(53 days)
The intended use of PADECG is to acquire resting ECG signals from adult and pediatric patients through body surface ECG electrodes. It is only intended to be used in hospitals or healthcare facilities by doctors and trained healthcare professionals. The cardiogram recorded by PADECG 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. It is mainly used in ECG inpatient department of hospitals or healthcare facilities.
PADECG is iPad-Based ECG work station. PADECG System primarily composed of DX12(iOS) Transmitter and PADECG Analysis Software, the product is designed to collect and analyzes 12-Lead resting ECG. The DX12(iOS) Transmitter contains lead wires and sends the ECG data to PADECG Analysis Software through Bluetooth. The PADECG Analysis Software will be uploaded to the App Store, so that customers can download it to their own iPad and install it. The PADECG Analysis Software which is installed in the iPad can display the ECG data. The PADECG Analysis Software can analysis the ECG data, and provide an advisory diagnostic result.
The provided text describes the 510(k) premarket notification for the Edan Instruments, Inc. PC ECG, model PADECG. The information focuses on demonstrating substantial equivalence to a predicate device (Edan Instruments, Inc., SE-1515, K152427) rather than providing detailed acceptance criteria and a study proving the device meets those criteria for its interpretive statements.
However, based on the information available and common regulatory practices for ECG devices with interpretive capabilities, we can infer some details regarding the "ECG interpretation feature validation by database testing" mentioned.
Here's an attempt to answer your questions based on the provided text, and where information is not explicitly stated, common practice for similar devices is used as a reasonable inference:
1. A table of acceptance criteria and the reported device performance
The document does not explicitly state a table of acceptance criteria for the interpretive algorithm's performance (e.g., sensitivity, specificity for specific diagnoses). Instead, it mentions that "ECG interpretation features were also validated by database testing." The "Comparison between PADECG and Predicate Device SE-1515" table (pages 4-5) details technical specifications of the device itself and explicitly states:
| Item | PADECG | SE-1515 (Predicate) |
|---|---|---|
| Algorithm | Algorithm of the Smart ECG Measurement and Interpretation Programs (SEMIP), version 1.8 | Algorithm of the Smart ECG Measurement and Interpretation Programs (SEMIP), version 1.8 |
| Heart Rate Meter | 30 BPM ~300 BPM, ±1BPM | 30 BPM ~300 BPM, ±1BPM |
| Measuring the ECG | Amplitudes (mV), intervals (ms), and slopes (mV/s) can be ensured on all ECG waveforms | Amplitudes (mV), intervals (ms), and slopes (mV/s) can be ensured on all ECG waveforms |
| Reanalysis | Manually change the measurement marks of medians and the interpretation result | Manually change the measurement marks of medians and the interpretation result |
| Interpretation library | Has Interpretation library and can edit | Has Interpretation library and can edit |
| Resolution | 2.52uV/LSB | 2.52uV/LSB |
| Time Constant | ≥3.2 s | ≥3.2 s |
| Frequency Response | 0.05 Hz ~ 150 Hz (-3 dB) | 0.05 Hz ~ 150 Hz (-3 dB) |
| Input Impedance | ≥20MΩ (10Hz) | ≥20MΩ (10Hz) |
| System Noise | 85% or >90%) for various diagnostic categories (normal, abnormal, specific arrhythmias, ST-T changes, etc.). |
- Agreement with measurements: High correlation (e.g., R-squared > 0.95) and minimal bias in automated measurements of intervals (PR, QRS, QT), amplitudes (P, QRS, T), and axes compared to expert measurements.
- Clinical Significance: Demonstrating that the advice provided by the algorithm does not lead to significant misdiagnosis or harm when used as an advisory tool.
Given that the PADECG uses the "Algorithm of the Smart ECG Measurement and Interpretation Programs (SEMIP), version 1.8," which is the same algorithm as its predicate device (SE-1515), the primary evidence for meeting acceptance criteria for interpretation relies on the predicate device's prior validation and the demonstration that the PADECG implements this identical, validated algorithm correctly. The statement "ECG interpretation features were also validated by database testing" for the PADECG suggests that this algorithm's performance was confirmed on a test set, likely to ensure its faithful implementation on the new platform.
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- Sample Size: Not specified. The document only states "database testing."
- Data Provenance: Not specified (e.g., country of origin, retrospective/prospective). This is a common omission in 510(k) summaries, which often focus on the type of testing rather than granular details of the dataset.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)
- Number of Experts: Not specified.
- Qualifications of Experts: Not specified. For ECG interpretation, ground truth is typically established by board-certified cardiologists or electrophysiologists, often with significant experience in ECG reading.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
- Adjudication Method: Not specified. For ECG interpretation, consensus or adjudication by multiple expert readers is standard practice to establish ground truth.
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
- MRMC Comparative Effectiveness Study: No, the document does not mention an MRMC comparative effectiveness study where human readers' performance with and without AI assistance was evaluated. The device's interpretation is clearly stated as "advisory basis only," indicating it's not a standalone diagnostic device but a tool that assists a professional.
- Effect Size of Improvement: Not applicable, as no such study was reported.
6. If a standalone (i.e. algorithm only, without human-in-the-loop performance) was done
- Standalone Performance: Yes, implicitly. The "ECG interpretation features were also validated by database testing" refers to the performance of the algorithm itself against a pre-established ground truth. While the device is not standalone in general clinical use (it advises clinicians), the algorithm's performance in interpreting ECGs from the database is a standalone evaluation of its output against ground truth. The device is cleared as an "advisory" tool, meaning its standalone diagnostic accuracy is assessed but not necessarily expected to be perfect or replace human judgment.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
- Type of Ground Truth: Not explicitly stated but heavily implied to be expert consensus or reference standard ECG interpretations derived from cardiologists. For ECG interpretation, this is the gold standard for validating algorithms. Pathology or outcomes data are generally not the direct ground truth for ECG interpretation algorithms, though they might be used in broader clinical studies of the overall diagnostic pathway.
8. The sample size for the training set
- Training Set Sample Size: Not specified. The document focuses on the validation of the interpretation features via "database testing" for the specific device being cleared. Details of the training set used for the original development of the "SEMIP, version 1.8" algorithm are not provided in this 510(k) summary.
9. How the ground truth for the training set was established
- Training Set Ground Truth Establishment: Not specified in this document. For the original development of the SEMIP algorithm, it would likely have involved a large dataset of ECGs interpreted by multiple cardiologists, with discrepancies resolved through an adjudication process to establish the most accurate ground truth.
§ 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).