(213 days)
The DINAMAP Compact Monitor is intended to monitor a single adult, pediatric or neonatal patient's vital signs at the bedside. Vital signs parameters include noninvasive blood pressure (systolic, diastolic and mean arterial pressure), pulse rate, temperature and/or oxygen saturation (pulse oximetry). The portable device is designed for use in numerous clinical settings, primarily in various hospital departments such as emergency, radiology, recovery, medical/surgical, labor & delivery, endoscopy, cardiac step-down, etc. and can also be used during many specialized procedures in satellite areas, or in ambulatory surgery centers, physicians' offices or alternate care settings.
The DINAMAP Compact Monitor is a prescription device intended for use only by health care professionals. Three configurations of the monitor with the following vital signs parameters will be available: Noninvasive Blood Pressure and Heart Rate, Noninvasive Blood Pressure and Heart Rate, and Predictive Oral/Rectal Thermometry Noninvasive Blood Pressure and Heart Rate, Predictive Thermometry, and Nellcor® Pulse Oximetry and Heart Rate In addition, the currently-marketed Sherwood Medical Inc. FirstTemp™ Genius™ Infrared Tympanic Thermometry Unit (K920713) may be physically attached to the side of (but not electrically integrated with) the DINAMAP Compact Monitor. The device is designed for monitoring adult, pediatric and neonatal patients in hospital, outpatient surgery center, physician office and/or alternate healthcare settings. It is portable and capable of operation from an external AC mains power source or an internal lead-acid rechargeable battery. An optional printer is also available. The Compact Monitor provides connection for the currently marketed Johnson & Johnson Medical, Inc. (JJMI, formerly Critikon, Inc.) OBSERVER* Central Station (K933404), other monitoring devices, a remote display, data collection system, remote alarm and/or host information system.
The DINAMAP Compact Monitor is a prescription device intended for use by healthcare professionals for monitoring vital signs (noninvasive blood pressure, pulse rate, temperature, and/or oxygen saturation) in adult, pediatric, and neonatal patients in various clinical settings.
Here's an analysis of the acceptance criteria and supporting studies based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
The provided text for the K970182 submission does not explicitly state numerical acceptance criteria for each vital sign parameter (e.g., specific accuracy ranges for blood pressure or temperature). Instead, it states that "Several clinical studies were conducted which demonstrate safety and effectiveness" for:
- Predictive Thermometry Accuracy
- Adult Noninvasive Blood Pressure Accuracy
- Pediatric Noninvasive Blood Pressure Accuracy
- Neonatal Noninvasive Blood Pressure Accuracy
- Pulse Oximetry (implicitly covering accuracy for this parameter, though "accuracy" isn't explicitly listed next to it as for the others)
The document concludes that the device is "safe, effective and substantially equivalent to the predicate devices." This implies that the performance in these clinical studies met the expected safety and effectiveness benchmarks, likely derived from the predicate devices or relevant standards at the time (though these specific benchmarks are not detailed).
Therefore, a table with specific numerical acceptance criteria and reported performance cannot be fully constructed from the provided text.
2. Sample Size Used for the Test Set and Data Provenance
The document mentions "Several clinical studies" for predictive thermometry accuracy, and adult, pediatric, and neonatal noninvasive blood pressure accuracy. However, no specific sample sizes for these test sets are provided in the current document. The data provenance (e.g., country of origin, retrospective or prospective nature) is also not mentioned.
3. Number of Experts Used to Establish Ground Truth and Qualifications
The document does not specify the number of experts used or their qualifications for establishing ground truth for any of the clinical studies mentioned.
4. Adjudication Method for the Test Set
The document does not describe any adjudication method (e.g., 2+1, 3+1, none) used for the test sets.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done
This device is a vital signs monitor, not an AI-assisted diagnostic imaging device. Therefore, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study comparing human readers with and without AI assistance is not applicable and was not performed. The device itself performs the measurements; it does not assist human interpretation of complex cases in the same way AI might for medical imaging.
6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) was Done
The device is inherently a "standalone" system in its measurement function, as it provides direct readings of vital signs. The clinical studies mentioned (e.g., "Predictive Thermometry Accuracy," "Adult Noninvasive Blood Pressure Accuracy") would inherently assess the algorithm's performance in generating these measurements independently. There isn't a "human-in-the-loop" for the initial measurement generation itself; humans then interpret and act upon the device's numerical output. Therefore, yes, standalone performance (algorithm only) was assessed for each vital sign parameter.
7. The Type of Ground Truth Used
The document does not explicitly state the type of ground truth used for each parameter. However, for a vital signs monitor:
- Noninvasive Blood Pressure: Ground truth would typically be established by invasive blood pressure measurements (e.g., arterial line) or a highly accurate non-invasive reference standard (e.g., mercury sphygmomanometer with auscultation by trained observers), often performed simultaneously or sequentially with the device under test.
- Pulse Oximetry: Ground truth would typically involve co-oximetry of arterial blood samples.
- Predictive Temperature: Ground truth would likely be established by a continuous core body temperature measurement device or a highly accurate traditional thermometer (e.g., rectal probe for a set duration) against which the "predictive" algorithm's output is compared.
8. The Sample Size for the Training Set
The document does not specify any sample sizes for a "training set." This type of conventional "training set" concept is more common in modern machine learning-based devices. For this device, developed in the mid-1990s, the development process would have involved engineering design, calibration, and verification testing, rather than a distinct "training set" in the AI sense. The clinical studies mentioned serve as the validation evidence.
9. How the Ground Truth for the Training Set was Established
As no specific "training set" is described in the context of modern AI/ML development, the method for establishing ground truth for such a set is not applicable/described. The device's algorithms were likely developed and refined through engineering principles, calibration studies, and internal testing, with the clinical studies serving as external validation against observed clinical states (ground truth as described in point 7).
§ 870.1025 Arrhythmia detector and alarm (including ST-segment measurement and alarm).
(a)
Identification. The arrhythmia detector and alarm device monitors an electrocardiogram and is designed to produce a visible or audible signal or alarm when atrial or ventricular arrhythmia, such as premature contraction or ventricular fibrillation, occurs.(b)
Classification. Class II (special controls). The guidance document entitled “Class II Special Controls Guidance Document: Arrhythmia Detector and Alarm” will serve as the special control. See § 870.1 for the availability of this guidance document.