Search Results

The Smiths Medical Peel-Away Sheath Introducers are indicated for the introduction of catheters into the vascular system.
The Smiths Medical Peel-Away Sheath Introducers are indicated for the introduction of catheters into the subclavian vein.

Each Smiths Medical Peel-Away Sheath Introducer consists of a dilator and a peelable sheath. Both the dilator and the sheath have a hub at the proximal end. The dilator slides inside the sheath and the hubs are engaged so that sheath and dilator may be manipulated as a single unit. One version of the Smiths Medical Peel-Away Sheath Introducer has a valve on the proximal end of the hub.

The introducers are available in French sizes ranging from 6 to 11. Interior diameters of the sheath range from .085 to .147 inches. Outside diameters range from .116 to .182 inches. The length of the dilator for the non-valved introducer is nominally 8 inches from hub to tip with a 6 inch sheath. The dilator for the valved introducer is 7 inches long with a 5 inch sheath.

The Peel-Away Sheath Introducer is used to facilitate the insertion of a catheter into the vascular system by dilating a vessel and introducing the sheath. The hubs are then disengaged and the dilator is removed leaving the sheath through which a catheter may be inserted. The sheath hubs are then broken and the sheath is peeled away and removed from the catheter.

The provided document is a 510(k) premarket notification for a medical device (Smiths Medical Peel-Away Sheath Introducers). It does not contain information about acceptance criteria or a study proving that the device meets those criteria in the context of an AI/ML algorithm or clinical performance measures.

This document describes a regulatory submission for a physical medical device, focusing on substantial equivalence to predicate devices, non-clinical testing (physical properties, biocompatibility), and indications for use. It explicitly states that "Human clinical studies were deemed not necessary to evaluate the safety or effectiveness of the Smiths Medical Peel-Away Sheath Introducer."

Therefore, I cannot fulfill your request for the following sections as the information is not present in the provided text:

1. A table of acceptance criteria and the reported device performance
2. Sample sized used for the test set and the data provenance
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
4. Adjudication method for the test set
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
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
7. The type of ground truth used
8. The sample size for the training set
9. How the ground truth for the training set was established

Ask a specific question about this device

The Medfusion® Model 4000 Syringe Infusion Pump is indicated for the following uses:

• . In the administration of fluids requiring precisely controlled infusion rates including blood or blood products. lipids, drugs, antibiotics, enteral solutions and other therapeutic fluids.
• . By the following delivery routes: arterial, epidural, intrathecal, subcutaneous, and enteral.
• . By the following delivery modes: continuous, volume/time, mass, body weight, custom dilution, intermittent and bolus.
• . In critical care, anesthesia, neonatal and pediatric applications or other healthcare settings where the use of the syringe infusion pump can be monitored or supervised by a clinician.
• . Inside the MRI room mounted outside the 150 Gauss line and with shielded magnets of field strength of 1.5 Tesla.

The PharmGuard® Toolbox 2 Medication Safety Software is indicated to provide a vehicle to create and securely upload user-defined configuration parameters, a library of drug names and associated user-defined infusion parameters to Medfusion® Model 4000 Syringe Infusion Pump with software version 1.X. The PharmGuard® Toolbox 2 Medication Safety Software collects and downloads operational, infusion and alarm history events, library usage counts, and PharmGuard® safety events from the Medfusion® Model 4000 Syringe Infusion Pump. It is intended to provide a dataset users can collect and analyze to improve overall processes and lessen the likelihood of operator error when entering infusion parameters into the Medfusion® Model 4000 Syringe Infusion Pump.

The PharmGuard® Supported Syringes is an accessory to the PharmGuard® Toolbox 2 Medication Safety Software that expands the available supported syringes that can be selected when creating user defined configuration parameters using the PharmGuard® Toolbox 2 Medication Safety Software.

The Medfusion® Model 4000 Syringe Infusion Pump software version 1.1 is a wireless capable electro-mechanical syringe infusion pump.

The PharmGuard® Toolbox 2 Medication Safety Software is designed to accommodate the features and capabilities of the 4000 pump with software version 1.X.

The provided 510(k) summary for K111386 describes the Medfusion® Model 4000 Syringe Infusion Pump and its associated software and accessories. This document focuses on demonstrating substantial equivalence to predicate devices and does not contain the kind of detailed acceptance criteria, study design, or performance metrics typically seen in studies for AI/CADe devices.

