(343 days)
The Lucina-Melodi Powered Breast Pump is intended to express and collect milk from the breasts of lactating women.
The Lucina-Melodi Powered Breast Pump is an advanced breast pump powered by a smart software. It has a 2 phase suction cycle. It is portable and is battery powered, with a rechargeable battery build in the system. It weighs less than 1kg. It is intended for single user usage, and can be use on both breasts at the same time. The device has a build in color LCD screen, and easy to use buttons and graphic user interface.
The device can be run on battery power and also while plugged in to the AC adapter. Internally, it gets its suction from a diaphragm motor. The PCB board will control the speed and the suction of the motor to provide optimal suction or based on the settings that the user provided. The device has a smart 2 phase software running which provide 2 different speeds to the user. Phase 1 runs at a higher speed than phase 2. The device has a large color LCD screen, with 6 easy to use buttons.
The requested information described in the acceptance criteria and study proving device performance is not fully present in the provided text for the Lucina-Melodi Powered Breast Pump (K102516). This document is a 510(k) premarket notification summary, which focuses on demonstrating substantial equivalence to a predicate device rather than providing a detailed clinical study report typically associated with AI/software performance.
However, I can extract the relevant information that is available about the "bench testing" that served as the primary evidence for substantial equivalence.
Here's the breakdown of what can be inferred and what is explicitly stated:
1. Table of Acceptance Criteria and Reported Device Performance
The device is a powered breast pump, and the "acceptance criteria" presented are essentially performance characteristics compared to a predicate device. The performance data is from "bench tests" rather than clinical outcomes related to milk expression efficiency in lactating women.
| Acceptance Criteria (Implied) | Reported Device Performance (Lucina-Melodi) | Predicate Device (Medela Pump In Style Advance) Performance |
|---|---|---|
| Vacuum Range | 50-250 MMHG | 50-250 MMHG |
| Pressure Consistency & Stability | Consistent and stable at different levels | (Not explicitly stated for predicate in this context, but implied similar) |
| Peak Pressure Consistency | Consistent throughout test at several levels | (Not explicitly stated for predicate in this context, but implied similar) |
| Cycles Per Minute (CPM) Consistency | Consistent over time | (Not explicitly stated for predicate in this context, but implied similar) |
Note on "Acceptance Criteria" for a breast pump: For a device like a breast pump, the primary acceptance criteria would revolve around safety and effectiveness in expressing milk. While the 510(k) focuses on substantial equivalence of technical specifications, a full "acceptance criteria" for clinical performance (e.g., milk volume, comfort) would typically involve clinical studies, which are not detailed here. The "reported device performance" in this context refers to the bench test results demonstrating comparable mechanical function.
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size for Test Set: Not explicitly stated. The document refers to "bench testing" and "data collected," but no specific number of units tested, duration of tests, or number of data points is provided.
- Data Provenance: The device was developed by Genadyne Biotechnologies Inc. (Great Neck, NY, USA). The bench tests were conducted to support the 510(k) submission, indicating the data was generated specifically for regulatory purposes. The data is retrospective in the sense that it was collected as part of the device development and testing process prior to submission, not from an ongoing, prospective clinical trial.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of those Experts
- Number of Experts: Not applicable/not stated. For a mechanical device like a breast pump, "ground truth" is established through engineering and performance testing against specifications and comparison to the predicate device, not typically through expert consensus readings of images or clinical assessments as might be seen with AI/diagnostic tools. The "experts" would be the engineers and technicians involved in the bench testing and design.
- Qualifications of Experts: Not stated.
4. Adjudication Method for the Test Set
- Adjudication Method: Not applicable/not stated. Adjudication methods like 2+1 or 3+1 are typically used in studies involving human interpretation (e.g., radiologists reading images) where disagreement among experts needs resolution to establish a ground truth. For a bench test of a mechanical device, performance is measured objectively against predefined parameters.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, and if so, what was the effect size of how much human readers improve with AI vs without AI assistance
- MRMC Study: No. This type of study is irrelevant for a powered breast pump. MRMC studies are used for diagnostic aids or AI tools that assist human interpreters (e.g., radiologists, pathologists). The Lucina-Melodi is a standalone mechanical device, not an AI-assisted diagnostic tool.
- Effect Size: Not applicable.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done
- Standalone Performance: Yes, in a sense. The "bench tests" represent the standalone performance of the device's mechanical functions (vacuum, pressure, cycles per minute). The device itself operates "standalone" in terms of its mechanical action. However, it's not an "algorithm only" device in the typical AI sense; it's a mechanical device with "smart software" controlling its function. The provided text describes the electrical and mechanical components and their direct output.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
- Type of Ground Truth: The ground truth for the bench tests was based on engineering specifications and direct measurements of mechanical parameters (vacuum range, pressure consistency, CPM consistency). This was then compared to the known specifications and performance characteristics of the legally marketed predicate device (Medela Pump In Style Advance Breast Pump). The goal was to show that the new device performed equivalently in these technical aspects to the predicate.
8. The sample size for the training set
- Sample Size for Training Set: Not applicable. For a 510(k) submission of a mechanical device, there isn't typically a "training set" in the context of machine learning. The device's "smart software" likely involves control algorithms that were designed and validated through engineering principles and testing, not by training on a dataset of "cases."
9. How the ground truth for the training set was established
- Ground Truth for Training Set: Not applicable. Since there's no "training set" in the AI/ML sense, there's no corresponding ground truth to establish for it. The control logic for the pump's "2 phase suction cycle" would have been developed based on scientific understanding of breast pump function and user needs, then validated through testing.
§ 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).