(94 days)
The Giraffe Incubator Carestation is an Infant Incubator. Incubators provide heat in a controlled manner to neonates who are unable to thermo-regulate based on their own physiology. They achieve this by providing an enclosed temperature controlled environment to the infant. This device may incorporate a Servo Controlled Oxygen Delivery System. This is indicated to provide a stable oxygen concentration within the infant compartment at the value set by the operator (21-65%).
The Giraffe Incubator Carestation is an updated version of the cleared predicate Giraffe Incubator. The Giraffe Incubator Carestation is an enclosed infant bed, which provides thermal support for infants who are unable to provide for their own heat requirements. The device maintains the infant's temperature by circulating heated air within the closed bed compartment. The operator may select either the air or skin temperature control method. Depending on the control method selected, heat is regulated based on either the air temperature or the infant's skin temperature compared to the operator selected control temperature. Physical access to the patient is obtained through the side portholes or by opening one of the side doors. The Giraffe Incubator Carestation incorporates an optional weighing scale, Uninterruptible Power Supply (UPS) & Shuttle, Mounting Accessories Rail and Shelves and Storage drawers.
The provided text describes a 510(k) premarket notification for the "Giraffe Incubator Carestation CS1", which is an updated version of a predicate device, the "Giraffe Incubator". The focus of the modifications is primarily on updating the user interface from a graphical monochrome display to a digital touchscreen.
Based on the provided document, the device in question does not involve AI or machine learning algorithms, and therefore, the acceptance criteria and study information related to those aspects are not applicable. The device is a neonatal incubator, and the modifications are related to its hardware and user interface.
Consequently, many of the requested points regarding AI/ML device performance and studies cannot be answered from this document.
Here's what can be extracted:
1. A table of acceptance criteria and the reported device performance
The document does not provide a specific table of acceptance criteria with detailed performance metrics in the way one would for an AI/ML diagnostic device with quantifiable sensitivity, specificity, etc. Instead, it refers to compliance with voluntary standards and quality assurance measures for the modified device to demonstrate substantial equivalence to the predicate device.
The "reported device performance" is essentially the device's adherence to these standards and the successful verification and validation activities.
| Acceptance Criteria / Performance Aspect | Reported Device Performance |
|---|---|
| Risk Analysis | Complies with ISO 14971 |
| Design Reviews | Complies with OSR, ISO 13485 |
| Unit Level Testing | Module verification performed |
| Integration Testing | System verification performed |
| Software Testing | Verification and Validation according to IEC 62304 ("moderate" level of concern) |
| Performance Testing | Verification of performance specifications, including IEC 60601-2-19 |
| Safety and EMC Testing | Verification per ES 60601-1, IEC60601-1-2 |
| Usability Testing | Validation per IEC 62366 |
| Main System Control Software | Not changed from predicate |
| UI Functionality/Workflow | Graphical User Interface incorporates graphical elements compatible with current Giraffe functionality and workflow. Information displayed and device functionality/features are equivalent, with a different layout and touch screen functionality. |
| Power Supply | Upgraded from 75W to 120W to support new interface power requirements. |
| Device Visual Indicator Light | Updated |
| Hands Free Alarm Silencing (HFAS) | Capability introduced |
| Indications for Use & Intended Use | No change from predicate |
| Patient Contacting Materials | Identical to predicate |
| Function, Performance, Safety, Clinical Use | Unaffected by changes |
2. Sample size 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 as it is not an AI/ML study. The testing described is verification and validation of hardware and software components, not a clinical trial on a 'test set' of patient data in the typical sense.
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 provided and is not applicable for a device that is not an AI/ML diagnostic tool. Validation activities would involve engineers and testers.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
This information is not provided and is not applicable.
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, a multi-reader multi-case (MRMC) comparative effectiveness study was not done. This device is not an AI-assisted diagnostic tool.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
This information is not applicable. The device is an incubator, not a standalone algorithm.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
For the hardware and software modifications, the "ground truth" would be engineering specifications, established medical device safety and performance standards (like IEC 60601-2-19), and the functional requirements derived from the predicate device. These are verified through various testing methodologies described (module verification, system verification, etc.). It's not a clinical 'ground truth' in the diagnostic sense.
8. The sample size for the training set
This information is not applicable as there is no mention of a training set, the device is not an AI/ML product.
9. How the ground truth for the training set was established
This information is not applicable as there is no mention of a training set, the device is not an AI/ML product.
In summary, the provided document describes a 510(k) submission for an updated medical device (a neonatal incubator) with hardware and user interface modifications, not an AI/ML-driven device. Therefore, most of the detailed questions related to AI/ML study design and performance metrics found in your request are not addressed by this document. The safety and effectiveness are established through compliance with existing standards and verification/validation testing against the predicate device.
§ 880.5400 Neonatal incubator.
(a)
Identification. A neonatal incubator is a device consisting of a rigid boxlike enclosure in which an infant may be kept in a controlled environment for medical care. The device may include an AC-powered heater, a fan to circulate the warmed air, a container for water to add humidity, a control valve through which oxygen may be added, and access ports for nursing care.(b)
Classification. Class II (performance standards).