(167 days)
The SurgiCount+ System Software is a multifunctional software application intended to be used as an adjunct in the estimation of blood loss and management of surgical sponges and other absorbent items. The system incorporates three distinct software configurations: Triton AI, SC+ Sponge Counting, and Triton QBL. Additionally, combined workflows (SC+ AI and SC+QBL) are provided for use in clinical environments that require both the tracking of absorbent surgical items and estimation of patient blood loss.
The Triton AI configuration is intended to be used with surgical sponges, software, hardware and accessory devices that have been validated for use with the application to estimate the hemoglobin (Hb) mass contained on used surgical sponges. The configuration is also intended to calculate an estimate of blood volume on used surgical sponges from the estimated Hb mass and a user-entent Hb value. The validated surgical sponges, hardware, software, accessory devices and Hb mass ranges are listed in the Instructions for Use.
The SC+ Sponge Counting configuration is intended for use as an adjunctive technology for augmenting the manual process of counting, displaying and recording the number of RFID-tagged absorbent articles used during surgical procedures, and providing a non-invasive means of locating RFID-tagged absorbent articles within an operating room and surgical sites.
The Triton QBL (Quantification of Blood Loss) configuration is intended to be used to record the weight of used surgical sponges and other absorbent items in order to calculate the quantity of fluid volume on the sponges/absorbent items.
The SurgiCount+ [SC+] System Software is a multi-functional software application that is intended to be used as an adjunct in the estimation of blood loss and management of surgical sponges and other surgical substrates. The system incorporates three distinct software configurations: Triton AI, SC+ Sponge Counting, and Triton Quantitative Blood Loss [QBL]. Additionally, combined workflows (SC+AI and SC+QBL) are provided for use in clinical environments that require both the tracking of absorbent surgical items and estimation of patient blood loss. Two of the five software configurations (Triton Al and SC+Al) are Class II functions. The remaining configurations are Class I functions.
The Class II Triton Al software configuration estimates the hemoglobin (Hb) mass contained on used surgical sponges using an AI algorithm that analyzes the image of each sponge. It also calculates an estimate of blood volume on used surgical sponges from the estimated Hb mass and a user-entered patient Hb value. The Triton Al software configuration's sponge counting functionality has been modified to enhance the product's surgical sponge counting/management functionality, compared to the predicate device. New workflow steps allow users to scan, identify, and count RFID-tagged surgical sponges and other absorbent items, and to locate missing surgical sponges inside the operating room and, noninvasively, in surgical sites.
The SaMD product includes the following nonmedical device and Class I consumable and hardware accessories: a mobile device (Apple iPad Pro), RFID-tagged surgical sponges/absorbent items, an RFID reader, a bluetooth-enabled scale, and a stand (or optional wall mount) that houses the hardware accessories and connects the accessory devices to electrical power.
The provided text describes the Stryker SurgiCount+ System, an image processing device for estimating external blood loss. Here's a breakdown of the acceptance criteria and study details based on the provided FDA 510(k) summary:
1. Acceptance Criteria and Reported Device Performance
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Hemoglobin (Hb) Algorithm Performance Validation: Limits of agreement between actual hemoglobin mass and sHbL measured by the SurgiCount+ software within an acceptance limit of ±1.99 g Hb. | The limits of agreement between the actual hemoglobin mass and sHbL measured by the SurgiCount+ software fell within the acceptance limit of ±1.99 g Hb. (Implicitly, this means it met the criteria). |
| Sponge Recognition Algorithm (SRA) Performance Validation: Failure rate (sum of false images and failed detection) of less than or equal to 6.5% for a representative 18x18 inch sponge type. | The SRA had a failure rate (sum of false images and failed detection) of 0.19%, when used to detect a representative 18x18 inch sponge type. (Well below the acceptance criterion). |
| Electromagnetic Compatibility (EMC) Testing: Conformance with IEC 60601-1-2 and demonstration of electromagnetic compatibility (EMC) safety and effectiveness in the hospital environment. | The SurgiCount+ System conforms with IEC 60601-1-2 and demonstrates electromagnetic compatibility (EMC) safety and effectiveness in the hospital environment. |
| Wireless Coexistence Testing: Functioned as designed in the presence of Wi-Fi and Bluetooth interferers that were no closer than 30 cm away from the SurgiCount+ System's iPad (Implicitly, no significant interference). | The SurgiCount+ System functioned as designed in the presence of Wi-Fi and Bluetooth interferers that were no closer than 30 cm away from the SurgiCount+ System's iPad. |
| Human Factors Validation: The system is reasonably safe and effective for its intended users and use environment, and all use risks were effectively mitigated. No significant residual or new usability risks were found. (Implicitly, the study findings indicated this). | The validation study concluded that the SurgiCount+ System is reasonably safe and effective for its intended users and use environment and that all use risks were effectively mitigated. No significant residual or new usability risks were found. |
2. Sample Size Used for the Test Set and Data Provenance
- Hb Algorithm Performance Validation: The text states, "Testing was conducted to evaluate the accuracy of the Hb algorithm in estimating the Hb mass on surgical sponges, compared to the known Hb mass on each sponge as determined by a reference assay." This implies that a set of surgical sponges was used, each with a "known Hb mass." However, the exact sample size (number of sponges) for this test set is not explicitly stated.
