Search Results
Found 20 results
510(k) Data Aggregation
(117 days)
Minnesota 55112
Re: K250199
Trade/Device Name: VitalFlow Console
Regulation Number: 21 CFR 870.4100
cardiopulmonary failure
Classification: Class II (with special controls)
Regulation Number: 21 CFR 870.4100
The VitalFlow Console (Upgrade Over USB) device meets all special controls identified in 21 CFR 870.4100
The VitalFlow Console controls the speed of the VitalFlow Centrifugal blood pump during extracorporeal cardiopulmonary life support for adult patients with acute respiratory failure or acute cardiopulmonary failure, where other available treatment options have failed, and continued clinical deterioration is expected or the risk of death is imminent. The VitalFlow Centrifugal pump is driven by the VitalFlow Motor Drive or the VitalFlow Emergency Handcrank.
The VitalFlow Console provides control of blood pumping through an extracorporeal circuit during extracorporeal membrane oxygenation (ECMO) procedures. The console powers the VitalFlow motor drive unit which provides rotation of the VitalFlow Centrifugal pump. Pump motor speed (RPM) can be adjusted by the user and flow and bubble detection is provided by an ultrasonic flow probe and displayed on the touchscreen. The touchscreen display allows users to set alarm limits for all measured parameters. The device will alarm visually and audibly when limits are exceeded. Status indicators, power/battery life and secondary RPM indicator are provided. Data download and data streaming from the console is available for ECMO circuit data only; no patient data is stored for output.
The provided FDA 510(k) clearance letter for the VitalFlow Console (K250199) generally describes the device and its indications for use, and makes a case for substantial equivalence to a predicate device. However, it does not provide specific details about acceptance criteria or the study that proves the device meets those criteria, particularly regarding AI or algorithm performance.
The core of this submission is about a software upgrade to an existing hardware device (VitalFlow Console) which enables software upgrades via USB. The FDA clearance is based on demonstrating that this change does not raise new questions of safety or effectiveness and maintains the existing performance characteristics. Therefore, the information typically requested in your prompt (e.g., sample size for test sets, number of experts for ground truth, MRMC studies, AI effect size, etc.) would primarily be relevant if the upgrade introduced a new AI/algorithmic component or significantly altered a measurement or diagnostic function that required such validation.
Based on the document, here's what can be extracted and what cannot:
Analysis of the Provided Document Regarding Acceptance Criteria and Performance Study:
The document explicitly states:
"Software verification (which included Cybersecurity) was used to verify the performance characteristics of the subject device with the upgrade over USB change."
And:
"Substantial equivalence of the performance characteristics is demonstrated through regression testing. The VitalFlow Console (Upgrade Over USB) continues to meet international standards for safety and has demonstrated effectiveness at maintaining the device performance."
This indicates that the performance study focused on regression testing to ensure the new software upgrade feature (upgrade over USB) did not negatively impact the existing performance of the device or introduce new risks, especially related to cybersecurity. It was not a de novo study to establish new performance metrics for an AI or algorithmic component, as the device's fundamental function (controlling a blood pump) remains unchanged, and the cleared modification is about the method of software updating.
Therefore, most of the specific questions about AI/algorithm performance studies (e.g., number of experts, ground truth type, MRMC study) are not applicable to the scope of this particular 510(k) submission.
Extracted Information:
1. A table of acceptance criteria and the reported device performance:
| Acceptance Criteria (Inferred from Submission) | Reported Device Performance (from Submission) |
|---|---|
| Maintain Predicate Device's Performance Characteristics | "Continues to meet international standards for safety and has demonstrated effectiveness at maintaining the device performance." |
| No New Questions of Safety or Effectiveness Raised by Upgrade Over USB Feature | "The modified VitalFlow Console (Upgrade Over USB)... does not raise new or different questions of safety or effectiveness." |
| Compliance with Special Controls (21 CFR 870.4100) | "The VitalFlow Console (Upgrade Over USB) device meets all special controls identified in 21 CFR 870.4100." (e.g., technological characteristics, non-clinical performance via regression testing) |
| Cybersecurity Compliant | "Software verification (which included Cybersecurity) was used to verify the performance characteristics..." |
| Labeling Remains Adequate | "The Instructions for Use remain unchanged from the predicate submission K230364." |
2. Sample size used for the test set and the data provenance:
- Sample Size: Not explicitly stated. The testing mentioned is "Software verification" and "regression testing." For software changes, the "test set" would typically refer to the test cases used in the verification and validation (V&V) activities. The document does not provide the number of test cases run or the duration/number of runs for regression testing.
- Data Provenance: Not explicitly stated. Given that it's regression testing for a software update on an existing device, it would likely involve internal testing data and potentially real-world data from the existing predicate device's operational environment. It's implicitly a combination of retrospective (based on existing device performance) and prospective (new tests for the updated software) testing, but the document doesn't specify. Country of origin not mentioned.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Not Applicable / Not Stated. This type of information is typically required for studies establishing diagnostic accuracy or clinical effectiveness, often involving human readers/interpreters. This submission focuses on a software update for a control console, where "ground truth" would relate to the correct functioning of the software and hardware rather than clinical interpretation by experts. "Software verification" and "regression testing" would involve engineering and software quality assurance expertise to establish whether the device performed as specified.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:
- Not Applicable / Not Stated. Adjudication methods are relevant for subjective interpretations (e.g., medical images). For software verification and regression testing, failures are objective (e.g., a test case passes or fails, a function behaves as expected or not).
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 study was not conducted as this submission is not about a diagnostic AI/CAD device or a device that assists human interpretation in a new way. It's about a software update for a control console.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Not Applicable / Not Stated in this context. The "algorithm" here is the control software for the blood pump. Its "standalone" performance would be measured by its ability to precisely control the pump's RPM, detect flow, and manage alarms, which is what "software verification" and "regression testing" would assess. The document confirms these existing performance characteristics are maintained.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- Not Applicable in the traditional sense. For software verification and regression testing, the "ground truth" is the established functional and performance requirements of the device. This is confirmed through testing against design specifications, system requirements, and pre-existing performance benchmarks of the predicate device.
8. The sample size for the training set:
- Not Applicable. This is not an AI/Machine Learning device where a "training set" is relevant. The "software update" refers to a traditional software engineering change, not an AI model retraining.
9. How the ground truth for the training set was established:
- Not Applicable. As above, no training set for an AI model.
Summary of Device and Changes:
- Device: VitalFlow Console, controls a centrifugal blood pump for extracorporeal cardiopulmonary life support.
- Predicate: VitalFlow Console (K230364).
- Change in K250199: Enables software upgrades to be uploaded through the USB port (previously required Medtronic service personnel to open the console and connect laptops to individual boards).
- Regulatory Focus: Ensuring the new USB update feature does not compromise the safety or effectiveness of the device, particularly regarding cybersecurity and maintaining existing performance.
- Performance Study Type: Software verification and regression testing, indicating an engineering-focused validation rather than a clinical outcome or AI performance study.
Ask a specific question about this device
(164 days)
Re: K240880
Trade/Device Name: VitalFlow™ Set with Balance™ Biosurface Regulation Number: 21 CFR 870.4100
|
| Regulation Number: | 21 CFR 870.4100
The VitalFlow™ Set with Balance™ Biosurface device meets all special controls identified in 21 CFR 870.4100
The VitalFlow Set with Balance Biosurface is indicated for respiratory/cardiopulmonary support up to 48 hours that provides assisted extracorporeal circulation and physiologic gas exchange (oxygenation) of the patient's blood in adults with acute respiratory failure or acute cardiopulmonary failure, where other available treatment options have failed, and continued clinical deterioration is expected or the risk of death is imminent.
