(176 days)
The intended use of the Spacelabs Healthcare CardioExpress (CardioExpress) is to acquire ECG signals from adult and pediatric patients using ECG electrodes. CardioExpress is only intended to be used in hospitals or healthcare facilities by doctors and trained healthcare professionals. The cardiogram recorded by CardioExpress can help users to analyze and diagnose heart disease. However, the interpreted ECG with measurements and interpretive statements are only intended to be used on adult patients, and is offered to clinicians on an advisory basis only.
The Spacelabs Healthcare (Spacelabs) CardioExpress, Models 98400-SL3-IEC, 98400-SL3-AHA, 98400-SL6-IEC, 98400-SL6-AHA, 98400-SL12-IEC, and 98400-SL12-AHA, are a series of electrocardiographs (ECGs) designed to acquire, analyze, display, and record ECG signals from ECG electrodes connected to a patient.
After been amplified, filtered and analyzed, the ECG signal waveforms and analysis results are presented on a liquid crystal diode (LCD) display, and recorded on the paper through either a thermal or USB printer. ECG data, result and patient information may be stored in the memory file. The file can be transmitted to a personal computer (PC) through either an UART or Ethernet connection.
The CardioExpress can optionally contain auto analysis software which assists in performing auto measurement and auto interpretation of data. The CardioExpress consists of two (2) basic components: (1) the signal acquisition module, and (2) the central processing unit. All models contain a rechargeable battery.
The CardioExpress series of ECG monitors are provided in three (3) primary models: CardioExpress SL-3; CardioExpress SL-6; and CardioExpress SL-12.
Here's an analysis of the acceptance criteria and study information for the Spacelabs Healthcare CardioExpress Electrocardiograph, based on the provided text:
Acceptance Criteria and Device Performance
The provided document describes the Spacelabs Healthcare CardioExpress electrocardiographs (ECG) and their substantial equivalence to predicate devices. The "acceptance criteria" discussed are primarily compliance with various international standards for medical electrical equipment, including safety, usability, alarm systems, and specific requirements for ECGs. The "reported device performance" is the confirmation that the device complies with these standards and its predetermined specifications.
Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria Category | Specific Standard/Requirement | Reported Device Performance |
|---|---|---|
| Software Testing | - Robust software development process |
- Verification and validation per internal requirements
- FDA guidance (e.g., "The content of premarket submissions for software contained in medical devices," "Off-the-shelf software use in medical devices," "General principles of software validation," "Cybersecurity for networked medical devices") | Test results indicate that the CardioExpress complies with its predetermined specifications and the applicable standards and guidance documents. |
| Electrical Safety Testing | IEC 60601-1: 1988, Am1: 1991, and Am2: 1995 (Medical electrical equipment. Part 1: Particular requirements for safety) | Test results indicated that CardioExpress complies with the Standard. |
| Electromagnetic Compatibility (EMC) Testing | IEC 60601-1-2: 2001 (Medical electrical equipment - Part 1-2: General requirements for safety - Collateral standard: Electromagnetic compatibility - Requirements and tests) | Test results indicated that CardioExpress complies with the Standards. |
| Performance Testing (General) | - Internal requirements - IEC 60601-1-6: 2004 (Usability)
- IEC 60601-1-8: 2003, Am1: 2006 (Alarm systems)
- IEC 60601-2-25: 1993, Am: 1999 (Particular requirements for the safety of electrocardiographs)
- IEC 60601-2-51: 2003 (Particular requirements for safety, including essential performance, of recording and analyzing single channel and multichannel electrocardiographs) | Test results indicate that CardioExpress complies with its predetermined specifications and the applicable standards. Verification and validation activities were conducted to establish the performance and safety characteristics of CardioExpress. |
Study Information
It's important to note that the provided text is a 510(k) summary, which focuses on demonstrating substantial equivalence to a legally marketed predicate device rather than presenting a novel clinical trial for efficacy. Therefore, many of the detailed study parameters typically found in clinical trials for new AI/ML devices might not be explicitly stated or applicable in the same way.
-
Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective):
- The document does not explicitly state a sample size for a test set in the context of a clinical performance study. The "test results" mentioned pertain to compliance with electrical, EMC, software, and general performance standards. These tests often use controlled environments and simulated data or hardware, not patient-derived datasets in a clinical sense.
- Similarly, there is no information provided regarding data provenance (country of origin, retrospective/prospective) for any test set involving patient data. This is consistent with the nature of a 510(k) submission primarily focusing on technical and safety standards compliance.
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- This information is not provided. The document mentions the device includes "auto analysis software which assists in performing auto measurement and auto interpretation of data." However, it clarifies that "the interpreted ECG with measurements and interpretive statements are only intended to be used on adult patients, and is offered to clinicians on an advisory basis only." This suggests the device's interpretation is an aid and not a definitive diagnosis that would require extensive expert ground truth establishment in a clinical performance study for this 510(k). The regulatory submission focuses on the safety and foundational performance of the device as an electrocardiograph.
-
Adjudication method (e.g. 2+1, 3+1, none) for the test set:
- This information is not available in the provided text. Adjudication methods are typically associated with clinical performance studies where expert consensus is used to establish ground truth for a diagnostic interpretation. Since such a study for the auto-interpretation feature is not described, neither is an adjudication method.
-
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 is mentioned or appears to have been done for this 510(k) submission. The document states the auto-analysis software "assists" and is "offered to clinicians on an advisory basis only," indicating it's not claiming improved human reader performance through AI assistance in a comparative effectiveness study.
-
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- The document implies the auto-analysis software can function in a "standalone" computational sense (performing auto measurement and interpretation). However, it explicitly states the interpreted ECG... is only intended to be used on adult patients, and is offered to clinicians on an advisory basis only. This means that while the algorithm can generate interpretations, its intended use always involves a human clinician for final diagnosis. Therefore, a standalone clinical performance study (where the algorithm's interpretation alone dictates patient management) would not be applicable given the advisory nature of the interpretation. The testing described primarily covers the technical correctness and safety of the device's functions.
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc):
- Due to the nature of the 510(k) submission focusing on technical and safety compliance of a basic ECG device, specific ground truth types (like pathology or outcomes data) for clinical interpretation accuracy are not detailed. The "ground truth" for the performance tests mentioned would be the expected output or behavior according to the specified IEC standards and internal design specifications.
-
The sample size for the training set:
- The document does not provide a sample size for a training set. The device (an ECG machine) is designed to acquire and analyze ECG signals, and its software includes "auto analysis." This auto-analysis likely relies on well-established algorithms for ECG waveform and rhythm analysis, which may have been developed and refined over decades using large, diverse datasets. However, no specific details about "training sets" for a deep learning or complex AI model are presented in this submission.
-
How the ground truth for the training set was established:
- As no training set is described, information on how its ground truth was established is not provided. If "auto analysis software" refers to rule-based or conventional signal processing algorithms, the "ground truth" for their development would be based on established cardiology principles and guidelines, rather than a prospectively labeled dataset in the modern AI sense.
§ 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).