demographics" (Table S1).

Pilot study (PD patients in-clinic + 1 week live-on): 118 patients
Longitudinal patient study (PD patients long-term live-on): 225 patients
Longitudinal control study (Elderly controls): 171 individuals
This totals 514 individuals participating in the development and validation studies, from which data was used for algorithm design (training) and testing (hold-out sets).

9. How Ground Truth for Training Set was Established

The ground truth for the training set (algorithm design phase) was established through:

In-clinic tasks: Patients performed specific tasks during clinic visits, and their movement was captured by the Apple Watch. These in-clinic observations would have been correlated with simultaneous or contemporaneous clinical assessments like MDS-UPDRS ratings by clinicians.
All-day data: Continuous data collected by the Apple Watch over longer periods, which would have been analyzed and perhaps retrospectively correlated with patient diaries, medication logs, and clinical assessments at follow-up visits.
The MM4PD algorithm was designed to match MDS-UPDRS tremor constancy and its outputs were mapped to expert ratings of dyskinesia. This indicates that clinical scores and expert consensus from neurologists or movement disorder specialists were the primary ground truth for algorithm development.

Summary

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

November 17, 2022

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 & 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 FDA logo is the text "U.S. FOOD & DRUG ADMINISTRATION" in blue.

H2O Therapeutics % Yagmur Selin Gulmus-Kolay CEO, H2O Therapeutics Mustafa Kemal Mah. 2119. Sok. No 3 Bilkent Cankava. Ankara 06510 Turkey

Re: K220820

Trade/Device Name: Parky App Regulation Number: 21 CFR 882.1950 Regulation Name: Tremor Transducer Regulatory Class: Class II Product Code: GYD, NXQ, ISD Dated: October 13, 2022 Received: October 18, 2022

Dear Yagmur Gulmus-Kolay:

We have reviewed your Section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database located at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.

If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.

Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part

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

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 (DICE@fda.hhs.gov) or phone (1-800-638-2041 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) K220820

Device Name Parky App

Indications for Use (Describe)

The Parky App is intended to quantify kinematics of movement disorder symptoms including tremor and dyskinesia, in adults (45 years of age or older) with mild to moderate Parkinson's disease.

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}------------------------------------------------

510(k) Summary

1. Submitter:

H2O Therapeutics Address: Mustafa Kemal Mah. 2119. Sok. No 3 Bilkent, Çankaya, Ankara, 06510 Turkey Contact Person: Ms. Yagmur Selin Gulmus Kolay Phone: +90 312 219 62 19 Email: selin@h2otherapeutics.com Date Prepared: November 15th, 2022

2. Device:

Trade Name: Parky App Common Name: Movement Disorder Monitoring System Classification Name: Tremor Transducer (21 CFR 882.1950) Device Classification: II Product Code(s): GYD, NXQ, ISD

3. Predicate Device

K213519, Rune Labs Kinematics System. The predicate device has not been recalled.

4. Device Description

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

Image /page/4/Picture/0 description: The image shows the logo for h2o therapeutics. The logo is in black and white. The "h2o" is in a bold, sans-serif font, with a small degree symbol above the "o". Below "h2o" is the word "therapeutics" in a smaller, sans-serif font.

Image /page/4/Figure/1 description: This image shows a diagram of a patient using an Apple Watch and iPhone to track symptoms and share them with clinicians. The process starts with the patient downloading an app from the iOS App Store (step 1). The Apple Watch then collects sensor data and quantifies it as symptom information (step 2). The symptom information is periodically pulled from the Apple Watch by the Parky iOS application (step 3), and then sent to the cloud where reports are generated (step 4). Finally, the reports are shared with healthcare professionals (step 5), and the clinicians' decision-making process is supported by the provided reports (step 6).

Fig.1 System Components and Operation Overview

5. Indications for Use

The Parky App is intended to guantify kinematics of movement disorder symptoms including tremor and dyskinesia, in adults (45 years of age or older) with mild to moderate Parkinson's disease.

