(89 days)
The CADD-Sentry Pro" Medication Safety Software – Administrator allows you to establish a therapy-based protocol library that will be used by the CADD-Sentry Pro Medication Safety Software - Point of Care to program the CADD-Prizm® PCS II Ambulatory Infusion Pump (software revision H or higher).
The CADD-Sentry Pro" Medication Safety Software – Point of Care allows use of a personal computer to send CADD-Sentry Pro " Medication Safety Software -Administrator established therapy-based protocols to the CADD-Prizm® PCS II Ambulatory Infusion Pump (software revision H or higher).
The Smiths Medical MD, Inc. CADD-Sentry Pro™ Medication Safety Software, a software program that operates on commercially available personal computers or similar hardware platforms such as tablets, is designed for pump programming of the CADD-Prizm® PCS II Ambulatory Infusion Pump (software revision H or higher) through a therapy-based protocol database defined by the user. The CADD-Sentry Pro™ Medication Safety Software consists of an Administrator and a Point-of-Care (POC) software module that employs serial communications to send and receive pump information. Both modules are compatible with barcode scanners (or similar input devices) through various PC connections. Barcode format is determined by the user; but is limited to 20 alphanumerical characters. The CADD-Sentry Pro™ Medication Safety Software does not allow duplicative Drug, Protocol or User identification entries.
The CADD-Sentry Pro™ Medication Safety Software - Administrator module allows the user to create and save therapy-based protocols, including pump settings. The Administrator module allows therapy-based protocols to be stored and edited within userdefined protocol libraries. The Administrator user determines POC user access and editing capabilities of these libraries. Other Administrator module features include barcode printing, reports, and sending and receiving pump identification.
The CADD-Sentry Pro™ Medication Safety Software – Point-of-Care module allows the user to send and receive pump settings via serial communication sourced from protocol libraries established using the Administrator module. Additional features include storing and printing pump programs and reports, verifying pump settings to established protocols and viewing history logs in the easier view of the PC monitor.
The provided 510(k) summary for the CADD-Sentry Pro™ Medication Safety Software does not contain the detailed information necessary to fully address all aspects of your request regarding acceptance criteria and a study proving device performance in the manner typically expected for AI/ML-based medical devices.
This document describes a software-only device used for programming infusion pumps, and its validation appears to be centered on functional and software verification testing rather than performance metrics against a medical condition or diagnostic task. Therefore, many of the requested fields, particularly those related to clinical performance, ground truth, experts, and comparative effectiveness, are not applicable in this context.
Here's an analysis of the available information:
1. Table of acceptance criteria and the reported device performance:
| Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|
| Software Validation (e.g., proper functioning, no critical errors) | "Test plans associated with software validation... were performed." |
| Verification of Software Controlled Programming Functions | "verification of software controlled programming functions... were performed." |
| Proper Software and Pump Operation | "software related to proper software and pump operation were performed." |
| Safety and Effectiveness | "Based upon the information provided, the CADD-Sentry Pro™ Medication Safety Software is safe, effective and performs to established specifications." |
| Substantial Equivalence to Predicate Devices | "The CADD-Sentry Pro™ Medication Safety Software was compared to and found to be substantially equivalent to the following commercially available predicate devices: CADD-Diplomat® PC Communications System, Medication Safety System and Medley™ System with Bar Code Module with respect to indications for use and performance features." |
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective):
The document only states that "Test plans" were performed for "software validation, verification of software controlled programming functions, and software related to proper software and pump operation." It does not specify a "test set" in the sense of patient data or clinical samples that would have a sample size or provenance. These appear to be internal functional tests of the software.
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):
Not applicable. Ground truth, in the context of medical image analysis or diagnostic AI, refers to a definitive correct answer for a medical condition. This device is a software utility for programming an infusion pump, not a diagnostic tool requiring expert interpretation of medical data to establish ground truth.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:
Not applicable. Adjudication methods are typically used in studies where multiple human readers or algorithms interpret data, and their findings need to be reconciled. This is a functional software validation, not a reader study.
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. The document explicitly states: "Human clinical studies were deemed not necessary to evaluate the safety or effectiveness of the CADD-Sentry Pro™ Medication Safety Software." This type of study is focused on the impact of the software on human performance or diagnostic accuracy, which is not relevant for this device.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
The device itself is essentially a "standalone algorithm" in the sense that it performs its function of programming the pump automatically based on user input. The "functional testing" performed would be considered the standalone evaluation of the software's performance, ensuring it correctly implements the defined protocols and communicates with the pump. Performance is assessed against its functional specifications.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc):
The "ground truth" for this device would be its own functional specifications and the correct operation of the infusion pump. For example, if the software is designed to program the pump with a specific flow rate and volume, the ground truth would be that the pump is indeed programmed with that exact flow rate and volume after the software transmits the data. This would be verified through system testing rather than clinical ground truth like pathology.
8. The sample size for the training set:
Not applicable. This device is not an AI/ML system that learns from a training set of data. It is a deterministic software program that performs predefined functions.
9. How the ground truth for the training set was established:
Not applicable, as there is no training set for this type of software.
§ 880.5725 Infusion pump.
(a)
Identification. An infusion pump is a device used in a health care facility to pump fluids into a patient in a controlled manner. The device may use a piston pump, a roller pump, or a peristaltic pump and may be powered electrically or mechanically. The device may also operate using a constant force to propel the fluid through a narrow tube which determines the flow rate. The device may include means to detect a fault condition, such as air in, or blockage of, the infusion line and to activate an alarm.(b)
Classification. Class II (performance standards).