Search Filters

Search Results

Found 2265 results

510(k) Data Aggregation

    K Number
    K250126
    Manufacturer
    Date Cleared
    2025-10-21

    (277 days)

    Product Code
    Regulation Number
    878.4400
    Reference & Predicate Devices
    Predicate For
    N/A
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    ArtiSeal Vessel Sealing System - ArtiSeal Instruments are a bipolar electrosurgical instrument intended for use only with the ArtiSeal Generator in minimally invasive or open surgical procedures where ligation (sealing) and division (Cutting) of vessels and tissue bundles is desired. ArtiSeal Vessel Sealing System - ArtiSeal Instruments can be used on vessels (arteries and veins) up to and including 7 mm. It is indicated for use in general surgery.

    Device Description

    The ArtiSeal Vessel Sealing System - ArtiSeal Instruments (AS01M) is a sterile, single-use, invasive instrument which is used with electrosurgical generator (ArtiSeal Generator), intended to be used during laparoscopic/minimally invasive or open surgical procedures where ligation and division of vessels and tissue bundles is desired.

    When activating the sealing button of ArtiSeal Vessel Sealing System-ArtiSeal instruments, the ArtiSeal Generator applies radiofrequency (RF) energy to the electrode portion of the jaw. Heat is generated from the electrode for ligation.

    During surgical procedures, the user operates the grip lever to open and close the jaw. Furthermore, the jaw can be bent up, down, left, and right within a range of up to ±90° or more by adjusting the grip accordingly. The jaw also provides 360° articulation (rotation) by turning the grip.

    AI/ML Overview

    N/A

    Ask a Question

    Ask a specific question about this device

    K Number
    K252114
    Date Cleared
    2025-10-02

    (87 days)

    Product Code
    Regulation Number
    866.1640
    Reference & Predicate Devices
    N/A
    Predicate For
    N/A
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use
    Device Description
    AI/ML Overview
    Ask a Question

    Ask a specific question about this device

    K Number
    K243833
    Date Cleared
    2025-09-29

    (290 days)

    Product Code
    Regulation Number
    868.5440
    Reference & Predicate Devices
    Predicate For
    N/A
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The Oxygen Concentrator is used on a prescriptive basis by patients requiring supplemental oxygen. It supplies a high concentration of oxygen and is used with a nasal cannula to channel oxygen from the concentrator to the patient. The Portable Oxygen Concentrator is intended to provide supplemental oxygen in a home, institutional, or travel environment (not include emergency medical services environment). The oxygen concentrator for adult use, providing pulsed oxygen flow.

    Device Description

    Portable Oxygen Concentrator, model: JAY-1000P is a portable oxygen generator that is intended to release oxygen for respiratory therapy by means of physical means (a molecular sieve). It supplies a pulsed high concentration of oxygen and is used with a nasal cannula to channel oxygen from the concentrator to the patient. The JAY-1000P is small, portable and may be used in home, institutional, or travel environment.

    The portable oxygen concentrator consists of two parts: an oxygen concentrator and accessories. The oxygen concentrator is composed of compressor, battery, solenoid valve, molecular sieve, circuit control system, heat dissipation system, and a flow control device. Accessories include power adapters.

    AI/ML Overview

    N/A

    Ask a Question

    Ask a specific question about this device

    K Number
    K252435
    Date Cleared
    2025-09-26

    (56 days)

    Product Code
    Regulation Number
    878.4815
    Reference & Predicate Devices
    Predicate For
    N/A
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The Magnetic Surgical System is indicated for use in patients within a BMI range of 20 to 60 kg/m2 and designed to grasp and retract soft tissues and organs to facilitate access and visualization of the surgical site for the following:

    • The body and fundus of the gallbladder in laparoscopic cholecystectomy procedures
    • The liver in bariatric procedures
    • The prostate and periprostatic tissue in prostatectomy procedures
    • The colon, rectum, and pericolorectal tissue in colorectal procedures

    The Grasper Tip 12.5 is indicated for use in patients within a BMI range of 20 to 60 kg/m2 and designed to grasp and retract soft tissues and organs to facilitate access and visualization of the surgical site for the following:

