FORMULA FOR ARCHIMED by BIOSOUND ESAOTE, INC.

Formula for ArchiMed (model 4230) represents a multi-channel electrocardiograph machine equipped with an SVGA monitor, a PC keyboard and a trackball. It is intended to be used for acquisition, digitization, display and recording of conventional diagnostic twelve (12) simultaneous lead ECG waveforms. The 4230 is equipped with a resting interpretation program covering adult populations. This analysis program is offered to the physician on an advisory basis only and the physician is asked to overread and validate (or change) the ECG interpretation.

Formula for ArchiMed is also equipped with software that can be used for exercise stress testing. It incorporates a hard disk with 4 serial ports to add networking capabilities and to accommodate printing to a laser printer.

AI/ML Overview

The provided document (K974079) is a 510(k) Pre-Market Notification for the "Formula for ArchiMed" electrocardiograph and does not include detailed information about specific acceptance criteria or a dedicated study proving performance against such criteria. Instead, it focuses on demonstrating substantial equivalence to a predicate device.

Therefore, much of the requested information regarding acceptance criteria, sample sizes, expert involvement, and ground truth establishment for a performance study is not available in the provided text.

Here's a breakdown of what can be extracted and what is missing:

1. Table of Acceptance Criteria and Reported Device Performance

This information is not available in the provided 510(k) summary. The document does not describe specific acceptance criteria (e.g., sensitivity, specificity, accuracy targets) or report the device's performance against such criteria through a dedicated study. Instead, it highlights that the new system incorporates the same algorithms for key functions as the predicate device.

Acceptance Criteria	Reported Device Performance
Not specified	Not specified

2. Sample size used for the test set and the data provenance

This information is not available. The document does not describe a performance study with a test set. It mentions "The new systems incorporate the same algorhythms for baseline stabilization, template and medians update, fiducial points (and ST measurements) and aberrant beat detection than the predicate device." This suggests reliance on the predicate device's established performance rather than a new, dedicated study with a specific test cohort for the Formula for ArchiMed.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

This information is not available. As no specific test set or performance study is detailed, there's no mention of experts establishing ground truth. The device is intended to be used by a physician, and the analysis program is offered on an advisory basis, with the physician asked to "overread and validate (or change) the ECG interpretation." This implies that the physician is the ultimate arbiter of truth in clinical practice.

4. Adjudication method for the test set

This information is not available. No test set or adjudication method is described.

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

This information is not available. The document does not describe an MRMC study. The "Formula for ArchiMed" is an electrocardiograph with an interpretation program, not an "AI" in the modern sense of a machine learning-based diagnostic aid that would typically be evaluated in such a study for human reader improvement. The device provides an "advisory basis only" interpretation to the physician.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

This information is not available. While the device has an "interpretation program," the document emphasizes it's an "advisory basis only" tool, and the physician is expected to "overread and validate (or change) the ECG interpretation." This means its performance is always considered in conjunction with a human, and a standalone algorithmic performance study is not detailed or implied.

7. The type of ground truth used

This information is not available for a specific validation study of the Formula for ArchiMed. However, since it's an electrocardiograph providing an "interpretation program," the implied "ground truth" in clinical practice would be a physician's expert diagnosis, potentially corroborated by other diagnostic tests or clinical outcomes. The document states "This analysis program is offered to the physician on an advisory basis only and the physician is asked to overread and validate (or change) the ECG interpretation." This implies expert consensus/overread by a physician is the ultimate ground truth in its intended use.

8. The sample size for the training set

This information is not available. The document makes no mention of a training set as would be relevant for machine learning algorithms. It states that the new system uses the "same algorhythms" as the predicate device (Esaote ACTA Formula K#922703). This suggests that the underlying algorithms were developed and validated prior to this submission, and their development details are not part of this 510(k).

9. How the ground truth for the training set was established

This information is not available. As no training set or specific algorithm development for the Formula for ArchiMed is detailed, the method for establishing ground truth for any underlying algorithms used by the predicate device is not provided.

Summary

Regulation Number and Section

§ 870.2340 Electrocardiograph.

(a)
Identification. An electrocardiograph is a device used to process the electrical signal transmitted through two or more electrocardiograph electrodes and to produce a visual display of the electrical signal produced by the heart.(b)
Classification. Class II (performance standards).