Search Results

The device is a modularly structured program package that is exclusively used with Sorin/Stockert heart lung machines. The system allows detailed recording of perfusion data during cardiopulmonary bypass as well as the processing and evaluation of this data. The data may be recorded automatically or entered manually.

The Sorin CONNECT is used to collect and view data generated during cardiopulmonary bypass surgery. It interfaces with Sorin Heart-Lung machines to capture this data.

The Sorin CONNECT includes the following main components:

• The Datapad display monitor. It's used to display the collected data.
• The data recording software installed on the Datapad; known as "CONNECT Recorder". . lt's used to save the collected data.
• The PC software for reviewing data; known as "CONNECT Manager". It's used to view ● the recorded data and manually enter additional data including clinician's comments.
• . An RFID card reader used to transfer the data from the Heartlink card to the Datapad.
• . A pole mounting system (holder) to attach the Datapad to an IV pole.

The provided text is a 510(k) summary for the Sorin CONNECT, a data management system for heart-lung machines. It focuses on demonstrating substantial equivalence to a predicate device and outlines hardware and software updates. However, it does not contain information regarding acceptance criteria and a study proving the device meets those criteria, as typically found in clinical performance studies of AI/ML devices.

Specifically, the document states:

• NON CLINICAL TEST RESULTS: Electrical safety (IEC 60601-1) and electromagnetic compatibility (IEC 60601-1-2) were determined.
• IN VITRO TEST RESULTS: "Verification, validation, and testing activities, were conducted to demonstrate compliance to the product's specifications and compliance to safety and effectiveness requirements."

This implies that the testing performed for this 510(k) submission was primarily focused on hardware updates, software compatibility, and meeting electrical and EMC standards, rather than evaluating the performance of an AI/ML algorithm against a predefined set of diagnostic or predictive acceptance criteria.

Therefore, for your specific request regarding acceptance criteria and a study proving the device meets them, the following information is not present in the provided text:

1. Table of acceptance criteria and reported device performance: Not available. The document refers to "product's specifications" and "safety and effectiveness requirements" in a general sense, but no specific performance metrics or acceptance thresholds are listed.
2. Sample size used for the test set and data provenance: No test set involving patient data or clinical outcomes is described. The "testing activities" refer to non-clinical and in-vitro testing for compliance.
3. Number of experts used to establish the ground truth and qualifications: Not applicable, as there's no clinical performance evaluation involving expert consensus on patient data.
4. Adjudication method: Not applicable.
5. Multi Reader Multi Case (MRMC) comparative effectiveness study: Not applicable.
6. Standalone (algorithm only) performance: Not applicable, as it's a data management system hardware/software update, not an AI/ML algorithm.
7. Type of ground truth used: Not applicable.
8. Sample size for the training set: Not applicable, as no AI/ML model training is described.
9. How the ground truth for the training set was established: Not applicable.

In summary, the provided document describes a 510(k) submission for updates to a medical device focused on data management (Sorin CONNECT), demonstrating substantial equivalence through non-clinical and in-vitro testing for hardware/software functionality, electrical safety, and EMC. It does not provide the kind of performance data, acceptance criteria, or study details typically associated with AI/ML device evaluations.

Ask a specific question about this device

The XTRA Autotransfusion System is indicated for intraoperative recovery of blood, washing of blood collected in the postoperative period, and preoperative sequestration (with indirect patient connection). Typical clinical applications of autotransfusion include the following surgical specialties: Cardiovascular, Orthopedics, Thoracic, Transplant Surgery, Emergency (Trauma), Neurosurgery, Obstetrics and gynecology, and Urology.

XTRA is an Autotransfusion System designed to recover shed blood during intraoperative and postoperative procedures and for collection of platelet poor plasma (PPP) and platelet rich plasma (PRP) in preoperative procedures.

It is a software-controlled device provided with disposable and hardware elements that include the following major components: master, driving actuators (pump, centrifuge, clamps, pump loop ejector, cover lock), control and monitoring sensors, and an user interface (display panel and keyboard).

The modified device is a software upgraded version (SW 1.05.0) of the unmodified device (SW 1.02.0).

The current SW release 1.05.0 has been implemented to improve device's performances and to respond to feedback/indications coming from the users in the field. Other minor changes have been also implemented for user convenience and some bugs have been fixed. The main performances improvement implemented with the new SW upgrade consists of the introduction of a new factory protocol (Pfat) that has been optimized to eliminate non emulsified fat from the processed blood. The labeling and the instructions for use have been generally updated to include Pfat features as well as to reflect the modifications, where applicable.

Here's a breakdown of the acceptance criteria and study information for the XTRA Autotransfusion System based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

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

The document does not specify the exact sample size used for the in vitro test set. It only states that "Comparative tests were performed according to internal methods developed by the manufacturer."

The data provenance is internal to the manufacturer (Sorin Group Deutschland GmbH) as the tests were performed "in vitro" and according to their "internal methods." The country of origin of the data is implicitly Germany, where the submitter is located. The tests were prospective in vitro experiments.