    • The pillar of the diaphragm and peripillar tissue in bariatric or hiatal hernia procedures

    Pediatric use:

    The Magnetic Surgical System is indicated for use in adolescents (12-21) within a BMI range of 20 to 34 kg/m2 and designed to grasp and retract soft tissues and organs to facilitate access and visualization of the surgical site for the following:

    • The body and fundus of the gallbladder in laparoscopic cholecystectomy procedures
    Device Description

    The Magnetic Surgical System comprises two hand-held instruments, the Magnetic Grasper and the external Magnetic Controller. The Magnetic Grasper, disposable and provided sterile for single use, comprises two main components: a detachable Grasper Tip (6.5cm overall length) and a shaft with Handle. An optional 12.5cm length Grasper Tip (also single use, disposable, and provided sterile) may be used as a replacement for the 6.5cm Grasper Tip and can be used interchangeably with the Shaft.

    The Magnetic Grasper is actuated via its pistol-grip handle with two distinct scissor-type motions to open and close the Grasper Tip jaws. Once the Magnetic Grasper is inserted through a compatible >= 10 mm laparoscopic port to the surgical site and the Grasper Tip is attached to the desired tissue, the Grasper Tip can be detached from the Shaft and controlled externally using the Magnetic Controller. Traction of the tissue is maintained through the magnetic field attraction between the Grasper Tip and the Magnetic Controller.

    The Magnetic Controller is a non-sterile, reusable unit with handles that is held external to the body and emits a magnetic field that attracts the detachable Grasper Tip. Once the Grasper Tip is attached to the desired tissue and detached from the Shaft, the Magnetic Controller is placed external to the body to magnetically attract the Grasper Tip to manipulate the target tissue. Adjusting the distance between the Magnetic Controller and the Grasper Tip will modulate the magnetic attraction used for tissue retraction/mobilization. If desired, the user can connect the Magnetic Controller to a commercially available surgical support arm that is compatible with its arm mount.

    AI/ML Overview

    N/A

    Ask a Question

    Ask a specific question about this device

    K Number
    K252105
    Device Name
    Ligence Heart
    Manufacturer
    Date Cleared
    2025-09-26

    (85 days)

    Product Code
    Regulation Number
    892.2050
    Reference & Predicate Devices
    Predicate For
    N/A
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    Ligence Heart is a fully automated software platform that processes, analyses and makes measurements on acquired transthoracic cardiac ultrasound images, automatically producing a full report with measurements of several key cardiac structural and functional parameters. The data produced by this software is intended to be used to support qualified cardiologists or sonographers for clinical decision making. Ligence Heart is indicated for use in adult patients. Ligence Heart has not been validated for the assessment of congenital heart disease, valve disease, pericardial disease, and/or intra-cardiac lesions (e.g., tumors, thrombi).

    Device Description

    Ligence Heart is an image post-processing software used for viewing and quantifying adult cardiac ultrasound DICOM studies. The device is intended to generate structured measurement reports for echocardiography analysis and aid qualified sonographers and cardiologists in their decision-making process.

    Ligence Heart automatically identifies standard transthoracic echo views with machine-learning–based view classification, cardiac cycle selection, and border detection, then generates reproducible quantitative left-ventricular volumetric and functional measurements. The results are inserted into a PACS-compatible report that the reviewing cardiologist or sonographer can accept, edit, supplement with additional manual measurements, or entirely replace with manual measurements. The software also organizes, displays, and compares each measurement with reference-guideline ranges. Completed reports are exported in PDF, streamlining routine echocardiography workflow while leaving final diagnostic responsibility with the clinician.

    AI/ML Overview

    Here's a breakdown of the acceptance criteria and the study proving Ligence Heart meets them, based on the provided FDA 510(k) clearance letter:

    Acceptance Criteria and Reported Device Performance

    Acceptance Criteria (Primary Clinical Performance Endpoint)Reported Device Performance
    Individual Equivalence Coefficient (IEC): Upper level of the 95% confidence interval for agreement between Ligence Heart and expert sonographers < 0.25 (non-inferiority margin).All four parameters met the non-inferiority criterion, implying IEC < 0.25.
    Secondary Agreement Metric (for consistency)
    Intraclass Correlation Coefficients (ICC) for all four parameters.ICCs were $\ge$ 0.90 for all four parameters.