VitalFlow Sets with Balance™ Biosurface contain components used to prepare an extracorporeal circuit for ECMO procedures. The components include the VitalFlow Tubing Sets packaged together with the legally marketed Nautilus VF Oxygenator and VitalFlow Centrifugal Pump as a standard kit. The components are connected together to prepare an extracorporeal circuit for ECMO procedures.
The VitalFlow Tubing Set contains a preassembled drainage and return loop "ECMO Circuit," tubing assemblies, and other components used to prepare a basic extracorporeal circuit. The tubing assembly is provided pre-connected to the inlet of the VitalFlow Centrifugal Pump. The "Priming Circuit" contains components to supplement the basic extracorporeal circuit, as needed per hospital protocols for setting up the ECMO circuit. A venous reservoir and one-way valve are included in the priming circuit to facilitate ease of priming the ECMO circuit.
This product is nonpyrogenic, is intended for single use, and has been sterilized using ethylene oxide.
The Medtronic VitalFlow™ Set with Balance™ Biosurface is indicated for respiratory/cardiopulmonary support up to 48 hours for adults with acute respiratory or cardiopulmonary failure. The acceptance criteria and supporting study details are as follows:
1. Acceptance Criteria and Reported Device Performance
The acceptance criteria for the VitalFlow Set with Balance Biosurface primarily focus on demonstrating substantial equivalence to a predicate device and ensuring acceptable performance through pre-clinical bench testing and real-world clinical evidence. While explicit numerical acceptance criteria for many mechanical and biocompatibility tests are not provided in the summary, the overall conclusion is that the device "does not raise different questions of safety or effectiveness" compared to the predicate. The clinical summary provides comparative performance data for complications.
| Acceptance Criteria Category | Specific Criteria / Performance Target (Implied) | Reported Device Performance |
|---|---|---|
| Technological Characteristics | Consistent with intended use in extracorporeal support and compatible with other devices/accessories. | Geometry and design parameters are consistent with intended use and compatible with other devices/accessories in the extracorporeal circuit. |
| Biocompatibility | Must be biocompatible in accordance with ISO 10993-1. | Demonstrated to be biocompatible in accordance with ISO 10993-1. |
| Sterility and Shelf-Life | Maintain sterility, integrity, durability, and reliability over stated shelf-life. | Sterilization adoption evaluation and shelf-life assessment demonstrate maintenance of sterility, integrity, durability, and reliability over a 2-year shelf life. |
| Non-clinical Performance | Substantial equivalence of performance characteristics démontré on bench, mechanical integrity, durability, and reliability testing. | Pre-clinical bench studies were conducted, including simulated use durability, tensile strength, pressure tests, functional testing, kink testing, blood trauma testing, and coating coverage. The summary states "sufficient to demonstrate," implying these tests met internal criteria for equivalence. |
| Clinical Performance (Complications) | Comparable or favorable complication rates compared to "All other ECMO Systems" (a large cohort from the ELSO Registry). | Overall Complication Rate (≥ 1 of any): VitalFlow Set: 38.5% (75/195) vs. All other ECMO Systems: 35.1% (21501/61176). |
| Mechanical Complications: |
- Oxygenator Failure (Prevalence): VitalFlow Set: 4.6% (9/195) vs. All other ECMO Systems: 8.0% (4878/61176).
- Oxygenator Failure (Rate per 1000 Hrs): VitalFlow Set: 0.30 vs. All other ECMO Systems: 0.35.
- Pump Failure (Prevalence): VitalFlow Set: 2.6% (5/195) vs. All other ECMO Systems: 0.6% (368/61176).
- Pump Failure (Rate per 1000 Hrs): VitalFlow Set: 0.16 vs. All other ECMO Systems: 0.02.
- Thrombosis/Clots in Circuit Component: VitalFlow Set: 1.0% (2/195) vs. All other ECMO Systems: 2.1% (1272/61176).
Hemolysis: - Moderate or Severe Hemolysis: VitalFlow Set: 2.1% (4/195) vs. All other ECMO Systems: 5.2% (3197/61176).
(Other specific complication rates are listed in the table in the document and generally show comparable or lower rates for VitalFlow Sets, with the exception of pump failure prevalence and rate). |
| Labeling | Include detailed summary of non-clinical evaluations, instructions for anticoagulation, circuit setup, performance, and maintenance. | Instructions for Use include the required details. |
2. Sample Size for Test Set and Data Provenance
- Sample Size for Clinical "Test Set": 195 patients (VitalFlow Set group).
- Data Provenance: The data comes from a "summary of real-world evidence (195 reports) of the clinical experience with the VitalFlow Set from the ELSO Registry." This indicates the data is retrospective and derived from a registry, which typically collects data from multiple institutions/countries. The specific country of origin is not explicitly stated but the ELSO Registry is an international organization.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
The document does not specify the number of experts or their qualifications for establishing ground truth for the clinical complication data from the ELSO Registry. Registry data often involves reporting by treating clinicians, and data validation/adjudication processes vary by registry but are not detailed here.
4. Adjudication Method for the Test Set
The document does not describe any specific adjudication method (e.g., 2+1, 3+1) for the clinical complication data from the ELSO Registry. It is implied that the reported complication rates are based on the data as collected and recorded within the registry.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
No MRMC comparative effectiveness study was mentioned. The study evaluates the device's performance in a real-world setting rather than comparing human readers with and without AI assistance.
6. Standalone Performance Study (Algorithm Only Without Human-in-the-Loop Performance)
This question is not applicable as the device is a medical device (extracorporeal circuit components) and not an AI algorithm. Its performance is inherent to its mechanical and biological functions, not an algorithm's output.
7. Type of Ground Truth Used
The ground truth for the clinical performance data (complication rates) is based on real-world outcomes data collected and reported to the ELSO Registry. For the pre-clinical tests, the ground truth would be established by validated test methods and engineering specifications.
8. Sample Size for the Training Set
This question is not applicable as the device is not an AI algorithm requiring a training set. The "training set" concept does not apply to the development and evaluation of this type of medical device.
9. How the Ground Truth for the Training Set Was Established
This question is not applicable for the reasons stated above.
Ask a specific question about this device
(53 days)
Trade/Device Name: Bio-Medicus Life Support Catheter and Introducer Regulation Number: 21 CFR 870.4100
failure |
| Regulation Number: | 21 CFR 870.4100
Bio-Medicus Life Support™ Catheter and Introducer device meets all special controls identified in 21 CFR 870.4100
Cardiopulmonary Bypass (CPB): Bio-Medicus Life Support catheters are peripheral-access catheters used to perfuse vessels or organs in conjunction with extracorporeal cardiopulmonary bypass (CPB) procedures. The catheter introducer is intended to facilitate proper insertion and placement of the appropriately sized catheter within the vessel. Catheter models with tip lengths of 18 cm (7.09 in), 50 cm (19.7 in), or 55 cm (21.7 in) and without additional side holes may be used as either drainage or reinfusion catheters. This product is intended for use in adult and pediatric patients for up to 6 hours.
