(128 days)
The Philips Avent single/double electric breast pump Advanced is intended to express and collect milk from the breast of a lactating woman, and to alleviate engorgement of the breast. The device is intended for a single user.
The Philips Avent Single/Double electric breast pump Advanced is intended to express and collect milk from the breast of a lactating woman. The device is intended for a single user.
The subject devices are for repeated use by a single user and are for use in home and professional healthcare environments. The devices are not sterile.
The subject devices are electrically powered single (Single Advanced) and double (Double Advanced) breast pumps consisting of the following key components: a motor unit with a press-button user interface, and expression kit with milk collection container (double pump: two kits and containers) connected with the motor unit via a silicone tube. The motor unit operates on embedded software. Software updates by end-users are not supported.
The breast pump extracts milk from the breasts by creating a seal around the nipple and applying and releasing suction to the nipple. The milk is collected in a milk collection container, which can be used for storage. To prevent milk from flowing into the vacuum system, the expression kit includes a silicone diaphragm that physically separates the milk-contacting pathway from the vacuum system.
The motor unit operates on an external mains adapter that is provided with the system via a micro-USB type connection. Models SCF392 and SCF394 include a rechargeable battery that can be used for device operation. The rechargeable battery can be charged from the external mains adapter if the motor unit is not in operation.
The expression kit is provided in two types: cushion-type and flange-type.
The cushion-type expression kit has a silicone cushion which is mounted on the expression kit pump body. The cushion comes into contact with the breast for the expression session.
In the flange-type expression kit, the silicone cushion is integrated in a rigid frame. This integrated part (flange) can be attached to the pump body with a screw connection. The silicone part comes into contact with the breast for the duration of the expression. The rigid frame is not in contact with the breast.
All other components of the subject devices are not in contact with the breast.
The provided document is a 510(k) summary for the Philips Avent Single/Double electric breast pump Advanced. This type of document is a premarket notification to the FDA to demonstrate that a device is substantially equivalent to a legally marketed predicate device.
The questions you are asking typically relate to the performance of AI/ML-driven medical devices in diagnostic or screening applications, where metrics like sensitivity, specificity, and reader performance are critical.
This document, however, describes a powered breast pump, which is a physical device, not an AI/ML diagnostic tool. Therefore, many of your specific questions regarding acceptance criteria and studies (e.g., sample size for test set, data provenance, number of experts for ground truth, adjudication method, MRMC studies, standalone performance, training set size, ground truth for training set) are not applicable to the information provided for this type of medical device.
I can, however, extract the information that is relevant to the document for a medical device such as a breast pump, which focuses on safety and performance in a different context.
Here's the relevant information based on the provided text:
1. A table of acceptance criteria and the reported device performance
The document doesn't provide a direct "acceptance criteria table" with numerical thresholds for clinical performance metrics (like accuracy for an AI device). Instead, it lists various engineering and safety standards that the device complies with, along with technical specifications that define its functional performance. The "reported device performance" is compliance with these standards and the specified operating ranges.
