(249 days)
The Masimo Rad-97 and Accessories can communicate with network systems for supplemental remote viewing and alarming (e.g., at a central station, the Masimo Rad-97 and Accessories are indicated to provide the continuous non-invasive monitoring data obtained from the Masimo Rad-97 and Accessories for functional oxygen saturation of arterial hemoglobin (SpO2) and pulse rate (PR) to multiparameter devices for the display on those devices.
The Masimo Rad-97 and Accessories are indicated for the continuous non-invasive monitoring of functional oxygen saturation of arterial hemoglobin (SpO2) and pulse rate (PR) of adult, pediatric, and neonatal patients during both no motion and motion conditions, and for patients who are well or poorly perfused in hospital-type facilities, mobile, and home environments.
The Masimo Rad-97 and Accessories are indicated for the continuous non-invasive monitoring of carboxyhemoglobin saturation (SpCO) of adult, pediatric, and infant patients during no motion conditions in hospitals and hospital-type facilities. The Masimo Rad-97 and Accessories are not intended to be used as the sole basis for making diagnosis or treatment decisions related to suspected carbon monoxide poisoning; it is intended to be used in conjunction with additional methods of assessing clinical signs and symptoms.
The Masimo Rad-97 and Accessories are indicated for the continuous non-invasive monitoring of methemoglobin saturation (SpMet) of adult, pediatal patients during no motion conditions in hospitals and hospital-type facilities.
The Masimo Rad-97 and Accessories are indicated for the continuous non-invasive monitoring of total hemoglobin concentration (SpHb) of adult and pediatic patients during no motion conditions in hospital-type facilities.
The Masimo Rad-97 and Accessories are indicated for the continuous non-invasive monitoring of respiratory rate (RRa) for adult, pediatric, and neonatal patients during no motion conditions in hospitals, hospital-type facilities, home environments, and transport within healthcare facilities.
The optional Nomoline Capnography product family is intended to other medical backboard devices for monitoring of breath rate and CO2. The Nomoline Capnography product family is intended to a patient breathing circuit for monitoring of inspired gases during anesthesia, recovery and respiratory care. The environment is the operating suite, intensive care unit and patient population is adult, pediativ and infant patients.
The optional non-invasive blood pressure (NIBP) module is indicated for the noninvasive measurement of arterial blood pressure in hospitals, hospital-type facilities, mobile, and home environments. The NIBP module is designed to measure blood pressure for patient population described in the following table:
| Patient Population | Approximate Age Range |
|---|---|
| Newborn (neonate) | Birth to 1 month of age |
| Infant | 1 month to 2 years of age |
| Child | 2 to 12 years of age |
| Adolescent | 12-21 years of age |
| Adult | 21 years of age and older |
The subject device, Masimo Rad-97 System and Accessories (Rad-97 product family), features a touchscreen display that continuously displays numeric values for the measured monitoring parameters. The Rad-97 product family can be operated on AC power or internal rechargeable battery.
The subject device (Rad-97 product family) is substantially the same as the predicate (Rad-97 product family) cleared under K180046, and has the same indications for use. The Rad-97 comprises of the same measurement technologies as cleared in the predicate, which includes the Masimo rainbow SET technology, capnography technology, and noninvasive blood pressure (NIBP) technology. These technologies enable the Rad-97 product family to provide noninvasive monitoring of functional oxygen saturation of arterial hemoglobin (SpO2), pulse rate (PR), Perfusion Index (Pi), Pleth Variability Index (PVi), carboxyhemoglobin (SpCO), methemoglobin (SpMet), total hemoglobin (SpHb), oxygen content (SpOC), acoustic respiration rate (RRa), and/or optional capnography parameters or optional noninvasive blood pressure (NIBP) parameters.
The subject of this submission is the update to the SpO2 performance specification for the RD SET Disposable sensors for the neonate population to match that of the cleared 1.5% Arms for adults (K180046).
The document describes a 510(k) premarket notification for the "Masimo Rad-97 and Accessories" with a focus on an update to the SpO2 performance specification for the neonate population. The primary goal of the submission is to demonstrate that the device, specifically the RD SET Disposable sensors, maintains its performance for neonates consistent with previously cleared specifications for adults.
Here's a breakdown of the acceptance criteria and the study that proves the device meets them:
1. A table of acceptance criteria and the reported device performance
The document does not explicitly state "acceptance criteria" in a table format with a pass/fail. Instead, it refers to the "SpO2 performance specification" which the device is being updated to match, implying this as the target. The key performance metric cited is ARMS (Accuracy Root Mean Square).
