The Cardiotron EKG Multi-Phase Information Analysis System is intended to be used as an aid to diagnosis by means of analysis of the EKG waveform in the frequency domain (power spectral estimate).

Device Description

The Cardiotron EKG Multi-Phase Information Analysis System will be available in two models, the basic model system and the remote model system. The basic model system consists of two standard EKG amplifiers and an off-the-shelf analog-to-digital ("A/D") converter, EKG lead wires, a computer, a monitor, and a printer. The remote model system additionally includes a dummy terminal or computer. The EKG amplifiers are supplied by the Fortune, Co. The additional components, which are off-the-shelf products, are unmodified. The computer is programmed with the Company's multi-phase information analysis software.

AI/ML Overview

Here's an analysis of the provided 510(k) summary, focusing on acceptance criteria and the study used to demonstrate device performance.

Important Note: The provided document is a 510(k) summary, which is a high-level overview. It generally lacks the detailed methodology, raw data, and specific statistical analyses found in a full study report. Therefore, some information will be inferred or noted as missing based on the summary's content.

Acceptance Criteria and Device Performance

The provided 510(k) summary doesn't explicitly state "acceptance criteria" in a table format with specific thresholds for sensitivity and specificity. Instead, it leverages the performance of its predicate device, the New York Heart Instrument Inc.'s EKG Multi-Phase Information Diagnosis System, Model FFF-IA, to establish substantial equivalence.

The summary states: "Both systems also contain the same approximately 78 questions that are asked of the patient, and the answers stored in a database... In addition, both systems provide the same ischemia indexes in the form of a positive or negative index. They also have the same sensitivities (i.e., approximately 90%) and specificities (i.e., approximately 85%)."

From this, we can infer the implied acceptance criteria are to demonstrate performance comparable to or better than the predicate's reported 90% sensitivity and 85% specificity. The study described in the 510(k) is implicitly aimed at showing the Cardiotron system achieves these values.

Table 1: Implied Acceptance Criteria and Reported Device Performance

Performance Metric	Implied Acceptance Criterion (from Predicate Device)	Reported Device Performance (Cardiotron EKG Multi-Phase Information Analysis System)
Sensitivity	Approximately 90%	Approximately 90%
Specificity	Approximately 85%	Approximately 85%

Study Proving Device Meets Acceptance Criteria

The 510(k) summary describes the Cardiotron system's performance by directly stating it has "the same sensitivities (i.e., approximately 90%) and specificities (i.e., approximately 85%)" as the predicate device. This implies that testing was conducted to confirm these metrics for the Cardiotron system, likely as part of comparing it to the predicate. The summary also explicitly mentions: "the Company has validated the software to demonstrate that the software functions as intended."

Here's an breakdown of the study information based on the provided text:

Sample size used for the test set and the data provenance:
- Sample Size: Not specified in the document.
- Data Provenance: Not specified (e.g., country of origin, retrospective/prospective). The summary focuses on technological equivalence and software validation rather than a clinical trial detailed with patient demographics.
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Not specified. The document does not detail how the ground truth for measuring sensitivity and specificity was established. Given the context of EKG analysis for ischemia, "diagnosis" by a physician (e.g., cardiologist) or a more definitive test would typically serve as ground truth, but this is not mentioned.
Adjudication method (e.g., 2+1, 3+1, none) for the test set:
- Not specified.
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. The document makes no mention of an MRMC study or of evaluating human reader performance with or without AI assistance. The device is intended "as an aid to diagnosis," implying it provides output for a physician to interpret, but its impact on reader performance is not studied here.
If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:
- Yes, implicitly. The stated sensitivities (90%) and specificities (85%) refer to the performance of the system (algorithm only) in providing "ischemia indexes in the form of a positive or negative index." This is a direct measurement of the algorithm's diagnostic capability without human interpretation factored into the reported metrics.
The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- Not specified. For EKG interpretation related to ischemia, common ground truths include:
  - Coronary angiography results
  - Stress test findings (e.g., nuclear imaging, echocardiography)
  - Clinical diagnosis by a cardiologist
  - Follow-up for cardiac events.
    The summary does not clarify which of these (or other methods) were used to establish the ground truth against which the EKG system's performance was measured.
The sample size for the training set:
- Not specified. Given the system uses "the same algorithms" as the predicate device, it's possible that the training was done on a dataset used for the predicate, or that the algorithms are pre-established and primarily validated on a test set. This detail is absent.
How the ground truth for the training set was established:
- Not specified, as the training set details are not provided.