Extracorporeal Membrane Oxygenation (ECMO) and Extracorporeal Life Support (ECLS): The Bio-Medicus Life Support catheters and introducers are single-lumen drainage or reinfusion peripheral-access catheters to be used in ECMO or ECLS with an extracorporeal circuit intended for use in adult and pediatric patients with acute respiratory or acute cardiopulmonary failure. where other available treatment options have failed, and continued clinical deterioration is expected or the risk of death is imminent.
The Bio-Medicus Life Support™ catheter is a single-lumen catheter used to drain or reinfuse blood. The introducer facilitates proper insertion and placement of the appropriately sized catheter over a guidewire within the vessel. These devices are intended to perfuse vessels or organs in conjunction with extracorporeal support, including cardiopulmonary bypass (CPB), Extracorporeal Membrane Oxygenation (ECMO) and Extracorporeal Life Support (ECLS). Catheter models with tip lengths of 18 cm (7.09 in), 50 cm (19.7 in), or 55 cm (21.7 in), with and without additional side holes may be used as either drainage or reinfusion catheters.
These devices are sterile, nonpyrogenic, disposable, intended for single use only. Do not store the product above 25℃ (77°F).
The provided text is a 510(k) summary for the Medtronic Bio-Medicus Life Support Catheter and Introducer. It details the device, its intended use, comparison to a predicate device, and performance testing. However, it does not describe acceptance criteria for an AI-powered device, nor does it detail a study proving such a device meets acceptance criteria.
The information provided pertains to a traditional medical device (a catheter and introducer) with a material formulation change, and the "performance testing" described is bench testing and biocompatibility assessments to demonstrate substantial equivalence to a predicate device. There is no mention of AI, machine learning, or software performance in terms of diagnostic accuracy or effect on human readers.
Therefore,Based on the provided text, it is not possible to describe the acceptance criteria or a study that proves a device meets acceptance criteria for an AI-powered device. The document pertains to a traditional medical device (catheter and introducer), specifically addressing a material change to a component (luer cap). There is no mention of AI, machine learning, or any form of algorithm-driven performance evaluation.
The "Summary of Performance Testing" section focuses on demonstrating substantial equivalence of the modified luer cap through risk-based testing, functional testing, and biocompatibility assessment, which are standard for physical medical devices.
Here's a breakdown of why the requested information cannot be provided from the given text:
- No AI Component: The device described (Bio-Medicus Life Support Catheter and Introducer) is a physical medical device. The document explicitly states the "device modification was made to the predicate device: Luer cap material formulation change (vented connector models)." This is a hardware change, not a software or AI change.
- No Diagnostic or Classification Task: The device's function is to facilitate extracorporeal support procedures (CPB, ECMO, ECLS), not to interpret data, diagnose conditions, or assist human readers in a diagnostic capacity.
- No Performance Metrics for AI: The "performance testing" described is for the physical integrity and biocompatibility of the luer cap ("functional testing and biocompatibility assessment"), which are not the types of metrics (e.g., sensitivity, specificity, AUC, human reader improvement) that would be used for AI device acceptance criteria.
To directly answer your request based on the provided text, I must state that the information is not present:
- A table of acceptance criteria and the reported device performance: Not applicable. The document describes bench testing to qualify a material change, not AI performance metrics.
- Sample sized used for the test set and the data provenance: Not applicable. The "test set" here refers to physical components for bench testing, not a dataset for AI evaluation.
- Number of experts used to establish the ground truth... and qualifications: Not applicable. Ground truth as typically defined for AI validation (e.g., for image interpretation) is not established for this physical device.
- Adjudication method: Not applicable. There is no interpretive task requiring adjudication.
- If a multi-reader multi-case (MRMC) comparative effectiveness study was done: No. This type of study is for AI-assisted human performance, which is not relevant to this device.
- If a standalone (i.e., algorithm only without human-in-the-loop performance) was done: Not applicable. There is no algorithm.
- The type of ground truth used: Not applicable.
- The sample size for the training set: Not applicable. There is no training set for an AI model.
- How the ground truth for the training set was established: Not applicable.
In conclusion, the provided FDA document is for a traditional medical device (catheter) and does not contain any information related to AI acceptance criteria or AI performance studies.
Ask a specific question about this device
(208 days)
Massachusetts 02451
Re: K232926
Trade/Device Name: Novalung ultimate kit (US) Regulation Number: 21 CFR 870.4100
|
| Regulatory Class: | Class II per 21 CFR § 870.4100
Coating materials
The Novalung ultimate kit (US) meets all special controls required by 21 CFR § 870.4100
The Novalung System is indicated for long-term (> 6 hours) respiratory/cardiopulmonary support that provides assisted extracorporeal circulation and physiologic gas exchange (oxygenation and CO2 removal) of the patient's blood in adults with acute respiratory failure or acute cardiopulmonary failure, where other available treatment options have failed, and continued clinical deterioration is expected or the risk of death is imminent. These may include:
- · Failure to wean from cardiopulmonary bypass following cardiac surgery in adult patients
- · ECMO-assisted cardiopulmonary resuscitation in adults
The Novalung ultimate kit (US) is a single use, ethylene oxide (EO) sterilized device comprised of a disposable tubing set and accessories. The Novalung ultimate kit (US) contains a disposable tubing set, pump head, oxygenator with heat exchanger, and accessories (gas line, priming line, stopcocks, luer caps, Christmas tree connector, tubing clamps, cable ties). The tubing set is pre-connected to a hollow fiber membrane oxygenator and blood pump head (Deltastream DP3 3/8"), which forms an extracorporeal circuit. All blood-contacting surfaces of the tubing set, except for the blood pump head, are coated with x.ellence coating. The Novalung ultimate kit (US) tubing set has three (3) integrated pressure sensors (IPS) that connect to the Novalung System sensor box. The flow sensor detects air bubbles in the extracorporeal circuit and measures blood flow. The Novalung ultimate kit (US) provides treatment for a blood flow range of 1-6.5 L/min and has a total extracorporeal priming volume of 670 mL ± 10%. In the Novalung ultimate kit (US), blood flows from the patient through the tubing set with IPSs, through the pump head and the oxygenator, and back to the patient. Blood flow is driven through the oxygenator by the pump head that is powered by the Novalung System console's pump drive.
The provided document is a 510(k) premarket notification for a medical device called the "Novalung ultimate kit (US)". This device is an extracorporeal circuit and accessories used for long-term respiratory/cardiopulmonary support. There is no mention of Artificial Intelligence (AI) or machine learning (ML) in this document, so it does not contain the information needed to answer your questions about AI device acceptance criteria or performance studies.
The document primarily focuses on demonstrating the substantial equivalence of the Novalung ultimate kit (US) to a legally marketed predicate device (Novalung System XLung kit, K191407) through non-clinical performance testing and biocompatibility assessments.
Therefore, I cannot provide the requested information regarding:
- A table of acceptance criteria and reported device performance related to an AI/ML device.
- Sample sizes used for a test set, data provenance, or details about training sets for an AI/ML device.
- Number of experts, qualifications, or adjudication methods for establishing ground truth for an AI/ML device.
- MRMC studies or effect sizes for human readers with and without AI assistance.
- Standalone performance of an algorithm.
- Type of ground truth used for an AI/ML device.
