(116 days)
Cerner FetaLink+ is a software-only application intended for use on iOS mobile devices by obstetrical healthcare clinicians to view near real time the simultaneous measurement of fetal heart rate(s) and uterine contractions waveforms in one view. FetaLink+transforms the ongoing measurements into a visual wave display which conveys the frequency, duration and relative strength of uterine contractions combined with the patient data of pregnant women in the antepartum and/or intrapartum phases of pregnancy.
Cerner FetaLink+ is the software application that runs on the user's iPhone or iPad. The application displays patient clinical waveform data including maternal heart rates, maternal oxygen saturation, maternal blood pressure, and uterine contractions. Within the application, the user can view annotations associated to waveform data.
The provided text describes the Cerner FetaLink+ device, its intended use, and a comparison to a predicate device (AirStrip OB®). However, it does not contain information about specific acceptance criteria, a study proving the device meets these criteria, or a detailed breakdown of performance metrics and ground truth establishment typically found in a clinical performance study.
The document refers to various types of internal testing but none of these are presented as a formal study with acceptance criteria and reported performance metrics.
Here is a breakdown of what can be extracted and what information is missing based on your request:
1. A table of acceptance criteria and the reported device performance
No specific quantitative acceptance criteria or reported device performance metrics (e.g., accuracy, sensitivity, specificity) are provided in the document for the FetaLink+ device. The document states:
"Cerner's validation demonstrated that all functional requirements and hazard analysis software mitigations for Cerner FetaLink+ were executed and the expected results achieved. Based on the results of the testing performed, Cerner FetaLink+ was evaluated to be a safe and effective device for use in a live patient environment."
This is a general statement rather than a specific performance metric against a defined acceptance criterion.
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. The text mentions "functional testing," "formative and summative usability," and "interference testing," but does not specify the sample size of data or patients used for these tests, nor the provenance of any data if it were used in performance evaluation.
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 in the document. The document describes the device as displaying data, not making diagnoses or interpretations that would require expert ground truth for performance evaluation in the typical sense of AI/CADe devices.
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set
This information is not provided in the 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
There is no mention of a multi-reader multi-case (MRMC) comparative effectiveness study or any assessment of human reader improvement with or without AI assistance. The device is described as a display tool, not an AI-driven diagnostic aid in the traditional sense that would typically involve a MRMC study for AI assistance.
6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done
The device itself is a "software-only application intended for use on iOS mobile devices by obstetrical healthcare clinicians to view near real time the simultaneous measurement of fetal heart rate(s) and uterine contractions waveforms." It is an information display tool, not an algorithm that performs standalone analysis or makes diagnoses. Therefore, the concept of "standalone performance" for an algorithm that operates without human-in-the-loop is not directly applicable in the way it would be for a CADe/AI device. The "performance" here relates to the accurate display of data, which was likely covered by the "functional testing."
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
As the device's primary function is to display waveform data, the "ground truth" for its performance would likely refer to the accuracy of the displayed data compared to the source data from the monitoring devices. This type of ground truth (e.g., accuracy of data transmission and display) is implied by "functional testing" but not explicitly detailed with specific methods like expert consensus or pathology.
8. The sample size for the training set
This information is not applicable/not provided. The device, as described, is a data display application. There is no indication that it utilizes machine learning or AI models that would require a "training set" in the context of typical AI device development.
9. How the ground truth for the training set was established
This information is not applicable/not provided for the same reason as point 8.
Summary of what is present:
The document focuses on:
- Description of the Device: FetaLink+ displays continuous fetal heart rate, uterine contraction waveforms, and other maternal vital signs and clinical data on iOS devices.
- Intended Use: For obstetrical healthcare clinicians to view near real-time and historical waveform data.
- Comparison to Predicate Device: Detail similarities in functionality with AirStrip OB®.
- Performance Testing (General): Mentions "functional testing," "hazard analysis," "unit testing," "regression testing," "exploratory testing," "assembly testing," "formative and summative usability," and "interference testing."
- Conclusions: States that all functional requirements were met, usability issues were mitigated, and the device was found to be "adequately safe and effective."
In conclusion, while the document confirms that testing was conducted and the device was deemed safe and effective, it lacks the specific, quantifiable acceptance criteria and detailed study results (including sample sizes, ground truth methods, and expert involvement) that would be expected for a comprehensive performance study of a device making diagnostic-type claims or using advanced AI. The device appears to be a data display tool, and its "performance" testing likely centered on accurate data presentation and application functionality, rather than diagnostic accuracy against a clinical ground truth.
§ 884.2740 Perinatal monitoring system and accessories.
(a)
Identification. A perinatal monitoring system is a device used to show graphically the relationship between maternal labor and the fetal heart rate by means of combining and coordinating uterine contraction and fetal heart monitors with appropriate displays of the well-being of the fetus during pregnancy, labor, and delivery. This generic type of device may include any of the devices subject to §§ 884.2600, 884.2640, 884.2660, 884.2675, 884.2700, and 884.2720. This generic type of device may include the following accessories: Central monitoring system and remote repeaters, signal analysis and display equipment, patient and equipment supports, and component parts.(b)
Classification. Class II (performance standards).