(255 days)
The SE-1202 12-lead electrocardiograph is intended to acquire ECG signals from adult and pediatric patients through body surface ECG electrodes. The electrocardiograph is only intended to healthcare facilities by doctors and trained healthcare professionals. The cardiogram recorded by the electrocardiograph can help users to analyze and diagnose heart disease. However, the interpreted ECG with measurements is offered to clinicians on an advisory basis only.
CONTRAINDICATIONS:
SEMIP algorithm is not intended for interpretive statements of neonatal patients from birth to 28 days.
The SE-1202 electrocardiograph features a 10.1" LCD touch screen, an operation panel, user-programmable reports, and the ability to operate on either battery or AC power. It is capable of simultaneous acquisition, display, and print of 12-lead ECG. It uses algorithm to generate measurements, data presentations, graphical presentations and interpretative statements. The record can be saved in flash memory or send to PC.
The provided document is a 510(k) Premarket Notification from Edan Instruments, Inc. for their Electrocardiograph SE-1202. It establishes substantial equivalence to a predicate device (Edan Instruments, Inc, Electrocardiograph: SE-12, SE-12 Express, SE-1200, and SE-1200 Express, K171942).
The document does not contain details about a study addressing specific acceptance criteria for an AI/algorithm's performance as typically required for devices with interpretive or diagnostic AI functionalities. Instead, it focuses on the performance of the electrocardiograph hardware and its ability to meet general electrical safety, EMC, and basic functional standards (e.g., heart rate range, noise, filter specifications).
The device's software includes an algorithm (SEMIP or Glasgow) that generates measurements, data presentations, graphical presentations, and "interpretative statements." However, the document explicitly states that these interpretations are "offered to clinicians on an advisory basis only." Furthermore, it contraindicates the SEMIP algorithm for neonatal patients.
Given that the core of the request is about acceptance criteria and a study that proves the device meets specific acceptance criteria related to its performance, and the document explicitly states "Clinical data: Not applicable," it indicates there wasn't a clinical study designed to test the interpretive algorithm's performance against detailed criteria for accuracy, sensitivity, or specificity in a diagnostic context. The "Performance validation via EDAN proprietary database" is mentioned, but no specifics about this validation, its acceptance criteria, or its results are provided.
Therefore, many of the requested details cannot be extracted from this document, as it describes a device where the interpretive statements are advisory and clinical data showing performance of these interpretive features in a diagnostic capacity was not deemed necessary for this 510(k) clearance.
However, I will extract what is available and clearly state what information is not present.
Here's an analysis of the acceptance criteria and the study as described in the provided document:
1. Table of Acceptance Criteria and Reported Device Performance
The document primarily focuses on demonstrating equivalence to a predicate device through technical specifications and compliance with general medical device standards, rather than defining and meeting specific analytical or clinical performance acceptance criteria for an AI/algorithm's diagnostic accuracy. The "acceptance criteria" here are more about meeting safety, EMC, and basic functional parameters of the ECG device itself, and showing the interpretive algorithm's presence but framing its output as advisory.
| Criteria Category / Parameter | Acceptance Criteria (from document, implicitly or explicitly) | Reported Device Performance (from document) |
|---|---|---|
| Electrical Safety | Conformity with ANSI AAMI ES 60601-1:2005/(R) 2012 and A1:2012, C1:2009(R) 2012 and A2:2010/(R) 2012 | Found to comply. |
| Electromagnetic Compatibility (EMC) | Conformity with IEC 60601-1-2:2014 (Fourth Edition) | Found to comply. |
| Functional/Bench Performance | Conformity with IEC 60601-2-25 Edition 2.0 2011-10 | Bench testing results show that the subject device meets its accuracy specification and meets relevant consensus standards. Performance validated via EDAN proprietary database. (Specific "accuracy specification" details are not provided in this document excerpt). |
| Software Verification & Validation | As recommended by FDA's Guidance for Industry and FDA Staff, "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices." | Conducted and documentation provided. |
| Intended Use | Acquire ECG signals from adult and pediatric patients; used in healthcare facilities by doctors and trained professionals; cardiogram helps analyze/diagnose heart disease; interpreted ECG with measurements is advisory. | Same as the predicate device. |
| Contraindication | SEMIP algorithm not intended for interpretive statements of neonatal patients from birth to 28 days. | Explicitly stated as a contraindication. |
| Basic Performance Specs (Example) | HR Range: 30 BPM ~ 300 BPM, Noise: ≤12.5 µVp-p, Input Impedance: ≥100 MΩ (10 Hz) | Met, or comparable to predicate device. For example, HR Range: 30 BPM ~ 300 BPM, Noise: ≤12.5 µVp-p, Input Impedance: ≥100 MΩ (10 Hz). |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size: Not specified for any performance testing related to the interpretive algorithm. The document mentions "Performance validation via EDAN proprietary database" but does not give details on the size or characteristics of this database.
- Data Provenance: Not specified (e.g., country of origin). The document indicates it's an "EDAN proprietary database," suggesting it's internal.
- Retrospective or Prospective: Not specified.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
- This information is not provided in the document. Given that the interpretive statements are "advisory" and no clinical data was submitted, detailed ground truth establishment by experts for evaluative purposes is not described.
4. Adjudication Method for the Test Set
- This information is not provided in the document.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done
- No. The document explicitly states "Clinical data: Not applicable." Therefore, an MRMC study was not performed or submitted for this 510(k). As a result, no effect size of human readers improving with AI vs. without AI assistance is reported.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was Done
- The document mentions "Performance validation via EDAN proprietary database" for the algorithm. However, specific details of this "standalone" performance (e.g., metrics like sensitivity, specificity, accuracy for specific arrhythmias or findings) are not provided, nor are the acceptance criteria for these metrics. The focus of the submission is on substantial equivalence of the overall device, not on analytical performance of the interpretive algorithm in isolation for diagnostic claims.
7. The Type of Ground Truth Used
- For the "Performance validation via EDAN proprietary database," the type of ground truth is not specified. Given the nature of ECG interpretation, it would typically involve cardiologist consensus or perhaps correlation with other diagnostic modalities for specific findings, but this document does not describe it.
8. The Sample Size for the Training Set
- This information is not provided. The document notes the use of "SEMIP or Glasgow" algorithms. These tend to be well-established, rule-based or statistical algorithms, rather than deep learning models that would have a distinct "training set" in the modern sense. If newer machine learning components were integrated, their training data size is not disclosed.
9. How the Ground Truth for the Training Set was Established
- This information is not provided. For established algorithms like SEMIP or Glasgow, their development likely involved expert consensus and large ECG databases over time, but the specific method for their training data's ground truth is not detailed here.
§ 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).