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

Not applicable. This device is an autotransfusion system, and the reported tests are in vitro performance evaluations of its processing capabilities (fat removal and washing performance), not diagnostic interpretations requiring expert human review. The "ground truth" for these tests would be objective measurements of the device's output (e.g., amount of fat removed, effectiveness of washing).

4. Adjudication Method for the Test Set

Not applicable. As noted above, the tests are in vitro performance evaluations, not diagnostic image interpretations that would require adjudication among experts.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done

No, an MRMC comparative effectiveness study was not done. The study performed was an in vitro performance test of the device itself, comparing its performance to an unmodified version of the device, rather than assessing human reader performance with or without AI assistance.

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

Yes, the studies described are standalone in vitro performance tests of the device (which includes software) without human intervention in the performance evaluation itself. The device is a software-controlled system, and its "algorithm" (the software upgrade to version 1.05.0) was tested for its impact on fat removal and washing performance.

7. The Type of Ground Truth Used

The ground truth used for these in vitro performance tests would be objective measurements and laboratory results related to the device's functional outputs, specifically:

• For "fat removal performance": objective measurements of the presence or absence of non-emulsified fat in processed blood.
• For "washing performance": objective measurements of the effectiveness of the washing process (e.g., removal of plasma, waste products).

8. The Sample Size for the Training Set

The document does not mention a "training set" in the context of device performance testing. The device is a "software upgraded version" of an existing system, and the reported tests are in vitro performance validations of this upgrade. There's no indication that machine learning or AI models requiring a training set were developed or validated in this submission. The software upgrade focused on "improving device's performances and to respond to feedback/indications coming from the users in the field."

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

Not applicable, as no training set for a machine learning model is mentioned in the provided text.

Ask a specific question about this device

The Sorin FlexTherm Heater-Cooler System is used with a Stöckert S3 heart-lung machine and / or any other heart-lung machine featuring a separate temperature control for extracorporeal perfusion of durations of up to 6 hours.

Sorin FlexTherm is designed to provide temperature control during extracorporeal procedures. The device can be used in conjunction with heat exchangers tubing sets and heating/cooling blankets present on the market with an intended use in ECC (cardiopulmonary bypass heat exchangers, cardioplegia heat exchangers) and able to withstand a pressure of at least 2 bar. The device is used to warm or cool a patient during cardiopulmonary bypass procedures lasting up to six (6) hours.

As the unmodified device, the Sorin FlexTherm is a software-controlled device provided with hardware elements.

The main components for both devices are the housing provided with wheels, compressor, condenser unit, evaporator, expansion valves, water tanks, heaters, pumps, valves, sensors and a user interface/display.

Here's a breakdown of the acceptance criteria and study information for the Sorin FlexTherm device, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance:

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

• Sample Size for Test Set: The document does not specify a numerical sample size for the in-vitro performance tests. It only states that "Comparative tests were performed according to internal methods developed by the manufacturer."
• Data Provenance: The document does not provide information on the country of origin of the data or whether the tests were retrospective or prospective. It only mentions in vitro testing.

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

• Not Applicable: This information is not provided. The study conducted was in vitro testing, not a clinical study involving expert assessment of patient data for ground truth establishment. The ground truth for these tests would likely be the known physical properties and expected performance of the device and simulators.

4. Adjudication Method for the Test Set:

• Not Applicable: Adjudication methods like 2+1 or 3+1 are typically used in clinical studies for resolving discrepancies in expert interpretations of data (e.g., image readings). Since this was an in vitro performance study, such adjudication methods would not be relevant.

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

• No, an MRMC study was NOT done. The document primarily describes in vitro testing and compliance with safety standards, and software validation. There is no mention of human readers, comparative effectiveness with or without AI assistance, or any effect sizes related to human performance improvement.

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study:

• Yes (implicitly). The in vitro tests described ("Functional performances without patient simulator" and "Functional performances with patient simulator") are solely focused on the device's inherent performance. The software validation also indicates an assessment of the algorithm's functionality independently. There is no human intervention in the device's operational performance being evaluated in these tests, making them standalone assessments of the device's capabilities.

7. Type of Ground Truth Used:

• The ground truth for the in vitro tests would be based on known physical parameters, engineering specifications, and established performance benchmarks for temperature control, precision, and pump capacity. For example, if a target temperature is 37°C, the ground truth is simply 37°C, and the device's output is measured against that. For electrical safety and EMC, the ground truth is compliance with the specified IEC standards.

8. Sample Size for the Training Set:

• Not Applicable / Not Provided: This device is a hardware heater-cooler system with embedded software. While the software was developed and validated, the document does not indicate that it uses machine learning or AI models that require a "training set" in the conventional sense (i.e., a large dataset for model training). The software development followed standard life cycle processes, which involves design, coding, and validation, rather than data-driven machine learning training.

