The CoVa™ Monitoring System is intended for use under the direction of a licensed medical professional by adult patients at home to record, store, and transmit the following physiological data: i) Heart Rate including Heart Rate Variability; ii) Thoracic Impedance; iii) Respiration Rate; and iv) Posture. The CoVaTM Monitoring System only displays these physiological data to licensed medical professionals.

The CoVaTM Monitoring System is indicated for patients: i) with fluid-management problems; ii) taking diuretic medication; iii) living with heart failure; iv) living with end-stage renal disease; v) recovering from a coronary artery disease-related event; and/or vi) suffering from recurrent dehydration.

Device Description

toSense's CoVaTM Monitoring System features a body-worn Sensor, Gateway, and Web-based System.

The Sensor non-invasively measures heart rate (HR), heart rate variability (HRV), respiration rate (RR), and thoracic index (TI). To determine these parameters, the Sensor measures and processes single-lead electrocardiogram (ECG) and thoracic bioimpedance (TBI) waveforms. Additionally, the Sensor measures skin temperature (TEMP) and posture using, respectively, a temperature sensor and accelerometer.

The Sensor has a form factor similar to a conventional necklace, with all measurement electronics built into its strands and base. A pair of customized disposable Electrodes, each featuring two electrode regions, snaps into a magnetic interface on the backside of the base, and then attaches to the patient's chest to make a measurement. The Sensor is designed for measurement periods less than about 5 minutes.

Using a Bluetooth transceiver, the Sensor wirelessly transmits information it measures from the patient to a Gateway, which can be a tablet computer or mobile phone running the Android operating system. Each of these systems receives information from the Sensor, and then forwards it to a Web-based System through either a local-area network (e.g., network based on 802.11), or a wide-area cellular network (e.g. AT&T). The Web-based System displays information, and can also forward it to a third-party system through a web-services interface.

AI/ML Overview

The provided text describes the acceptance criteria and the studies conducted for the CoVa Monitoring System.

Here's an analysis of the requested information:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state pre-defined acceptance criteria in terms of specific performance thresholds (e.g., minimum correlation coefficient, maximum mean absolute error). Instead, it presents the results of regression models (slope and intercept) comparing the CoVa system to reference devices and simulators. The implicit acceptance criterion appears to be "substantially equivalent" to predicate devices, as stated in the conclusion.

Parameter Evaluated	Acceptance Criterion (Implicit)	Reported Device Performance (Slope)	Reported Device Performance (Intercept)	Study Type
Thoracic Impedance (vs. reference device)	Substantially equivalent to FDA-cleared reference device	0.86	35.8	Clinical Study 1 (Hemodialysis patients)
Thoracic Impedance (vs. reference device)	Substantially equivalent to FDA-cleared reference device	0.65	117	Clinical Study 2 (Fluid-management issues)
Respiration Rate (vs. reference device)	Substantially equivalent to FDA-cleared reference device	1.00	1.62	Clinical Study 3 (Healthy volunteers)
Thoracic Impedance (absolute accuracy)	Substantially equivalent to simulator output	1.00	0.09	Clinical Study 4a (Bench Study)
Respiration Rate (absolute accuracy)	Substantially equivalent to simulator output	1.02	-0.60	Clinical Study 4b (Bench Study)
Heart Rate (absolute accuracy)	Substantially equivalent to simulator output	1.00	-0.41	Clinical Study 4c (Bench Study)
Heart Rate Variability (absolute accuracy)	Substantially equivalent to simulator output	1.02	-2.53	Clinical Study 4d (Bench Study)
Temperature (absolute accuracy)	Substantially equivalent to simulator output	0.99	0.35	Clinical Study 4e (Bench Study)

Further performance details:

Thoracic Impedance (Clinical Study 1): Average Pearson's correlation with fluid removed by hemodialysis: r = 0.93 (p < 0.0001). Measurement sensitivity: 1.72 Ohms/Liter. Measurement precision for long-term monitoring: 1-2 Ohms. Measurement precision for short-term monitoring: < 1 Ohm.