Ask a specific question about this device
(29 days)
: K234118
Trade/Device Name: CentriMag™ Acute Circulatory Support System Regulation Number: 21 CFR 870.4100
|
| | Class II, QNR, 21 CFR 870.4100
The CentriMag Extracorporeal Blood Pumping System is a non-roller-type cardiopulmonary and circulatory bypass blood pump used to pump a patient's blood through an extracorporeal circuit for periods lasting less than 6 hours for the purpose of providing either: i. Full or partial cardiopulmonary bypass (i.e., circuit includes an oxygenator) during open surgical procedures on the heart or great vessels: or ii. Temporary circulatory bypass for diversion of flow around a planned disruption of the circulatory pathway necessary for open surgical procedures on the aorta or vena cava The CentriMag™ Blood Pump for use with the CentriMag™ Acute Circulatory Support System (Motor, Monitor, Console, and Flow Probes) is indicated for controlling blood flow as part of an extracorporeal membrane oxygenation (ECMO) circuit. ECMO is intended to provide assisted extracorporeal circulation and physiologic gas exchange of the patients' blood for adult patients with acute respiratory failure and/or acute cardiopulmonary failure. where other available treatment options have failed, and continued clinical deterioration is expected or the risk of death is imminent.
The CentriMag™ Acute Circulatory Support System, hereafter referred to as the CentriMag System, was designed to provide temporary mechanical circulatory support. To date, the CentriMag system in the United States (US) is indicated as a component of an extracorporeal bypass circulatory support circuit for use during cardiopulmonary bypass (CPB) surgery (up to 6 hours), it is also indicated for controlling blood flow as part of an extracorporeal membrane oxygenation (ECMO) circuit. The CentriMag System provides circulatory assistance for patients in acute hemodynamic compromise, a population whose treatment options are limited. The CentriMag System is composed of: - CentriMag Primary Console - CentriMag Motor - CentriMag Blood Pump - CentriMag Flow Probe - · Mag Monitor The CentriMag Motor is a reusable, non-sterile component of the CentriMag System. The CentriMag Motor holds the blood pump and drives the impeller inside the blood pump. The motor turns the magnet (and impeller) within the blood pump (Full MagLev™ technology) at a speed that is set on the console by the user. When the impeller is rotated, a pressure gradient develops between the center and outside edge of the pump, causing blood to flow from the inflow to the outflow port of the pump. The amount of flow through the pump depends on the speed of the impeller, and the difference between the inlet and outlet pressures.
The provided documents describe a 510(k) submission for the Abbott CentriMag™ Acute Circulatory Support System. This submission is a "Special 510(k)," which means it addresses a modification to an already cleared device. The primary change is an update to the CentriMag Motor, specifically a new "snap-in motor locking feature" replacing a "screw locking feature."
Therefore, the acceptance criteria and performance study described are focused on demonstrating that this change does not negatively impact the safety and effectiveness of the device and that the new design is substantially equivalent to the predicate device.
Here's the breakdown of the requested information based on the provided text:
1. A table of acceptance criteria and the reported device performance
Since this is a Special 510(k) for a design change (motor locking mechanism), the "performance" is about demonstrating that the new design is as safe and effective as the previous one, and that it conforms to requirements for its intended use. The document doesn't list specific numerical acceptance criteria (e.g., a "failure rate must be less than X%"). Instead, it describes categories of testing performed to ensure the new design performs adequately.
| Acceptance Criteria Category (Implicit via testing) | Reported Device Performance (Summary of results) |
|---|---|
| Mechanical Integrity & Robustness: The new snap-in locking feature can withstand physical stresses (drop, shock, vibration). | Environmental Testing: Drop, shock, and vibration testing was executed. (Implies satisfactory performance, as no issues were raised). |
| Durability: The new locking feature maintains its function over a prolonged period of use. | Durability Testing: Performed. (Implies satisfactory performance, as no issues were raised). |
| Cleanability: The new motor design can be adequately cleaned. | Cleaning Testing: Performed for the CentriMag Motor. (Implies satisfactory performance, as no issues were raised). |
| Manual Usability & Accuracy: The operating manual accurately reflects the device's function and can be followed by users. | Operating Manual Verification Testing: Performed. (Implies satisfactory performance, as no issues were raised). |
| Human Factors & Usability: The changes in the user interface (due to the snap-in feature) are safe and effective for users. | Summative Human Factors Validation Testing: Performed for the changes in user interface. (Implies satisfactory performance, as no issues were raised). |
| No New Safety or Performance Issues: The design change does not introduce new hazards or reduce performance. | Overall Conclusion: "The results of these tests provide reasonable assurance that the proposed device has been designed and tested to assure conformance to the requirements for its intended use. No new safety or performance issues were raised during the testing..." |
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 specify the sample sizes for any of the verification or validation tests (e.g., number of motors subjected to durability testing, number of users in human factors testing).
The testing described (Mechanical, Durability, Cleaning, Operating Manual Verification, Human Factors Validation) are typically prospective engineering and usability tests conducted by the manufacturer, not retrospective studies on patient data. The provenance for such tests would be the manufacturer's testing facilities, likely in the US (given the submitter's address in California).
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)
This section is not applicable in the context of this 510(k) submission. The "ground truth" concept, often associated with clinical diagnostic studies requiring expert review of medical images or patient outcomes, is not relevant here. The studies described are hardware and human factors engineering tests. For human factors, users (not necessarily "experts" in the medical sense, but representative users of the device) would participate to validate the user interface changes. Their qualifications are not specified but would typically align with the intended users (e.g., perfusionists, surgeons, nurses).
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
This is not applicable to the type of engineering and human factors testing described. Adjudication methods like "2+1" are used in clinical studies where multiple experts independently review cases and discrepancies are resolved by a third party.
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
This is not applicable. The device is a mechanical circulatory support system (pump, motor, console, flow probe), not an AI-assisted diagnostic or clinical decision support tool that would involve human readers interpreting data.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
This is not applicable. The device is a physical medical device (mechanical support system), not a software algorithm or AI. Its operation inherently involves a human in the loop (a clinician operating the system).
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
"Ground truth" as traditionally understood in clinical validation studies (e.g., pathology for cancer detection, long-term outcomes for treatment efficacy) is not directly applicable here. For the engineering tests, the "ground truth" is simply the documented design specifications and functional requirements of the device. For human factors, the "ground truth" or success criteria would be based on validated usability principles and the ability of representative users to safely and effectively operate the device with the new feature.
8. The sample size for the training set
This is not applicable. This is a hardware modification to an existing device, not a machine learning or AI algorithm that requires a training set.
9. How the ground truth for the training set was established
This is not applicable, as there is no training set for a hardware modification.
Ask a specific question about this device
(58 days)
Pittsburgh, Pennsylvania 15238
Re: K233736
Trade/Device Name: LifeSPARC System Regulation Number: 21 CFR 870.4100
Extracorporeal Circuit and Accessories for Long-Term
Respiratory/Cardiopulmonary Failure (21 CFR 870.4100
Extracorporeal Membrane Oxygenation
The LifeSPARC System is a centrifugal blood pump system intended to assist in circulation of the patient's blood when part of an extracorporeal circuit including physiologic gas exchange of the patient's blood in adult patients with acute respiratory failure or acute cardiopulmonary failure, where other available treatment options have failed, and continued clinical deterioration is expected or the risk of death is imminent. These may include:
· Failure to wean from cardiopulmonary bypass following cardiac surgery in adult patients;
· ECMO-assisted cardiopulmonary resuscitation in adults.
Cardiopulmonary Bypass
The LifeSPARC System is intended to pump the blood through an extracorporeal circuit for periods lasting less than 6 hours for the purpose of providing either: (i) Full or partial cardiopulmonary bypass (i.e., circuit includes an oxygenator) during open surgical procedures on the heart or great vessels; or (ii) Temporary circulatory bypass for diversion of flow around a planned disruption of the circulatory pathway necessary for open surgical procedures on the aorta or vena cava.