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

• Not Applicable / Not Provided: As noted above, the concept of a "training set" and associated ground truth establishment for machine learning models does not appear to apply to this device's software development as described in the document. The software validation relied on established software engineering principles and FDA guidance.

Ask a specific question about this device

Sorin CONNECT is a modularly structured program package that is exclusively used with Sorin/Stöckert heart lung machines. The system allows detailed recording of perfusion data during cardiopulmonary bypass as well as the processing and evaluation of this data. The data may be recorded automatically or entered manually.

The Sorin CONNECT is aiming to capture, display and store numerical or other perfusion related information entered by the user or captured from Stocket/Sorin Heart Lung Machine and from any compatible external device via a serial cable connection to the HLM interface. The capture of the data is performed automatically from the HLM via a serial cable communication or via RFID while simultaneously allowing for simple, manual user inputs The Sorin CONNECT Data Management System includes a hardware unit (the Personal Computer, hereinafter referred to as Datapad II, and the RFID card/reader hereinafter identified as Heartlink) and the software only product. The Sorin CONNECT software can be embedded into Datapad II (Online version hereinafter identified as Connect recorder) or available also on a server computer (server version hereinafter identified as Connect Manager). The Datapad II with embedded Connect Recorder allows for collection of all data that occur during an operation in order to generate a complete case record; its database store data in trend, event, calculation and it is possible to display on the monitor tabular trends or to view measurement trend graphs, with different measurements combined in each graph, to help the perfusionist in identify changes in the patient's physiological condition. The Connect Manager is a central database application in which all case records are stored and processed; in this case it is possible to consolidate data from different Connect Recorders on one central server computer. The application stores and manages data for documentation, reporting, analysis and export after the clinical case has been done: data are stored in a specific database and it is possible to display on the server workstation tabular trends, measurement trend graphs as well as statistical analysis and document them on a printer. The two different Sorin CONNECT applications have access to their own, independent database and data transfer among the databases takes place using either an USB memory stick or a network (Ethernet) connection: - HLM32.DBS is the database on the server computer. This database contains all case records that are already closed. - ONLINE32.DBS is the database on each of the online computers. This database contains the current case record(s) data. The Sorin CONNECT, through actuators, software and control mechanisms, performs the data collection, storage and management as requested by the operator through the user interface. Operating modes include automatic collection of data and manual insertion of data via keyboard The supported medical devices for Sorin CONNECT are the Stöckert/Sorin Heartlung machines SC (K982014), S3 (950990), S5 (K071318) and C5 (K093882).

The provided text outlines the acceptance criteria and the study conducted for the Sorin CONNECT Data Management System to demonstrate its substantial equivalence to predicate devices, rather than a study proving the device meets specific performance criteria in a clinical setting.

The study described is primarily focused on non-clinical bench testing for safety and performance specifications, and a comparison of technological characteristics with predicate devices to establish substantial equivalence for regulatory purposes.

Here's an analysis based on the provided information:

1. Table of Acceptance Criteria and Reported Device Performance:

The document doesn't present a table with specific, quantifiable acceptance criteria (e.g., accuracy, sensitivity, specificity) for device performance in the way one might expect for a diagnostic or therapeutic AI device. Instead, the "acceptance criteria" are implied by the standards and characteristics listed in the comparison table with predicate devices and the scope of the non-clinical tests.

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

The document mentions "performance testing... simulating various scenarios of real customer deployment in the hospital" but does not specify a numerical sample size for this testing. It implies a simulated environment rather than actual patient data. There is no information regarding country of origin or whether the data was retrospective or prospective, as it appears to be a systems/software validation rather than a clinical data study.

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

Not applicable. This device is a data management system, not a diagnostic device requiring expert interpretation of medical images or measurements to establish a "ground truth" for a test set. The validation is against technical specifications and predicate device characteristics.

4. Adjudication Method for the Test Set:

Not applicable. As described above, there's no clinical "ground truth" or expert review process detailed for this type of software system validation.

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

No, an MRMC study was not done. This type of study is relevant for diagnostic devices where human readers interpret cases, and the AI's impact on their performance is evaluated. The Sorin CONNECT is a data management system, not an AI-powered diagnostic tool.

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study:

Yes, a form of "standalone" evaluation was performed in the sense that the software's performance was tested against its specifications and predicate device characteristics in simulated environments, independent of active human clinical decision-making during the test. The "performance testing" described directly assesses the system's functionality.

7. Type of Ground Truth Used:

The "ground truth" for this device's validation is adherence to:

• Predicate Device Characteristics: The comparison table explicitly uses the characteristics of the IntelliVue Clinical Information Portfolio and TLink Data Management System as a benchmark for substantial equivalence.
• Technical Standards and Regulations: Compliance with various international and national standards (e.g., IEC 62304 for software, ISO 14971 for risk management, FDA guidances for cybersecurity and off-the-shelf software, electrical safety, EMC).
• Internal Performance Specifications: The testing aimed to "verify and stress the PC server and client specifications" and confirm performance.