    Study Details

    1. Sample size used for the test set and the data provenance:

    • Sample Size: 524 echocardiographic studies. (Initially, 600 were acquired, but 76 were excluded).
    • Data Provenance: Retrospective, acquired from a U.S.-based independent Echocardiography Core Laboratory.

    2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

    • Number of Experts: Three independent expert sonographers.
    • Qualifications of Experts: The document explicitly states "expert sonographers." No further specific details (e.g., years of experience, board certification) are provided in this excerpt.

    3. Adjudication method (e.g., 2+1, 3+1, none) for the test set:

    • The document states, "524 echocardiographic studies were assessed by all three human readers..." This implies that all three contributed to the ground truth, but it doesn't explicitly state an adjudication method like 2+1 or 3+1. Given the use of "agreement between Ligence Heart and three independent expert sonographers...quantified using the reference-scaled IEC," it suggests that each expert's measurements were compared against the device, rather than a consensus ground truth being established before comparison with the device.

    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, an MRMC comparative effectiveness study was not explicitly done to measure human reader improvement with AI assistance. The study focused on the standalone performance of the Ligence Heart device and its interchangeability with expert human measurements. It did not directly assess how human readers' performance would change when using the AI as an assistant.

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

    • Yes, a standalone performance study was done. The primary clinical performance endpoint measured the agreement between "Ligence Heart" (the automated measurements) and "three independent expert sonographers." This evaluates the device's output independently against expert human measurements.

    6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

    • Expert measurements/readings. The ground truth for the comparison was established by the measurements from "three independent expert sonographers."

    7. The sample size for the training set:

    • The document explicitly states, "Test datasets were strictly segregated from algorithm training datasets, as they are from completely separate cohorts." However, the sample size for the training set is not provided in this excerpt.

    8. How the ground truth for the training set was established:

    • The document states that the test datasets were "strictly segregated from algorithm training datasets." However, how the ground truth for the training set was established is not described in this excerpt. It can be inferred that it likely involved expert annotations or measurements, similar to the test set, but the details are not available here.
    Ask a Question

    Ask a specific question about this device

    K Number
    K250093
    Date Cleared
    2025-09-26

    (255 days)

    Product Code
    Regulation Number
    868.2375
    Reference & Predicate Devices
    Predicate For
    N/A
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    Linshom Continuous Predictive Respiratory Monitoring System (CPRMS) is indicated for use by healthcare professionals in healthcare facilities, such as procedural areas and recovery rooms, to monitor breathing in adult, (at least 22 years of age) patients.

    The CPRMS is a non-invasive system that graphically displays temperature changes against time and reports values of respiratory rate and seconds since last breath, along with a trend of tidal volume.

    CPRMS measurements are used as an adjunct to other clinical information sources.

    Device Description

    The Linshom CPRMS (Continuous Predictive Respiratory Monitoring System) is a portable and reliable system for detection of spontaneous respiration. It's non-invasive and is not corrupted by motion artifacts. The system autonomously adapts to the local thermal environment to deliver a usable signal without complicated hardware and firmware processing.

    AI/ML Overview

    N/A

    Ask a Question

    Ask a specific question about this device

    K Number
    K251973
    Date Cleared
    2025-09-23

    (89 days)

    Product Code
    Regulation Number
    878.4860
    Reference & Predicate Devices
    Predicate For
    N/A
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The Luminance Red Cold Sore device is indicated for shortening the time to healing of herpes simplex labialis lesions on and around the lips with time to healing defined as the time to patient described re-epithelialization.

    This device is suitable for users with Fitzpatrick skin types I-IV.

    Device Description

    The Luminance Red Cold Sore Device is a lightweight, hand held device that consists of a body handle and treatment head. The body handle contains LEDs that emit non-therapeutic visible red light and therapeutic invisible near-infrared light (1072 nm+/- 12 nm) through the treatment head. The non-therapeutic visible red light serves as a guidelight and is intended to enhance the usability of the device. The body consists of a plastic shell, which includes a button to turn the device on, a button to start treatment, and a digital countdown timer. The Luminance Red Cold Sore Device is powered by a lithium-ion battery.