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

Clinical Study 1 (Thoracic Impedance):
- Sample Size: 33 subjects, 13 test devices, 500 measurements.
- Provenance: Retrospective/Prospective not explicitly stated, but implies prospective collection as subjects "receiving chronic maintenance hemodialysis." Location (country) not specified, but typically assumed to be the US for FDA submissions unless otherwise noted.
- Subject Type: Subjects "receiving chronic maintenance hemodialysis and, in some cases, suffering from congestive heart failure."
Clinical Study 2 (Thoracic Impedance):
- Sample Size: 23 subjects, 2 test devices, 560 measurements.
- Provenance: Retrospective/Prospective not explicitly stated, but implies prospective collection as measurements were made "daily in the home environment over an extended period of time." Location not specified.
- Subject Type: Subjects "all having fluid-management issues, such as congestive heart failure."
Clinical Study 3 (Respiration Rate):
- Sample Size: 19 subjects, 2 test devices, 682 measurements.
- Provenance: Retrospective/Prospective not explicitly stated, but implies prospective ("adult subjects undergoing breathing patterns"). Location not specified.
- Subject Type: "Healthy volunteers using breathing patterns with variable rates and tidal volumes that simulate those encountered by intended-use populations."
Clinical Studies 4a-e (Absolute Accuracy):
- Sample Size:
  - 4a (TI): 8 devices, 88 measurements
  - 4b (RR): 1 device, 15 measurements
  - 4c (HR): 1 device, 67 measurements
  - 4d (HRV): 1 device, 15 measurements
  - 4e (TEMP): 1 device, 40 measurements
- Provenance: Bench studies using simulators. Location not specified.
- Subject Type: Simulator.

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

The document does not mention the use of experts to establish a "ground truth" for the test set in the traditional sense (e.g., expert consensus on image interpretation). Instead, the ground truth for these studies was established by FDA-cleared reference devices or calibrated simulators.

Clinical Studies 1, 2, 3: Ground truth was established by "FDA-cleared reference devices" or an "acceptance-standard device" (for RR in Clinical Study 3). The qualifications of personnel operating these reference devices are mentioned as "Trained personnel."
Clinical Studies 4a-e: Ground truth was established by "calibrated simulators."

4. Adjudication Method for the Test Set

Not applicable. The ground truth was established by reference devices or simulators, not human adjudication.

5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study Was Done, If So, What Was the Effect Size of How Much Human Readers Improve with AI vs Without AI Assistance

No MRMC comparative effectiveness study involving human readers and AI assistance is mentioned in the provided text. The studies focus on the performance of the device itself against reference standards.

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

Yes, the studies described are standalone performance evaluations of the CoVa Monitoring System's algorithms and sensors. The device directly measures and processes physiological data, comparing its output to reference devices or simulators. There is no mention of a human-in-the-loop component in these performance evaluations. The system "only displays these physiological data to licensed medical professionals," implying that professional interpretation occurs after the device has performed its measurements and calculations.

7. The Type of Ground Truth Used

Clinical Studies 1, 2, 3 (Clinical Trials): FDA-cleared reference devices measuring the same physiological parameters (thoracic impedance, respiration rate).
Clinical Studies 4a-e (Bench Studies): Calibrated simulators designed to accurately produce known values for thoracic impedance, respiration rate, heart rate, heart rate variability, and skin temperature.

8. The Sample Size for the Training Set

The document primarily describes validation studies and does not provide information on the sample size used for the training set of any algorithms within the CoVa Monitoring System. It focuses on the evaluation of the device's performance post-development.

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

Since the document does not discuss the training set, it does not describe how ground truth for a training set was established.

Summary

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

Image /page/0/Picture/1 description: The image shows the logo for the U.S. Department of Health & Human Services. The logo is a circular seal with the words "DEPARTMENT OF HEALTH & HUMAN SERVICES - USA" arranged around the perimeter. Inside the circle is a stylized image of three human profiles facing to the right, with flowing lines connecting them.

Food and Drug Administration 10903 New Hampshire Avenue Document Control Center - WO66-G609 Silver Spring, MD 20993-0002

May 1, 2015

toSense, Inc. Nandini Murthy Regulatory Consultant to toSense, Inc 4225 Executive Square, Suite 570 La Jolla, California 92037

K142087 Trade/Device Name: Cova Monitoring System Regulation Number: 21 CFR 870.2300 Regulation Name: Cardiac Monitor (Including Cardiotachometer and Rate Alarm) Regulatory Class: Class II Product Code: MWI, DSB, FLL Dated: April 1, 2015 Received: April 2, 2015

Dear Nandini Mirthy,

Re:

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. 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 801); medical device reporting (reporting of medical devicerelated adverse events) (21 CFR 803); good manufacturing practice requirements as set forth in

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

the quality systems (QS) regulation (21 CFR Part 820); and if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.