8. Sample Size for the Training Set:

Not applicable. The Sorin CONNECT Data Management System described is not an AI/ML device that requires a training set in the conventional sense for learning patterns from data. It's a software system for data capture, display, and storage.

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

Not applicable, as there is no training set for this device.

Ask a specific question about this device

The Sorin Centrifugal Pump (CP5) is a cardiopulmonary bypass speed control device indicated for use exclusively with the Sorin Revolution®, for speedcontrolled pumping through the cardiopulmonary bypass circuit for typical durations of six hours or less.

The CP5 has been qualified only for typical durations of six hours or less, appropriate to cardiopulmonary bypass procedures and has not been qualified through in vitro, in vivo, or clinical studies, for long term use as a bridge to transplant, pending recovery of the natural heart, or extracorporeal membrane oxygenation (ECMO) procedures.

The Sorin CP5 is intended for use as a component part of or optional accessory for the Sorin heart lung machine consoles and with the Stöckert Air Purge (APC) the Borin heads they System. The Sorin CP5 consists of the drive unit, a mounting receptacle for the Dystein. The Cretaining key, splash protection, and a 3-joint mast holder with fast clamp connector. It integrates the functional capabilities of the SCP, the SCP Plus, and the Sorin Pulse Mode Control within a single device.

The Sorin CP5 consists of hardware, firmware, and electronics that are used to drive the centrifugal pump for surgical procedures requiring cardiopulmonary bypass for typical durations of six (6) hours or less. The SCP drive unit uses magnetic coupling with the disposable centrifugal pump.

The Sorin CP5 with the loaded centrifugal pump recirculates the contents of the extracorporeal circuit during cardiopulmonary bypass.

The design, materials, and physical properties of the CP5 are essentially unchanged from that of the parent/predicate devices already reviewed and cleared by the FDA.

The provided text describes a 510(k) summary for the Sorin Centrifugal Pump (CP5). However, it explicitly states that no clinical testing and no comparative nonclinical testing served as the basis for substantial equivalence. The summary focuses on technological characteristics compared to predicate devices and internal validation.

Therefore, the requested information regarding an acceptance criteria table, detailed study parameters, ground truth establishment, expert involvement, and MRMC studies cannot be extracted from the provided text, as such studies were not performed or are not reported.

Here's what can be extracted based on the information provided:

1. Table of Acceptance Criteria and Reported Device Performance:

The document states: "Testing of the Sorin Centrifugal Pump (CPS) demonstrates that the CP5 fulfills prospectively defined performance criteria and meets user needs." However, the specific quantitative or qualitative acceptance criteria and the corresponding reported device performance values are not detailed in this summary.

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

Not applicable. The document states: "No comparative nonclinical testing served as the basis for substantial equivalence." and "No clinical testing served as the basis for substantial equivalence." The testing performed involved "integration testing of hardware and firmware, functional testing, testing of organized (IEC 60601-1 including deviations for the US) and associated tooling, success (IEC 60601-1-2), and validation testing (simulated use and in use)." This describes internal validation, not a test set based on patient data.

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

Not applicable, as no external test set with ground truth established by experts is described.

4. Adjudication method for the test set:

Not applicable, as no external test set requiring adjudication is described.

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 a cardiopulmonary bypass centrifugal pump, not an AI-assisted diagnostic tool for human readers. No MRMC study was performed or is mentioned.

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

The device is a hardware component (centrifugal pump) with firmware, not a standalone algorithm. Performance testing was internal validation of the hardware and firmware.

7. The type of ground truth used:

Not applicable in the context of clinical or diagnostic performance. The "ground truth" for the internal validation would be the design specifications and expected functional behavior.

8. The sample size for the training set:

Not applicable, as this is not an AI/machine learning device with a training set.

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

Not applicable, as this is not an AI/machine learning device with a training set.

Ask a specific question about this device

The Stockert Centrifugal Pump System is a cardiopulmonary bypass speed control device (21CFR 870.4380) that is indicated for use with the Cobe Revolution® Pump Head/Dideco Synergy™/ECC.OTM for for speed controlled pumping through a cardiopulmonary bypass circuit for typical durations of six hours or less. The SCP Plus is intended for use as a component part of or optional accessory to the S3 and S5 System (or any compatible system using the SS firmware versions of 3.0. or greater) and the Stöckert Air Purge Control (APC) System.

The SCP Plus has been qualified only for typical durations of six hours or less, appropriate to cardiopulmonary bypass procedures and has not been qualified through in vitro, in vivo, or clinical studies for long-term use as a bridge to transplant, pending recovery of the natural heart, or extracorporeal membrane oxygenation (ECMO) procedures.

The SCP Plus System is intended for use as a component part of or optional accessory to the S3 and S5 System (or any compatible system using the S5 firmware versions of 3.0. or greater) and with the Stöckert Air Purge (APC) System. The System consists of the drive unit, a mounting receptacle for the pump head, a retaining key, splash protection, and a 3-joint mast holder with fast clamp connector.

