(63 days)
The SurgiCount Medical Safety-Sponge System™ is indicated for use in counting and recording the number of thermally labeled surgical sponges, laparotomy sponges and towels used during surgical procedure.
The Safety Sponges include surgical sponges, laparatomy pads and surgical towels, each unit of which contains a unique identification label permanently fused to the gauze or fabric. The labels allow the sponges and towels to be individually recognized by a commercially available sight laser imager.
The Safety Sponge Counter is a commercially available mobile computer with specialized software designed for mobile data collection. Integrated imaging technology allows capture of the information coded in the unique identification label on the sponges, pads and towels. The computer counts the initial number of sponges opened, and using the custom software program, reports the total sponges used at the end of the procedure or on demand, and compares that number to the original. Individual sponges may be identified as entered into the surgical field but not discarded, so that the surgical field can be explored before surgically closing the patient.
Here's an analysis of the provided text regarding the SurgiCount Medical Safety-Sponge System's acceptance criteria and study:
1. Table of Acceptance Criteria and Reported Device Performance
The document does not explicitly state quantitative acceptance criteria (e.g., "accuracy must be >99%"). Instead, it focuses on qualitative substantial equivalence and functional performance.
| Acceptance Criterion (Implicit) | Reported Device Performance |
|---|---|
| Label Permanence | Labels do not flake or peel. |
| Material Biocompatibility | Material is comparable to commercially available predicates. |
| Unique Labeling Accuracy | Manufacturing validation ensured one and only one unique label per pad. |
| Software Functionality (Counting) | Software functioned as intended under simulated use, properly counting sponges in simulated body fluids. |
| Software Functionality (Reporting) | Software provided hard copy reports equivalent to those used for blood bag inventory products. |
| Clinical Accuracy (Clean Sponges) | Accurately counted surgical sponges into and out of the field on clean sponges. |
| Clinical Accuracy (Soiled Sponges) | Accurately counted surgical sponges into and out of the field on soiled sponges (through blood and bodily fluids). |
| Clinical Time Efficiency | Compared accuracy and time spent for counting sponges. (Implicitly, the system is expected to be more effective/efficient than hand counting). |
| User Assessment | Operating personnel's assessment of the software program and ease of use was favorable. |
| Safety | No adverse events were reported; labels are as safe as the predicate device. |
| Effectiveness | System provides improved accuracy, comparable to inventory control systems for blood bags. |
2. Sample Size Used for the Test Set and Data Provenance
- Test Set Sample Size: Not explicitly stated. The clinical study involved a "surgical setting" but the number of procedures, sponges, or specific data points is not quantified.
- Data Provenance: Clinical data was prospective ("tested clinically under non-significant risk IRB approvals in a surgical setting"). The country of origin is not specified, but given the 510(k) submission to the FDA, it is highly likely to be the United States.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
This information is not provided in the document. The document mentions "operating personnel's assessment," but it doesn't specify if these personnel established ground truth for sponge counts or if their assessment was for user experience.
4. Adjudication Method for the Test Set
This information is not provided in the document.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- No Multi-Reader, Multi-Case (MRMC) study was explicitly mentioned. The study compared the device (AI) to traditional hand counting and assessed accuracy and time efficacy. It did not evaluate human readers with and without AI assistance in the traditional MRMC sense.
- Effect Size: Not applicable, as an MRMC study of human readers with/without AI assistance was not performed. The text does state the system makes its use "more effective than hand counting sponges" and provides "improved accuracy," but no specific quantitative effect size is given for human performance enhancement.
6. Standalone (i.e., algorithm only without human-in-the-loop performance) Study
- Yes, a standalone performance study was done. The core of the product is a "mobile computer with specialized software" that performs the counting. The "software validation of the hand-held scanning device" and "simulated finished product testing of the total system" where the software "properly counting sponges in simulated body fluids" directly demonstrate algorithm-only performance. The clinical study also validates the system's ability to "accurately counted surgical sponges into and out of the field, on both clean and soiled sponges," implying standalone algorithm accuracy.
7. Type of Ground Truth Used
Based on the description, the ground truth was likely established through manual, independent counting of sponges for comparison with the device's count. The description implies that the study aimed to verify the accuracy of the device's count against a known correct count (the actual number of sponges).
8. Sample Size for the Training Set
This information is not provided in the document. The document describes the system as using "commercially available" components and software "similar to the predicate software" for inventory control, suggesting it may not have required extensive de novo training data for a complex machine learning model in the modern sense. It's more likely a rule-based or OCR-like system.
9. How the Ground Truth for the Training Set Was Established
This information is not provided in the document, and it's unclear if a distinct "training set" with ground truth, as understood in modern AI development, was even used. Given the technology described (reading unique ID labels with a laser imager), the system might be more of a deterministic counting system rather than an AI model requiring a large, annotated training set. Its functionality relies on reliable label reading and matching, not "learning" from diverse input data to classify or detect.
§ 880.2740 Surgical sponge scale.
(a)
Identification. A surgical sponge scale is a nonelectrically powered device used to weigh surgical sponges that have been used to absorb blood during surgery so that, by comparison with the known dry weight of the sponges, an estimate may be made of the blood lost by the patient during surgery.(b)
Classification. Class I (general controls). The device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter, subject to the limitations in § 880.9. The device also is exempt from the current good manufacturing practice requirements of the quality system regulation in part 820 of this chapter, with the exception of § 820.180, with respect to general requirements concerning records, and § 820.198, with respect to complaint files.