    AI/ML Overview

    N/A

    Ask a Question

    Ask a specific question about this device

    K Number
    K251718
    Date Cleared
    2025-08-29

    (86 days)

    Product Code
    Regulation Number
    N/A
    Reference & Predicate Devices
    Predicate For
    N/A
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    ArTT Augments and Buttresses are indicated to be used, in combination with EMPOWR Acetabular Cup System, as an alternative to structural allograft in skeletally mature patients in cases of segmental acetabular deficiencies.

    ArTT Augments and Buttresses are indicated for cementless use to the bone interface; and are affixed to the mating acetabular cup using bone cement.

    Device Description

    This 510(k) submission aims at introducing new device components, the ArTT Augments and Buttresses and Bone Screws (Revision Bone Screws (Dia. 6.5mm), Locking Bone Screws (Dia. 6.5mm), Locking Bone Screws (Dia. 4mm), Bone Screws (Dia. 4mm)) to be used in combination with the EMPOWR Acetabular Cup System (K190057) manufactured by Encore Medical, L.P.

    ArTT Augments and Buttresses are manufactured from Ti6Al4V 3D printed (ISO 5832-3) and are indicated for cementless use to the bone interface; they are affixed to the mating acetabular cup using bone cement. ArTT Augments are available in 9 diameters (Dia. 50mm to 66mm) and 3 eccentricities (Ecc. 10mm, Ecc. 15mm, Ecc. 20mm), while ArTT Buttresses are available in 3 diameters (Dia.50mm, Dia.56mm, Dia.62mm), 3 heights (H. 15mm, H. 30mm, H. 60mm) and 3 configurations (Neutral, Left, Right).

    Bone Screws are manufactured from Ti6Al4V (ISO 5832-3 - ASTM F1472); they are intended for cancellous or cortical bone and are available in several lengths.

    AI/ML Overview

    This FDA 510(k) clearance letter pertains to
    "ArTT Augments and Buttresses and Bone Screws" for orthopedic use. It's important to note that this document is a clearance letter, not a detailed scientific study publication. As such, it provides summary information about the device and the types of testing performed to demonstrate substantial equivalence, rather than a deep dive into specific study methodologies or acceptance criteria with detailed performance metrics.

    Based on the provided text, here's an analysis of the acceptance criteria and the study that proves the device meets them:

    1. Table of Acceptance Criteria and Reported Device Performance:

    The document does not explicitly state specific quantitative acceptance criteria (e.g., minimum tensile strength, maximum wear rate, specific pull-out force thresholds) or precise numerical performance results for the ArTT Augments and Buttresses and Bone Screws.

    Instead, it states:

    • "Mechanical tests demonstrated that the device performance fulfilled the intended use, and that the device is substantially equivalent to the predicate device."
    • "Other performance requirements were fulfilled through rationales and comparisons with previously cleared components (K210717, latest 510(k) approval)."

    This implies that the acceptance criteria were based on:

    Acceptance CriteriaReported Device Performance
    Performance fulfills intended use.Demonstrated by mechanical testing and comparison with predicate devices.
    Substantially equivalent to predicate device (Zimmer Trabecular Metal Acetabular Augments - K061067 and DePuy Gription TF 5.5mm Sterile Locking Screws - K123924).Confirmed through mechanical testing on "worst case components or constructs" and rationales. Specific tests mentioned include Fretting fatigue, Torsional properties, driving torque, and pull-out load.
    Mechanical properties (fretting fatigue, torsional properties, driving torque, pull-out load) meet established standards/protocols."Fretting fatigue testing of the ArTT Augments and Buttresses with Bone screws (Internal protocol)" and "Torsional properties, driving torque and pull-out load of Bone Screws (ASTM F543)". The results fulfilled these requirements.