6. Comparison of Technological Characteristics to The Predicate

The proposed device, Parky App has identical working principle to the predicate, K213519, Rune Labs Kinematics System. Both devices collect movement recordings by the help of Apple Watch motion sensor and quantified Parkinson's Related movement disorders, specifically tremor and dyskinesia. Table 1 below provides a technological comparison of the proposed and predicate devices:

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

Image /page/5/Picture/0 description: The image shows the logo for H2O therapeutics. The logo is in black and white. The "h2o" is in a bold, sans-serif font, and the "therapeutics" is in a smaller, lighter font.

Characteristic	Proposed Device	Predicate, K213519	Comparison
Intended Use	To measure the degree of tremor caused by certain diseases.	To measure the degree of tremor caused by certain diseases.	Identical to the predicate device.
Indications for Use	The Parky App is intended to quantify kinematics of movement disorder symptoms including tremor and dyskinesia, in adults (45 years of age or older) with mild to moderate Parkinson's disease.	The Rune Labs Kinematic System is intended to quantify kinematics of movement disorder symptoms including tremor and dyskinesia, in adults (45 years of age or older) with mild to moderate Parkinson's disease.	Identical to the predicate device.
Rx vs OTC	Rx	Rx	Identical to the predicate device.
Measurement Method	Recording of symptoms via wrist worn watch.	Recording of symptoms via wrist worn watch.	Identical to the predicate device.
Biocompatibility	Apple watch is manufactured from non-skin irritating and non-sensitizing materials.	Apple watch is manufactured from non-skin irritating and non-sensitizing materials.	Identical to the predicate device.
Electrical Safety	Electrical safety was assessed according to IEC 62368-1 (2014), "Audio/video, information and communication technology equipment - Part 1: Safety requirements."	Electrical safety was assessed according to IEC 62368-1 (2014), "Audio/video, information and communication technology equipment - Part 1: Safety requirements."	Identical to the predicate device.
Electromagnetic Compatibility (EMC)	The Apple Watch conforms to EU standards EN 301	The Apple Watch conforms to EU standards EN 301	Identical to the predicate device.
Characteristic	Proposed Device	Predicate, K213519	Comparison
	489-1 (V2.2.20), EN301 489-3 (V2.1.1), EN301 489-17 (V3.2.0),and EN 301 489-52(V1.1.0).	489-1 (V2.2.20), EN301 489-3 (V2.1.1),EN 301 489-17(V3.2.0), and EN 301489-52 (V1.1.0).
Software	Software Validationwas conducted perFDA Guidance"Content of PremarketSubmissions for DeviceSoftware Functions"issued on May 11,2005	Software testingestablished that thesystem meets thesoftware requirementsand user needs for theintended uses.	Identical to thepredicate device.
Cybersecurity	Cybersecurity threatanalysis and mitigationhas been conductedaccording to"Content of PremarketSubmissions forManagement ofCybersecurity inMedical Devices".	Not specified.	We haveconductedextensivecybersecuritytesting andmitigation effortsto ensure thesecurity of ourpatient data.
Outputs andFeatures	The Rune Lab deviceoutputs are thepercentage of the timethat tremor anddyskinesia werelikely to occur.	The Rune Lab deviceoutputs are thepercentage of the timethat tremor anddyskinesia werelikely to occur.	Identical to thepredicate device.
Data Transmission	Cellular or WirelessNetwork	Cellular and WirelessNetwork	Identical to thepredicate device.
Over-the-CounterSoftware	Utilizes Apple'sMM4PD API and AppleWatch's accelerometerto measure andquantify dyskinesia andtremor related toParkinson's Disease	Utilizes Apple'sMM4PD API andApple Watch'saccelerometer tomeasure and quantifydyskinesia and tremor	Identical to thepredicate device.
Characteristic	Proposed Device	Predicate, K213519 related to Parkinson's Disease	Comparison
Performance Data	Device Measurementshighly correlated toclinical evaluations oftremor severity (RankCorrelationCoefficient=0.80) andmapped to expertratings of dyskinesiapresence (P<0.001)during in-clinic tasks.Device capturedsymptom changes inresponse to treatmentthat matched theclinician's expectationsin 94% of evaluatedsubjects.	Rune medical usesthe same API that wasvalidated with thesame performancedata, published byPowers et al 1.	Identical to thepredicate device.

Table 1: Comparison of Parky App to Predicate Device.

