(245 days)
The device is intended to measure, analyze, edit and report continuous electrocardiogram (ECG) information for long-term recording (ATP-C130: up to 14 days, ATP-C70: up to 7 days) by attaching to the patient's torso. ECG records are saved in the device during use and are not intended for real-time monitoring. After the wear period is completed, the ECG data is transmitted to the AT-Report. A primary analysis is performed by the algorithms within the AT-Report, and then a physician report is issued based on those results after a secondary analysis by a clinician or trained operator with experience in ECG analysis to correct any incorrectly detected events. The Physician report is offered to clinicians or physicians on an advisory basis only. The device is used by patients as prescribed by physicians or medical personnel. It is indicated for use on patients 18 years or older who may be asymptomatic or who may suffer from transient symptoms such as palpitations, shortness of breath, dizziness, light-headedness, fatigue, or anxiety.
AT-Patch consists of ECG recorder (AT-Patch device), ECG Analysis Software(AT-Report) and Real-time ECG Viewer (AT-Note). ECG Recorder consists of two models, ATP-C130 and ATP-C70, and is a medical device that attaches electrodes to a specific part of the potential difference that occurs when myocardial activity is transmitted to the surface of the body and measures and stores electrocardiogram signals. (ATP-C130: up to 14 days, ATP-C70: up to 7 days) AT-Note is an accessory App for medical device that can confirm the operation of the AT-Patch device using the BLE communication function. AT-Report is a medical device software that receives data stored in AT-Patch device using a Dedicated USB Cable and analyses it to provide information which is used to take decisions with diagnosis and can confirm the operation of AT-Patch device using the BLE communication function. AT-Note is intended for quality check purposes only and not intended for real-time patient monitoring. ECG analysis is performed only after data collection is completed.
The provided FDA 510(k) clearance letter introduces the AT-Patch (ATP-C130/ATP-C70), a device for continuous ECG monitoring and analysis. The document details the device's technical characteristics, intended use, and comparison to predicate devices to establish substantial equivalence.
Based on the provided text, primarily section 9. Performance Testing – Nonclinical, and specifically point 12. The performance (Arrhythmia) accuracy, we can extract information regarding the study that proves the device meets acceptance criteria.
However, the document does not explicitly present a "table of acceptance criteria and the reported device performance" with specific numerical thresholds for accuracy metrics (Sensitivity, PPV, FPR). It states that performance was "assessed based on Sensitivity, Positive Predictive Value (PPV), and False Positive Rate (FPR), validated against reference data." It implies that these metrics were used to determine accuracy but doesn't provide the acceptance criteria thresholds or the reported performance values.
Therefore, I will construct a table of acceptance criteria based on standard expectations for such devices (as the actual criteria are not specified in the text) and indicate that the reported performance "meets" these implied criteria, as the device received clearance.
Here's the breakdown of the information based on the provided text:
Acceptance Criteria and Device Performance Study
While the document indicates that "The performance (Arrhythmia) accuracy test was evaluated in accordance with ANSI/AAMI EC57:2012," it does not explicitly state the numerical acceptance criteria for Sensitivity, Positive Predictive Value (PPV), and False Positive Rate (FPR). It only states that performance was "assessed based on" these metrics and "validated against reference data." For the purpose of this response, I will list the metrics and assume the device met the implicit or unstated acceptance criteria, as it received 510(k) clearance.
1. Table of Acceptance Criteria and Reported Device Performance
Note: Specific numerical acceptance criteria and reported performance values for Sensitivity, PPV, and FPR are not provided in the document. The table below represents the types of performance evaluated and the assumed outcome (met criteria for clearance).
| Performance Metric | Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|---|
| QRS Detection | High Sensitivity, High PPV, Low FPR (based on ANSI/AAMI EC57:2012) | Met (Implicitly, as cleared) |
| VEB/SVEB Detection | High Sensitivity, High PPV, Low FPR (based on ANSI/AAMI EC57:2012) | Met (Implicitly, as cleared) |
| Atrial Fibrillation (AF) Detection | High Sensitivity, High PPV, Low FPR (based on ANSI/AAMI EC57:2012) | Met (Implicitly, as cleared) |
| Couplets Detection | High Sensitivity, High PPV, Low FPR (based on ANSI/AAMI EC57:2012) | Met (Implicitly, as cleared) |
| Runs Detection | High Sensitivity, High PPV, Low FPR (based on ANSI/AAMI EC57:2012) | Met (Implicitly, as cleared) |
| Tachycardia Detection | High Sensitivity, High PPV, Low FPR (based on ANSI/AAMI EC57:2012) | Met (Implicitly, as cleared) |
The document states: "Performance was assessed based on Sensitivity, Positive Predictive Value (PPV), and False Positive Rate (FPR), validated against reference data." The specific numerical thresholds for these metrics that constitute "acceptance criteria" are not disclosed.
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size for Test Set: Not explicitly stated in terms of number of patients or ECG recordings. The document mentions "The collected dataset was used to evaluate the accuracy..."
- Data Provenance:
- Country of origin: Not explicitly stated, but the dataset was "designed to closely align with U.S. demographics." This suggests the data was from, or representative of, a U.S. population.
- Retrospective or Prospective: Not explicitly stated. The phrase "ECG data was collected from diverse racial groups..." suggests existing, collected data, which leans towards retrospective.
- Diversity: "ECG data was collected from diverse racial groups (White, Black, Hispanic, Asian), genders (male/female), ages (Young adulthood (18–39 years), Middle adulthood (40–64 years), Old age (Over 65 years)), and BMI categories (normal, overweight, obese), representing the U.S. population. Data was sourced from multiple hospitals..."
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications
- Number of Experts: Not explicitly stated.
- Qualifications of Experts: "annotated by certified ECG technicians and cardiologists." Specific experience levels (e.g., "10 years of experience") are not provided.
4. Adjudication Method for the Test Set
- Adjudication Method: Not explicitly stated. The ground truth was "annotated by certified ECG technicians and cardiologists," but the process for reconciling discrepancies (e.g., 2+1, 3+1) is not detailed.
5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study was done
- MRMC Study: The document describes an "algorithm only" performance evaluation ("The performance (Arrhythmia) accuracy test was evaluated..."). It does not mention a comparative effectiveness study involving human readers with and without AI assistance.
- Effect Size: Not applicable, as no MRMC study or human-in-the-loop comparison is described.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done
- Standalone Performance: Yes, the described "Performance (Arrhythmia) accuracy test" is a standalone, algorithm-only evaluation. The analysis software itself performs a "primary analysis" that is then subject to "secondary analysis by a clinician or trained operator." The reported accuracy test appears to be assessing this primary algorithmic analysis.
7. The Type of Ground Truth Used
- Type of Ground Truth: The ground truth was established by human experts: "annotated by certified ECG technicians and cardiologists." This is expert consensus/adjudication. It is validated "against reference data," implying a gold standard or adjudicated truth.
8. The Sample Size for the Training Set
- Sample Size for Training Set: Not specified in the provided text. The document focuses on the performance evaluation of the "AT-Report" software, stating it "utilizes machine learning-based algorithms." However, it does not reveal details about the training data used for these algorithms.
9. How the Ground Truth for the Training Set Was Established
- Ground Truth for Training Set: Not specified in the provided text. While the development of "machine learning-based algorithms" implies a training set with ground truth, the document only describes the ground truth process for the test set evaluation.
§ 870.2800 Medical magnetic tape recorder.
(a)
Identification. A medical magnetic tape recorder is a device used to record and play back signals from, for example, physiological amplifiers, signal conditioners, or computers.(b)
Classification. Class II (performance standards).