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

    • Sample Size for Test Set: The document states that mechanical testing was performed on "worst case components or constructs." However, it does not specify the exact number of samples or specimens used for each test (e.g., how many augments, how many screws of each type).
    • Data Provenance: The studies were "Non-clinical testing" conducted by the manufacturer, Limacorporate S.p.A. The location of the testing laboratories or specific origin of data (e.g., retrospective/prospective in a clinical sense) is not described, as these are non-clinical (mechanical) tests.

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

    This section is not applicable as the studies described are non-clinical (mechanical) tests. The "ground truth" for mechanical testing is typically established by engineering standards (e.g., ASTM F543) and internal protocols, not by expert consensus from medical professionals.

    4. Adjudication Method for the Test Set:

    This section is not applicable for non-clinical mechanical testing, where adjudication methods like 2+1 or 3+1 by human experts are not used. Performance is measured against engineering specifications and standards.

    5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size:

    No, an MRMC comparative effectiveness study was not done. The clearance is for a physical orthopedic implant system, not an AI software/diagnostic device that would involve human readers interpreting cases.

    6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done:

    No, a standalone (algorithm only) performance study was not done. This device is a physical implant system, not an algorithm or AI.

    7. The Type of Ground Truth Used:

    For the mechanical tests conducted, the "ground truth" implicitly refers to:

    • Engineering Standards: Specifically mentioned is ASTM F543 for torsional properties, driving torque, and pull-out load of bone screws.
    • Internal Protocols: Used for fretting fatigue testing.
    • Performance of Predicate Devices: The measured performance of the ArTT Augments and Buttresses was deemed "substantially equivalent" to that of the predicate devices. This means the performance of the predicate likely served as a benchmark or reference point for establishing acceptable performance.

    8. The Sample Size for the Training Set:

    This section is not applicable as this is a physical medical device, not an AI/machine learning model that requires a training set.

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

    This section is not applicable for the same reason as above (physical medical device, no training set).

    Ask a Question

    Ask a specific question about this device

    K Number
    K243774
    Date Cleared
    2025-08-27

    (264 days)

    Product Code
    Regulation Number
    888.1100
    Reference & Predicate Devices
    Predicate For
    N/A
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The ELID (Endoscopic Less Invasive Decompression) system intended to provide lumbar decompression of the spine to treat various spinal condition(s) using minimally invasive techniques and instrumentation.

    Device Description

    The ELID (Endoscopic Less Invasive Decompression) System consists of instrumentation intended to aid the user in completing steps necessary to perform lumbar decompression. Instruments include a bone needle, flat blade dilator, dilator tubes, and rongeurs. Instruments in the ELID (Endoscopic Less Invasive Decompression) System are supplied non-sterile, reusable, and manufactured from aluminum per ASTM B211, Nitinol per ASTM 2063, or stainless steel per ASTM A564.

    AI/ML Overview

    The provided text is a U.S. FDA 510(k) Clearance Letter and a 510(k) Summary for the ELID (Endoscopic Less Invasive Decompression) System. While it describes the device, its indications for use, technological characteristics, and a list of performance tests conducted, it does not provide specific acceptance criteria or detailed study results that demonstrate the device meets those criteria.

    The "Performance Data" section states that certain tests were conducted and their results "show that the strength of the ELID (Endoscopic Less Invasive Decompression) System is sufficient for its intended use and is substantially equivalent to legally marketed predicate devices." However, it does not quantify this performance, nor does it specify the acceptance criteria for each test.

    Therefore, I cannot fulfill your request for:

