AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The CAS 740 Series Vital Signs Monitor is indicated for use for non-invasive monitoring of blood pressure, oxygen saturation, pulse and temperature of adult, pediatric and neonatal patients, in the care of health professionals.

Device Description

The CAS 740 Monitor is a replacement monitor based on the existing 9303 Vital Signs Monitor, and the CAS 9001 or 9002 EMS monitors. The 740 are primarily a repackaging of these monitors. The primary parameter is non-invasive blood pressure, which is included in all models. Blood pressure measurement is based on oscillometric technology. The additional two parameters are pulse oximetry and temperature. A purchaser has pulse oximetry choices that include modules manufactured by Masimo, Nellcor or Nonin. The temperature parameter utilizes predictive technology from SureTemp (Welch Allyn Inc.). The monitor is a rugged, portable and lightweight unit widely adaptable for many applications and mounting schemes. Used for spot-checking or continuous monitoring, features include an easily replaceable Nickel Metal Hydride rechargeable battery pack, wireless infrared printer communication, and many more.

AI/ML Overview

The provided document describes the CAS 740 Series Monitor, a vital signs monitor, and details its equivalence to predicate devices, not an AI/ML powered device. Therefore, the questions related to AI/ML specific studies, such as multi-reader multi-case studies, standalone algorithm performance, or ground truth establishment for training sets, are not applicable.

However, the document does provide information regarding acceptance criteria and a study for the Non-Invasive Blood Pressure (NIBP) component.

1. Table of Acceptance Criteria and Reported Device Performance

ParameterAcceptance Criteria (Standard Reference)Reported Device Performance (CAS 740 Series NIBP)
Non-Invasive Blood PressureAAMI SP10:2002 requirementsPerformance equivalent to the NB module (predicate) in bench test simulations. Clinical studies in accordance with AAMI SP10:2002, with results meeting the standard.

2. Sample Size Used for the Test Set and Data Provenance

The document states that the clinical studies for NIBP were conducted in accordance with AAMI SP10:2002. The AAMI SP10 standard (now ISO 81060-2) typically requires a minimum of 85 subjects for clinical validation to ensure a statistically robust evaluation of NIBP device accuracy. The document does not specify the exact number of subjects or the country of origin, nor whether the data was retrospective or prospective, beyond stating "clinical studies."

3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications of Those Experts

For Non-Invasive Blood Pressure measurements validated against a standard like AAMI SP10, the "ground truth" is typically established by simultaneously taken reference blood pressure measurements (e.g., intra-arterial measurements or trained auscultatory measurements using a mercury sphygmomanometer) by qualified healthcare professionals. The document does not specify the exact number or qualifications of these professionals beyond implying adherence to the AAMI SP10 standard, which mandates specific protocols for reference measurements.

4. Adjudication Method for the Test Set

The document does not explicitly state an adjudication method in the context of expert consensus, as this is not typically applicable for NIBP accuracy studies where direct physiological measurements serve as the reference. Adherence to AAMI SP10 implies a standardized method for obtaining reference measurements.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

No. This is not applicable as the CAS 740 Series Monitor is a vital signs monitor and not an AI/ML powered device requiring interpretation of medical images or data by multiple readers.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

Yes, for the Non-Invasive Blood Pressure component, standalone performance was assessed. The document states: "CAS has tested and demonstrated ND Plus performance equivalent to the NB module in bench test simulations." This refers to the algorithm's performance in simulation without human interaction to interpret the NIBP readings. Additionally, the clinical studies, while involving patients, assess the device's ability to accurately measure blood pressure on its own.

7. The Type of Ground Truth Used

For the Non-Invasive Blood Pressure (NIBP) component, the ground truth was based on reference blood pressure measurements obtained according to the AAMI SP10:2002 standard during clinical studies. These are direct physiological measurements.

8. The Sample Size for the Training Set

The document does not describe a "training set" in the context of an AI/ML algorithm. The NIBP measurement relies on oscillometric technology and algorithms that were likely developed and refined using physiological data, but the term "training set" with specific size is not mentioned for this type of device.

9. How the Ground Truth for the Training Set Was Established

As there is no mention of a "training set" in the AI/ML context, this question is not directly applicable. The underlying algorithms for oscillometric NIBP would have been developed and validated against a combination of empirical data and theoretical models of blood pressure oscillations, with accuracy verified through extensive testing against established reference methods.

§ 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.