The LifeSPARC Pump is a sterile, single-use, low prime volume centrifugal pump with an integrated motor and a single-point, pivot bearing. It is sterilized using ethylene oxide (EO) and sized to fit in the palm of the hand or to secure to the patient.
The LifeSPARC Controller provides the interface between pump and user, as well as the power and electrical signals to drive the pump. It is a microprocessor-based electromechanical pump drive system designed to operate on standard AC current (100/240 VAC, 50/60 Hz) or on internal, rechargeable batteries for intra-hospital transport.
The provided document is a 510(k) premarket notification summary for the CardiacAssist, Inc. LifeSPARC System. This submission appears to be for a software update to an already cleared device, not for a new device requiring extensive clinical trials to prove its performance against specific acceptance criteria.
The document does not contain the information requested regarding acceptance criteria and a study that proves the device meets those criteria, as such a study would typically be conducted for a novel device or a significant change in intended use, which is not the case here.
Here's why the requested information is absent and what the document does indicate:
-
A table of acceptance criteria and the reported device performance: This is not present. The submission focuses on demonstrating "substantial equivalence" to previously cleared versions of the LifeSPARC System, specifically due to a software update. This means the performance is assumed to be equivalent to the predicate devices, rather than being re-evaluated against new, explicit acceptance criteria.
-
Sample size used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective): Not applicable in the context of this submission. The testing mentioned is "Software Verification and Validation testing (including Cybersecurity)," which typically does not involve human patient data or "test sets" in the clinical sense.
-
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" established by clinical experts is relevant for diagnostic or AI-driven devices that interpret complex data (like medical images). This device is a mechanical pump system with a controller, and its "performance" is assessed through engineering and software validation.
-
Adjudication method (e.g., 2+1, 3+1, none) for the test set: Not applicable for the reasons stated above.
-
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 not an AI diagnostic tool and does not involve "human readers" interpreting data with or without AI assistance.
-
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: The document mentions "Software Verification and Validation testing." This type of testing evaluates the algorithm's performance in isolation (standalone), but it's in the context of a software update for a medical device's control system, not a diagnostic algorithm.
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc.): Not applicable. For software validation, the "ground truth" would be the expected functional behavior of the software as defined by its requirements and specifications.
-
The sample size for the training set: Not applicable. This is not an AI/machine learning model that requires a training set.
-
How the ground truth for the training set was established: Not applicable.
Summary of what the document does state regarding performance and testing:
- Device Change: The submission is for an update to the software version of a currently cleared device (LifeSPARC System). All other aspects of the device are identical to the predicate and reference devices.
- Testing Performed: "Software Verification and Validation testing (including Cybersecurity) was completed for the Subject device with the new software."
- Conclusion: "Testing described in this notification demonstrates that the Subject LifeSPARC System performance is substantially equivalent to the legally marketed Predicate LifeSPARC System (K211830) and Reference device (K232132)." The document explicitly states that "no concerns regarding safety and effectiveness result from the software changes."
In essence, this FDA 510(k) clearance is based on demonstrating that the software update does not change the safety or effectiveness of the device compared to its previously cleared versions, and therefore, it is "substantially equivalent." It is not a submission for a new device requiring extensive new clinical performance data against pre-defined acceptance criteria.
Ask a specific question about this device
(51 days)
15238
Re: K232480
Trade/Device Name: ProtekDuo Veno-Venous Cannula Sets Regulation Number: 21 CFR 870.4100
Extracorporeal Circuit and Accessories for Long-Term
Respiratory/Cardiopulmonary Failure (21 CFR 870.4100
devices.
Special Controls:
The ProtekDuo Cannula Sets meet all special controls required by 21 CFR 870.4100
The ProtekDuo Veno-Venous Cannula is a single use dual lumen cannula, which provides both venous drainage and reinfusion of blood via the jugular vein, that is indicated for use in adult patients with acute requiring Veno-Venous Extracorporeal Membrane Oxygenation, where other available treatment options have failed and continued clinical deterioration is expected or the risk of death is imminent.
Each ProtekDuo Veno-Venous Cannula Set includes a dual lumen cannula and an introducer. The introducer is designed to accept a standard 0.038-inch guidewire. The ProtekDuo Veno-Venous Cannula Sets are intended as single patient, single use, sterile devices.
Each ProtekDuo Veno-Venous Cannula consists of two (2) distinct lumens, each made of polyurethane with a wire-reinforced cannula body. The inner lumen is located entirely within the outer lumen forming two concentric channels.
The distal section (inner lumen/cannula) of the cannula body is the smaller diameter lumen with six (6) side holes near the distal tip opening. The proximal sections of each lumen are clear and not wire-reinforced to allow visualization of blood and to enable clamping to prevent blood flow during set-up and removal of the cannula from the extracorporeal circulatory support equipment. A non-vented barbed connector is affixed to both proximal ends (inner/distal and outer/proximal lumens) of the cannula and allow for connection of standard 3/8-inch blood circuit tubing for subsequent connection to extracorporeal circulatory support equipment. The cannula has two suture wings that can be used for securing the cannula in place to the patient. The cannulas also have printed insertion depth markings measured from the distal tip.
Each introducer consists of a tube and hub. The introducer fits inside the inner lumen of the cannula during insertion of the cannula/introducer assembly. The introducer is used to advance the cannula over a guidewire and facilitate cannula placement within the target vessel. The introducer has a hub at its proximal end to manage introducer insertion and removal from the cannula. The hemostasis cap minimizes blood loss when the cannula/introducer assembly is inserted into the target vessel. The introducer body is constructed from radiopaque polyvinyl chloride material for visualization under fluoroscopy.
This document describes the premarket notification (510(k)) for the ProtekDuo Veno-Venous Cannula Sets, asserting their substantial equivalence to legally marketed predicate devices. The information provided outlines the device's technical characteristics, its intended use, and the non-clinical testing performed to demonstrate its performance.
However, the provided text does not contain specific acceptance criteria or details of a study that proves the device meets those criteria in the context of an AI/human reader performance study. The document focuses on regulatory approval (510(k) clearance) based on substantial equivalence to existing devices, primarily through non-clinical testing and an in vivo animal study. It does not mention any AI component or human reader performance evaluation.
Therefore, I cannot fulfill the request to provide information based on the input about:
- A table of acceptance criteria and reported device performance (in the context of AI/human reader performance)
- Sample sized used for the test set and data provenance (for an AI/human reader study)
- Number of experts used to establish ground truth and qualifications (for an AI/human reader study)
- Adjudication method (for an AI/human reader study)
- MRMC comparative effectiveness study, effect size
- Standalone (algorithm only) performance study
- Type of ground truth used (for an AI/human reader study)
- Sample size for the training set (for an AI)
- How ground truth for the training set was established (for an AI)
The document's "acceptance criteria" are related to regulatory conformity (e.g., biocompatibility, sterility, mechanical integrity) and "performance" refers to the device's physical and functional characteristics (e.g., flow rates, tensile strength) demonstrated through non-clinical bench testing and an animal study, not human or AI diagnostic performance.