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

Image /page/6/Picture/0 description: The image shows the logo for h2o therapeutics. The logo consists of the letters "h2o" in bold black font, with a degree symbol above the "o". Below the "h2o" is the word "therapeutics" in a smaller, lighter font. The logo is simple and modern, with a focus on the company's name.

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

Image /page/7/Picture/0 description: The image shows the logo for H2O Therapeutics. The logo consists of the letters "h2o" in lowercase, with a degree symbol above the "o". Below the "h2o" is the word "therapeutics" in a smaller font size. The text is in a dark gray color.

In summary, Parky App uses the same underlying software (MM4PD) and hardware (Apple Watch) towards its intended use as the predicate device. Software validation and cybersecurity assessment have been conducted to ensure the safe and effective use of the app, and to safequard the collected data. The proposed device is substantially equivalent to the predicate towards its intended use.

The medication reminder, product code NXQ, and the step counter, ISD, are both 510(k) exempt devices and are not subject to 510(k) notification.

7. Safety

7.1. EMC and Electrical Safety

Parky App uses the same generation of apple watch as the predicate device. Apple Watch conforms to the following EMC and Electrical Standards:

1 Powers R, Etezadi-Amoli M, Arnold EM, Kianian S, Mance I, Gibiansky M, Trietsch D, Alvarado AS, Kretlow JD, Herrington TM, Brillman S, Huang N, Lin PT, Pham HA, Ullal AV. Smartwatch inertial sensors continuously monitor real-world motor fluctuations in Parkinson's disease. Sci Transl Med. 2021 Feb 3;13(579):eabd7865. doi: 10.1126/scitranslmed.abd7865. PMID: 33536284.

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

Image /page/8/Picture/0 description: The image shows the logo for "h2o therapeutics". The logo is in black and white. The "h2o" is in a bold, sans-serif font, and the "therapeutics" is in a smaller, lighter font.

Electrical safety was assessed according to IEC 62368-1 (2014), "Audio/video, information and communication technology equipment – Part 1: Safety requirements."
Apple Watch conforms to EU standards EN 301 489-1 (V2.2.20). EN 301 489-3 (V2.1.1). -EN 301 489-17 (V3.2.0), and EN 301 489-52 (V1.1.0).

7.2. Biocompatibility and Sterility

Parky App uses the same generation of Apple Watch as the predicate device. All patient contacting materials are identical to the predicate device. The proposed device is not intended to be used as sterile.

8. Software

8.1. Software Validation and Verification

Software documentation was provided according to the FDA guidance titled: "Content of Premarket Submissions for Device Software Functions", issued on May 11, 2005. The level of concern was moderate as defined in the guidance.

8.2. Cybersecurity

Parky is an internet-connected app. Thus, a Cybersecurity Threat Assessment and Remediation Analysis (CTARA) was conducted, and all risks were mitigated per the FDA guidance titled: "Content of Premarket Submissions for Management of Cybersecurity in Medical Devices" issued on October 18, 2018.

9. Performance Data

9.1. Clinical Testing

A clinical study' with 343 participants with PD, including a longitudinal study of up to 6 months in a 225-subject cohort was conducted to demonstrate the ability of the MM4PD API used in Parky App to continuously track and categorize two common symptoms of Parkinson's disease: Tremor and Dyskinesia. M4PD measurements correlated to clinical evaluations of tremor severity (Rank Correlation Coefficient=0.80) and mapped to expert ratings of dyskinesia presence (P<0.001) during in-clinic tasks. The ability of MM4PD to identify tremors and the likelihood of dyskinesia was tested with the final algorithm in holdout sets. In addition, MM4PD captured symptom changes in response to treatment that matched

2 Powers R, Etezadi-Amoli M, Arnold EM, Kianian S, Mance I, Gibiansky M, Trietsch D, Alvarado AS, Kretlow JD, Herrington TM, Brillman S, Huang N, Lin PT, Pham HA, Ullal AV. Smartwatch inertial sensors continuously monitor real-world motor fluctuations in Parkinson's disease. Sci Transl Med. 2021 Feb 3:13(579):eabd7865. doi: 10.1126/scitranslmed.abd7865. PMID: 33536284.

