Search Results

The diagnostic ultrasound system and probes are designed to obtain ultrasound images and analyze body fluids.

The clinical applications include: Fetal/Obstetrics, Abdominal, Gynecology, Intraoperative, Small Organ, Neonatal Cephalic, Adult Cephalic, Trans-vaginal, Muscular-Skeletal (Conventional, Superficial), Urology, Cardiac Adult, Cardiac Pediatric, Trans-esophageal(Cardiac) and Peripheral vessel.

It is intended for use by, or by the order of, and under the supervision of, an appropriately trained healthcare professional who is qualified for direct use of medical devices. It can be used in hospitals, private practices, clinics and similar care environment for clinical diagnosis of patients.

Modes of Operation: 2D mode, Color Doppler mode, Pulsed Wave (PW) Doppler mode, Continuous Wave (CW) Doppler mode, Tissue Doppler Imaging (TDI) mode, Tissue Doppler Wave (TDW) mode, Power Doppler (PD) mode, ElastoScan™ Mode, Multi-Image mode(Dual, Quad), Combined modes, 3D/4D mode

The RS85 / RS80 EVO are a general purpose, mobile, software controlled, diagnostic ultrasound system. Its function is to acquire ultrasound data and to display the data as 2D mode, M mode, Color Doppler imaging, Power Doppler imaging (including Directional Power Doppler mode; S-Flow), PW Spectral Doppler mode, CW Spectral Doppler mode, Harmonic imaging, Tissue Doppler imaging, Tissue Doppler Wave, 3D imaging mode (real-time 4D imaging mode), Elastoscan* Mode, MV-Flow Mode or as a combination of these modes.

The RS85 / RS80 EVO also give the operator the ability to measure anatomical structures and offers analysis packages that provide information that may aid in making a diagnosis by competent health care professionals. the RS85 / RS80 EVO have real time acoustic output display with two basic indices, a mechanical index and a thermal index, which are both automatically displayed.

This document describes a 510(k) submission for the Samsung Medison RS85 and RS80 EVO Diagnostic Ultrasound Systems. The submission focuses on demonstrating substantial equivalence to previously cleared predicate devices, primarily through non-clinical testing.

Based on the provided text, a significant limitation is that no clinical studies were conducted to support the substantial equivalence of the RS85/RS80 EVO. The acceptance criteria and "device performance" described below are therefore derived from non-clinical tests and comparisons to the predicate device, not from human clinical data related to diagnostic accuracy or improved patient outcomes.

Therefore, the requested information about acceptance criteria and a study proving the device meets them will be based on the provided non-clinical testing and substantial equivalence claims. A Multi-Reader Multi-Case (MRMC) comparative effectiveness study was NOT done as no clinical efficacy studies were conducted. Similarly, no standalone (algorithm-only) performance was assessed as this is not an AI-driven diagnostic device beyond what is discussed in the software evaluation context.

Acceptance Criteria and Reported Device Performance (Non-Clinical)

Since no clinical studies were performed, the "acceptance criteria" are based on compliance with regulatory standards and demonstrating comparable performance to the predicate device through non-clinical testing.

Study Proving Device Meets Acceptance Criteria

The study proving the device meets the acceptance criteria is a non-clinical test program designed to demonstrate compliance with recognized standards and substantial equivalence to a predicate device, rather than a clinical efficacy or performance study on human subjects.

1. Sample Size Used for the Test Set and Data Provenance:

   • Test Set Sample Size: Not applicable in the traditional sense of patient data. The "test set" consisted of the new RS85/RS80 EVO systems, their components (transducers, software), and their operational characteristics.
   • Data Provenance: The data is based on laboratory-based non-clinical testing performed by Samsung Medison Co., Ltd. in the Republic of Korea. The testing is retrospective in the sense that it relies on established standards and comparative analysis against known predicate device performance, not forward-looking clinical trials.

2. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications of Experts:

   • Not applicable. Ground truth for non-clinical testing is established by compliance with published engineering and safety standards (e.g., IEC, ANSI, ISO, NEMA) and comparison to the predicate device's established performance characteristics. No human experts are used to "read" or "adjudicate" test results in the clinical diagnostic sense for this type of submission.

3. Adjudication Method for the Test Set:

   • Not applicable. Non-clinical test results are typically evaluated against pre-defined quantitative thresholds set by the standards or against the established performance of the predicate device. There is no "adjudication" in the sense of multiple human readers resolving discrepancies.

4. 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 MRMC comparative effectiveness study was done. The submission states: "The subject of this premarket submission, RS85 / RS80 EVO, did not require clinical studies to support substantial equivalence." This device is a diagnostic ultrasound system, not explicitly an AI-assisted diagnostic tool as described in the prompt's context for MRMC studies. The software functionality evaluation focuses on maintaining image quality, not on improving human reader performance with AI.

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

   • No standalone algorithm performance study was done. The device itself is an ultrasound imaging system operated by a human, not a standalone AI algorithm producing diagnostic outputs without human interaction.