If you desire specific advice for your device on our labeling regulation (21 CFR Part 801), please contact the Division of Industry and Consumer Education at its toll-free number (800) 638-2041 or (301) 796-7100 or at its Internet address

http://www.fda.gov/MedicalDevices/ResourcesforYou/Industry/default.htm. 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

http://www.fda.gov/MedicalDevices/Safety/ReportaProblem/default.htm for the CDRH's Office of Surveillance and Biometrics/Division of Postmarket Surveillance.

You may obtain other general information on your responsibilities under the Act from the Division of Industry and Consumer Education at its toll-free number (800) 638-2041 or (301) 796-7100 or at its Internet address

http://www.fda.gov/MedicalDevices/ResourcesforYou/Industry/default.htm.

Sincerely vours,

Mitchell Stein

forBram D. Zuckerman, M.D. Director Division of Cardiovascular Devices Office of Device Evaluation Center for Devices and Radiological Health

Enclosure

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

Section 4

Indications for Use Form

510(k) Number (if known): K142087

Device Name:

Indications for Use:

The CoVa™ Monitoring System is intended for use under the direction of a licensed medical professional by adult patients at home to record, store, and transmit the following physiological data: i) Heart Rate including Heart Rate Variability; ii) Thoracic Impedance; iii) Respiration Rate; and iv) Posture. The CoVat™ Monitoring System only displays these physiological data to licensed medical professionals.

Prescription Use X (Part 21 CFR 801 Subpart D)

AND

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

(PLEASE DO NOT WRITE BELOW THIS LINE-CONTINUE ON ANOTHER PAGE OF NEEDED)

Concurrence of CDRH. Office of Device Evaluation (ODE)

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

510(k) Summary

Dateprepared	May 1, 2015
Name	toSense, Inc.4225 Executive SquareSuite 570La Jolla, CA 92037(619) 733-4968
ContactPerson	Matthew Banet, Ph.D.Chief Technology Officer
Trade Name	CoVaTM Monitoring System
CommonName	Mobile patient monitoring system, cardiac monitor
ClassificationName	Patient Physiological Monitor (without arrhythmia detection or alarm); Impedance Plethysmograph
ClassificationRegulations	21 CFR 870.2300 (MWI), 21 CFR 870.2770 (DSB), 21 CFR 880.2910 (FLL)
PredicateDevices	Zoe Fluid Status Monitor (referred to herein as the 'Zoe monitor')Manufacturer: Non-Invasive Technologies, Inc.Number: K042113Clearance Date: September 14, 2004Avivo Mobile Patient Management System (referred to herein as the 'Corventis monitor')Manufacturer: CorventisNumber: K113187Clearance Date: January 4, 2012ViSi Mobile Monitoring System (referred to herein as the 'ViSi monitor')Manufacturer: Sotera WirelessNumber: K112478Clearance Date: March 22, 2012
Description	toSense's CoVaTM Monitoring System features a body-worn Sensor, Gateway, and Web-based System.The Sensor non-invasively measures heart rate (HR), heart rate variability (HRV), respiration rate (RR), and thoracic index (TI). To determine these parameters, the Sensor measures and processes single-lead electrocardiogram (ECG) and thoracic bioimpedance (TBI) waveforms. Additionally, the Sensor measures skin temperature (TEMP) and posture using, respectively, a temperature sensor and accelerometer.The Sensor has a form factor similar to a conventional necklace, with all measurement electronics built into its strands and base. A pair of customized disposable Electrodes, each featuring two electrode regions, snaps into a magnetic interface on the backside of the base, and then attaches to the patient's chest to make a measurement. The Sensor is designed for measurement periods less

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

than about 5 minutes.

Indications for Use

The CoVa" Monitoring System is intended for use under the direction of a licensed medical professional by adult patients at home to record, store, and transmit the following physiological data: i) Heart rate including heart rate variability; ii) Respiration rate; iii) Thoracic impedance; and iv) Posture. The CoVa"M Monitoring System only displays these physiological data to licensed medical professionals.

The CoVa™ Monitoring System is indicated for patients: i) with fluid-management problems; ii) taking diuretic medication; iii) living with heart failure; iv) living with end-stage renal disease; v) recovering from coronary artery disease-related event; and/or vi) suffering from recurrent dehydration.