    • A table of acceptance criteria and the reported device performance. The document only lists the types of tests performed (Cleaning Validation, Sterilization Validation, Biocompatibility, Usability Testing, Particulate Analysis) but doesn't provide the detailed results or the specific quantitative acceptance thresholds for these tests.
    • Sample sizes used for the test set and the data provenance. The document mentions "test modes" but does not detail the sample sizes for these tests or the origin of any data (e.g., human or ex-vivo samples, country of origin, retrospective/prospective).
    • Number of experts and their qualifications for ground truth establishment. This type of information is typically relevant for AI/ML-based devices relying on expert annotations, which is not clearly indicated as a component of the ELID system described. The ELID system seems to be a set of physical surgical instruments.
    • Adjudication method. Similar to the point above, this is generally for AI/ML performance evaluation against expert ground truth.
    • MRMC comparative effectiveness study. This is typically for AI/ML devices assisting human readers/interpreters, which doesn't seem to be the primary function of the ELID system.
    • Standalone performance. This again relates to AI/ML algorithms. The ELID system appears to be a set of manual surgical instruments.
    • Type of ground truth used. For an AI/ML device, this could be expert consensus, pathology, or outcomes data. For the ELID system, ground truth would likely refer to engineering specifications and performance evaluations for mechanical properties, biocompatibility, etc. The document does not specify this in detail.
    • Sample size for the training set. Not applicable, as this is a physical medical device, not an AI/ML algorithm requiring a training set.
    • How the ground truth for the training set was established. Not applicable.

    In summary, the provided document is a regulatory clearance letter acknowledging substantial equivalence based on a set of non-clinical performance tests, but it does not disclose the detailed quantitative acceptance criteria or the specific results of these tests, nor does it describe AI/ML related study methodologies like those you've requested. The "Performance Data" section only states that the results "show that the strength... is sufficient for its intended use and is substantially equivalent."

    Ask a Question

    Ask a specific question about this device

    K Number
    K251580
    Date Cleared
    2025-08-20

    (89 days)

    Product Code
    Regulation Number
    866.1640
    Reference & Predicate Devices
    Predicate For
    N/A
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The MTS (MIC Test Strip) Sulbactam-Durlobactam 0.004/4-64/4 μg/ml is a quantitative method intended for the in vitro determination of antimicrobial susceptibility of bacteria. MTS consists of specialized paper impregnated with a pre-defined concentration gradient of an antimicrobial agent, which is used to determine the minimum inhibitory concentration (MIC) in μg/ml of antimicrobial agents against bacteria as tested on agar media using overnight incubation and manual reading procedures. MTS Sulbactam- Durlobactam at concentrations of 0.004/4-64/4 μg/ml should be interpreted at 16-20 hours of incubation.

    Testing with MTS Sulbactam-Durlobactam at concentrations of 0.004/4-64/4 μg/mL is indicated for Acinetobacter baumannii calcoaceticus complex as recognized by the FDA Susceptibility Test Interpretive Criteria (STIC).

    The MTS Sulbactam-Durlobactam 0.004/4-64/4 μg/mL has demonstrated acceptable performance with the following organisms:

    Acinetobacter baumannii calcoaceticus complex

    Device Description

    MTS Sulbactam-Durlobactam 0.004/4 - 64/4 μg/mL is made of special high-quality paper impregnated with a predefined concentration of gradient sulbactam across 15 two-fold dilutions like those of a conventional MIC method and durlobactam at a fixed concentration of 4 μg/mL. One side of the strip is labeled with the sulbactam-durlobactam code (SUD) and the MIC reading scale in μg/mL. When the MTS is applied onto an inoculated agar surface, the performed exponential gradient of antimicrobial agent diffuses into the agar for over an hour. After 16-20 hours incubation, a symmetrical inhibition ellipse centered along the strip is formed. The MIC is read directly from the scale in terms of μg/mL at the point where the edge of the inhibition ellipse intersects the MIC Test Strip. The MIC Test Strip (MTS) is single use only.

    Sulbactam-durlobactam is an intravenous beta-lactam combination antibiotic used to treat hospital-acquired pneumonia and ventilator-associated bacterial pneumonia caused by susceptible isolates of Acinetobacter baumannii-calcoaceticus complex.
    MTS is supplied in 3 different packaging options (no additional reagents are included). There is a 10- test box, a 30- test box and a 100-test box.

    AI/ML Overview

    Here is a description of the acceptance criteria and the study proving the device meets those criteria, based on the provided FDA 510(k) clearance letter for the MTS Sulbactam-Durlobactam device:

    Device: MTS Sulbactam-Durlobactam 0.004/4 - 64/4 µg/mL (SUD)
    Intended Use: Quantitative method for in vitro determination of antimicrobial susceptibility of Acinetobacter baumannii calcoaceticus complex using MIC Test Strips with manual reading after overnight incubation.