The Stöckert Centrifugal Pump (SCP) Plus System consists of hardware, firmware, and electronics that are used to drive the centrifugal pump for surgical procedures requiring cardiopulmonary bypass for typical durations of six (6) hours or less. The SCP drive unit uses magnetic coupling with the centrifugal pump.

This document describes the acceptance criteria and accompanying study for the Sorin Group Deutschland GmbH Stöckert Centrifugal Pump (SCP) Plus System.

No information regarding a multi-reader multi-case (MRMC) comparative effectiveness study, standalone algorithm performance, or training set details is available in the provided text, as this is a traditional 510(k) for a medical device (a pump), not an AI/ML-driven device.

1. Acceptance Criteria and Reported Device Performance

The SCP Plus System was evaluated against prospectively defined performance criteria. The document states that the device's performance characteristics remain unchanged from its predicate device (K091008). Therefore, the acceptance criteria are implicitly tied to maintaining the established performance and safety standards of the predicate device.

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

The provided document does not specify a "test set" in the context of diagnostic performance evaluation with a defined sample size for images or patient data. This is a submission for a physical medical device (a pump), not a diagnostic algorithm.

The testing conducted was primarily non-clinical performance testing (safety, EMC, functional acceptance tests) of the physical device and its components. The document does not describe any studies involving human subjects or data derived from patients.

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

This section is not applicable as the document does not describe a "test set" requiring ground truth established by experts (e.g., radiologists, pathologists). The evaluation focused on engineering and performance criteria for a physical pump.

4. Adjudication Method for the Test Set

This section is not applicable as there was no test set requiring expert adjudication.

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

No, a multi-reader multi-case (MRMC) comparative effectiveness study was not done. The provided text describes a 510(k) submission for a physical medical device (a centrifugal pump), not an AI/ML-driven diagnostic or assistive tool. Therefore, there is no mention of human readers improving with or without AI assistance.

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

No, a standalone performance study (in the context of an algorithm) was not done. The device is a physical pump designed to operate within a cardiopulmonary bypass circuit, and its performance is assessed through engineering and functional tests, not as an "algorithm only."

7. The Type of Ground Truth Used

For the non-clinical performance testing, the "ground truth" was established by:

• Compliance with international and national standards (IEC60601-1 for safety, IEC60601-1-2 for EMC).
• Adherence to formal prospectively defined functional acceptance test specifications.
• Meeting user needs and performance identical to the predicate device.

There was no "ground truth" derived from expert consensus, pathology, or outcomes data in the context of diagnostic accuracy, as this is not a diagnostic device.

8. The Sample Size for the Training Set

This section is not applicable. The SCP Plus System is a hardware device with firmware, not a machine learning model, so there is no concept of a "training set" for an algorithm.

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

This section is not applicable for the same reasons as above.

Ask a specific question about this device

The Sorin C5 System is indicated for speed-controlled pumping of blood through the cardiopulmonary bypass circuit for durations of six (6) hours or less, left ventricular venting, cardiotomy suction, and administration of cardioplegia solution, when used by a qualified perfusionist who is experienced in the operation of the C5 System.

The C5 System has been qualified only for durations appropriate to cardiopulmonary bypass procedures and has not been qualified, through in vitro, in vivo, or clinical studies, for long term use as a bridge to transplant, pending recovery of the natural heart, or extracorporeal membrane oxygenation (ECMO) procedures.

The Sorin C5 System modification consists of the addition of the mast pumps and the Electrical Venous Occluder (EVO) to the Sorin C5 System. The function of the modified Sorin C5 System is identical to that of the parent C5 system. Masts pumps expand the number of pumps available to the perfusionist. The Electrical Venous Occluder allows the perfusionist to respond more quickly to detections of air in the extracorporeal circuit. This Special 510(k) was submitted for the addition of optional components and accessories that are provided to assist the perfusionist in their conduct of cardiopulmonary bypass. The mast pumps allow for additional pumping for such activities as left ventricular venting, cardiotomy suction, and administration of cardioplegia solution. The EVO replaces a maximum of two manual tubing clamps and interfaces perfusionist-selected roller pumps to clamp the venous line when a pump alarm condition occurs.

This 510(k) summary (K103762) for the Sorin C5 System is a Special 510(k) submission for modifications to an existing device rather than a new device with a comprehensive clinical or standalone performance study. Therefore, much of the requested information regarding acceptance criteria and detailed study designs for AI-powered devices is not directly applicable or available in this document.

The submission focuses on demonstrating substantial equivalence to a predicate device (Stöckert S5 System and the parent Sorin C5 System) for the modifications introduced, which are the addition of mast pumps and an Electrical Venous Occluder (EVO).

Here's an analysis based on the provided text, addressing the points where information is available or noting when it's not applicable:

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

The document does not explicitly present a table of acceptance criteria with corresponding performance metrics for the modified device in the way one would expect for an AI/algorithm-driven device. The "performance" assessment here is focused on demonstrating that the added components function as intended and do not negatively impact the overall system's safety and effectiveness compared to the predicate.