In the context of the provided document, the "acceptance criteria" are implied by the performance of the predicate devices and general safety/effectiveness standards for infusion pumps. The "study that proves the device meets the acceptance criteria" refers to a series of non-clinical bench tests that ensure the device functions as intended and safely.

Therefore, many of the requested fields (e.g., sample size for test set, number of experts for ground truth, MRMC study, training set details) are not applicable or cannot be extracted from this type of regulatory submission for a traditional medical device like an infusion pump.

Here's an attempt to answer the questions based only on the provided text, acknowledging that many fields will be "Not Applicable" or "Not Provided" given the nature of the device and submission:

Acceptance Criteria and Device Performance

The acceptance criteria for this device are broadly aligned with ensuring its safety, effectiveness, and functional performance, demonstrating substantial equivalence to its predicate devices. The "reported device performance" refers to the successful completion of various bench tests and validation studies.

Study Details (Based on Provided Text):

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

• Sample Size: Not specified for individual bench tests. The testing involved various units of the Medfusion® 4000 Syringe Infusion Pump and associated software.
• Data Provenance: Not specified, but generally, bench testing is conducted in-house by the manufacturer. Retrospective/Prospective is not applicable as this describes non-human, laboratory-based testing.

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 / Not provided. The "ground truth" for an infusion pump's performance is objective measurement against engineering specifications and industry standards, not expert consensus in the medical imaging sense. Human Factors Engineering studies involved "clinicians" but their specific number or qualifications beyond being "clinicians" is not detailed.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

• Not applicable / Not provided. Adjudication methods are typically for subjective assessments (e.g., reading medical images). Bench testing involves objective pass/fail criteria against predefined specifications.

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

• Not applicable. This device is an infusion pump, which is a hardware device with software, not an AI/CADe system designed to assist human readers in image interpretation or diagnosis.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

• Not applicable. While the software operates within the pump, "standalone performance" in the context of AI/CADe is not relevant here. The device's performance is inherently its function (algorithm and hardware combined) in delivering fluids.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)

• Engineering Specifications and Performance Standards: The "ground truth" for the tests mentioned are the specific acceptable ranges for flow rates, alarm thresholds, resistance levels, and compliance with national/international safety and performance standards (e.g., EN IEC 60601-1, ASTM-F2052).

8. The sample size for the training set

• Not applicable. The device is not an AI/ML model that is "trained" on a dataset in the conventional sense. Its software is programmed and validated.

9. How the ground truth for the training set was established

• Not applicable. As above, there is no "training set" for this type of device. The software is developed based on engineering requirements and validated through testing.

Ask a specific question about this device

This product is indicated for the administration into or withdrawal of fluids from implanted ports. It is designed to help protect against accidental needlestick injuries.

The GRIPPER® Micro needle is comprised of the inserter and the infusion site with extension tubing and a standard luer fitting; there are versions either with or without needless access connector y-site. The inserter incorporates a sharp trocar needle and retractor arm. The infusion site incorporates a small septum and an attached blunt cannula. When fully assembled, the inserter and infusion site are combined with the trocar needle inserted through the septum and blunt cannula. After insertion of the cannula and trocar into the implanted port, the inserter retractor arm is activated removing the trocar needle from the cannula and infusion site septum leaving the blunt cannula in the implanted port. The trocar needle tip is captured in the inserter to prevent needle stick injury, and the inserter is discarded. Upon removal of the infusion site from the implanted port, the blunt cannula is designed to further prevent needle stick injury that may result from rebounding action during infusion site extraction.

The provided text describes the GRIPPER® Micro 1.25 Inch Needle, which is an intravascular administration set designed to administer or withdraw fluids from implanted ports while preventing accidental needlestick injuries.

Here's an analysis of the acceptance criteria and the study that proves the device meets them:

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample size used for the test set and the data provenance

• Sample Size for Test Set: 500 activations.
• Data Provenance: The study was a "Simulated Use Study" conducted in accordance with FDA Guidance. This implies a prospective study involving human participants in a controlled, simulated environment, rather than retrospective real-world data. The country of origin for the data is not explicitly stated, but given the FDA guidance and the submitter's address in St. Paul, MN, it is highly probable the study was conducted in the USA.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

• The text does not specify a number of "experts" used to establish ground truth in the traditional sense of diagnostic assessment.
• Instead, the "ground truth" for the simulated use study was the successful capture of the trocar tip in the capture zone. This is an objective, binary outcome.
• The participants in the study were "Health care professionals... experienced in accessing and de-accessing implantable portals." Their role was to perform the simulated activities, not to adjudicate or establish a diagnostic ground truth.

