Search Results

The Lacevo Wearable Breast Pump (Model S70) is a powered breast pump intended to be used by lactating women to express and collect milk from their breasts. It is intended for a single user.

The Lacevo Wearable Breast Pump (Model S70) is a wearable powered breast pump designed for lactating woman to express and collect milk from the breast.

There are 4 modes available for the device, Expression mode, Massage mode, Auto mode and Stimulation mode. There is an LED status display for the S70, and the working mode and battery indicator are shown on the pump body. The user interface includes an on/off switch, mode selection/long press, and vacuum adjustment.

S70 is operated as a single or double pumping system, one on each breast. The pump is provided non-sterile and is reusable by a single user. The device is powered by rechargeable Li-ion battery (3.7V, 1200mAh). S70 is designed not to be used during charging.

The breast pump does not incorporate any off-the-shelf (OTS) software. The device incorporates embedded software which controls all the features of the product. All milk contacting components of the device are compliant with 21 CFR 177 which is applicable for the subject device.

The provided FDA 510(k) clearance letter for the Lacevo Wearable Breast Pump (Model S70) describes the device, its intended use, and a comparison to a predicate device, along with a summary of non-clinical performance testing. However, it does not detail acceptance criteria for studies related to AI/ML performance validation, nor does it describe an AI/ML model performance study. This is expected, as a breast pump, while it may contain embedded software, is not a device typically cleared based on complex AI/ML algorithms requiring a comprehensive AI/ML performance study as described in your prompt.

Therefore, I cannot provide the requested information regarding AI/ML acceptance criteria, study details, sample sizes for test/training sets, expert qualifications, ground truth establishment, or MRMC studies, because this information is not present in the provided document.

The document focuses on the mechanical, electrical, and biocompatibility safety and efficacy of a medical device (a breast pump), rather than the performance of an AI/ML algorithm.

However, I can extract information regarding the device's general performance testing acceptance criteria and validation, which are relevant to its substantial equivalence.

Device: Lacevo Wearable Breast Pump (Model S70)

Based on the provided document, here's a description of the acceptance criteria and the studies that prove the device meets these criteria. Please note, as mentioned, this is not an AI/ML performance study.

1. A table of acceptance criteria and the reported device performance (Non-AI/ML specific)

2. Sample size used for the test set and the data provenance:

• Sample Size for Testing: The document does not specify the number of units or samples used for the performance, biocompatibility, electrical safety, or software testing. It generally states that "Bench performance testing was conducted" and "Electrical safety and EMC testing were conducted on the Wearable Breast Pump device, consisting of all the modules and accessories in the system."
• Data Provenance: Not specified, but generally, these tests would be conducted internally by the manufacturer (Shenzhen TPH Technology Co., Ltd. in CHINA) or by accredited third-party laboratories.

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 is not applicable as the studies described are device performance tests and not AI/ML algorithm validation requiring expert-derived ground truth. The "ground truth" for these tests are objective measurements against engineering specifications and international standards.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:

• Not applicable, as this refers to adjudication for expert consensus on ground truth in studies often involving image interpretation or complex clinical assessments, which is not the nature of the tests described in this document.

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:

• No, an MRMC study was not done. This type of study is relevant for AI-assisted diagnostic or interpretative devices, which this breast pump is not.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:

• Not applicable as this is a physical device, not an AI/ML algorithm. The embedded software controls the device's functions, but it's not a standalone AI model being evaluated.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc):

• The "ground truth" for these performance tests are the pre-defined engineering specifications for vacuum pressure, cycle speed, battery life, etc., and the requirements of the relevant international standards (e.g., ISO 10993 for biocompatibility, IEC 60601 series for electrical safety). The device performance is measured and compared directly against these objective, established criteria.

8. The sample size for the training set:

• Not applicable. This is not an AI/ML device that requires a training set for model development. The software mentioned is embedded control software, not a learned AI model.

9. How the ground truth for the training set was established:

• Not applicable, as there is no AI/ML training set mentioned or implied by the device's description.

Ask a specific question about this device