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

The document does not provide details on specific "test set" sample sizes in the context of clinical data or AI model evaluation. The testing described is verification and validation (V&V) testing of hardware and integrated system functionality, not a clinical study with patient data.

• Sample Size: Not applicable in the context of a "test set" for performance evaluation via clinical data. The V&V testing would involve a sufficient number of tests to confirm functionality and safety, but these are typically engineering tests, not patient data samples.
• Data Provenance: Not applicable. No patient data or clinical data is mentioned as being used for performance evaluation of the modifications.

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. "Ground truth" in the context of expert consensus on diagnostic or prognostic outcomes is not relevant here as this is a hardware modification submission, not an AI or diagnostics device. The "ground truth" for the V&V testing would be engineering specifications and functional requirements.

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

Not applicable. This is not a study requiring adjudication of expert opinions on clinical cases.

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. No MRMC study was conducted, as this device is a hardware modification to a heart-lung machine, not an AI-assisted diagnostic or therapeutic tool.

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

Not applicable. This device is a console with added components, not a standalone algorithm. The EVO component has an automated function (clamping the venous line upon pump alarm), but its performance is verified through engineering tests, not an "algorithm only" study in the sense of AI.

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

The "ground truth" for this submission refers to:

• Engineering Specifications: Functional requirements for the mast pumps and EVO.
• Safety Standards: Compliance with IEC 60601-1 and IEC 60601-1-2.
• Predicate Device Performance: The established safety and effectiveness of the existing Sorin C5 System and the predicate Stöckert S5 System.

8. The sample size for the training set

Not applicable. This is not an AI/machine learning device; therefore, there is no "training set."

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

Not applicable. As there is no training set mentioned.

Ask a specific question about this device

The Stöckert Air Purge Control (APC) System detects air in the venous line and removes air from the venous bubble trap of the Synergy™/ECC.O™ System tubing circuit. The Synergy™/ECC.O™ shall only be used in conjunction with the Stöckert S5 (or any compatible system using the S5 firmware versions of 3.0 or greater) and the SCP Plus System.

The Stöckert S5 System is indicated for speed controlled pumping of blood through the cardiopulmonary bypass circuit for durations of six hours or less, left ventricular venting, cardiotomy suction and administration of cardioplegia solution.

The Stöckert APC System consists of the APC sensor module (Catalog Number: 23-45-22), 3-joint mast holder with fast clamp connectors for two bubble sensors, 420mm (Catalog Number: 23-26-96), bubble sensor for 3/8 inch tubing (Catalog Number: 23-07-50), and ultrasonic gel, bottle, 250 mL (Catalog Number: 96-06-10). All of these components are identical to those used with the Stöckert S5 System (K091008).

The Stöckert APC can be operated automatically and manually using the APC displet of the heart lung machine.

The Stöckert APC bubble trap is placed just before the venous bubble trap of the Synergy™/ECC.OTM. When bubble activity is sensed, the assigned roller pump on the heart lung machine console begins operation to remove a set tubing volume (as determined by tubing size and pump speed (RPM)) or to run for a set time (in seconds) at a perfusionist-selected flow rate. This fluid is pumped into an appropriate blood collection reservoir. The technology of the Stöckert APC is based on the technology of the Stöckert Air Purge Control System (K041558).

The Stöckert APC is used for detecting air in the venous line and removing air from the venous bubble trap of the Synergy™/ECC.O™ System tubing circuit.

Here's an analysis of the provided text regarding the acceptance criteria and study for the Stöckert Air Purge Control (APC) System:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state quantitative acceptance criteria or a detailed "reported device performance" against specific metrics. Instead, it makes a general statement about the device fulfilling "prospectively defined functional acceptance test" criteria.

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

The document does not specify a distinct "test set" in the sense of a dataset for evaluating an algorithm. The testing described is hardware and system validation.

• Sample Size for Test Set: Not applicable as it's not a data-driven algorithmic evaluation. The testing involved the Stöckert APC System itself, integrated with a heart-lung machine.
• Data Provenance: Not applicable. The testing was described as "non-clinical performance testing" and "simulated use/in-use validation testing" of the physical system, likely conducted internally by the manufacturer (Sorin Group Deutschland GmbH).

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

Not applicable. The ground truth for electrical safety, EMC, and functional performance would be established by engineering standards and internal testing protocols, not by expert consensus on a dataset.

4. Adjudication Method for the Test Set

Not applicable. This is not a study involving human reader interpretation or diagnostic output that requires adjudication.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size of How Much Human Readers Improve with AI vs. Without AI Assistance

No. This device is a hardware system for detecting and removing air during cardiopulmonary bypass, not an AI or diagnostic imaging device that would involve human readers.

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

Yes, in a way. The "functional acceptance test and simulated use/in-use validation testing" evaluated the Stöckert APC System's performance in detecting air and initiating removal autonomously (which could be considered its "standalone" performance), even though it operates within the larger Stöckert S5 heart-lung machine system. The device's function is automated.