4. Adjudication method for the test set

• There was no explicit adjudication method described in the text for the simulated use study.
• The outcome (successful capture of the trocar tip) appears to be an objective, directly observable event rather than one requiring expert interpretation or consensus. It likely involved a pass/fail assessment recorded for each activation.

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. This device is a medical needle, not a diagnostic imaging AI system. The study focused on the physical performance and safety features of the device during simulated use, not on human interpretation or AI assistance.

6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done

• No, a standalone algorithm performance study was not done. This device is a physical medical device. The "simulated use study" involved human healthcare professionals interacting with the device to evaluate its performance and safety features.

7. The type of ground truth used

• For the simulated use study, the ground truth was objective device performance: successful capture of the trocar tip in the capture zone. This is a direct outcome measure of the safety feature's functionality.

8. The sample size for the training set

• The concept of a "training set" is not applicable to this device or its evaluation. This is a physical medical device, not a machine learning algorithm.

9. How the ground truth for the training set was established

• Not applicable (as explained in point 8).

Ask a specific question about this device

The Lockbox is intended to hold a Medfusion™ 3000 Series Syringe Pump and provide reasonably secure access to the medication syringe contained within.

The Lockbox is an accessory to the Medfusion™ 3000 Series Syringe Pump. It is a lockable, plastic enclosure for the pump when the pump is loaded with a commercially available syringe containing medication. The Lockbox may be attached to an IV pole with the Pole Mount Bracket or with modification to a horizontal square rail.

The provided text describes a 510(k) submission for a medical device called "Lockbox for Medfusion™ 3000 Series Pumps". This device is a lockable plastic enclosure for an infusion pump and is primarily evaluated based on its physical properties and biocompatibility, not on AI or diagnostic performance metrics. Therefore, many of the requested categories for AI-based device evaluation are not applicable.

Here's an analysis of the available information:

Acceptance Criteria and Study Details for "Lockbox for Medfusion™ 3000 Series Pumps"

Given the nature of the device (a physical lockbox accessory for an infusion pump), the acceptance criteria and study methods differ significantly from those typically used for AI/diagnostic devices. The focus is on physical suitability, safety (biocompatibility), and achieving its stated intended use.

1. Table of Acceptance Criteria and Reported Device Performance

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

• Test Set Sample Size: Not explicitly stated in terms of a specific number of units for bench testing or usability studies.
• Data Provenance: The testing was "non-clinical" and involved "Bench Testing" and "Usability Studies." This suggests in-house testing performed by Smiths Medical MD, Inc. No information regarding country of origin for data or whether it was retrospective/prospective is provided, as it's not relevant for this type of device testing.

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

• Not applicable in the context of this device. The "ground truth" for a physical lockbox relates to its mechanical function, security, and material science, which are typically assessed by engineers and materials scientists rather than medical experts in a diagnostic "ground truth" sense.

4. Adjudication Method for the Test Set

• Not applicable. The evaluation of physical properties and usability does not involve an adjudication method like those used for diagnostic decisions.

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

• No, a MRMC comparative effectiveness study was not done. This type of study is relevant for AI-assisted diagnostic devices where human readers interpret medical images or data. The Lockbox is a physical accessory, not a diagnostic tool or something that directly influences human reader performance.

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

• Not applicable. There is no algorithm or AI component in the Lockbox device. Its "performance" is entirely physical and mechanical.

7. The Type of Ground Truth Used

• The "ground truth" was established based on engineering specifications, material science principles, and functional requirements for a secure enclosure. For biocompatibility, it was based on similarity to established biocompatible materials used in other Smiths Medical products.

8. The Sample Size for the Training Set

• Not applicable. There is no AI model or algorithm that required a "training set" for this device.

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

• Not applicable. As there is no training set, there is no ground truth establishment for it.

