(86 days)
The EnteraLite® Infinity™ Enteral Feeding Pump is a rotary peristaltic pump designed to deliver programmed doses of enteral nutrition solutions at selectable rates.
The EnteraLite® Infinity™ Enteral Feeding Pump as referred to as Infinity™ with disposable set is a small, lightweight pump used to dispense liquid nutrients at a user controlled rate to patients. The device may be used in the hospital or at home by bedridden or ambulatory patients. The device is also designed for use with pediatric patients.
The device is a software controlled, variable flow rate, peristaltic pump. It operates up to 24 hours (at a nominal flow rate of 125 ml/hr) from internal rechargeable batteries. The batteries are recharged by a wall mounted charger that plugs into a standard 100 to 240 volt alternating current wall socket. The charger is available in various input voltage and plug configurations to accommodate international requirements. The charger converts line voltage to a safe low voltage of 5 volts DC that is supplied from the charger to the pump. A "fuel gauge" type indicator on the pump's LCD display continuously shows the state of battery charge.
The pump motor runs at a single speed and is turned on and off at programmed intervals to obtain the desired flow rate. The motor drive circuit is controlled by a microcontroller that allows the motor to pause longer at lower flow rates with correspondingly shorter pauses at higher flow rates. The software embodied within the microcontroller is extensively validated and verified as part of the design process.
The pump includes several safety features. An air-in-line sensor rapidly detects whenever nutrient flow is interrupted and alerts the user with both a visual and audible alarm. Two pressure sensors detect occlusions both on the nutrient bag (distal) side and the patient (proximal) side of the pump. The user is alerted to proximal or distal occlusions by both visual and audible alarms.
The disposable tubing set consists of a bag, or spike for nutrient bag, DEHP free PVC connecting tubing, an integral cassette with a silicone pumping segment, and an enteral adapter. The set also contains a patented anti-free flow device within the cassette, a version of which is used in the stationary pumps manufactured by ZEVEX, which prevents free flow of fluids if the tubing set is inadvertently or purposely removed from the pump.
A backpack (convertible to a waistpack) is available for use under ambulatory conditions. The pump may be operated in any orientation.
The provided text is a 510(k) summary for the EnteraLite® Infinity™ Enteral Feeding Pump. This document is a regulatory submission to the FDA, primarily focusing on establishing substantial equivalence to a predicate device.
It does not contain information about acceptance criteria or a study proving device performance against those criteria in the context of many of the requested categories. This type of information is typically found in detailed design validation reports, risk analysis documents, and specific performance testing protocols, which are usually part of the full 510(k) submission but are not included in this publicly available summary.
Specifically, the document discusses the device's technical characteristics, intended use, and its similarities to a predicate device (K954735). It mentions software validation and verification as part of the design process and highlights safety features like air-in-line and pressure sensors. However, it does not provide quantitative data, sample sizes, expert qualifications, or details on ground truth establishment as would be present in a study report.
Therefore, many of the requested details cannot be extracted from this document.
Here's what can be addressed based on the provided text, alongside an explanation of why other points cannot be answered:
1. A table of acceptance criteria and the reported device performance
- Cannot be provided. The document does not list specific acceptance criteria for performance metrics (e.g., flow rate accuracy, alarm response time) nor does it present reported device performance against such criteria in a quantitative format. It generally states that the software is "extensively validated and verified" and describes safety features, but no numerical performance data is given.
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- Cannot be provided. The document does not mention any specific "test set" or sample sizes used for performance testing. It focuses on the device's design and features, not the methodology or results of extensive testing with a defined test set. Data provenance is also not mentioned.
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)
- Cannot be provided. This question pertains to studies involving expert review for establishing ground truth, typically in AI/ML performance evaluation (e.g., image interpretation). This document describes a medical device (an enteral feeding pump), which does not involve establishing ground truth through expert review in this manner. The "ground truth" for a pump would be established by physical measurements and engineering specifications.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
- Cannot be provided. Similar to point 3, adjudication methods are relevant for expert consensus in classification or diagnostic tasks, which is not applicable to the description of an enteral feeding pump in this document.
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
- Cannot be provided. MRMC studies are specific to evaluating diagnostic technologies (like AI in radiology). This document describes a mechanical/electrical medical device (an infusion pump) and therefore, an MRMC study comparing human readers with and without AI assistance is not relevant or described. The device itself is not an AI diagnostic tool.
6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done
- Cannot be provided. This question is also typically relevant for AI algorithms. While the pump is "software controlled," the "standalone performance" refers to the entire device's operation, not an isolated algorithm in the context of AI evaluation. The document implies the pump's performance is tested as a complete system, but it doesn't detail standalone algorithm testing in the way this question implies for AI.
7. The type of ground truth used (expert concensus, pathology, outcomes data, etc)
- Cannot be provided as requested. For a device like an enteral feeding pump, "ground truth" would be established by:
- Engineering specifications and calibration standards: for flow rate accuracy, pressure limits, alarm thresholds, battery life.
- Simulated usage conditions: testing air-in-line detection, occlusion detection with known conditions.
- Pre-defined pass/fail criteria: based on regulatory standards and user needs.
However, the document does not explicitly state the types of "ground truth" or how they were established. It only mentions the features.
8. The sample size for the training set
- Cannot be provided. The concept of a "training set" is relevant for AI/ML models that learn from data. While the pump has software, it's not described as an AI/ML device that requires a training set in the typical sense. The software is validated through traditional software engineering verification and validation processes, not machine learning training.
9. How the ground truth for the training set was established
- Cannot be provided. As explained in point 8, the concept of a "training set" for AI/ML does not apply to the device described in this document in the traditional sense. Therefore, ground truth establishment for a training set is not pertinent here.
§ 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).