Based on the provided document, here's what can be extracted regarding the device's acceptance criteria and proof of performance:
The acceptance criteria for the ProtekDuo Veno-Venous Cannula Sets are primarily defined by the Special Controls outlined in 21 CFR 870.4100 for Extracorporeal Circuit and Accessories for Long-Term Respiratory/Cardiopulmonary Failure. The study proving the device meets these criteria is a series of non-clinical tests (bench tests) and an in vivo animal study.
1. Table of Acceptance Criteria (Special Controls) and Reported Device Performance:
| Acceptance Criteria (Special Controls) | Reported Device Performance (Summary) |
|---|---|
| #1: Technological Characteristics (geometry, design, compatibility) | Established through use in ECMO procedures. Designed to be compatible with other extracorporeal circuit devices and accessories. |
| #2: Biocompatibility | Demonstrated to be biocompatible for prolonged (24 hours to 30 days) contact with circulating blood in accordance with ISO 10993-1. |
| #3: Sterility and Shelf-Life | Testing demonstrates sterility as provided and maintenance of sterility, integrity, durability, and reliability over the stated shelf-life. |
| #4: Non-clinical Performance Evaluation (bench, mechanical integrity, EMC, software, durability, reliability) | Substantial equivalence demonstrated by performance characteristics assessed through: Simulated Use/Reliability (30 days), Hemolysis, Pressure/Flow Characteristics, Tensile Strength, Leak, Deflection/Stiffness (Cannula, Introducer, Assembly), Kink Resistance, and Recirculation. |
| #5: In vivo Evaluation (performance over intended duration, clinical evaluation summary) | A 14-day in vivo evaluation demonstrated performance over a long-term duration of use in a biologic test system. (Note: This is an animal study, not a human clinical trial for this 510(k)). |
| #6: Labeling (non-clinical/in vivo summaries, instructions, compatibility, maintenance) | The Directions for Use contain the information detailed in this Special Control. |
2. Sample Size Used for the Test Set and Data Provenance:
- Test Set (Non-Clinical/Bench Testing): Specific sample sizes for each non-clinical test (e.g., number of cannulas tested for tensile strength, number of setups for pressure/flow) are not detailed in this summary. However, these would be standard engineering test sample sizes to ensure statistical validity for the specific tests performed (e.g., according to ISO standards or internal validation protocols).
- Test Set (In Vivo): The summary mentions a "14-day in vivo evaluation" in a "biologic test system." The specific number of animals used for this study is not provided in this document.
- Data Provenance: The testing appears to be conducted by the manufacturer or contract research organizations as part of their regulatory submission for the device. The country of origin for the data is implied to be related to the applicant's location (Pittsburgh, PA, USA) or its testing facilities. It is a prospective set of tests and studies specifically performed for this 510(k) submission.
3. Number of Experts Used to Establish Ground Truth and Qualifications: Not applicable as this submission is for a medical device (cannula) based on physical and biological performance, not an AI or diagnostic imaging device requiring expert reader ground truth.
4. Adjudication Method: Not applicable.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study: Not applicable.
6. Standalone (i.e., algorithm only without human-in-the-loop performance) Study: Not applicable.
7. The Type of Ground Truth Used:
For the non-clinical tests, the "ground truth" is established by physical measurement standards, engineering specifications, and established biological/material compatibility protocols (e.g., ISO standards for biocompatibility, flow dynamics equations for pressure/flow).
For the in vivo animal study, the "ground truth" would be the observed physiological function and integrity of the device within the biologic system over the 14-day period.
8. The Sample Size for the Training Set: Not applicable, as this is not an AI/machine learning device.
9. How the Ground Truth for the Training Set Was Established: Not applicable.
Ask a specific question about this device
(23 days)
Michigan 48130
Re: K232767
Trade/Device Name: Nautilus VF ECMO Oxygenator Regulation Number: 21 CFR 870.4100
|
| Regulation Number: | 21 CFR 870.4100
risks of this device are mitigated by meeting the Special Controls required by the regulation, 21 CFR 870.4100
The Nautilus VF ECMO Oxygenator with integrated heat exchanger is intended to provide assisted long-term extracorporeal circulation and physiologic gas exchange (oxygenation and carbon dioxide removal) of the patient's blood for up to 48 hours in adult and pediatric adolescent patients with acute respiratory failure or acute cardiopulmonary failure, where other available treatment options have failed, and continued clinical deterioration is expected or the risk of death is imminent. The integrated heat exchanger is intended to heat or cool the blood as needed during use. Integrated fluid path pressure, temperature, and oxygen saturation monitoring is achieved by built-in sensor modules.
The Nautilus™ ECMO oxygenators are diffusion membrane oxygenators used in extracorporeal life support procedures to oxygenate blood, remove carbon dioxide and regulate blood temperature. Blood enters the device and passes through both the heat exchange membrane, where temperature is adjusted, and the gas transfer membrane, where oxygen is added and carbon dioxide is removed.
The Nautilus™ VF ECMO Oxygenator device contains integrated sensors that connects to the VitalFlow Console (K230364) for the display of measured parameters. The following measured parameters are measured: inlet pressure, inlet oxygen saturation, outlet oxygen saturation, and outlet blood temperature. The difference between the inlet and outlet pressure, is calculated. The device is intended to be interconnected with a VitalFlow Console device that receives digital data from the oxygenator.
The oxygenator devices are single-use, nontoxic, non-pyrogenic, and not made from natural latex rubber materials.
The provided FDA 510(k) summary for the Nautilus VF ECMO Oxygenator describes the device and its substantial equivalence to a predicate device. However, it does not contain information typically found in a study proving a device meets acceptance criteria within the context of AI/ML-powered medical devices.
This document is for a medical device (an oxygenator) and its associated monitoring components, not an AI/ML diagnostic or prognostic algorithm. Therefore, the questions related to AI/ML specific criteria (such as effect size of human readers with AI vs. without AI, ground truth establishment for training sets, number of experts for ground truth, etc.) are not applicable in this context.
Here's an analysis of the information that is present or can be inferred, formatted to address your questions where possible, and noting where information is missing or irrelevant to this type of device:
Device Acceptance Criteria and Performance
The document describes "Performance Evaluations" and "Special Controls" that were met to demonstrate substantial equivalence to the predicate device (Nautilus™ Smart ECMO Module (K191935) and Nautilus™ ECMO Oxygenator (K191935)). These act as the acceptance criteria for the device clearance.
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria Category | Specific Criteria/Evaluation | Reported Device Performance |
|---|---|---|
| Performance Evaluations | Electrical Safety/EMC | Evaluated, demonstrated substantial equivalence. |
| Software Validation | Evaluated, demonstrated substantial equivalence. | |
| Cybersecurity analysis | Evaluated, demonstrated substantial equivalence. | |
| Special Controls | Technological Characteristics | Geometry and design parameters are consistent with intended use. Compatible with other ECLS devices. Oxygenator geometry is same as predicate. Electronic module modified but demonstrated equivalent performance. |
| Biocompatibility | Demonstrated biocompatible for prolonged use per ISO 10993-1:2009 and GLP (21 CFR 58). No modifications to blood contact surfaces. | |
| Sterility and Shelf-life | Testing demonstrates sterility as provided, and maintenance of sterility, integrity, durability, and reliability over stated shelf-life. | |
| Non-clinical Performance | Substantial equivalence demonstrated by bench performance, mechanical integrity, electromagnetic compatibility, software, durability, reliability, and accuracy. Further demonstrated by EMC, software validation, and cybersecurity analysis. | |
| In vivo Evaluation | Demonstrates performance over long-term duration in a biologic test system. Summary of initial real-world clinical experience into ELSO registry was included. Original design's evaluation applicable as oxygenator design is unchanged. | |
| Labeling | Includes detailed summary of non-clinical evaluations, installation, setup, maintenance, changeout, adverse effects, and performance characteristics related to compatibility. |
2. Sample size used for the test set and the data provenance
The document mentions "bench studies" for performance evaluations, and "in vivo evaluation" using a "biologic test system" and a "summary... described the initial real-world clinical experience... into the ELSO registry."