Ask a specific question about this device

The CADD® -Solis Medication Safety Software - Administrator allows use of a computer to create therapy based protocol libraries to be used with the CADD®-Solis Ambulatory Infusion Pump or CADD-Prizm® PCS II Ambulatory Infusion Pump (software revision H or higher).

The CADD"-Solis Medication Safety Software -- Point of Care allows use of a computer to send therapy-based protocols developed by the CADD® -Solis Medication Safety Software -Administrator to the CADD®-Solis Ambulatory Infusion Pump and CADD-Prizm® PCS II Ambulatory Infusion Pump (software revision H or higher).

The Smiths Medical MD, Inc. CADD® -Solis 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 -Solis Planorms such as lables, is designed for pains programming so managers infusion Pump (software revision H or higher) through a therapy-based protocol database defined by the user. The CADD®-Solis 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®-Solis Medication Safety Software does not allow duplicative Drug, Protocol or User identification entries.

The CADD®-Solis Medication Safety Software – Administrator module allows the user to create, cdit, and save therapy-based protocols and pump settings within user-defined protocol libraries. The Administrator user determines POC user access and library editing capabilities. Other Administrator module features include barcode printing, reports, and sending and receiving pump information.

The CADD®-Solis Medication Safety Software – Point of Care module allows the user to download therapy based protocols to the CADD® Solis Ambulatory Infusion Pump and CADD-Prizm® PCS II Ambulatory Infusion Pump (software revision H or higher) and send and receive pump settings via serial communication. Additional features include storing and printing pump program settings and reports, verifying pump settings to established protocols and viewing history logs in the easier view of a PC monitor.

The provided documentation for the CADD®-Solis Medication Safety Software does not contain the detailed acceptance criteria and study information typically associated with AI/ML device evaluations. This submission is for a software that manages infusion pump protocols, essentially a data management and programming tool, not an AI/ML diagnostic or predictive device.

Therefore, many of the requested points are not applicable or cannot be answered from the provided text.

Here's an analysis based on the available information:

1. Table of Acceptance Criteria and Reported Device Performance

Explanation: The document states that functional testing was performed ("Test plans associated with software validation, verification of software controlled programming functions and pump operation were performed.") and that the device "performs to established specifications." However, it does not explicitly list what those specifications or acceptance criteria were (e.g., specific error rates, performance metrics, or thresholds). This is common for software tools that are not performing diagnostic or analytical tasks with clearly defined output metrics.

2. Sample size used for the test set and the data provenance

• Sample Size (Test Set): Not applicable. The "study" was functional testing and software validation, not a test set of medical data in the way a diagnostic AI would use.
• Data Provenance: Not applicable. The device processes therapy-based protocols and pump settings, not patient data in the typical sense.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

• Number of Experts: Not applicable. Ground truth, in the context of medical image interpretation or disease diagnosis, is not relevant here. The "ground truth" for this software would be the correctness of its programming functions and its ability to accurately manage and transfer drug protocols. This would typically be verified against design specifications and user requirements by software engineers and potentially clinical users, but it's not "expert-established ground truth" in the AI/ML sense.
• Qualifications of Experts: Not applicable.

4. Adjudication method for the test set

• Adjudication method: Not applicable. The software's performance was evaluated through functional testing and software validation processes, not through adjudication of medical interpretations or diagnoses.

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

• MRMC Study: No. This device is a software tool for managing infusion pump protocols, not an AI-assisted diagnostic or interpretive system that would involve human readers. Clinical studies were "deemed not necessary to evaluate the safety or effectiveness."

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

• Standalone Performance: The "functional testing" performed would generally evaluate the software's performance in isolation (standalone) against its design specifications. However, the nature of the device (protocol management for infusion pumps) inherently involves a human-in-the-loop for creating and applying these protocols to the physical pumps. It's not an algorithm that makes independent clinical decisions.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)

• Ground Truth Type: Not applicable in the context of AI/ML evaluation. The "ground truth" for this software would be the correct execution of its programming functions and the accurate storage/retrieval/transfer of defined therapy protocols and pump settings, as per its design specifications. This is typically verified through software quality assurance processes.

8. The sample size for the training set

• Training Set Sample Size: Not applicable. This software is not an AI/ML model that undergoes training on a dataset. It is a deterministic software application.

