K Number
K992635
Date Cleared
1999-12-20

(136 days)

Product Code
Regulation Number
870.4200
Panel
CV
Reference & Predicate Devices
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The Stöckert S3 heart lung machine and the SC heart lung system are integrated heart lung machines for cardiopulmonary bypass. The Interface Module IDDD provides serial data output from the Stöckert S3 and SC Heart Lung Machines for recording on an external PC or other recording devices. Serial output information from external devices like blood gas analyzers or patient monitors can also be input to the Interface Module IDDD to be passed through to the serial output. The output protocol provides a complete overview of all relevant data obtained from the heart lung machine as well as from external devices. The serial output data are intended for procedure documentation, and are not intended for making clinical decisions for diagnosis.

Device Description

The Stöckert Interface Module IDDD is an addition to the Stöckert S3 heart lung machine (K950990) and the SC heart lung system (K982014), which were both previously cleared for marketing. The Interface Module IDDD provides serial data output from the Stöckert S3 and SC Heart Lung Machines for recording data on an external PC or other recording devices. Serial output information from external devices like blood gas analyzers or patient monitors can also be input to the Interface Module IDDD to be passed through to the serial output. The Interface Module IDDD is installed into the Electronics and Power Supply Pack (E/P) of the S3 or the Sensor Module Rack of the SC. A CAN bus system manages the data transfer.

AI/ML Overview

The provided text describes the Stöckert Instrumente Interface Module IDDD, an accessory to cardiopulmonary bypass heart-lung machines. The document focuses on its substantial equivalence to predicate devices and testing performed to ensure its safety and functionality.

Here's an analysis of the acceptance criteria and study information contained in the document:

1. Table of Acceptance Criteria and Reported Device Performance

Acceptance CriteriaReported Device Performance
Electrical Safety (IEC 60601-1)Performed using both SC and S3 Systems with IDDD installed.
Functional Safety (IEC 60601-1)Performed using both SC and S3 Systems with IDDD installed.
Electromagnetic Compatibility (Emissions and Immunity)Conducted on the STÖCKERT S3 Perfusion System with all components and accessories, including IDDD, during operation in no-load and full-load states.
EMI/EMC Pass Criteria:
No pump stopsMet
No pump runawayMet
No sensor alarmsMet
Stable displayed valuesMet
Correctly functioning IDDD after testingMet
Impact on SC and S3 heart-lung system functions (safety critical pump functions)Tested to show correct functioning with the IDDD Module in place.
CAN message acceptance (Code Inspection of CAN receivers)Code inspection showed that CAN messages from the IDDD are only accepted by the CDM (set messages) and by IDDD modules themselves (data messages). IDDD messages are not accepted by other CAN receivers.

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

The document does not explicitly state a "sample size" in the conventional sense for a test set of data. Instead, the testing involved:

  • Physical Devices: Stöckert S3 System, SC heart-lung system, and an Interface Module IDDD installed in each.
  • Operating Conditions: No-load and full-load states for EMI/EMC testing, with pump heads running at 100 RPM.

The data provenance is not specified, but given the manufacturer (Stöckert Instrumente GmbH, Munich, Germany) and the testing descriptions, it can be inferred that the testing was conducted prospectively by the manufacturer. No information regarding country of origin of "data" is provided, as the "data" being evaluated is the device's operational performance, not clinical or diagnostic data.

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

This information is not provided in the document. The testing described is primarily engineering and safety testing, not diagnostic performance evaluation requiring expert consensus on ground truth.

4. Adjudication Method for the Test Set

This information is not applicable and therefore not provided in the document. Adjudication methods are typically used in clinical studies where disagreement among experts needs resolution to establish ground truth for classification or diagnostic tasks. The described tests are objective pass/fail criteria based on device functionality and safety standards.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

No, an MRMC comparative effectiveness study was not done. This type of study is relevant for AI-powered diagnostic or interpretive devices that assist human readers. The Interface Module IDDD is an accessory for data output and documentation, not an interpretive or diagnostic AI tool.

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

Yes, in essence, standalone testing was performed. The described electrical safety, functional safety, and EMI/EMC tests evaluate the device's performance independently of human interaction beyond setting up and operating the system for the test. The "algorithm" here refers to the device's internal logic for data transfer and processing. The tests establish that the device operates correctly on its own and does not interfere with the primary heart-lung machine functions.

7. The Type of Ground Truth Used

The "ground truth" used for this device's evaluation is primarily engineering specifications, safety standards (IEC 60601-1), and functional requirements. For example:

  • Electrical Safety: Compliance with IEC 60601-1.
  • Functional Safety: Correct operation of safety-critical pump functions.
  • EMI/EMC: No pump stops, no pump runaway, no sensor alarms, stable displayed values, and correctly functioning IDDD.
  • CAN Message Acceptance: Only specified messages are accepted by respective modules.

These are objective, measurable outcomes directly related to the device's design and intended function, rather than subjective interpretations like pathology results or expert consensus on a diagnosis.

8. The Sample Size for the Training Set

This information is not applicable and therefore not provided. The Interface Module IDDD is a hardware accessory for data transfer, not an AI or machine learning model that requires a "training set" of data.

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

This information is not applicable and therefore not provided, as there is no training set for this type of device.

§ 870.4200 Cardiopulmonary bypass accessory equipment.

(a)
Identification. Cardiopulmonary bypass accessory equipment is a device that has no contact with blood and that is used in the cardiopulmonary bypass circuit to support, adjoin, or connect components, or to aid in the setup of the extracorporeal line, e.g., an oxygenator mounting bracket or system-priming equipment.(b)
Classification. (1) Class I. The device is classified as class I if it does not involve an electrical connection to the patient. The device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to § 870.9.(2) Class II (special controls). The device is classified as class II if it involves an electrical connection to the patient. The special controls are as follows:
(i) The performance standard under part 898 of this chapter, and
(ii) The guidance document entitled “Guidance on the Performance Standard for Electrode Lead Wires and Patient Cables.” The device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to § 870.9.