- Sample Size for Bench Studies: Not specified. Bench studies typically involve a set number of device units for various tests (e.g., electrical, mechanical, software).
- Sample Size for In Vivo Evaluation: Not specified, but refers to a "biologic test system" and "initial real-world clinical experience with the first records of clinical ECMO cases entered sequentially into the ELSO registry." The exact number of cases or subjects is not provided in this summary.
- Data Provenance: The "ELSO registry" implies multi-center, international data, but the specific country of origin or whether it's retrospective/prospective is not detailed for the "real-world clinical experience" summary. The "biologic test system" would be a controlled lab setting.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
This information is not applicable and not provided for this type of medical device. The evaluation of an oxygenator focuses on its physical, chemical, electrical, and biological performance characteristics, not on diagnostic accuracy requiring expert interpretation or "ground truth" establishment in the way an AI algorithm for image analysis would.
4. Adjudication method for the test set
This information is not applicable and not provided. Adjudication methods (like 2+1, 3+1) are typically used for establishing ground truth in clinical studies involving interpretation (e.g., by radiologists) where there might be disagreements, which is not the case for an oxygenator's performance evaluation.
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
This information is not applicable as this is not an AI/ML-driven diagnostic or assistive device requiring human reader interaction.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
This information is not applicable as this is not an AI/ML-driven device. The device has integrated sensors and connects to a console for display, so there's a human-in-the-loop for monitoring parameters, but it's not an AI algorithm.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
For an oxygenator, "ground truth" would refer to established scientific and engineering principles, validated measurement techniques, and regulatory standards. For example:
- Biocompatibility: Established by adherence to ISO 10993 standards.
- Sterility: Validated sterilization methods and testing.
- Performance (e.g., gas exchange, heat exchange): Measured against validated laboratory methods and established clinical ranges for physiological parameters (e.g., blood oxygenation, CO2 removal).
- Safety (Electrical/EMC): Adherence to relevant IEC standards.
- In vivo: Performance in a "biologic test system" and "real-world clinical experience" as mentioned, assessed against physiological outcomes.
8. The sample size for the training set
This information is not applicable as this is not an AI/ML-driven device with a "training set" in the machine learning sense. The device is hardware with integrated sensors and software components that are validated, not trained.
9. How the ground truth for the training set was established
This information is not applicable for the same reasons as #8.
Ask a specific question about this device
(240 days)
Michigan 48130
Re: K223898
Trade/Device Name: VitalFlowTM Centrifugal Pump Regulation Number: 21 CFR 870.4100
|
| Regulation Number: | 21 CFR 870.4100
of substantial equivalence to the Predicate with respect to the Special Controls described by 21CFR 870.4100
The VitalFlow Centrifugal Pump meets all special controls required by 21 CFR 870.4100.
risks of this device are mitigated by meeting the Special Controls required by the regulation, 21 CFR 870.4100
The VitalFlow™ Centrifugal Pump is intended to pump blood through the extracorporeal circuit for circulatory support up to 48 hours, in adult patients with acute respiratory failure or acute cardiopulmonary failure, where other available treatment options have failed, and continued clinical deterioration is expected or the risk of death is imminent.
The VitalFlow™ Centrifugal Pump is driven by the VitalFlow™ Console and Drive Motor, or the Emergency Handcrank.
The VitalFlow Centrifugal Pump is a sterile, single-use centrifugal blood pump. It is a non-invasive, nonpyrogenic device designed to move blood through the extracorporeal circuit by centrifugal force. The pump is the disposable portion of the pumping system and it is electromagnetically coupled to an instrument that monitors and displays the flow and pressure of the blood. Blood enters the inlet port of the pump, where a cone with impeller blades within the pump housing rotates and the blood is gently accelerated toward the outlet of the pump.
The VitalFlow Centrifugal Pump can be driven through magnetic coupling by an External Drive Motor or the Emergency Handcrank.
The provided document is a 510(k) Summary for the VitalFlow™ Centrifugal Pump, a Class II medical device. It details the device's indications for use, description, and studies conducted to demonstrate its substantial equivalence to predicate and reference devices.
Here's an analysis of the acceptance criteria and study information:
1. Table of Acceptance Criteria and Reported Device Performance
The document does not explicitly present a table of "acceptance criteria" with quantitative targets in the way one might expect for a diagnostic AI device (e.g., target specificity, sensitivity). Instead, the acceptance criteria are framed within the context of demonstrating substantial equivalence to predicate devices and meeting specific "Special Controls" outlined in 21 CFR 870.4100. The performance is assessed through various bench, animal, and real-world clinical data.
Therefore, the table below summarizes the Special Controls as acceptance criteria and how the device's performance, as reported, addresses them.
| Acceptance Criteria (Special Controls from 21 CFR 870.4100) | Reported Device Performance and Evidence |
|---|---|
| Technological Characteristics | Geometry and design parameters are consistent with the intended use in extracorporeal life support procedures. Device is designed to be compatible with other extracorporeal circuit devices and accessories. (Implies meeting functional specifications for flow, pressure, etc.) |
| Biocompatibility | Demonstrated to be biocompatible in accordance with ISO 10993-1:2018 and GLP (21 CFR 58). |
| Sterility and Shelf-life | Testing demonstrates sterility and maintenance of sterility, integrity, durability, and reliability over the stated shelf-life. |
| Non-clinical Performance | Demonstrated substantial equivalence through performance characteristics on the bench, mechanical integrity, durability, and reliability. Bench studies demonstrated a blood pump use duration of 14 days, with mechanical stability and critical flow performance attributes maintained. High flow blood trauma testing and hydraulic performance were also conducted. |
| In vivo Evaluation | A 96-hour animal study (13 sheep) to evaluate safety and performance for long-term ECMO use (target ACT 180-220 sec). Sustained high (5 L/min) and low (2 L/min) blood flow rates for 96 hours with no clots in any location in the device and confirmed blood pump functionality. |
| Clinical Evidence of Performance | A summary of real-world evidence (1048 reports) from ELSO.org (Extracorporeal Life Support Organization registry) on the Affinity CP Centrifugal Blood Pump (which the VitalFlow Centrifugal Pump is stated to be "the same as"). This demonstrated acceptable long-term performance in ECMO patients over 200,000 hours of ECMO time, averaging 225.6 hours per adult patient. The overall complication rate (34.7%) and specific mechanical complication rate (1.2%) for the AP40 group were comparable to or better than "All Other Pumps" (Non-AP40 group) in the registry, with a notably lower moderate or severe hemolysis rate (1.1% vs 4.6%). The pump failure rate (per 1000 hours) was 0.06 for VitalFlow (AP40) vs 0.03 for other pumps. |
| Labeling | Instructions for use include detailed summary of non-clinical evaluations, installation, circuit setup, maintenance, adverse effects, and performance characteristics relevant to compatibility. |
2. Sample Size Used for the Test Set and Data Provenance
The document describes several types of studies:
- Bench Performance Evaluations: No specific sample size is given for individual tests, but it states "Design verification studies were performed by the original manufacturer... and supplemented by MC3 bench performance testing, including long-term characterization." This implies multiple samples were tested for each characteristic.