9. How the ground truth for the training set was established

• Training Set Ground Truth: Not applicable. As it's not an AI/ML model, there is no training set or associated ground truth establishment process in that context.

Ask a specific question about this device

The CADD™ Medication Cassette reservoirs are intended for the delivery of medications and fluids for subcutaneous, intramuscular, intravenous, intra-arterial, intraperitoneal, or intraspinal infusion.

The CADD™ Medication Cassette Reservoir with Flow Stop feature is a modification to the current CADD™ Medication Cassette Reservoir with Flow Stop. The modification incorporates a 250 mL reservoir and a two-part housing assembly. It is provided with a medication bag and pump tube, extension tube, pressure plate with Flow Stop feature, rear housing, clamp and leur assembled with the cover set into the rear housing assembly but not snapped together. This two-part housing design is intended to allow manipulation of the medication bag for removal of air bubbles prior to permanently snapping the housing together.

The provided text describes a 510(k) premarket notification for a medical device called the CADD™ Medication Cassette Reservoir. This document outlines general information about the device, its intended use, and a summary of studies performed. However, it does not contain the detailed information necessary to fully answer all aspects of your request regarding acceptance criteria and a study proving those criteria.

Here's a breakdown of what can and cannot be answered based on the provided text:

1. A table of acceptance criteria and the reported device performance

• Acceptance Criteria: The document states that the device "meets the acceptance criteria for the safety and performance requirements set by the CADD™ Medication Cassette Reservoir with Flow Stop specifications." However, it does not list specific acceptance criteria (e.g., maximum flow rate deviation, burst pressure, material compatibility thresholds).
• Reported Device Performance: Similarly, while it states "All tests performed demonstrate that the CADD™ Medication Cassette Reservoir with Flow Stop meets the acceptance criteria," it does not provide specific performance data or values for any of these tests.

Therefore, a table cannot be constructed with the information provided.

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 mentions "Functional Testing," but it does not specify the sample size for any tests conducted.
• Data Provenance: This information is not available in the provided text.

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)

• Since there were no human clinical studies (see point 5 and 6), there was no ground truth established by experts in the context of the device's functional performance. The "ground truth" here would be the engineering specifications against which the device was tested.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

• This is not applicable as there were no clinical studies involving human interpretation or 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

• No MRMC study was done. The document explicitly states: "Human clinical studies were deemed not necessary to evaluate the safety or effectiveness of the CADD™ Medication Cassette Reservoir with Flow Stop."
• AI assistance is not relevant for this type of medical device (a medication cassette reservoir).

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

• This question is not applicable as the device is a physical medical reservoir, not an algorithm or AI system. The "Functional Testing" described would be considered a standalone performance evaluation of the device itself against its specifications.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)

• The "ground truth" used for this device would be its engineering specifications and design requirements. The functional tests were conducted to ensure the device performs according to these pre-defined (but not enumerated in the document) criteria. This is implicitly stated as "meets the acceptance criteria for the safety and performance requirements set by the CADD™ Medication Cassette Reservoir with Flow Stop specifications."

8. The sample size for the training set

• This question is not applicable as the device is a physical medical component, not a learning algorithm that requires a training set.

9. How the ground truth for the training set was established

• This question is not applicable for the same reason as point 8.

Summary of available information regarding acceptance criteria and studies:

The document states that the CADD™ Medication Cassette Reservoir with Flow Stop was subjected to functional testing to demonstrate compliance with its internal specifications.

• Acceptance Criteria: Not explicitly listed but referred to as "safety and performance requirements set by the CADD™ Medication Cassette Reservoir with Flow Stop specifications."
• Study Type: Functional Testing (engineering/bench testing).
• Outcomes: "All tests performed demonstrate that the CADD™ Medication Cassette Reservoir with Flow Stop meets the acceptance criteria..."
• Clinical Studies: Deemed "not necessary."
• Predominant Ground Truth: Engineering and design specifications.

Ask a specific question about this device

The LockBox is a plastic enclosure designed to hold a CADD®-Solis infusion pump and a medication reservoir or syringe.

The LockBox is an accessory to the CADD® -Solis ambulatory infusion pump. It is a plastic enclosure for the CADD®-Solis ambulatory infusion pump when it is attached to commercially available medication rescrvoir. The reservoir may be a flexible IV bag up to 500 mL in size or a syringe up to 60 mL. The Lockbox may be attached to a CADD-Prizm Polcmount Bracket.

