(163 days)
The Cogent HMS is intended for patients for whom the monitoring of CCO and calculated hemodynamic parameters is indicated for diagnostic and prognostic evaluation by a clinician. The Cogent HMS is intended for use with ICU Medical pulmonary artery catheters and central venous oximetry catheters and with ICU Medical Cogent sensors. The Cogent HMS is intended to measure and calculate venous oxygen saturation in patients. PulseCO functionality is limited to adult patients.
The Cogent HMS is designed to compute and display cardiac and oximetry parameters relevant to patient care in the hospital acute care areas including Intensive Care Units and the Operating Room. Monitoring parameters include cardiac output and blood oxygen saturation levels, as well as other derived hemodynamic parameters. Measurements are obtained through the compatible ICU Medical pulmonary artery and central venous oximetry catheters, and ICU Medical CardioFlo™ sensors.
Input data for derived parameters may be keyed in by a clinician or may be obtained from a bedside monitor.
The Cogent HMS provides the following functions:
- monitors patient cardiac output continuously (CCO) using continuous thermodilution -(TdCO), and intermittently, using bolus thermodilution (Bolus CO);
- monitors continuous cardiac output (CCO) using pulse power analysis on an arterial pressure waveform;
- monitors venous oxygen saturation (SvO2) by measuring the reflectance spectrum of the blood; and
- provides a general-purpose interface to the analog input/output channels of other monitoring devices.
The Cogent HMS consists of:
- a base unit (patient interface module or PIM);
- a dedicated touch-screen display unit (user interface module or UIM) which allows for patient monitoring remotely (up to 50 feet); and
- associated cables
The PIM and UIM modules communicate with each other in docked, tethered (wired) or wireless mode.
The provided text describes a 510(k) premarket notification for the ICU Medical Cogent™ Hemodynamic Monitoring System (HMS). However, the document focuses on demonstrating substantial equivalence to a predicate device (K152006) primarily due to updates to the operating system (Windows 7 to Windows 10), software (version 1.1.8 to 1.4.0), and minor hardware changes. The submission primarily relies on non-clinical testing and verification, rather than a clinical study with detailed acceptance criteria and performance metrics for a novel algorithm.
Based on the provided text, the device is an updated version of an already cleared hemodynamic monitoring system. Therefore, the "acceptance criteria" discussed are largely related to ensuring the updated device performs equivalently to its predicate and meets relevant safety and performance standards. No specific "acceptance criteria" in terms of clinical performance metrics of an AI algorithm are explicitly stated, as the device is not presented as an AI-powered diagnostic algorithm with a performance threshold to meet.
Here's a breakdown of the information based on your request, as much as can be extracted from the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
As the submission is for an updated version of an existing device, the "acceptance criteria" largely revolve around demonstrating equivalent performance to the predicate device and compliance with relevant standards. The document doesn't provide a table of precise quantitative acceptance criteria for clinical performance (e.g., sensitivity, specificity for a diagnostic algorithm) and corresponding reported performance of a novel AI component. Instead, it states that "the measurement performance of the subject device is equivalent to that of the predicate device."
| Acceptance Criteria Category (Implied from text) | Reported Device Performance (Implied from text) |
|---|---|
| Software Performance | Verified and validated successfully (per IEC 62304 and FDA guidance). Software considered equivalent to predicate. |
| System Bench Testing (Simulated Use) | Measurement performance of the subject device is equivalent to that of the predicate device. |
| Electrical Safety | Complies with requirements per IEC 60601-1. |
| Electromagnetic Compatibility (EMC) | Complies with requirements per IEC 60601-1-2. |
| Cybersecurity | System is effective in addressing cybersecurity threats. |
| Risk Management | Risk management activities incorporated in accordance with ISO 14971:2019 and tested for correct implementation and effectiveness. |
| Functional Performance & Intended Use | Meets functional performance and intended use claims as described in device labeling. No different questions of safety and effectiveness introduced. |
| Biocompatibility | Not applicable, as the device itself does not have direct patient contact. (Patient-contacting accessories are cleared separately). |
2. Sample Size Used for the Test Set and Data Provenance
The document explicitly states: "No new human factors, animal, and/or clinical studies were conducted as was determined not required to demonstrate device safety and effectiveness for the subject device."
Therefore, there is no "test set" in the context of clinical data with a sample size or provenance for this specific 510(k) submission. The testing performed was primarily non-clinical (bench testing, software V&V).
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications
Since no new clinical studies were conducted for this submission, there is no mention of experts establishing ground truth for a test set.
4. Adjudication Method for the Test Set
Not applicable, as no new clinical test set was used.
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. The device is a hemodynamic monitoring system, not an AI-assisted diagnostic imaging or interpretation tool. The submission focuses on software and hardware updates to an existing monitoring device, not the evaluation of an AI algorithm's impact on human reader performance.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
The "Cogent System Software Validation" and various algorithm validations (PulseCO, Bolus CO, SO2, CCO) were performed, which could be considered standalone performance evaluations of the specific algorithms within the device. However, these are validations of established medical algorithms for physiological measurements, not novel AI algorithms in the common sense. The text implies these were bench validations, not clinical standalone performance studies.
7. The Type of Ground Truth Used
For the algorithm validations (e.g., PulseCO, Bolus CO, SO2, CCO), the ground truth was established through "in vitro validation" using flow simulators or electronically generated data. This suggests a controlled laboratory environment where the "true" physiological values could be precisely set or simulated.
8. The Sample Size for the Training Set
Not applicable. The document discusses updates to an existing device and its algorithms, not the training of a new AI algorithm that would require a distinct training set. The algorithms mentioned (e.g., thermodilution, pulse power analysis) are based on established physiological principles and are not typically "trained" in the machine learning sense with large datasets.
9. How the Ground Truth for the Training Set was Established
Not applicable, as there is no mention of a training set for a novel AI algorithm.
§ 870.1435 Single-function, preprogrammed diagnostic computer.
(a)
Identification. A single-function, preprogrammed diagnostic computer is a hard-wired computer that calculates a specific physiological or blood-flow parameter based on information obtained from one or more electrodes, transducers, or measuring devices.(b)
Classification. Class II (performance standards).