(270 days)
The BD Intelliport™ system is an automated record keeping system that incorporates patient safety features that are aligned with hospital patient records and protocols. The system is comprised of an injection port and software that enables the identification, measurement, alerting and documentation of the administration of medications to patients.
The BD Intelliport™ system allows the clinician to record anesthesia-related, medication administration events in the pre-op, intra-op, and PACU. The system is indicated for use by healthcare professionals in a hospital or medical center setting with patients who are receiving manually administered bolus intravenous injections as part of their care to facilitate documentation of the medications.
The BD Intelliport™ system is intended for patients whose body weights are >20kg.
The BD Intelliport™ system is not intended for use with blood, blood products, biologics, or chemotherapeutics.
The BD Intelliport™ system is not intended for use with refrigerated medications (excluding cefazolin)
Like the cited predicate device, the BD Intelliport Medication Management System, Version 1.2 is a system of hardware and software components that measures the delivered volume of intravenous (IV) bolus medications associated with anesthesiarelated, medication administration events in the pre-op, intra-op, and PACU, and provides automated documentation of medication identity, concentration, dose, delivered volume, and delivery timestamp to the hospital electronic medical record (EMR) system. There are two modes: EMR mode and Standalone mode. Standalone mode allows for printing dose history reports, but is not connected to an EMR
The device is organized by three subsystems, each of which includes several physical/software components:
- . Injection Site subsystem
- . Tablet subsystem
- . Gateway subsystem
The Injection Site subsystem is composed of two physical components (the Base and the ultrasonic Sensor) and the software residing inside the Base. The Tablet subsystem is composed of one physical component (the Tablet) and the software residing inside the Tablet. The Gateway subsystem consists of the Gateway software and the hospital server hardware on which the Gateway software resides. The device also includes an accessory for charging up to five Bases simultaneously.
During treatment, the clinician connects an intelligent injection port (the Injection Site) to a patient's fluid-delivery line and performs standard drug-delivery activities. The clinician injects the druq using BD Luer Lok, 1-60ml size syringes only, and then flushes with a separate normal, saline syringe. Flushing after each administration ensures all medication is administered to patient since there is a 0.334 ml dead space.
The device can be used with both encoded and non-coded syringes. If an encoded syringe is used, the device reads the two-dimensional barcode adhered to the syringe. The barcode contains information about the content in the syringe including the drug name and concentration. If a noncoded syringe is used, then the end user is prompted by the Tablet software to pick the drug name and concentration from the Encoded Drug List (EDL). When an encoded syringe is first connected to the device, the name of the drug is read back to the clinician and an allergy alert will trigger on the Injection Site base if the patient is allergic to the medication based on the patient's allergies record in their EHR (electronic health record). As the drug is injected, the device measures the volume of the injected drug via an ultrasonic sensor and records the time the drug was administered. Drug delivery information is stored and inserted into the patient's EHR by way of the Tablet and Gateway software in the EMR mode and available for printing in the Standalone mode.
Please find the requested information regarding the acceptance criteria and the study that proves the device meets the acceptance criteria for the BD Intelliport System, Version 1.2.
1. A table of acceptance criteria and the reported device performance
| Acceptance Criteria (Characteristic) | Predicate Device Specification | Subject Device Specification (Acceptance Criteria) | Reported Device Performance (Comments) |
|---|---|---|---|
| Volume measurement accuracy | ± 5% (for volumes >1.0 mL) | ||
| ± 20% (for volumes 0.4 – 1.0 mL) | ± 10% (for volumes >1.0 mL) | ||
| ± 0.2mL (for volumes 0.4 – 1.0 mL) | Equivalent – the specification of the subject device enforces a narrower distribution of measurements than that of the predicate device. Testing was performed to ensure the device volume measurements meet this specification with real drugs. | ||
| Potential volume error message logic | (Less comprehensive messages) | Subject device includes more messages to indicate potentially inaccurate volume measurements than the predicate device, and improved logic for “bubble” messages | Equivalent – reduces the risk related to inaccurate volume measurements. Software testing demonstrated compliance. |
| Untested drug “Enter Dose” messages | Not available | Available in subject device for untested drugs | Equivalent - reduces the risk related to inaccurate volume measurements. Software testing demonstrated compliance. |
| EMR connectivity | Send/receive medication data to/from EMR | Send/receive medication data to/from EMR | Equivalent. Software testing demonstrated compliance. |
| Encoded drug table (EDT) | 70 drugs on EDT | 161 drugs on EDT | Equivalent - medication identity feature verified; volume measurements are provided only for tested drugs. Software testing demonstrated compliance. |
| Environmental boundary (water) | Not explicitly stated in table | Operating between 15° C and 29° C, 20% and 85% relative humidity (non-condensing), and 84 kPa to 101 kPa | Testing was performed to ensure proper device function within these boundaries. |
| Human Factors/Usability | Not explicitly stated in table | Intended users can safely operate the device, and any residual risk related to potential use errors is acceptable. | Both formative and summative usability human factors testing studies were conducted, confirming safe operation and acceptable residual risk. |
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 does not explicitly state the sample size for the test set in quantitative terms for the identified performance criteria. For volume measurement accuracy, it states "Testing was conducted on a set of drugs commonly used in Anesthesia, bracketed based upon speed of sound and solvent/dissolved solids composition," implying multiple drugs were tested.
The document does not provide information on the country of origin of the data or whether the data was retrospective or prospective. The study appears to be bench and simulated human use testing, rather than clinical data from human patients.
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)
The document does not specify the number of experts or their qualifications for establishing ground truth within the context of the technical performance testing (e.g., volume accuracy). For human factors testing, it refers to "intended device users" and "clinicians," but does not detail their number or specific qualifications for establishing ground truth beyond their role as users.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
The document does not describe any specific adjudication method for establishing ground truth for the technical performance test sets. For human factors testing, it implies evaluation by human factors experts (though not explicitly stated as 'adjudication').
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 indication that a multi-reader multi-case (MRMC) comparative effectiveness study was performed. The device is described as an "automated record keeping system" and the studies reported are primarily non-clinical performance testing and simulated human use testing, not studies comparing human reader performance with and without AI assistance.
6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done
Yes, standalone (algorithm only) performance was assessed for aspects like volume measurement accuracy. The "Modification of the volume measurement algorithm to improve accuracy and precision" implies testing of the algorithm itself. The system also has a "Standalone mode" which allows for printing dose history reports without EMR connection, suggesting functionality independent of real-time human interaction for certain tasks.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
For volume measurement accuracy, the ground truth would likely be established through precise, laboratory-grade measurements of administered fluid volumes using calibrated equipment, comparing these to the device's reported measurements. The document mentions "Testing was performed to ensure that the device volume measurements meet the volume accuracy specification with real drugs," which supports this interpretation. For software functionalities like error messages and drug tables, the ground truth would be based on predefined software requirements and verification of their correct implementation.
8. The sample size for the training set
The document does not provide information about a "training set" or its sample size. The studies described are primarily verification and validation testing of the device's performance against specifications, rather than development or training of a machine learning model.
9. How the ground truth for the training set was established
As no training set is described in the provided text, there is no information on how its ground truth was established.
§ 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).