(261 days)
The iSE series electrocardiograph is intended to acquire ECG signals from adult and pediatric patients through body surface ECG electrodes. The electrocardiograph is only intended to be used in hospitals or 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 and interpretive statements is offered to clinicians on an advisory basis only. The electrocardiograph is capable of network communications and supports the informatized management of workflows in hospital and healthcare facilities.
iSE-1210 and iSE-1810 Electrocardiograph can support ECG Data Sampling of maximum 12 leads and maximum 18 leads separately. iSE series electrocardiograph uses algorithm to generate measurements, data presentations, graphical presentations and interpretative statements. The electrocardiograph is only intended to be used in hospitals or healthcare facilities by doctors and trained healthcare professionals.
The provided text is a 510(k) Premarket Notification summary for the Edan Instruments, Inc. Electrocardiograph (iSE series). It focuses on establishing substantial equivalence to previously cleared devices.
Based on the provided document, here's a breakdown of the acceptance criteria and the study that proves the device meets them:
Key Takeaway: This 510(k) summary does not include a clinical study with real patient data to prove the device's diagnostic performance against a ground truth for conditions like heart disease. Instead, it relies heavily on non-clinical bench testing, electrical safety, EMC, human factors, and software verification/validation to demonstrate that the new device (iSE series) is as safe and effective as its predicate devices, primarily in its ability to acquire and process ECG signals according to established industry standards. The interpretation of ECGs with measurements and interpretive statements is explicitly stated as advisory only.
Therefore, the acceptance criteria and study described will pertain to the technical performance and safety of the ECG acquisition and processing rather than the diagnostic accuracy of an AI algorithm in interpreting ECGs for specific heart conditions.
Acceptance Criteria and Device Performance
The document does not present a formal table of acceptance criteria with corresponding performance results in the format requested for diagnostic performance. Instead, it states that the device meets "accuracy specification" and "relevant consensus standards" through non-clinical bench testing.
Based on the "Performance Specifications" table (Table 1) and the "Performance testing-Bench" section, we can infer some performance aspects that were likely tested against standards.
Inferred Acceptance Criteria and Reported Device Performance (based on technical specifications and implied testing):
| Acceptance Criteria Category | Specific Criterion (Inferred from standards/specs) | Reported Device Performance |
|---|---|---|
| Electrical Safety | Compliance with ANSI AAMI ES 60601-1:2005/(R) 2012 and A1:2012, C1:2009/(R) 2012 and A2:2010/(R) 2012 | "assessed for conformity with the relevant requirements" (Pass) |
| Electromagnetic Compatibility (EMC) | Compliance with IEC 60601-1-2:2014 (Fourth Edition) | "assessed for conformity with the relevant requirements" (Pass) |
| ECG Signal Accuracy / Performance | Compliance with IEC 60601-2-25 Edition 2.0 2011-10 (Particular requirements for electrocardiographs) | "meets its accuracy specification and meet relevant consensus standards" (Pass) |
| Heart Rate (HR) Recognition Range | HR Range for accurate recognition: 30 BPM - 300 BPM | 30 BPM ~ 300 BPM (Same as predicate) |
| Analog-to-Digital Conversion | A/D Resolution: 24 bits | 24 bits (Same as predicate) |
| Sampling Frequency (ECG Unit) | Sampling Frequency: 64,000 Hz (for general ECG unit) | 64,000 Hz (Higher than predicate's 16,000 Hz, implying improved capability) |
| Frequency Response | Frequency Response: 0.01Hz ~ 350Hz (-3 dB) | 0.01 Hz ~ 350 Hz (-3 dB) (Wider than predicate's 0.01Hz~300Hz, implying improved capability) |
| Filter Performance | Functionality of AC, DFT, EMG, and LOWPASS Filters | AC Filter: Same; DFT Filter: Same; EMG Filter: Same; LOWPASS Filter: Different (350Hz/300Hz/270Hz/150Hz/100Hz/75 Hz vs. 300Hz/270Hz/150Hz/100Hz/75Hz for predicate) (Implied Pass) |
| Pacemaker Detection Sampling Frequency | Pacemaker Detection Sampling Frequency (for specific models) | iSE-1810: 16,000Hz, Rhythm Lead; iSE-1210: 80,000Hz, Rhythm Lead (Different from predicate) (Implied Pass) |
| Human Factors/Usability | Compliance with "Applying Human Factors and Usability Engineering to Medical Devices" guidance and IEC 62366-1:2020 | "safe and effective for the intended users, uses, and use environments" (Pass) |
| Software Verification & Validation | Compliance with FDA's "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices" | "conducted and documentation was provided" (Implied Pass) |
Study Details (Based on the provided document)
-
Sample size used for the test set and the data provenance:
- Test Set Sample Size: Not specified for any performance testing beyond "Functional and system level testing" and "usability testing." No specific number of patient ECGs are mentioned for any diagnostic validation.
- Data Provenance: The document does not specify the country of origin for any data (if patient data was used implicitly in some "accuracy specification" bench testing, which is unlikely given the context). The studies mentioned (Electrical safety, EMC, performance bench testing, human factors, software verification) are non-clinical bench and lab-based studies. There is no mention of prospective or retrospective patient data collection.
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Not Applicable. For non-clinical bench testing, the "ground truth" is typically defined by engineering specifications, calibration standards, and validated test equipment rather than expert human interpretation of medical data.
- The interpretative statement for the ECGs is offered "on an advisory basis only," indicating that the device's interpretation is not intended to replace a physician's diagnosis.
-
Adjudication method (e.g. 2+1, 3+1, none) for the test set:
- Not Applicable. The studies described are technical performance tests against standards, not human reader studies requiring adjudication of medical diagnoses.
-
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. An MRMC study was not conducted or reported. The device's interpreted ECGs are advisory, and there's no claim of AI assistance for human readers in the diagnostic process. The "algorithm" mentioned (SEMIP V1.92) generates measurements, data presentations, graphical presentations, and interpretative statements, but its performance is not assessed in a comparative effectiveness study with human readers.
-
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Partially Yes, for technical performance. The bench testing (e.g., meeting accuracy specifications, sampling frequency, frequency response) can be considered a standalone performance assessment of the device's ability to acquire and process ECG signals according to engineering and industry standards. However, this is distinct from a standalone diagnostic performance study typically seen for AI/CADe devices. The document explicitly states "Clinical data: Not applicable." This confirms that no standalone clinical diagnostic performance study was performed or needed for this 510(k) submission, as the device's interpretations are advisory.
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- Technical Specifications/Industry Standards. For the non-clinical tests, the "ground truth" for the device's performance is compliance with established electrical safety, EMC, and ECG technical performance standards (e.g., IEC 60601 series). There is no "ground truth" of patient diagnosis (e.g., pathology, outcomes, expert consensus on disease states) used as this device is broadly an ECG acquisition and processing device, with its interpretive statements being advisory.
-
The sample size for the training set:
- Not applicable / Not specified. The document makes no mention of AI model training or a training set. The "algorithm" (SEMIP V1.92) is mentioned as generating interpretive statements, but its development process (e.g., use of a training set, machine learning) is not described or evaluated in this 510(k) summary. Given the nature of a foundational ECG device and the "advisory basis only" statement for interpretations, it's highly likely this algorithm is rule-based or statistical rather than a deep learning model requiring a large training set of annotated ECGs for diagnostic purposes.
-
How the ground truth for the training set was established:
- Not applicable. As no training set is mentioned or evaluated in the provided document, the process for establishing its ground truth is not described.
§ 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).