The provided text describes a medical device called "LockBox for CADD®-Solis Ambulatory Infusion Pump," an accessory designed to enclose an infusion pump and its medication reservoir. This submission for 510(k) premarket notification does not include a study proving device performance against specific acceptance criteria in the typical sense of a clinical or analytical study with quantitative metrics.

Instead, the submission states:

"The LockBox was subjected to verification and validation testing as well as human factors usability testing. All tests performed demonstrate the LockBox meets the acceptance criteria for the safety and performance requirements set by the LockBox specifications."

This indicates that the device met internal acceptance criteria defined in its own specifications through a process of verification, validation, and human factors testing. However, the details of these internal acceptance criteria and the results of these tests are not provided in the document.

Therefore, many of the requested details cannot be filled from the given text.

Here's a breakdown of what can be extracted and what cannot:

Ask a specific question about this device

The CADD -Solis ambulatory infusion pump is indicated for intravenous, intraarterial, subcutaneous, intraperitoneal, in close proximity to nerves, into an intraoperative site (soft tissue, body cavity/surgical wound site), epidural space, or subarachnoid space infusion. The pump is intended for therapies that require a continuous rate of infusion, patient-controlled demand doses, or both (such as patientcontrolled analgesia).

The CADD®-Solis Medication Safety Software consists of the Administrator and the Point of Care software applications. This software allows you to create a set of standard pump Protocols to be used with the CADD®-Solis Ambulatory Infusion Pump and CADD-Prizm® PCS II Ambulatory Infusion Pump. The Point of Care software application is used for the CADD-Prizm® PCS II Ambulatory Infusion pump (with software revision H or higher) only.

The CADD® -Solis ambulatory infusion pump ("Solis Pump") provides measured drug therapy to patients in the hospital setting. The pump can be programmed to deliver medication at a continuous rate, patient controlled analgesia (PCA), clinician bolus, continuous rate plus PCA, and continuous rate plus clinician bolus.

The Smiths Medical MD, Inc. CADD® -Solis Medication Safety Software -Administrator ("Solis Safety Software - Administrator"), a server based software program that operates on commercially available computers, is designed to establish user defined therapy based protocols for use by the Solis Pump or for use by use CADD®-Solis Medication Safety Software – Point of Care (POC) to program the CADD-Prizm® PCS II Ambulatory Infusion Pump (software revision H or higher). The Solis Safety Software - Administrator does not allow duplicative Drug, Protocol or User identification entries.

The provided text describes two devices: the CADD®-Solis Ambulatory Infusion Pump and the CADD®-Solis Medication Safety Software – Administrator. The information primarily focuses on the regulatory submission (510(k) summary) and does not contain detailed acceptance criteria and a study that proves the device meets those criteria in the typical format of clinical performance evaluation studies (e.g., with metrics like sensitivity, specificity, or accuracy).

Instead, the submission indicates that:

• For both devices: "The Solis Pump and Solis Safety Software – Administrator were subjected to verification and validation testing. The verification and validation testing performed demonstrate the devices function as intended and perform to specification."
• For the Medication Safety Software: "Human clinical studies were deemed not necessary to evaluate the safety or effectiveness of the CADD-Sentry Pro™ Medication Safety Software." (Note: The document inconsistently refers to "CADD-Sentry Pro™ Medication Safety Software" here, but the 510(k) is for "CADD®-Solis Medication Safety Software - Administrator").
• Conclusion: "Based upon the information provided, the CADD-Sentry Pro™ Medication Safety Software is safe, effective and performs to established specifications."

Given this, I cannot provide a table of acceptance criteria and reported device performance with quantitative metrics, nor can I answer many of the specific questions about clinical study design (sample size, ground truth, expert qualifications, etc.) because such a clinical study, as typically understood for AI/diagnostic devices, was explicitly deemed "not necessary."

However, I can extract the information provided:

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample size used for the test set and the data provenance

• No specific sample size for a test set is mentioned.
• Data provenance is not specified. The studies mentioned are "verification and validation testing," which typically involves engineering and functional testing rather than clinical data sets.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

• Not applicable/Not provided. The document states clinical studies were "deemed not necessary."