7. The Type of Ground Truth Used

The ground truth used for this type of device would be:

• Engineering Standards: For electrical safety (IEC60601-1) and electromagnetic compatibility (IEC60601-1-2).
• Physical Principles and Design Specifications: For the air detection and removal capabilities. The "prospectively defined functional acceptance test" would have protocols and metrics based on the expected physical behavior of the system (e.g., ability to reliably detect a certain volume of air, ability to remove air within a specified time).

8. The Sample Size for the Training Set

Not applicable. This is not a machine learning or AI device that requires a training set.

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

Not applicable.

Ask a specific question about this device

The B-Cares is intended for use as a component part of or optional accessory to the Stöckert S5 system (or any compatible system using the S5 firmware versions of 3.0 or greater), during cardiopulmonary bypass for procedures up to six hours. The B-Cares is used exclusively for determining oxygen saturation, hematocrit value and temperature in the venous blood circuit.

The Sorin B-Cares described in this 510(k) Premarket Notification is identical to the device that was cleared under K092463 and uses the same in-line sensors cleared under K001388. When switched on, the Sorin B-Cares progresses from warm-through initialization . self test while resting on the holder. When self test is successful, Sat- (venous saturation) and Hct- (hematocrit) values are displayed. The sensor is then mounted on the disposable connector in the extra-corporal circuit. The B-Cares alerts (alarms or warns) the user if laboratory reference values have not been stored for venous O2 saturation and hematocrit. The Sorin B-Cares monitors blood values via the sensor head with two LED sources and a receiver in contact with the optical window integrated into the venous connectors. Temperatures are monitored using thermistors in the venous probes. The technology of the Sorin B-Cares is based on the technology of the Dideco Data Master (Sorin Group Italia is the parent company of Sorin Group Deutschland GmbH and was formerly known as Dideco). The B-Cares is used for determining oxygen saturation, hematocrit, and temperature in the venous blood circuit.

Here's a breakdown of the acceptance criteria and study information for the Sorin B-Cares device, based on the provided 510(k) summary:

1. Table of Acceptance Criteria and Reported Device Performance

The 510(k) summary does not provide a direct table of specific, quantitative acceptance criteria for parameters like accuracy or resolution of oxygen saturation, hematocrit, and temperature. Instead, it refers to the device meeting "prospectively defined performance criteria" and being "within clinically relevant ranges."

However, it does compare some specifications to the predicate device (Dideco Data Master). While not explicit acceptance criteria, these comparisons highlight the device's performance characteristics.

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

• Sample Size: The document does not specify a numerical sample size for the "test set." It refers to "Testing of the Sorin B-Cares (hardware, firmware, and performance)" as having demonstrated that the system "fulfills prospectively defined performance criteria."
• Data Provenance: The testing was "non-clinical" and appears to be internal performance testing conducted by the manufacturer. No details are provided regarding the country of origin of the data or whether it was retrospective or prospective, other than the mention of a "formal prospectively defined functional acceptance test."

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

This information is not provided. The study was non-clinical performance testing, not a clinical study involving experts establishing ground truth on patient data.

4. Adjudication Method for the Test Set

This information is not provided. As it was non-clinical performance testing, an adjudication method for ground truth would not typically be applicable in the same way as a clinical study.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, and its effect size

No, a multi-reader multi-case (MRMC) comparative effectiveness study was not done. The document explicitly states: "Formal clinical testing of the Sorin B-Cares has not been performed. Therefore, this section does not apply."

6. If a Standalone (Algorithm only without human-in-the-loop performance) was done

Yes, the testing described appears to be standalone performance testing of the device itself (hardware, firmware, and its ability to monitor blood values). The device's function is to display data digitally and alert the user, which is a standalone function, though it is used by a human in a clinical setting. The "non-clinical performance testing" focuses on the device's technical specifications and functionality independent of human interpretation or assistance for its core measurements.

7. The Type of Ground Truth Used

The "ground truth" for the non-clinical performance testing would be the actual, measured values from calibrated laboratory equipment or reference standards against which the device's readings (oxygen saturation, hematocrit, temperature) were compared. The text mentions that "Venous saturation and hematocrit values are calibrated to reference (laboratory) values," indicating that laboratory reference values serve as the ground truth.

8. The Sample Size for the Training Set

This information is not provided. The document describes a medical device for monitoring, not an AI/machine learning algorithm that requires a "training set" in the conventional sense. The device's technology is based on the Dideco Data Master, and its performance relies on physical principles (LED sources, receivers, thermistors) and firmware, not a learned model from a data training set.

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

This information is not applicable as the device does not employ a "training set" in the context of machine learning or AI that would require establishing ground truth in that manner. The device's core functionality is based on established scientific principles for measuring blood gases and hematocrit. Its calibration would involve comparison to laboratory reference measurements.