- Animal Studies (In vivo evaluation): A sample size of 13 sheep was used for the 96-hour study. The data provenance is a controlled research environment.
- Clinical Performance (Real-world evidence): This utilized 1048 reports from the ELSO.org registry for the Affinity CP Centrifugal Blood Pump (AP40 group). The document states this is a "summary of real-world evidence," implying retrospective data extraction from an international registry. The country of origin for the data isn't explicitly stated but the ELSO registry collects data internationally. The comparison group ("All Other Pumps") involved 51,032 reports.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications
This device is not an AI diagnostic device that relies on expert interpretation of images or signals to establish a "ground truth" in the traditional sense. The "ground truth" for its performance is established through objective measures in bench testing (e.g., flow, pressure, mechanical integrity), physiological parameters in animal studies (e.g., presence/absence of clots, functionality), and reported clinical outcomes in the ELSO registry.
Therefore, there is no mention of "experts" establishing ground truth in the context of adjudication for a test set. Design verification and animal study results would be assessed by engineers, veterinarians, and researchers involved in those studies. Clinical outcomes in the ELSO registry are reported data.
4. Adjudication Method for the Test Set
Given that this is not an AI diagnostic device evaluating, for example, medical images requiring consensus on findings, there is no adjudication method (e.g., 2+1, 3+1) mentioned or applicable for the test sets described.
5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study was done
No, an MRMC comparative effectiveness study was not done. This type of study typically assesses the performance of human readers (e.g., radiologists) with and without AI assistance for tasks like diagnosis or detection. The VitalFlow™ Centrifugal Pump is a mechanical device, not an AI diagnostic tool, so such a study is not relevant.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done
No, a standalone (algorithm-only) performance study was not done, as the VitalFlow™ Centrifugal Pump is a physical medical device. The "standalone" performance here would refer to the device's function outside of a human-in-the-loop context, which is effectively what the bench and animal studies demonstrate regarding its mechanical integrity and ability to pump blood.
7. The Type of Ground Truth Used
The "ground truth" for evaluating the VitalFlow™ Centrifugal Pump's performance is multi-faceted:
- Bench Testing: Engineering specifications and performance metrics (e.g., pressure-flow curves, durability, wear, integrity, blood trauma data).
- Animal Studies: Direct observation of device functionality, physiological parameters, and absence of adverse events like clot formation in a living system over a defined period (96 hours).
- Clinical Performance (Real-world evidence): Reported clinical outcomes and complication rates from a large patient registry (ELSO.org), providing real-world data on pump failure, hemolysis, circuit changes, and other adverse events. This relies on the accuracy of data submitted to the registry.
8. The Sample Size for the Training Set
The document is for a traditional medical device (centrifugal pump), not an AI/Machine Learning device. Therefore, there is no "training set" in the context of AI model development that would typically have a distinct sample size. The design verification, bench testing, and animal studies serve as part of the overall development and validation process.
9. How the Ground Truth for the Training Set Was Established
As there is no AI training set, this question is not applicable. The "ground truth" for the device's design and engineering would be based on established medical and engineering principles, material science, and regulatory requirements, which are then verified through rigorous testing, as mentioned above.
Ask a specific question about this device
(196 days)
Dexter, Michigan 48130
Re: K230364 Trade/Device Name: VitalFlow™ Console Regulation Number: 21 CFR 870.4100
|
| Regulation Number: | 21 CFR 870.4100
of substantial equivalence to the Predicate with respect to the Special Controls described by 21CFR 870.4100
The VitalFlow Centrifugal Pump meets all special controls required by 21 CFR 870.4100.
risks of this device are mitigated by meeting the Special Controls required by the regulation, 21 CFR 870.4100
The VitalFlow™ Console controls the VitalFlow™ Centrifugal blood pump during extracorporeal cardiopulmonary life support for adult patients with acute respiratory failure or acute cardiopulmonary failure, where other available treatment options have failed, and continued clinical deterioration is expected or the risk of death is imminent. The VitalFlow Centrifugal pump is driven by the VitalFlow Motor Drive or the VitalFlow Emergency Handcrank.
The VitalFlow Console provides control of blood pumping through an extracorporeal circuit during extracorporeal life support (ECLS) procedures. The console powers the VitalFlow motor drive unit which provides rotation of the VitalFlow Centrifugal pump. Pump motor speed (RPM) can be adjusted by the user and flow and bubble detection is provided by an ultrasonic flow probe and displayed on the touchscreen. The touchscreen display allows users to set alarm limits for all measured parameters. The device will alarm visually and audibly when limits are exceeded. Status indicators, power / battery life and secondary RPM indicator is provided. Data download and data streaming from the console is available for ECLS circuit data only; no patient data are stored or exported.
The VitalFlow Emergency Handcrank (drive unit) can be used in emergency situations to manually drive the centrifugal pump in the case of console and or motor drive failure.
The provided text describes the VitalFlow™ Console, an extracorporeal circuit component, and its FDA 510(k) clearance (K230364). The document outlines the device's indications for use, description, and the performance evaluations conducted to demonstrate substantial equivalence to a predicate device.
However, the document does not contain the detailed information necessary to answer all parts of your request, specifically regarding acceptance criteria for an AI/ML model, sample sizes for test sets in an AI context, expert ground truth establishment, MRMC studies, or training set details for an AI model. This is likely because the VitalFlow™ Console is a mechanical/electronic medical device, not an AI/ML-driven diagnostic or assistive device that would typically undergo such evaluations.
The "Bench Performance Evaluations" section lists various studies (Hydraulic performance, Reliability, EMC, Electrical Safety, Software Validation, Usability Studies), but these are standard engineering and regulatory tests for hardware and software functionality, not AI model performance.
Therefore, I cannot provide a table of acceptance criteria for an AI model or details about AI-specific testing from this document.
If you are looking for information regarding an AI/ML-driven medical device, this document does not seem to pertain to such a device.
From the provided text, I can infer the following about the device and its testing:
- Device Type: The VitalFlow™ Console is an extracorporeal circuit and accessories for long-term respiratory/cardiopulmonary failure (Product Code: QNR, Regulation Number: 21 CFR 870.4100). It controls features like pump motor speed (RPM), flow, and bubble detection.
- Purpose of Studies: The studies were conducted to demonstrate "substantial equivalence" of the VitalFlow™ Console to a predicate device (TandemHeart Escort Controller, K202751) and to meet the "Special Controls" described in 21 CFR 870.4100.
- Nature of Studies: The studies were primarily "Bench Performance Evaluations" and included aspects like hydraulic performance, reliability, EMC, electrical safety, software validation, and usability studies. These are typical engineering and functional performance tests for a physical device.
- Ground Truth: For a physical device like this, "ground truth" would be established through calibrated instruments and established engineering principles for parameters like flow rate, RPM, pressure, and electrical safety. It's not based on expert consensus on image interpretation or pathology.
- No AI Component: There is no mention of an AI/ML component or algorithm within the VitalFlow™ Console. Therefore, concepts like training sets, test sets for AI models, expert adjudication, or MRMC studies are not applicable to the information provided.
In summary, the provided document does not contain the information requested about AI/ML device acceptance criteria and study details because the VitalFlow™ Console appears to be a physical medical device, not an AI-driven one.
Ask a specific question about this device
Page 1 of 2