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

Image /page/9/Picture/0 description: The image shows the logo for H2O Therapeutics. The logo is composed of the letters "h2o" in bold, black font, with a small degree symbol above the "o". Below the "h2o" is the word "therapeutics" in a smaller, lighter gray font. The logo is simple and modern, and the use of the chemical formula for water suggests a focus on hydration or water-based therapies.

the clinician's expectations in 94% for cases of full patient history and 87,5% for cases of blind classification with 3 expert raters. There were no serious adverse events associated with the use of the device.

Table S1 below summarizes the patient demographics across all studies reported by Powers et al., 2021.

	Pilot studyPD patients in-clinic + 1 week live-on	Longitudinal patient studyPD patients long-term live-on	Longitudinal control studyElderly controls
Age [± Standard Dev]	68.1 yrs [±9.0]	71.4 yrs [±8.9]	74.7 yrs [±5.4]
Years with PD [± Standard Dev]	6.5 yrs [±5.6]	10.3 yrs [±6.5]	n/a
Gender	36 Female, 82 Male	69 Female, 156 Male	85 Female, 85 Male, 1 unknown
Most Affected Side	62 Right / 39 Left / 17 unspecified	105 Right / 120 Left	n/a
History of Tremor	-	166/225 Participants	n/a
History of Dyskinesia(History of Chorea)	-	94/225 Participants(66/94 with dyskinesia)	n/a
History of Freezing Gait	-	85/225 Participants	n/a
History of Slow Gait	-	172/225 Participants	n/a
		*self-reported history

Table S1. Study demographics. Patient demographics across all studies

An overview of the study design is provided below in Figure S1. This figure lists the design and validation phases with their respective number of subjects from each group.

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

Image /page/10/Figure/1 description: The image shows the MM4PD development and validation process for tremor and dyskinesia algorithms. The development process includes three stages: design in-clinic tasks, design all-day data, and test with hold-out data. The validation process includes human factors testing with 36 patient surveys, clinical decision support with 112 profiles evaluated by a single clinician, and a blinded matching task with 10 cases evaluated by 3 clinicians. The image also shows the number of patients and controls used in each stage of the development process.

Fig. S1. Overview of data collected for MM4PD development and validation. MM4PD

development of tremor and dyskinesia algorithms used sensor data from both in-clinic tasks and all-day data in Parkinson's patients as well as several elderly, control subjects with no reported Parkinson's disease. Some patients provided in-clinic data with both tremor across different sessions. The algorithm was tested with a hold-out dataset that had all-day data and a single in-clinic visit from a subset of subjects in the longitudinal patient study. MM4PD outputs were further validated in 3 ways: i) a human factors pilot to ensure patients understood the smartwatch symptom profiles, ii) a comprehensive review to determine where smartwatch symptom profiles matched clinician expectations when used alongside a comprehensive patient history, and iii) a blinded matching task by 3 expert raters who classified smartwatch symptom profiles as pre or post-treatment for a given medication change.

As described in Fig S1. above and detailed in Table 1 below, to design and validate MM4PD, 9 study results are presented within the Clinical Trial Report (Powers et al., 2021):

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

Image /page/11/Picture/0 description: The image shows the logo for h2o therapeutics. The logo is in black and consists of the letters "h2o" with a degree symbol above the "o". Below the "h2o" is the word "therapeutics" in a smaller font. The logo is simple and modern.

1a	Tremor algorithm design with in-clinic tasks	1b	Dyskinesia algorithm design with in-clinic tasks
2a	Tremor algorithm design with all-day data	2b	Dyskinesia algorithm design with all-day data
	Design lock for MM4PD Tremor and Dyskinesia Algorithms: minute-by-minute measurements ready to be tested inreal-world continuous use to match MDS-UPDRS tremor constancy
3a	Tremor algorithm test with hold-out data during thelongitudinal patient study	3b	Dyskinesia algorithm test with hold-out dataduring the longitudinal patient study
	Patient symptom profiles generated based on 15 min averages of MM4PD minute-by-minute outputs
4	Human factors testing for symptom profiles throughpatient surveys
5	Evaluation of symptom profiles by a clinician with accessto patient history
6	Evaluation of symptom profiles by 3 blind clinicianswithout access to patient history