Ask a specific question about this device

The Stöckert Gas Blenders (2L, 5L, and 10L) are intended to enable qualified personnel to set monitor and control gas flows of medical grade gases (air/02/CO2) during cardiopulmonary bypass. The Stockert Gas Blenders are used as components of or optional accessories to the Stöckert S5 System (or any compatible Sorin system using the S5 firmware versions of 3.0 or greater) for periods of six hours or less.

The Stöckert Gas Blender Base Unit is 200 mm wide, 185 mm high, and 270 mm deep and it weighs 2.5 kg. It can be used either from a suitable horizontal surface such as a table or cart or it can be mounted on one of the masts (using the mast holder). It is attached to HLM console with the supplied 24V/CAN connector. This connection provides both power and communication between the Stöckert Gas Blender and the System Display Panel of the HLM. The Stöckert Gas Blenders are designed to provide a maximum mixed gas flow rate of 2L/min, 5L/min or 10 L/min depending on the model used to allow the perfusionist to purge the oxygenator with gas during the priming process. The front panel is the user interface and includes the on/off key, displays and controls. The rear panel houses the three inlet gas connections, the gas mix outlet, and the 24V/CAN connector. Gas line connectors are fast release connectors, consisting of a male connector (installed on the tubing) and a coupler socket (on the housing of the Gas Blender). Both sets (male and female) of connectors are labeled with the respective gas for which they are intended to be used. The Stöckert Gas Blenders enable the qualified perfusionists who are managing the cardiopulmonary bypass circuit using a Stöckert S5 or Sorin C5 System to precisely set, monitor and control the gas flows required for the oxygenation of the patient's blood during extracorporeal circulation. The supply sources for air, O2 and CO2 are connected to the rear inlets of the Stöckert Gas Blender and the gas mixture outlet is connected to the oxygenator (not supplied). The Stöckert Gas Blenders are optional accessories to and designed to be operated with the Stöckert S5 System/Sorin C5 System. They cannot be operated independently from the heart lung machine console. The values for total gas flow (air + O2), FiO2 and CO2 can be adjusted independently without affecting the remaining two values. Gas flow is displayed at both the Stöckert Gas Blender base unit and the remote display module situated in the Stöckert S5 System/Sorin C5 System "control desk" or "System Panel." Set values and actual values are continuously monitored and any discrepancy between them causes both optical and acoustic alarms. If desired, the perfusionist may set alarm limits at the remote display module to monitor the blood flow/gas flow ratio for the arterial pump.

The provided text describes the Stöckert Gas Blender and its FDA 510(k) submission. However, it does not include detailed information about acceptance criteria or a study that specifically proves the device meets those criteria in the format requested.

The document is a 510(k) summary for a medical device (Stöckert Gas Blender). For this type of submission, substantial equivalence to a predicate device is the key, not necessarily a detailed clinical study demonstrating specific performance metrics against pre-defined acceptance criteria in the way a new drug or a novel AI diagnostic might.

Based only on the provided text, here's what can be extracted and what is missing:

1. Table of acceptance criteria and reported device performance:

This information is not provided in the document. The document states that "Design verification and validation testing presented in the 510(k) included electrical/safety testing (IEC60601-1), EMI/EMC testing (IEC60601-1-2), and Functional Acceptance testing, and design validation testing (internal and external)." However, it does not list the specific acceptance criteria for these tests (e.g., accuracy of gas flow, precision of mixture) or the numerical performance results of the device against those criteria.

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

This information is not provided. The document mentions general "testing" but no specific test sets or their characteristics.

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/not provided. This device is a gas blender for heart-lung machines, not an AI diagnostic that requires expert interpretation for ground truth. Its performance would be validated through engineering and functional testing.

4. Adjudication method for the test set:

This information is not applicable/not provided. (See point 3).

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

No. The document explicitly states: "No formal clinical testing was provided as the basis for substantial equivalence or is required." Therefore, no MRMC study was conducted or reported here.

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

This concept is not applicable to this device. The Stöckert Gas Blender is a physical medical device that blends gases, not an algorithm. Its "standalone performance" would be its functional performance, which is generally verified through engineering tests, but specific details are not provided in this summary.

7. The type of ground truth used:

This information is not explicitly stated or applicable in the traditional sense of clinical ground truth (e.g., pathology). For a physical device like a gas blender, "ground truth" would be established by reference standards, calibrated measurement equipment, and compliance with engineering specifications. The document mentions "prospectively defined design and performance specifications," which would form this basis.

8. The sample size for the training set:

This information is not applicable/not provided. As this is a physical device and not an AI/machine learning algorithm, there is no "training set."

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

This information is not applicable/not provided (see point 8).

In summary:

The provided document is a 510(k) summary for a medical device focused on demonstrating substantial equivalence to a predicate device. It confirms that engineering, safety, and functional testing were performed but does not delve into the specific acceptance criteria or the detailed results of those tests, nor does it involve clinical studies or AI-related performance metrics.

Ask a specific question about this device