The following are the contraindications for the CoVa™ Monitoring System:

. The System is not to be used on patients with implanted cardiac devices, such as pacemakers and implanted cardio-defibrillators (ICDs).
. The System is not defibrillator-proof. Thus the sensor should be removed from a patient before using an external defibrillator.
. The System includes magnetically active materials, and thus should not be used by patients undergoing a procedure involving magnetic resonance imaging (MRI).

Summary of Each indication for use and measurement assigned to the CoVa™ Monitoring System is also Substantial assigned to one or more of the Corventis, Zoe, or ViSi monitors. The System's proposed intended-Equivalence use population is also aligned with that of one or more of the predicate monitors.

The Sensor, along with the Zoe and Corventis monitors, all use an impedance-based technology to measure TI or an equivalent thereof. Our validations efforts, which compare the Sensor's measurements of TI to those made by a FDA-cleared reference device, indicate that measurements of TI made by these systems are substantially equivalent.

Both the Sensor and the Corventis monitors use the same impedance-based technology to measure RR. Our validations efforts, which compare the Sensor's measurements of RR to those made by a FDA-cleared reference device, indicate that measurements of RR made by these systems are substantially equivalent.

Both the Sensor and the Corventis monitor use standard technologies to measure ECG waveforms and, from these, calculate HR and HRV. The Sensor and the Corventis monitor also both use conventional tri-axial accelerometer sensors to measure motion-related properties of the patient, such as posture. The Sensor and the Corventis monitor both use a conventional Bluetooth wireless transceiver to send numerical and waveform information to a gateway device. And our Gateway and that used with the Corventis monitor both use a cellular transmitter or, alternatively, 802.11 to send information to a web-based system. Based on this, we do not believe our core technologies outside of those used for TI and RR raise any new questions of safety or effectiveness.

The Sensor measures TEMP with a thermal sensor in electrical contact with one of the Electrodes. During a measurement, the Electrode adheres to the patient's underlying skin, and within a few

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

minutes these components reach a thermal equilibrium. After this point the thermal sensor measures TEMP. The ViSi monitor measures skin temperature in a nearly identical manner using a small plastic component in its chest-worn sensor. Based on the commonality of these approaches, we do not believe our core technology for measuring TEMP raises any new questions of safety or effectiveness.

The Sensor, when compared to both the Corventis and Zoe monitors, has a different form factor and electrode configuration, and uses a different mechanism for securing its Electrodes. The Corventis monitor features a single, integrated patch with four electrode regions. The Zoe monitor features a remote, stand-alone console that connects to a pair of dual-region, body-worn electrodes through a pair of cables. The cables feature standard mechanical snaps to connect the electrodes. The console contains all measurement and data-processing electronics. The Zoe monitor is typically used daily and resides with the patient.

In contrast, the Sensor is shaped like a conventional necklace, and drapes around the patient's neck during a measurement. It is designed for one-time, daily use, and typically resides permanently with the patient. 2 disposable Electrodes, each containing 2 electrode regions, connect through a magnetic interface to the Sensor's base, and then attach to the patient. The Sensor's necklaceshaped form factor ensures that, on a daily basis, the Electrodes are positioned consistently on the patient.

Thus, we believe the mechanical differences between the Sensor and its predicates -i.e. the necklace-shaped form factor and the mechanism in which it supports electrodes- do not raise any new questions of safety.

Clinical and Non-Clinical Testing

toSense studied the CoVa™ Monitoring System (the test device) and its measurement of thoracic impedance with a clinical trial featuring 33 subjects receiving chronic maintenance hemodialysis and, in some cases, suffering from congestive heart failure. Table 1, below, refers to this study as 'Clinical Study 1'. Measurements were made on all subjects while they were receiving hemodialysis. The trial compared thoracic impedance measured with the test device to a similar impedance parameter measured simultaneously by a FDA-cleared reference device. Trained personnel applied both test and reference devices to subjects. Table 1 summarizes the comparison of the test and reference devices' impedance values using the rank-regression method, as investigated during Clinical Study 1. Additional analysis demonstrated an average Pearson's correlation between the test device's measurement of impedance and fluid removed by a machine performing the hemodialysis of r = 0.93 (p < 0.0001), and that the test device's measurement sensitivity was 1.72 Ohms/Liter. Studies estimate the test device's measurement precision for thoracic impedance when used for long-term monitoring, as calculated from the standard deviation of repeated measurements, may be in the order of magnitude of 1~2 Ohms. Separate studies estimate the test device's measurement precision for thoracic impedance when used for short-term monitoring, calculated in a similar manner, may be less than 1 Ohm.

