(262 days)
The Youha electric breast pumps (The INs, The INs Gen2, The INs NEXT, and P3) and BEBEBAO electric breast pump (P1s) are powered breast pumps intended to be used by lactating women to express and collect milk from their breasts. They are intended for a single user.
The subject devices are wearable-style breast pumps designed for lactating women to express and collect milk from the breast. They are electrically powered, software controlled, digital pumps for a single user. The subject devices include The INs, The INs Gen 2, The INs NEXT, P1s, and P3 models, which are capable of expression, massage, and mixed modes with ten associated suction levels for each. All five models have a single pumping configuration and can be operated in 'normal' or 'quiet' modes.
Massage, expression, and mixed pumping modes consist of 10 vacuum levels. Each Youha and BEBEBAO electric breast pump model is capable of providing vacuum levels from 40-190 mmHg with cycling rates from 90-110 cycles per minute in massage mode, vacuum levels from 80-280 mmHg with cycling rates from 40-75 cycles per minute in expression mode, and vacuum levels from 80-280 mmHg with cycling rates from 6-46 cycles per minute in mixed mode. The Youha electric breast pump is charged with a 5 V DC adaptor and powered by an internal rechargeable lithium-ion polymer battery. The motor unit operates on embedded software. Software updates by end-users are not supported. The subject devices do not have wireless capability or other external functionality (i.e., no Bluetooth or mobile application). The subject device is for repeated use by a single user in a home environment. The device is provided not sterile.
The motor unit operates on a rechargeable battery and can function when charging.
The breast pump expresses milk by creating a seal around the nipple using the breast shield 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, a backflow protection membrane physically separates the milk-contacting pathway from the vacuum system.
All other components (i.e., motor unit/housing) of the subject device are not in contact with the breast. All milk contacting components are compliant with 21 CFR 174-179.
The provided FDA 510(k) summary for the Youha electric breast pumps (K242725) outlines the device's technical specifications and the non-clinical performance testing conducted to demonstrate substantial equivalence to a predicate device. However, this document does not detail acceptance criteria and a study proving that the device meets those acceptance criteria in the context of an AI/ML medical device, as it is a powered breast pump, not an AI/ML system.
The prompt's request for detailed information such as "sample size used for the test set," "number of experts used to establish ground truth," "MRMC comparative effectiveness study," and "standalone (algorithm only) performance" are typical requirements for the validation of AI/ML-driven medical devices, particularly those involving image analysis or diagnostic support.
Since the Youha electric breast pump is a physical device with a software component that controls its operation (massage, expression, mixed modes, vacuum levels, cycle speeds), and not an AI/ML diagnostic or therapeutic device, the requested information (acceptance criteria for AI performance, clinical study results comparing AI-assisted vs. non-AI scenarios, etc.) is not applicable to this type of submission.
Therefore, I cannot fulfill the request to describe the acceptance criteria and the study that proves the device meets the acceptance criteria (as defined for an AI/ML device) using the provided document. The document focuses on performance testing relevant to a mechanical/electronic medical device, such as biocompatibility, electrical safety, electromagnetic compatibility, software validation (at a basic documentation level, not AI performance), vacuum level verification, backflow protection, use life, and battery performance.
To answer your specific questions based on the provided document and its scope:
-
A table of acceptance criteria and the reported device performance:
The document describes various performance tests and implies their acceptance criteria are met (e.g., "Vacuum level verification testing at each mode/cycle demonstrated that the devices meet mode/cycle specifications."). However, it does not present these in a formal table of acceptance criteria vs. specific reported values in the way one would for an AI/ML device's diagnostic performance (e.g., sensitivity, specificity, AUC).- Examples of Implicit Acceptance Criteria and Performance (derived from "Performance Testing" section):
Acceptance Criteria (Implied) Reported Device Performance Device meets mode/cycle specifications for vacuum levels. "Vacuum level verification testing at each mode/cycle demonstrated that the devices meet mode/cycle specifications." No liquid backflow into tubing. "Backflow protection testing was conducted to verify liquid does not backflow into the tubing." Device maintains specifications throughout proposed use life. "Use life testing was conducted to demonstrate that the device maintains its specifications throughout its proposed use life." Battery remains functional during stated battery use-life. "Battery performance testing was conducted to demonstrate that the battery remains functional during its stated battery use-life." Battery status 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."
- Examples of Implicit Acceptance Criteria and Performance (derived from "Performance Testing" section):
-
Sample sized used for the test set and the data provenance: Not applicable in the context of AI/ML test sets. The testing here refers to physical device units rather than data samples for an algorithm. The document does not specify the number of physical units tested for each non-clinical test.
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable. Ground truth as typically defined for AI/ML (e.g., for disease detection or image interpretation) is not established for a breast pump's functional performance.
-
Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not applicable. This refers to consensus methods for establishing ground truth in AI/ML studies.
-
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 is specific to AI/ML devices that assist human interpretation.
-
If a standalone (i.e. algorithm only without human-in-the loop performance) was done: Not applicable. The device's software controls its mechanical function; it's not a standalone diagnostic algorithm.
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc): Not applicable in the AI/ML sense. The "ground truth" for this device's performance would be engineering specifications and validated physical measurements (e.g., actual vacuum levels vs. specified, absence of backflow).
-
The sample size for the training set: Not applicable. The "software" mentioned refers to embedded code controlling the hardware, not a machine learning model that requires a training set.
-
How the ground truth for the training set was established: Not applicable for the reasons stated above.
In summary, the provided document details a 510(k) submission for an electric breast pump, which is a traditional medical device regulated under 21 CFR 884.5160 as a Class II powered breast pump. The testing described (biocompatibility, electrical safety, EMC, software validation at a basic level, and performance tests for vacuum, backflow, life, and battery) is appropriate for this type of device. The questions posed in the prompt are tailored for AI/ML device submissions, which are not relevant to this specific FDA clearance document.
§ 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).