Summary

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

510(k) SUMMARY K992703 for Cardiotron LLP Inc.'s Cardiotron EKG Multi-Phase Information Analysis System

Submitter's Name, Address, Telephone Number, Contact Person and Date Prepared

Premier Heart LLP 14 Vanderventer Avenue, Suite 138 Port Washington, NY 11050 Phone: (516) 883-3838 Facsimile: (516) 883-5812

Contact person: Dr. Joseph Shen

Date Prepared: March 20, 2000

Name of Device

Trade Name: Cardiotron EKG Multi-Phase Information Analysis System

Common Names: Computerized EKG Analysis System

Classification Names: Computerized EKG and Programmable Diagnostic Computers

Product Code: DQK

Predicate Device

New York Heart Instrument Inc.'s EKG Multi-Phase Information Diagnosis System, Model FFF-IA

Intended Use

The Cardiotron EKG Multi-Phase Information Analysis System is intended to be used as an aid to diagnosis by means of analysis of the EKG waveform in the frequency domain (power spectral estimate).

Technological Characteristics and Substantial Equivalence

The Cardiotron EKG Multi-Phase Information Analysis System will be available in two models, the basic model system and the remote model system. The basic model system consists of two standard EKG amplifiers and an off-the-shelf analog-to-digital ("A/D") converter, EKG lead wires, a computer, a monitor, and a printer. The remote model system additionally includes a dummy terminal or computer. The minor differences between the two devices is discussed in more detail below. The EKG amplifiers are supplied by the Fortune, Co. The additional components, which are off-the-shelf

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

products, are unmodified. The computer is programmed with the Company's multi-phase information analysis software.

To operate the system, six standard EKG leads are placed on the patient in lead positions II and V5. EKG data is collected from both leads simultaneously for approximately two to three minutes. In addition, the patient is asked, through prompts appearing on the display, approximately 78 questions related to his/her medical history, such as age, sex and smoker/non-smoker. These questions are stored in a database as a matter of convenience and as a record-keeping function and not subsequently used to provide a software-based diagnosis of the patient. For example, the Cardiotron's software has the ability to provide a partial medical history of the patient so that the physician can look up and review the answers to the questions in the software=s database. The data from the EKG leads is amplified and processed, using conventional techniques, in the EKG amplifier. The data is fed from the EKG amplifier to the A/D converter, which converts the data from an analog form to a digital form. The data, which has been converted to digital form, is fed to the computer where it is transformed from the time domain to the frequency domain through the application of Fast Fourier Transform power spectrum estimate equations which have been programmed in the multi-phase analysis software installed in the computer.

The Cardiotron System and the NYHI System both consist of two EKG amplifiers, an A/D Converter, EKG lead wires, a computer programmed with software, a monitor, and a printer. Moreover, both systems use the same algorithms in their software to process the data and provide a diagnosis. The same inventor developed the software for the NYHI System and the Cardiotron System. Both systems also provide the same power spectrum estimate used in the diagnosis. Both systems also contain the same approximately 78 questions that are asked of the patient, and the answers stored in a database. The answers to the questions also are used in the identical manner as recorded in a database for the convenience of the physician. In addition, both systems provide the same ischemia indexes in the form of a positive or negative index. They also have the same sensitivities (i.e., approximately 90%) and specificities (i.e., approximately 85%).

The only difference between the two systems is the selection of components, the actual software code itself, and the Cardiotron's remote use function and associated hardware. For example, the Cardiotron System uses EKG amplifiers supplied by Fortune, Co. whereas the NYHI System's EKG amplifiers are supplied by Minta, Co. This does not raise any new issues of safety or effectiveness because both amplifiers have very similar specifications. The Cardiotron System and NYHI System use different A/D converters, EKG lead wires, computers, printers, and monitors although they provide the same basic functions. These differences also do not raise new issues of safety or effectiveness because the components are all very similar. Where there are significant differences, those differences do not affect safety or effectiveness. For example, the NYHI System does not have a high resolution color monitor whereas the Cardiotron System has a high resolution color monitor. This difference is solely for marketing purposes.

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

As noted above, the Cardiotron System uses slightly different code. This difference, however does not raise new issues of safety or effectiveness. First, the software code merely automates the processing of mathematical algorithms, and the mathematical algorithms in the software code of both systems are the same. The code differs only in the manner in which data is stored and in the terms used in the code. Second, as described below, the Company has validated the software to demonstrate that the software functions as intended.