toSense also studied the test device's measurement of thoracic impedance with a clinical trial featuring 23 subjects, all having fluid-management issues, such as congestive heart failure. Table 1 refers to this study as 'Clinical Study 2'. Here, both test and reference devices measured impedance values daily in the home environment over an extended period of time. Trained personnel applied the reference device to all subjects. In some cases, trained personnel also applied the test device; in others, the subjects applied the test device. Table 1 summarizes the comparison of the test and reference devices' impedance values using the rank-regression method, as investigated during Clinical Study 2.

toSense also studied the test device and its measurement of respiration rate with a clinical trial featuring 19 adult subjects undergoing breathing patterns with variable rates and tidal volumes that

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

Page 4 of 5 simulate those encountered by intended-use populations. Table 1 refers to this study as 'Clinical Study 3'. The trial compared respiration rate values measured simultaneously with: 1) the test device; 2) a FDA-cleared monitor based on impedance pneumography (acceptance-standard device); and 3) a FDA-cleared monitor that measures end-tidal carbon dioxide and spriometry (reference device). Table 1 summarizes the comparison of the test and reference devices' impedance values using the rank-regression method, as investigated during Clinical Study 3.

K142087

Finally, toSense studied the test device's measurement accuracy of thoracic impedance, respiration rate, heart rate, heart rate variability, and skin temperature using bench studies featuring calibrated simulators. Table 1 refers to these studies as 'Clinical Studies 4a-e', respectively. Analysis of results from these studies, as determined using a standard regression model, are included in Table 1.

ClinicalStudy	ParameterEvaluated	N	Subject Type	Slope fromRegressionModel	InterceptfromRegressionModel
1	TI (compared toreference device)	33 subjects, 13test devices,500measurements	undergoingchronichemodialysis; mayhave CHF	0.86	35.8
2	TI (compared toreference device)	23 subjects, 2test devices,560measurements	fluid-managementissues	0.65	117
3	RR (compared toreference device)	19 subjects, 2test devices,682measurements	healthy volunteersusing breathingpatternsencountered byintended-usepopulations	1.00	1.62
4a	TI (absoluteaccuracy)	8 devices, 88measurements	simulator	1.00	0.09
4b	RR (absoluteaccuracy)	1 device, 15measurements	simulator	1.02	-0.60
4c	HR (absoluteaccuracy)	1 device, 67measurements	simulator	1.00	-0.41
4d	HRV (absoluteaccuracy)	1 device, 15measurements	simulator	1.02	-2.53
4e	TEMP(absoluteaccuracy)	1 device, 40measurements	simulator	0.99	0.35

Table 1: Summary of regression results for CoVa's measurements, as determined by Clinical Studies 1-4.

Performance

Components of the CoVa" Monitoring System have been tested and meet the requirements of the

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

	K142087Page 5 of 5
Testing	relevant sections of the following performance standards:
	IEC 60601-1 Standard: Medical Electrical Equipment - Part 1: General Requirements forBasic Safety and Essential Performance (2005)
	IEC 60601-1-2 Standard: Medical Electrical Equipment - Part 1-2: General Requirementsfor Basic Safety and Essential Performance, Collateral Standard: ElectromagneticCompatibility (2007)
	60601-1-6 Standard: Medical Electrical Equipment - Part 1-6: General Requirements forBasic Safety and Essential Performance, Collateral Standard: Usability; and IEC 62366Standard: Medical Devices – Application of Usability Engineering to Medical Device
	AAMI/ANSI EC13: Cardiac monitors, heart rate meters, and alarms (2002)
	ISO 80601-2-56 Medical electrical equipment - Part 2-56: Particular requirements for basic safetand essential performance of clinical thermometers for body temperature measurements
Conclusion	The CoVaTM Monitoring System has been tested and found to comply with recognizedperformance, safety, and electromagnetic compatibility standards for medical devices. Clinicalstudies indicate its measurements are substantially equivalent to those made by its predicatedevices.
	Based on the above, we believe the CoVaTM Monitoring System is as safe and effective as itspredicate devices.

Regulation Number and Section

§ 870.2300 Cardiac monitor (including cardiotachometer and rate alarm).

(a)
Identification. A cardiac monitor (including cardiotachometer and rate alarm) is a device used to measure the heart rate from an analog signal produced by an electrocardiograph, vectorcardiograph, or blood pressure monitor. This device may sound an alarm when the heart rate falls outside preset upper and lower limits.(b)
Classification. Class II (performance standards).