Search Results

The Triton Sponge System is a software application intended to be used as an adjunct in the estimation of blood loss and management of surgical sponges. The Triton Sponge System is intended to be used with surgical sponges, software, hardware and accessory devices which have been validated for use with Triton Sponge System to estimate the hemoglobin (Hb) mass contained on used surgical sponges. This version of the Triton Sponge System includes 4 updates from the predicate Triton System (K160338): Qualified new hardware accessory: Apple's iPad Pro to be used with Triton Sponge System. Qualified new accessory for imaging sponges: Users will use a commercially available 3D IR laser depth sensor (referred to as the Natural User Interface or NUI Sensor in the submission) that allows for automatic detection of sponges as well as a touch-free interface with the device to facilitate imaging of the sponge on Apple's iPad Pro device. To allow the use of the NUI Sensor with the Triton Sponge System, a new algorithm called the Sponge Recognition Algorithm (SRA) was added to the System. The SRA analyzes the depth maps provided by the NUI Sensor to determine whether or not a User is presenting a sponge for imaging. To allow the NUI Sensor to securely connect to the iPad Pro, NUI mounting brackets are provided to connect the NUI Sensor to the iPad Pro. Addition of a step to include imaging a calibration placard with Triton Sponge App to normalize ambient light settings. The calibration card is provided to standardize the image of each sponge. Updates to the Hemoglobin Algorithm to improve hemoglobin mass estimates by performing scene normalization as well as utilizing new data provided by the calibration palette and NUI Sensor.

AI/ML Overview

The provided text describes the Triton Sponge System, a software application intended to be used as an adjunct in the estimation of blood loss and management of surgical sponges. It explains the acceptance criteria for this device and the studies conducted to prove it meets these criteria.

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are derived from the "Special Controls Required for 21 CFR §880.2750" (Table 6-1 on page 14). The device performance is summarized from the "Special Control Met" column and the "PERFORMANCE DATA" section (pages 10-14).

Special Control Required (Acceptance Criteria)	Reported Device Performance
1. Non-clinical performance data must demonstrate that the device performs as intended under anticipated conditions of use. Demonstration of the performance characteristics must include a comparison to a scientifically valid alternative method for measuring deposited hemoglobin mass. The following use conditions must be tested: A. Lighting conditions; B. Range of expected hemoglobin concentrations; C. Range of expected blood volume absorption; and D. Presence of other non-sanguineous fluids (e.g., saline irrigation fluid)	Non-clinical performance testing using the iPad Pro and the NUI sensor was conducted and demonstrated that the device performs as intended under anticipated conditions of use including expected lighting conditions, range of expected hemoglobin values, range of expected blood volume absorption and presence of other non-sanguineous fluids. A strong positive linear correlation and acceptable agreement via Bland-Altman analysis were found between Triton sHbL and Assay sHbL.
2. Human factors testing and analysis must validate that the device design and labeling are sufficient for appropriate use by intended users of the device.	Human factors testing and analysis demonstrated that the Triton Sponge System, labeling, and the NUI sensor as an accessory to support scanning of images with the Triton Sponge System are sufficient for appropriate use by intended users of the Triton Sponge System. All users successfully completed tasks per protocol pass/fail criteria in a simulated setting.
3. Appropriate analysis and non-clinical testing must validate the electromagnetic compatibility (EMC) and wireless performance of the device.	EMC and wireless performance of the Triton Sponge System with new iPad Pro and accessory NUI Sensor have been validated against IEC 60601-1-2:2007. The iPad Pro maintained essential wireless functionality under all test conditions.
4. Appropriate software verification, validation and hazard analysis must be performed.	Software verification, validation and hazard analysis have been performed. Software verification demonstrated that all specified requirements, including hazard mitigations, have been fulfilled. Validation testing demonstrated that all device specifications conform with user needs and intended uses.
5. Software display must include an estimate of the cumulative error associated with estimated blood loss values.	An estimate of the cumulative error associated with blood loss values is displayed to the user with each estimated hemoglobin mass and blood loss value. This is informed by Bland-Altman methods from verification testing.
6. Labeling must include: A. Warnings, cautions, and limitations needed for safe use of the device; B. A detailed summary of the performance testing pertinent to use of the device, including a description of the bias and variance the device exhibited during testing; C. The validated surgical materials, range of hemoglobin mass, software, hardware, and accessories that the device is intended to be used with; and D. EMC and wireless technology instructions and information.	Labeling includes all details as required by the special controls. This includes prescription statement, warnings, cautions, limitations, performance testing summary (bias and variance), validated materials/ranges/hardware/accessories, and EMC/wireless information.

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

Sample Size for performance testing (bench-top and system validation): The document states "Testing involved running the software app/system test protocol with sample specimens" for bench testing and for system validation, it used "mock surgical case simulated by reconstituting whole blood samples of known Hb concentration from units of human packed red blood cells and plasma to create various pre-specified blood volumes. Serial dilution with sterile saline yielded sponge blood samples reconstituted to ranges of fluid volume, dilution, and Hb mass representative of a surgical operation."
- The exact number of "sample specimens" or "blood volumes" / "dilution levels" is not explicitly stated in the provided text.
Data Provenance: The data used for performance testing (bench-top and system validation) appears to be prospective and simulated in a laboratory/mock surgical setting. The blood samples were "reconstituted" and "serial dilution with sterile saline" was performed. There is no indication of patient data or data from a specific country of origin, suggesting it's synthetic or laboratory-generated.

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

The ground truth for the performance tests (bench and system validation) was established using "pre-measured Hb mass (Assay sHbL)" of the samples. This indicates a direct quantitative measurement rather than expert interpretation.

Therefore, no experts were used to establish the ground truth in the traditional sense of clinical assessment (e.g., radiologists, pathologists). The ground truth was based on laboratory assay measurements.
The qualifications of individuals performing these assays are not specified, but it's implied to be standard laboratory practice for measuring hemoglobin mass.

4. Adjudication Method for the Test Set

Since the ground truth for performance testing was based on pre-measured laboratory assays, there was no adjudication method involving multiple human readers or experts. The comparison was directly between the device's output and the established objective measurement.

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 conducted involving human readers with and without AI assistance to measure effect size. The studies described are primarily technical performance validation (accuracy of Hb estimation) and human factors usability of the device itself.

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

Yes, standalone performance testing was done for the algorithm's core function. The bench-top and system validation tests evaluated the algorithm's ability to estimate hemoglobin mass (sHbL) from imaged sponges by comparing "Triton sHbL" (algorithm output) to "Assay sHbL" (pre-measured ground truth).

The process involved the App capturing images, transferring them to a server-based hemoglobin algorithm software, which then calculated the Triton sHbL. This calculated value was then compared to the Assay sHbL. This effectively represents the algorithm's standalone performance in estimating Hb mass from image input.

7. The Type of Ground Truth Used

The type of ground truth used for the quantitative performance studies (bench-top and system validation) was objective laboratory measurement of hemoglobin mass, referred to as "pre-measured Hb mass (Assay sHbL)". This involved depositing known quantities of blood with known Hb mass on surgical sponges.

8. The Sample Size for the Training Set

The document does not explicitly state the sample size for the training set used to develop or refine the Hemoglobin Algorithm, nor does it specify if a separate training set was used for the Sponge Recognition Algorithm (SRA). The text focuses on the testing and validation of the device.

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

The document does not provide information on how the ground truth for any training set was established. It primarily details the methods for creating test data and establishing ground truth for validation purposes.

Ask a Question

Ask a specific question about this device

Page 1 of 1