- Sponge Recognition Algorithm (SRA) Performance Validation: The text states it was "used to detect a representative 18x18 inch sponge type." The specific sample size (number of images or instances) for this test is not explicitly stated.
- Human Factors Validation: "Fifteen nurses participated in a complete, end-to-end, usability validation."
- Data Provenance: The document does not specify the country of origin of the data or whether the study was retrospective or prospective. It describes non-clinical (bench) testing and human factors validation, suggesting controlled environments rather than real-world patient data collection for the primary performance validations.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
- The text does not provide information regarding the number or qualifications of experts used to establish ground truth for the Hb Algorithm or SRA performance validations. The ground truth for the Hb algorithm was established by a "reference assay."
- For Human Factors Validation, "Fifteen nurses" participated as users, but they were not establishing ground truth, rather their performance and feedback were observed and evaluated.
4. Adjudication Method for the Test Set
- The document does not specify any adjudication methods (e.g., 2+1, 3+1) for the performance validation test sets. The ground truths were established via objective measures (reference assay for Hb, assumed prior knowledge for SRA, and structured observation for Human Factors).
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and Effect Size
- No, an MRMC comparative effectiveness study was not described. The performance data provided are for the standalone device capabilities (Hb algorithm accuracy, SRA failure rate) and human factors validation (usability and safety), not a comparative analysis of human readers with vs. without AI assistance. The device is intended as an adjunct to blood loss estimation and sponge management, implying it supports human users, but a formal MRMC study to quantify human improvement with AI assistance is not mentioned.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done
- Yes, standalone performance was evaluated for the core AI components:
- Hemoglobin (Hb) Algorithm Performance Validation: This tested the algorithm's accuracy in estimating Hb mass compared to a known reference, which is a standalone evaluation of the algorithm's output.
- Sponge Recognition Algorithm (SRA) Performance Validation: This assessed the algorithm's ability to detect sponges and its failure rate, which is also a standalone evaluation.
7. The Type of Ground Truth Used
- Hemoglobin (Hb) Algorithm: The ground truth was established by a "reference assay" for the "known Hb mass on each sponge." This implies a laboratory measurement or biochemical analysis.
- Sponge Recognition Algorithm (SRA): The ground truth implicitly was the actual presence/absence and type of sponge, likely determined by controlled experimental setup where the correct sponge type was presented.
- Human Factors Validation: The "ground truth" here was the observational data of user performance collected through "clinically realistic scenarios" and user input, evaluated against predetermined safety and usability criteria.
8. The Sample Size for the Training Set
- The document states, "The algorithms generate the same output for a given input (are fixed) and have been trained using machine learning techniques to recognize the sponges and to estimate Hb mass and blood loss volume on the imaged substrates."
- However, the sample size for the training set is not provided in the given text.
9. How the Ground Truth for the Training Set Was Established
- The document states the AI algorithms were "trained using machine learning techniques to recognize the sponges and to estimate Hb mass and blood loss volume on the imaged substrates."
- While it mentions "known Hb mass" for the a test set, the method for establishing ground truth for the training set is not explicitly described. Given the nature of Hb mass estimation, it is highly probable that the training data also included images of sponges with independently measured "known Hb mass" established through venipuncture and lab analysis, similar to the method used for the testing data. For sponge recognition, it would likely involve labeled images indicating the presence and type of sponges.
§ 880.2750 Image processing device for estimation of external blood loss.
(a)
Identification. An image processing device for estimation of external blood loss is a device to be used as an aid in estimation of patient external blood loss. The device may include software and/or hardware that is used to process images capturing externally lost blood to estimate the hemoglobin mass and/or the blood volume present in the images.(b)
Classification. Class II (special controls). The special controls for this device are:(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:
(i) Lighting conditions;
(ii) Range of expected hemoglobin concentrations;
(iii) Range of expected blood volume absorption; and
(iv) Presence of other non-sanguineous fluids (
e.g., saline irrigation fluid).(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.
(3) Appropriate analysis and non-clinical testing must validate the electromagnetic compatibility (EMC) and wireless performance of the device.
(4) Appropriate software verification, validation, and hazard analysis must be performed.
(5) Software display must include an estimate of the cumulative error associated with estimated blood loss values.
(6) Labeling must include:
(i) Warnings, cautions, and limitations needed for safe use of the device;
(ii) 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;
(iii) The validated surgical materials, range of hemoglobin mass, software, hardware, and accessories that the device is intended to be used with; and
(iv) EMC and wireless technology instructions and information.