4. Adjudication method for the test set

• Not applicable/Not provided. Clinical studies with adjudication methods were not conducted.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done

• No. A multi-reader multi-case study was not conducted as clinical studies were "deemed not necessary."

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

• The "verification and validation testing" performed for the CADD®-Solis Medication Safety Software – Administrator can be considered a form of standalone testing, as it evaluates the software's functional performance against its specifications. However, this is not a standalone clinical performance study.

7. The type of ground truth used

• For the "verification and validation testing," the ground truth would be based on the established engineering specifications and intended functional behavior of the infusion pump and the software. It is not based on expert consensus, pathology, or outcomes data in a clinical sense.

8. The sample size for the training set

• Not applicable/Not provided. As no AI/ML algorithm requiring a training set is explicitly discussed in the clinical study context, this information is not relevant to the described studies. The software is described as a "server based software program" designed to "establish user defined therapy based protocols."

9. How the ground truth for the training set was established

• Not applicable/Not provided. No training set is mentioned.

Summary: The provided document is a 510(k) summary for medical devices (an infusion pump and its associated medication safety software). It describes "verification and validation testing" to show that the devices function as intended and perform to specification. Crucially, it states that "Human clinical studies were deemed not necessary" for the medication safety software. Therefore, the questions related to clinical study design, patient data, expert evaluation, and AI algorithm training sets are not addressed in this document. The "acceptance criteria" appear to be met through these internal functional and validation tests, rather than through a comparative clinical performance study.

Ask a specific question about this device

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 user-defined 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 text describes the CADD-Sentry Pro™ Medication Safety Software. However, it does not contain specific acceptance criteria, a detailed study proving performance against those criteria, or the typical elements of a performance study for AI/machine learning medical devices.

Instead, the document focuses on:

• Device Description: What the software does (Administrator module for creating protocols, Point-of-Care module for sending protocols to a pump).
• Intended Use: How the software is meant to be used.
• Device Comparison: Stating equivalence to a predicate device (itself, indicating a modification or re-submission).
• Summary of Studies: A very brief mention of "Functional Testing" related to software validation and "verification of software controlled programming functions," and a statement that "Human clinical studies were deemed not necessary."
• Conclusion: The software is "safe, effective and performs to established specifications."

Given the information, I can only provide a general response based on the limited details regarding testing.

Acceptance Criteria and Device Performance

The document does not explicitly state numerical acceptance criteria (e.g., sensitivity, specificity, accuracy targets) or measurable device performance metrics in the typical sense of a diagnostic or an AI-driven device. The "acceptance criteria" appear to be met through successful completion of "Functional Testing" and "verification of software controlled programming functions."

Study Details

1. Sample size used for the test set and data provenance:

   • Test Set Sample Size: Not specified. The document only mentions "Test plans associated with software validation, verification of software controlled programming functions, and software related to proper software and pump operation were performed." This implies internal software testing rather than a dataset of patient cases.
   • Data Provenance: Not applicable, as no external data set (e.g., patient data, images, clinical records) was used in the described testing suitable for AI/ML performance evaluation. The testing would have involved the software interacting with the infusion pump.

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

   • Not applicable. The "ground truth" in this context would likely be the expected correct behavior of the software and pump based on engineering specifications and design, rather than expert interpretation of clinical data.

3. Adjudication method (e.g., 2+1, 3+1, none) for the test set:

   • Not applicable. This type of adjudication method is used for clinical data where human expert disagreement needs resolution. The testing described is functional software testing.

4. 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. 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 software is a pump communication and programming system, not an AI diagnostic or decision support tool for human readers/clinicians, so an MRMC study is not relevant here.

5. If a standalone (i.e. algorithm only without human-in-the loop performance) was done:

   • The "functional testing" performed would be considered standalone in the sense that it evaluated the software's ability to perform its programmed functions (sending/receiving data, managing protocols) without a human interpreting outputs for diagnostic purposes. However, it's not "standalone" in the typical AI sense of providing a clinical assessment without human oversight. The software's function is to facilitate human programming of a pump.

6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

   • The "ground truth" for this device's functional testing would be the pre-defined functional specifications and expected behavior of the software and the CADD-Prizm pump as determined by its design and engineering requirements.

7. The sample size for the training set:

   • Not applicable. This is not an AI/ML device that requires a training set of data. The software's logic is explicitly programmed.