6. The Type of Ground Truth Used:

   • For non-clinical testing, the "ground truth" is established by:
     • Engineering Specifications and Performance Benchmarks: Adherence to established limits for acoustic output, electrical safety, EMC, and mechanical performance.
     • Regulatory Standards: Compliance with relevant ISO, IEC, ANSI, AAMI, and NEMA standards.
     • Predicate Device Performance: The established, cleared performance characteristics and functionality of the previously marketed predicate devices (K210959 and K211945).
     • Laboratory-based measurements and tests.

7. The Sample Size for the Training Set:

   • Not applicable. This is not an AI/machine learning submission requiring a training set for model development. The software evaluation focuses on the migration of existing, cleared software functionality.

8. How the Ground Truth for the Training Set was Established:

   • Not applicable, as there was no training set for an AI/ML model.

Ask a specific question about this device

The diagnostic ultrasound system and probes are designed to obtain ultrasound images and analyze body fluids.

The clinical applications include: Fetal/Obstetrics, Abdominal, Gynecology, Intraoperative, Small Organ, Neonatal Cephalic, Adult Cephalic, Trans-vaginal, Muscular-Skeletal (Conventional, Superficial), Urology, Cardiac Adult, Cardiac Pediatric, Trans-esophageal(Cardiac) and Peripheral vessel.

It is intended for use by, or by the order of, and under the supervision of, an appropriately trained healthcare professional who is qualified for direct use of medical devices. It can be used in hospitals, private practices, clinics and similar care environment for clinical diagnosis of patients.

Modes of Operation: 2D mode, Color Doppler mode, Pulsed Wave (PW) Doppler mode, Continuous Wave (CW) Doppler mode, Tissue Doppler Imaging (TDI) mode, Tissue Doppler Wave (TDW) mode, Power Doppler (PD) mode, ElastoScan™ Mode, Multi-Image mode(Dual, Quad), Combined modes, 3D/4D mode

The RS85 / RS80 EVO are a general purpose, mobile, software controlled, diagnostic ultrasound system. Its function is to acquire ultrasound data and to display the data as 2D mode, M mode, Color Doppler imaging, Power Doppler imaging (including Directional Power Doppler mode; S-Flow), PW Spectral Doppler mode, CW Spectral Doppler mode, Harmonic imaging, Tissue Doppler imaging, Tissue Doppler Wave, 3D imaging mode (real-time 4D imaging mode), Elastoscan Mode, MV-Flow Mode or as a combination of these modes.

The RS85 / RS80 EVO also give the ability to measure anatomical structures and offers analysis packages that provide information that may aid in making a diagnosis by competent health care professionals.

The RS85 / RS80 EVO have real time acoustic output display with two basic indices, a mechanical index and a thermal index, which are both automatically displayed.

The provided document, a 510(k) summary for the Samsung Medison RS85 / RS80 EVO Diagnostic Ultrasound System, does not contain the detailed acceptance criteria and performance study information typically required for an AI/ML-based medical device.

The document explicitly states in section 12: "The subject of this premarket submission, RS85 / RS80 EVO, did not require clinical studies to support substantial equivalence." This indicates that the regulatory clearance was based on substantial equivalence to a predicate device (RS85 Diagnostic Ultrasound System K192903) through non-clinical testing, rather than a performance study involving AI/ML components with specific acceptance criteria.

The information provided pertains to general ultrasound system functions, safety standards, and technological equivalence to a previous model, not to the performance of an AI-driven feature.

Therefore, I cannot extract the requested information regarding acceptance criteria and performance study details for an AI component from this document.

To answer your request, if this were a document for an AI/ML-driven device, the following would typically be observed:

1. A table of acceptance criteria and the reported device performance: This would be found in a dedicated section detailing the clinical or technical validation of the AI feature. It would list performance metrics (e.g., sensitivity, specificity, AUC, accuracy) with pre-defined thresholds and the actual values achieved by the device.

2. Sample sized used for the test set and the data provenance: This information would be crucial for evaluating the robustness and generalizability of the AI model. It would include the number of cases/patients in the test set, their demographic breakdown, and where the data was collected (e.g., single-center, multi-center, specific countries), and whether it was collected retrospectively or prospectively.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: For expert consensus ground truth, the number of readers, their specialty (e.g., board-certified radiologists), and years of experience would be detailed.

4. Adjudication method (e.g., 2+1, 3+1, none) for the test set: If multiple experts were used to establish ground truth, the method for resolving discrepancies (e.g., majority vote, senior expert arbitration) would be described.

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: This would be a specific section demonstrating the human-AI team performance, often comparing reader performance with and without AI assistance using metrics like AUC, sensitivity, or specificity, and reporting the statistically significant improvement (effect size).

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Often, an AI model's standalone performance is evaluated first, before assessing its impact in a human-in-the-loop setting.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc): This would specify the "gold standard" against which the AI's performance was measured.

8. The sample size for the training set: The number of cases/patients used to train the AI model would be an important detail to understand the model's learning capacity.

9. How the ground truth for the training set was established: The method for labeling or annotating the data used for training the AI model would be described.

In summary, the provided document focuses on the substantial equivalence of a general diagnostic ultrasound system and its transducers, rather than the performance evaluation of an AI/ML-driven component within such a system.

Ask a specific question about this device