(370 days)
The Electric Breast Pump is intended to be used by lactating women to express and collect milk from their breast, to alleviate engorgement of the breast, maintain the ability of lactation, and provide mother's milk for future feedings when separation of mother and baby occurs. It is intended for a single user in a home or hospital environment.
The Electric Breast Pump is intended to express and collect milk from the mother's breast, to alleviate engorgement of the breast, maintain the ability of lactation, and provide mother's milk for future feedings when separation of mother and baby occurs. This Electric Breast Pump is intended for a single user in a home or hospital environment. The Electric Breast Pump has two models: XN/MS-2224A and XN/MS-2224B. Both models are capable of single and double pumping and have two modes: stimulation and expression mode. Both models can be operated using AC power, a built-in rechargeable li-ion polymer battery, or AA batteries.
This document is a 510(k) Premarket Notification Summary for an Electric Breast Pump, not a study describing the acceptance criteria and performance of an AI/ML medical device. Therefore, a table of acceptance criteria and reported device performance related to AI/ML, sample size for test sets, data provenance, number and qualifications of experts, adjudication methods, MRMC studies, standalone performance, and ground truth establishment for AI/ML models are not applicable to the content provided.
The document focuses on the substantial equivalence of the new Electric Breast Pump to a legally marketed predicate device (Spectra S3 Plus Breast Pump) based on non-clinical performance testing, electrical safety, electromagnetic compatibility, biocompatibility, and software verification.
Here's an analysis of the provided document in the context of device acceptance criteria, but note it's for a physical medical device (breast pump), not an AI/ML algorithm.
Analysis of Acceptance Criteria and Study for the Electric Breast Pump (from the provided document)
Since the document describes a physical medical device (Electric Breast Pump) and not an AI/ML device, the questions regarding AI/ML-specific acceptance criteria, test sets, expert ground truth, MRMC studies, and training data are not directly applicable. However, I can extract the closest parallels and relevant information:
1. A table of acceptance criteria and the reported device performance:
The document doesn't present a formal table of acceptance criteria with corresponding performance results in the typical machine learning sense. Instead, it describes various performance tests that were conducted and implied acceptance through successful completion.
Implied Acceptance Criteria and Reported Performance (from Section 7: SUMMARY OF NON-CLINICAL PERFORMANCE TESTING):
| Test Category | Implied Acceptance Criteria | Reported Performance |
|---|---|---|
| Electrical Safety & EMC | Compliance with relevant IEC standards (IEC 60601-1, IEC 60601-1-11, IEC 60601-1-2, IEC 62133). | Not explicitly detailed in numerical results, but implied that the device met these standards as it supports a determination of substantial equivalence. |
| Biocompatibility | User-contacting materials must be non-cytotoxic, non-sensitizing, and non-irritating per ISO 10993. | "The user-contacting materials were shown to be non-cytotoxic, non-sensitizing, and non-irritating." (Success) |
| Software Verification | Compliance with FDA Guidance document "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices." | Not explicitly detailed, but implied that software verification and validation were conducted in accordance with the guidance, supporting substantial equivalence. |
| Vacuum Pressure & Cycle Rate | Functional operation across all settings for each model within acceptable ranges (implicitly comparable to predicate). | "Vacuum pressure and cycle rate testing was conducted at all settings for each device model." (Implied successful performance, as it contributes to substantial equivalence claim). The comparison table (Section 6) shows specific ranges for the subject device (e.g., Stimulation Mode: 70-105 cycles/min, 37.5-187.5 mmHg). |
| Backflow Prevention | Liquid must not backflow into the tubing/pump. | "Backflow testing was conducted to demonstrate that liquid does not backflow into the tubing/pump." (Success) |
| Use Life Testing | Maintenance of vacuum level and battery performance over time (implicitly throughout intended lifespan). | "Use life testing of vacuum level and battery performance" was conducted. (Implied successful performance.) |
| Battery Status Indicator | Indicator remains functional during stated battery life. | "Battery status indicator testing was conducted to demonstrate that the battery status indicator remains functional during its stated battery life." (Success) |
2. Sample size used for the test set and the data provenance:
- Sample Size: The document does not specify the sample size for each performance test (e.g., how many units were tested for electrical safety, how many materials samples for biocompatibility). The testing appears to be primarily laboratory-based engineering and material testing rather than a clinical trial with human subjects for performance evaluation.
- Data Provenance: Not explicitly stated, but the testing would have been conducted by or on behalf of the manufacturer, Guangdong Horigen Mother & Baby Products Co., Ltd., likely in China where the company is based. The data would be retrospective in the sense that it was generated prior to the 510(k) submission.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- This question is not applicable as there is no "ground truth" in the context of an AI/ML model being established by human experts for this physical device. The "ground truth" for these tests are objective measurements based on engineering standards and physical laws. For instance, the ground truth for electrical safety is whether the device adheres to predefined safety limits as measured by calibrated equipment.
4. Adjudication method for the test set:
- Not applicable for a physical device's non-clinical performance testing. Adjudication methods (like 2+1 or 3+1) are common in clinical studies or for establishing ground truth in AI/ML tasks where human interpretation is involved. Here, results are determined by instrumentation and adherence to standards.
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:
- Not applicable. This pertains to AI/ML algorithm evaluation in clinical decision-making. The Electric Breast Pump is a direct-use medical device, not an AI assistance tool.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Not applicable. This question refers to AI/ML algorithm performance. The "performance testing" described in the document (vacuum pressure, backflow, etc.) is the device's inherent function, which could be considered "standalone" in a very broad sense but not in the context of an AI algorithm.
7. The type of ground truth used:
- For this device, "ground truth" is established through:
- Engineering Standards and Specifications: Metrics like suction strength (mmHg), cycle speed (cycles/min), electrical safety parameters (e.g., leakage current limits), and material properties (cytotoxicity, sensitization).
- Objective Measurement: Performance values are measured using calibrated equipment against defined thresholds or ranges from relevant international standards (e.g., IEC, ISO).
- Functional Demonstrations: For tests like backflow prevention, the "ground truth" is simply the observable fact that liquid does not backflow.
8. The sample size for the training set:
- Not applicable. This concept belongs to AI/ML model development. For a physical device, there isn't a "training set" in the computational sense. Development involves design, prototyping, and iterative testing.
9. How the ground truth for the training set was established:
- Not applicable. As above, there's no "training set" for an AI/ML model here. The design and validation of the breast pump are based on established engineering principles, material science, and safety standards.
§ 884.5160 Powered breast pump.
(a)
Identification. A powered breast pump in an electrically powered suction device used to express milk from the breast.(b)
Classification. Class II (performance standards).