Third, the use of a dummy terminal or additional computer to collect and e-mail the data to a remote location does not raise new issues of safety or effectiveness. As described below, the Company has validated the software that performs these functions. Moreover, the transmission of digital data across the internet is a common operation performed by millions of people. The concern that the data may be lost has been addressed by the Cardiotron's software, which saves the data as well as transmits the data. Thus, if the data transmitted to the remote location is for some reason "lost", it can be resent.

In summary, the Cardiotron System and its predicate device, the NYHI System, have the same intended use and very similar, principles of operation, and technological characteristics. Although there are minor difference in the actual components and software code, these differences do not raise new questions of safety or efficacy.

40024448.doc

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

Image /page/3/Picture/1 description: The image is a black and white logo for the U.S. Department of Health & Human Services. The logo features a stylized depiction of an eagle with three swooping lines forming its body and wings. The eagle is positioned to the right of a circular arrangement of text that reads "DEPARTMENT OF HEALTH & HUMAN SERVICES - USA".

Public Health Service

Food and Drug Administration 9200 Corporate Boulevard Rockville MD 20850

MAR 2 1 2000

Mr. William D. Hare Cardiotron, LLC c/o Fish & Richardson, PC 601 13th Street, N.W. Suite 901 South Washington, DC 20005

Re: K992703 Multi-Phase EKG Information Analysis System Regulatory Class: II (two) Product Code: 74 DQK Dated: December 21, 1999 Received: December 22, 1999

Dear Mr. Hare:

We have reviewed your Section 510(k) notification of intent to market the device referenced above and we have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to leqally 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). You may, therefore, market the device, subject to the qeneral 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.

If your device is classified (see above) into either class II (Special Controls) or class III (Premarket Approval), it may be subject to such additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 895. A substantially equivalent determination assumes compliance with the Current Good Manufacturing Practice requirements, as set forth in the Quality System Regulation (QS) for Medical Devices: General regulation (21 CFR Part 820) and that, through periodic QS inspections, the Food and Drug Administration (FDA) will verify such assumptions. Failure to comply with the GMP regulation may result in regulatory action. In addition, FDA may publish further announcements concerning your device in the Federal Register. Please note: this response to your premarket notification submission does not affect any obligation you might have under sections 531 through 542 of the Act for devices under the Electronic Product Radiation Control provisions, or other Federal laws or regulations.

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

MAR 2 1 2000

Page 2 - Mr. William D. Hare

This letter will allow you to begin marketing your device as described in your 510(k) premarket notification. The FDA finding of substantial equivalence of your device to a legally marketed predicate device results in a classification for your device and thus, permits your device to proceed to the market.

If you desire specific advice for your device on our labeling regulation (21 CFR Part 801 and additionally 809.10 for in vitro diagnostic devices), please contact the Office of Compliance at (301) 594-4648. Additionally, for questions on the promotion and advertising of your device, please contact the Office of Compliance at (301) 594-4639. Also, please note the requlation entitled, "Misbranding by reference to premarket notification" (21 CFR 807.97). Other general information on your responsibilities under the Act may be obtained from the Division of Small Manufacturers Assistance at its toll-free number (800) 638-2041 or (301) 443-6597, or at its internet address "http://www.fda.gov/cdrh/dsma/dsmamain.html".

Sincerely yours,

Jeanne H. Weathers fer

James E. Dillard III Director Division of Cardiovascular, Respiratory, and Neurological Devices Office of Device Evaluation Center for Devices and Radiological Health

Enclosure

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

510(k) Number (if known): K992703

Device Name: Cardiotron Multi-Phase EKG Information Analysis System

Indications For Use:

The Cardiotron Multi-Phase EKG Information Analysis System is intended to be used as an aid to diagnosis by means of analysis of the EKG waveform in the frequency domain (power spectral estimate).

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

Concurrence of CDRH, Office of Device Bvaluation (ODE)

K. Westerlund
(Division Sign-Off)

vision of Cardiovascular, Respiratory, and Neurological Devic 2703 510(k) Number

Prescription Use Per 21 CFR 801.109)

Over-The-Counter Use

(Optional Format 1-2-96)

90428.W11

Regulation Number and Section

§ 870.1425 Programmable diagnostic computer.

(a)
Identification. A programmable diagnostic computer is a device that can be programmed to compute various physiologic or blood flow parameters based on the output from one or more electrodes, transducers, or measuring devices; this device includes any associated commercially supplied programs.(b)
Classification. Class II (performance standards).