| Category | Acceptance Criteria / Standard | Reported Device Performance |
|---|---|---|
| General Compliance | Substantial equivalence to predicate device (K161532) in terms of indications for use, safety, and effectiveness. | "The performance testing described above demonstrate that the subject devices are as safe and effective as the predicate device and supports a determination of substantial equivalence." |
| Electrical Safety | IEC 60601-1:2005 (3rd Edition) with US deviations per AAMI/ANSI ES60601-1:2005/(R)2012 and A1:2012, C1:2009(R)2012 and A2:2010/(R)2012 (Consolidated Text) | |
| IEC 60601-1-11 Edition 2.0 2015-01 (for use in the home) | Complies with IEC 60601-1:2005 and IEC 60601-1-11 Edition 2.0 2015-01. | |
| Electromagnetic | IEC 60601-1-2:2014 | Complies with IEC 60601-1-2:2014. |
| Software | FDA Guidance Document "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices." (May 11, 2005) | Software Verification and Validation Testing performed as recommended in the FDA Guidance Document. |
| Biocompatibility | ISO-10993 (including cytotoxicity, sensitization, and irritation tests: ISO 10993-5:2009, ISO 10993-10:2010) | Complies with ISO-10993 (cytotoxicity, sensitization, irritation). "All milk contacting components are compliant with 21 CFR 174-179, 21 CFR 177.1520 and 21 CFR 177.2600." |
| Lithium-Ion Battery | IEC 62133-2 Edition1.0 2017-02 Secondary cells and batteries containing alkaline or other non-acid electrolytes - Safety requirements for portable sealed secondary cells, and for batteries made from them, for use in portable applications - Part 2: Lithium systems. | Lithium-Ion Battery Testing according to IEC 62133-2 Edition1.0 2017-02. |
| Backflow Protection | N/A (implicit: effective separation of milk-contacting pathway from vacuum system) | Backflow protection testing performed. Device features a silicone diaphragm on the expression kit that separates the vacuum system of the motor unit from milk-contacting parts (similar to predicate). |
| Vacuum Performance | Stimulation Mode: Vacuum range for predicate: 127 ± 15 mmHg. | |
| Expression Mode: Vacuum range for predicate: -168 to -250 mmHg. (Subject device aims to fulfill comparable function within safe limits.) | Stimulation Mode: -45 to -150 mmHg | |
| Expression Mode: -45 to -270 mmHg | ||
| (Note: These ranges are comparable to the predicate. The subject device's range for expression is wider, extending to a higher suction level, but this is presented as a difference not necessarily an exceedance of criteria.) | ||
| Cycle Speed | Stimulation Mode: Cycle speed for predicate: 85 to 120 cycles/min. | |
| Expression Mode: Cycle speed for predicate: 42 to 53 cycles/min. (Subject device aims to fulfill comparable function within safe limits.) | Stimulation Mode: 105 to 120 cycles/min | |
| Expression Mode: 53 to 85 cycles/min | ||
| (Note: The subject device's cycle speeds are generally within or overlapping the predicate device's ranges, or considered functionally equivalent by the FDA.) | ||
| Use-life | N/A (implicit: device maintains performance over its expected lifetime) | Use-life testing performed. |
2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
This information is not provided in the document. The document describes compliance with engineering and electrical standards through testing, not a clinical study with human subjects for performance evaluation in the way an AI diagnostic device would be tested. The tests are focused on the device's hardware and software functionality, and material safety.
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)
This information is not applicable/not provided. Ground truth established by medical experts is paramount for diagnostic AI/ML devices. For a breast pump, "ground truth" relates to physical and electrical performance, and biocompatibility, which are assessed through engineering and materials science tests, not expert clinical consensus on interpretations.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
This information is not applicable/not provided. Adjudication methods are used in studies involving subjective interpretation, typically by multiple human readers, which is not the case for device safety and performance testing for a breast pump.
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
An MRMC study is not applicable/not provided. This type of study is relevant for AI-assisted diagnostic tools. The breast pump is a therapeutic/supportive device, not a diagnostic one.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
This is not applicable for this device in the context of typical AI/ML evaluation. While the device contains software, its "performance" is mechanical and electrical, not an AI algorithm making independent diagnostic decisions. The software verification and validation are for the embedded control software.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
The "ground truth" for this device's performance relies on objective measurements and adherence to established engineering, electrical, and biocompatibility standards. For example:
- Electrical safety tests verify voltage, current, and insulation against specified limits.
- EMC tests verify emission and immunity levels against regulatory standards.
- Vacuum/cycle performance tests measure actual vacuum levels and cycles per minute against the device's specified operating ranges.
- Biocompatibility tests use standardized laboratory assays to detect cytotoxicity, sensitization, and irritation.
8. The sample size for the training set
This information is not applicable/not provided. There is no "training set" in the context of an AI/ML algorithm for this breast pump. The software is likely deterministic control logic, not a machine learning model that requires training data.
9. How the ground truth for the training set was established
This information is not applicable/not provided due to the absence of a machine learning training set.
§ 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).