(266 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 during pre-procedure, intra-procedure and recovery phase. 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 with body weights >20 kg.
Do not use the BD Intelliport™ System with blood, blood products, biologics, or chemotherapeutics.
BD Intelliport™ System integrates into an intravenous line and automatically captures information about the anesthesia medications administered to the patient. It wirelessly transmits anesthesia medication administration information to the patient's Electronic Medical Record (EMR) via hospital server applications (Gateway software). The BD Intelliport™ System provides core technologies that enable key functions of the system:
• Medication Identification: Informs clinician of medication and concentration along with any informational notifications such as patient allergy and expired medication reminders. This occurs when syringes with the correct type of RFID encoded label are attached.
• Dose Measurement: Measures volume of drug administered to the patient through the system, then calculates dose weight.
• Automatic Charting: Wirelessly transmits measured doses to the EMR.
The following are the main system components:
• BD Intelliport™ Injection Site which is comprised of the following two components:
- BD Intelliport™ Sensor
- BD Intelliport™ Reader
• BD Intelliport™ Mount (optional accessory)
• BD Intelliport™ 2-Bay Charger (accessory)
• BD Intelliport™ Gateway
The provided FDA 510(k) clearance letter and summary for the BD Intelliport™ System (K243062) describes the performance testing conducted to demonstrate substantial equivalence to its predicate device (K182092). However, it does not provide specific acceptance criteria or reported device performance values in a quantifiable table format, nor does it detail a standalone study with quantitative results, or a multi-reader multi-case (MRMC) comparative effectiveness study.
The document primarily focuses on demonstrating substantial equivalence through a comparison of technological characteristics and a list of performance tests completed.
Here's an attempt to structure the answer based on the available information, with caveats where data is missing:
Acceptance Criteria and Device Performance
The 510(k) summary states that "The subject device, the BD Intelliport™ System, has met all predetermined acceptance criteria for the non-clinical and human factors testing conducted in accordance with relevant FDA guidance, recognized consensus standards, and internal requirements." However, the specific numerical acceptance criteria and the quantitative reported device performance values for most tests are not explicitly stated in the provided document.
The only quantitative performance criteria and reported values mentioned are for "Volume measurement accuracy" and "Volume Measurement Resolution."
| Acceptance Criteria | Reported Device Performance (Subject Device) |
|---|---|
| Volume measurement accuracy: | |
| For volumes >1.0 mL | ± 10% |
| For volumes 0.4 – 1.0 mL | ± 0.2mL |
| Volume Measurement Resolution | Uniform increments of 0.5 mL |
Note: The document states these are "Identical" to the predicate device, implying the reported performance matches the specified criteria.
Study Information
Due to the nature of a 510(k) summary, detailed study reports with specific quantitative results (beyond volume measurement accuracy) are not included. The document generally refers to "performance testing" and "human factors evaluation."
-
Sample size used for the test set and the data provenance:
- Test Set Sample Size: Not explicitly stated for each test. For "Volume Measurement Performance Window," the volume range tested was 0.5ml to 30ml, and average push speed 10ml/min to 400 ml/min. This implies tests were conducted across this range, but the number of injections or trials is not provided.
- Data Provenance: Not explicitly stated (e.g., country of origin). The studies appear to be non-clinical (laboratory-based) and human factors studies. The human factors testing likely involved simulated clinical environments.
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Not applicable/Not provided within the scope of this 510(k) summary. These types of details are usually found in full study reports, not the summary itself, especially for a device that primarily automates record-keeping and measurement, rather than making diagnostic assessments that require expert ground truth. The human factors testing involved "intended device users," but their specific qualifications or roles in establishing "ground truth" (in a diagnostic sense) are not outlined.
-
Adjudication method for the test set:
- Not applicable/Not provided. Adjudication methods (like 2+1, 3+1) are typically used in studies where there is disagreement in expert interpretation of diagnostic data. This device automates measurements and record-keeping, so such a method is not relevant.
-
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 explicitly reported or appears not to have been the primary method for demonstrating substantial equivalence. The device's primary function is "automated record keeping" and facilitating "documentation of the medications." It improves efficiency and accuracy of recording medication administration, rather than assisting human readers in interpreting medical images or data. The human factors evaluation assessed "critical tasks completed by intended device users," implying usability and user performance with the system, not a comparison of expert diagnostic accuracy with and without AI.
-
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- The document implies that standalone (algorithm-only) performance testing was conducted for various technical attributes. For example, "Bolus volume measurement accuracy," "Sensor flow rate," "Decoding response time," "Wifi functionality," and "Dose transmission time" are intrinsic functions of the system and its algorithms, which would have been tested independently of a human operator to verify their technical specifications. The "Flow Algorithm" itself was updated and "qualified through verification testing." However, explicit, detailed results from a standalone study with acceptance criteria are not presented in a formal table like format for all algorithm-driven functions.
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- For the technical performance tests (e.g., volume measurement), the "ground truth" would have been established using calibrated instruments and reference standards (e.g., known volumes, known flow rates) in a laboratory setting.
- For the human factors evaluation, the "ground truth" would be defined optimal task performance and safety outcomes as determined by medical device standards and clinical best practices.
-
The sample size for the training set:
- The document does not provide information on a training set size. The BD Intelliport System involves embedded software and algorithms (e.g., flow algorithm, RFID reading, EMR communication). While such systems often involve development and testing cycles, the summary does not detail a specific "training set" like one would find for a machine learning or AI algorithm that learns from data in a traditional sense. The "Flow Algorithm" was updated and "qualified through verification testing," which implies validation against known physical models or experimental data, rather than a statistical "training set" in the context of deep learning.
-
How the ground truth for the training set was established:
- As no "training set" is explicitly mentioned for a machine learning model, this question is not applicable in the context of the provided information. The "ground truth" for verifying the updated flow algorithm would have been established through physical experiments and engineering measurements with known parameters (e.g., precise drug volumes, flow rates) to ensure the algorithm accurately processes the sensor data.
§ 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).