8. How the ground truth for the training set was established:

   • Not applicable, as there is no training set for this type of software.

Ask a specific question about this device

POWER P.A.C. Implantable Venous Access Systems: The POWER P.A.C. implantable venous access systems are implantable vascular access devices designed to provide long term repeated access to the vascular system. Smiths Medical MD, Inc. POWER P.A.C. Implantable Venous Access Systems are indicated when patient therapy requires repeated vascular access for injection or infusion therapy and/or venous blood sampling. When used with a GRIPPER PLUS® POWER P.A.C. Safety Huber Needle or other power injectable huber needle, the Smiths Medical MD, Inc. POWER P.A.C. implantable venous access systems are indicated for power injection of contrast media. For power injection of contrast media. the maximum recommended infusion rate is 5 ml/sec.

GRIPPER PLUS® POWER P.A.C. Needle: The GRIPPER PLUS® POWER P.A.C. Safety Huber Needle is designed for the administration into or withdrawal of fluids from implanted ports. The GRIPPER PLUS® POWER P.A.C. Safety Huber Needle is indicated for the administration into or withdrawal of fluids from implanted ports. It is designed to help protect against exposure to bloodborne pathogens caused by accidental needlestick injuries. When used with power injectable implantable venous access ports, the GRIPPER PLUS® POWER P.A.C. Safety Huber Needle is indicated for power injection of contrast media.

POWER P.A.C. Implantable Venous Access Systems: The POWER P.A.C. implantable venous access systems are similar to the current PORT-A-CATH® and PORT-A-CATH® II implantable venous access systems and Power Injectable Implantable Infusion Port. They both are totally implantable venous access systems designed to permit repeated access to the venous system for the parenteral delivery of medications, fluids, nutritional solutions, and for the sampling of venous blood. However, when used with a power indicated huber needle, the POWER P.A.C. implantable venous access systems are indicated for power injection of contrast media. The POWER P.A.C. implantable.vanous access systems can be placed in the chest or arm. The POWER P.A.C. implantable venous access systems are supplied sterile and non-pyrogenic. All POWER P.A.C. implantable venous access systems are designed and intended for single patient use only. A system consists of a portal with one or two self-sealing septa and a single or dual lumen catheter and is accessible by percutaneous puncture with a non-sopina neede.

GRIPPER PLUS® POWER P.A.C. Needle: The GRIPPER PLUS® POWER P.A.C. Needle is similar to the current GRIPPER PLUS® needle, with the addition of an added indication. Both are supplied sterile and non-pyrogenic and are intended for the administration into or withdrawal of fluids from implanted ports. In addition, they both have a passive needle stick protection feature that is designed to help protect against exposure to bloodborne pathogens caused by accidental needlestick in its protection in help not protect against other routes of bloodborne pathogen transmission. The GRIPPER PLUS® POWER P.A.C. Needle is indicated for power injection of contrast media.

1. Acceptance Criteria and Reported Device Performance:

2. Sample Size and Data Provenance:

The document does not specify a separate "test set" in the context of clinical studies. The functional and design verification testing was performed on the devices themselves. There is no mention of country of origin or whether data was retrospective or prospective, as no clinical human data was collected.

3. Number of Experts and Qualifications:

Not applicable. No experts were used to establish ground truth for a test set, as no clinical studies were performed.

4. Adjudication Method:

Not applicable. No adjudication method was used as no clinical studies were performed.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:

No MRMC comparative effectiveness study was performed. The submission explicitly states "Clinical studies ... were deemed not necessary".

6. Standalone Performance (Algorithm Only):

Not applicable. This device is a medical product (catheter/port and needle) and not an algorithm or AI. The performance studies were for the physical device.

7. Type of Ground Truth Used:

The "ground truth" for the device's performance was established through functional testing and design verification testing against established engineering and design specifications. There was no pathological, outcomes data, or expert consensus ground truth in a clinical sense.

8. Sample Size for Training Set:

Not applicable. This device is a physical product, not an algorithm, so there is no "training set" in the context of machine learning.

9. How Ground Truth for Training Set Was Established:

Not applicable. There was no training set for an algorithm. The "ground truth" for the device's development was based on engineering specifications and predicate device designs.

Ask a specific question about this device