The acceptance criteria for SpO2 accuracy are implicitly set by the previously cleared performance for adults, which is 1.5% ARMS. The submission aims to align the neonate performance with this.
Reported Device Performance:
| Parameter | Range | Bias | Precision | ARMS | Subjects |
|---|---|---|---|---|---|
| Initial Study Data (Neonates) | |||||
| SaO2 | 70-100% | 0.08 | 2.58 | 2.59 | 19 |
| SaO2 | 85-100% | -0.09 | 1.39 | 1.40 | 12 |
| SaO2 | 70-85% | 0.37 | 3.83 | 3.85 | 7 |
| Aggregated Study Data (Neonates) | |||||
| All Data | 70-100% | 0.129 | 3.182 | 3.185 | 42 |
While the aggregated data shows an ARMS of 3.185%, the document states, "The analysis of the clinical data further supported the safe form, fit, and function of the RD SET Disposable Sensor on neonates. The Arms performance was calculated for reference purposes." And "The results of the clinical testing supported the subject device did not raise any different questions of safety and effectiveness as compared to the predicate device." This suggests that the clinical data, despite not strictly meeting the 1.5% ARMS in all ranges for neonates in the initial and aggregated studies, was deemed sufficient to support substantial equivalence due to the nature of the submission (labeling update, not a new device or significant modification) and the "reference purposes" of the ARMS calculation in this context. The core assertion is that the same device is being used, and the form, fit, and function for neonates are supported.
2. Sample size used for the test set and the data provenance
- Initial Study: 19 neonatal subjects.
- Aggregated Study: 42 neonatal subjects (including 22 pre-term neonates). This aggregation combines data from the initial study with data from "prior studies."
- Data Provenance: The studies collected "convenience blood samples from an arterial line" in a "clinical environment." The document specifies that the aggregated data was from "3 different sites." The country of origin is not explicitly stated, but given the FDA submission, it's typically assumed to be conducted in the US or under comparable ethical/clinical standards acceptable to the FDA. The data is prospective clinical data collected for the purpose of verifying the device's performance on neonates.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
The ground truth for SpO2 measurements was established using a reference co-oximeter from arterial blood samples. This is a direct, objective measurement, not one established by human expert consensus or interpretation. Therefore, the concept of "number of experts" or their "qualifications" for establishing ground truth as typically applied to image-based AI studies (e.g., radiologists interpreting images) is not applicable here. The accuracy of the co-oximeter itself would be the relevant qualification.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
Since the ground truth is established by a reference co-oximeter on arterial blood samples, there is no adjudication method involving human experts for the test set.
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 comparative effectiveness study was not done. This device is a physiological monitor (pulse oximeter), not an AI-assisted diagnostic imaging tool that would typically involve human readers interpreting AI outputs. The "AI" aspect is not explicitly mentioned or studied in the context of human reader improvement.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
The device itself provides the SpO2 measurements. The study assesses the accuracy of these measurements against a reference standard. While the device (Masimo Rad-97 with RD SET Disposable sensors) operates without human intervention in generating the SpO2 reading, the study framework is not typically referred to as a "standalone" or "algorithm only" study in the context of AI regulatory submissions. It's a performance validation study for a medical device. The "algorithm" here is the signal processing within the oximeter. The ARMS metric specifically reflects this standalone device accuracy.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
The ground truth used was objective reference measurements of SaO2 (arterial oxygen saturation) from arterial blood samples analyzed by a reference co-oximeter.
8. The sample size for the training set
The document does not mention a training set in the context of model development or machine learning. This submission is for a medical device (pulse oximeter) that relies on established physiological principles and signal processing, not a de novo AI/ML algorithm that requires distinct training and test sets in the typical sense. The device's underlying algorithms were presumably developed and validated in prior clearances (K180046). This submission is an update to the labeling for a specific patient population (neonates) using an existing sensor, justifying it with clinical performance data on that population.
9. How the ground truth for the training set was established
As there is no mention of a training set for an AI/ML model, this question is not applicable based on the provided document. The device's core technology and its existing cleared performance for adults underpin the rationale for extending the performance specifications to neonates.
§ 870.2300 Cardiac monitor (including cardiotachometer and rate alarm).
(a)
Identification. A cardiac monitor (including cardiotachometer and rate alarm) is a device used to measure the heart rate from an analog signal produced by an electrocardiograph, vectorcardiograph, or blood pressure monitor. This device may sound an alarm when the heart rate falls outside preset upper and lower limits.(b)
Classification. Class II (performance standards).