Table 1. Description of Design and Validation Studies Out of all 9 study results listed above, 3a and 3b were used to validate the tremor and dyskinesia algorithm performance in hold-out data sets and out-of-clinic settings, respectively. (Please see Fig 3E and 4E). 5 and 6 validate that the patient symptom profiles (generated through 15 minutes averages of MM4PD minute-by-minute outputs for tremor and dyskinesia separately) match clinician expectations based on MDS-UPDRS constants either with or without access to patient history, respectively (Please see Fig 6)

Image /page/11/Figure/3 description: This image is a boxplot showing the relationship between MDS-UPDRS tremor constancy and mean daily tremor percentage. The x-axis represents MDS-UPDRS tremor constancy, ranging from 0 to 4, while the y-axis represents the mean daily tremor percentage, ranging from 0 to 35. The sample size for each tremor constancy level is indicated above each boxplot, with n=19 for 0, n=6 for 1, n=4 for 2, and n=7 for both 3 and 4. The correlation coefficient (ρ) between the two variables is 0.72, indicating a strong positive correlation.

Fig. 3E. Smartwatch estimates of tremor severity and presence correlate to MDS-UPDRS ratings Mean daily smartwatch tremor estimates correlated with MDS-UPDRS tremor constancy ratings from the subject's last in-clinic visit in hold-out (n = 43) set with a Spearman's rank correlation of 0.72.

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

Image /page/12/Picture/0 description: The image shows the logo for H2O Therapeutics. The logo is black and white. The "h2o" is in lowercase letters, and the "o" has a degree symbol above it. The word "therapeutics" is written in a smaller font below the "h2o".

Image /page/12/Figure/1 description: The image is a boxplot comparing the percentage of time dyskinesia is detected in two groups: "No DK" and "Chorea". The y-axis represents the percentage of time dyskinesia is detected. The "No DK" group has a sample size of n=47, while the "Chorea" group has a sample size of n=10. A horizontal line with an asterisk above the two boxplots indicates a statistically significant difference between the two groups.

Fig. 4E. Smartwatch choreiform dyskinesia detection matches clinical evaluation. In a hold-out dataset (n=57) from the longitudinal patient study, the percentage of time dyskinesias were detected for the chorea group (5.9 ± 5.3%) significantly differed from subjects with no reported dyskinesias (2.0 ± 2.2%) (P = 0.027, Wilcoxon rank sum test)

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

Image /page/13/Picture/0 description: The image contains the logo for "h2o therapeutics". The "h2o" is in bold, dark gray font, with a degree symbol above the "o". Below "h2o" is the word "therapeutics" in a smaller, lighter gray font. The logo is simple and modern.

Image /page/13/Figure/1 description: The image shows two sets of data, each with a pie chart and a corresponding table. The first set, labeled 'A', presents a clinician evaluation with a pie chart showing 94% matched clinician's expectation and 6% unexpected but plausible, based on 104 patients. The table below details a longitudinal patient study with 112 patients undergoing medication or DBS changes, resulting in 98 symptom data changes matching medication change and 6 unexpected but plausible.

Fig. 6. Smartwatch symptom profiles match clinician expectations and provide

quantitative evidence for cases with uncertainty. The clinician reviewed the smartwatch symptom profiles of 112 subjects in the longitudinal patient study who underwent treatment changes. (A) Symptom changes matched the clinician's expectation of the prescribed medication change in 94% of cases. Unexpected cases revealed plausible incidence of known side effects to medications. (B) Three blinded movement disorder specialists classified 10 sets of profiles as pre-or post-treatment using only the patient's medication schedule and MDS-UPDRS tremor and dyskinesia ratings from the intake visit; 87.5% of classifications were correct; three misclassifications occurred because raters presumed that an alternate medication had a dominant effect. Six cases were deemed inconclusive and were excluded.

In summary, MM4PD algorithm outputs significantly correlate with MDS-UPDRS scores of the patients. In addition, system profiles generated through 15-minute means of MM4PD outputs match clinician expectations in out-of-clinic settings.

Regulation Number and Section

§ 882.1950 Tremor transducer.

(a)
Identification. A tremor transducer is a device used to measure the degree of tremor caused by certain diseases.(b)
Classification. Class II (performance standards).