    1. Acceptance Criteria and Reported Device Performance

    The study evaluated the performance of the MTS Sulbactam-Durlobactam device against a reference broth microdilution MIC method. The primary metrics for performance were Essential Agreement (EA) and Category Agreement (CA), along with an analysis of errors (very major, major, minor). While explicit "acceptance criteria" percentages are not directly stated in the summary, typical FDA criteria for AST systems are implied by the reported results. The guidance document referenced "Class II Special Controls Guidance Document: Antimicrobial Susceptibility Test (AST) Systems, August 28, 2009" would contain the specific acceptance thresholds. Based on the provided summary, the device performance is reported as follows:

    Table of Device Performance

    MetricDefinitionReported Performance
    Total Tested (Clinical & Challenge)Total number of organisms tested in the combined clinical and challenge groups.588 organisms
    Essential Agreement (EA)Percentage of isolates where the MTS MIC result is within +/- 1 doubling dilution of the reference broth microdilution MIC.97.3%
    Evaluable Essential AgreementPercentage of evaluable isolates (where a direct comparison is meaningful) with EA.97.1% (533 out of 549 evaluable)
    Category Agreement (CA)Percentage of isolates where the MTS susceptibility category (e.g., Susceptible, Intermediate, Resistant) matches the reference method's category.92.7% (545 out of 588)
    Very Major Errors (vmj)False Susceptible (device says Susceptible, reference says Resistant).0 (out of 49 Resistant)
    Major Errors (maj)False Resistant (device says Resistant, reference says Susceptible).2
    Minor Errors (min)Discrepancy in intermediate category only (e.g., device says Intermediate, reference says Susceptible/Resistant, or vice-versa).41
    ReproducibilityPercentage of MTS results within a doubling dilution of reference broth microdilution results96.3%

    Implied Acceptance Criteria (based on typical FDA AST requirements, generally >90% for EA and CA, and strict limits on major/very major errors):
    The reported performance values of 97.3% EA and 92.7% CA, along with very low major errors and zero very major errors, indicate that the device met the acceptance criteria as determined by the FDA. Specifically, the zero very major errors are critical for patient safety, as they avoid situations where a resistant infection might be incorrectly identified as susceptible, leading to inappropriate treatment.


    2. Sample Size and Data Provenance

    • Test Set Sample Size: 588 isolates for the combined clinical and challenge organism groups.
    • Data Provenance:
      • Clinical Testing: Performed at three (3) sites. The precise country of origin is not explicitly stated for the clinical sites, but the submitter (Liofilchem s.r.l.) is based in Italy, and their contact person for the 510(k) is in Westlake, Ohio, USA. The FDA clearance suggests testing was appropriate for the US market.
      • Challenge Isolate Testing: Performed at one site (Laboratory Specialists, Inc., which is the 510(k) preparer's company in Westlake, Ohio).
      • Nature of Data: The data combines retrospective (challenge isolates specifically selected to ensure MIC range coverage, including resistant isolates) and prospective (fresh clinical isolates tested at multiple sites) elements.

    3. Experts Used for Ground Truth and Qualifications

    This section does not directly apply as the device is an in vitro diagnostic (IVD) for antimicrobial susceptibility testing, not an imaging AI device requiring expert interpretation of images. The "ground truth" for antimicrobial susceptibility is established by a standardized laboratory method (broth microdilution) rather than human expert consensus on subjective data.


    4. Adjudication Method for the Test Set

    Adjudication methods (like 2+1, 3+1, etc.) are typically used in studies involving human interpretation or subjective assessments. For this AST device, the ground truth is established by a quantitative, objective laboratory method (CLSI broth microdilution guidelines). Therefore, no human adjudication method was employed for establishing the ground truth of the MIC values. Minor discrepancies or errors between the device and the reference method are simply categorized as such (major, minor, very major errors).


    5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

    An MRMC study is not applicable to this type of device. The MTS Sulbactam-Durlobactam is a manual antimicrobial susceptibility test system that determines the MIC directly. It is not an AI-assisted diagnostic imaging system where human readers interpret data with or without AI assistance. The performance is assessed by comparing the device's MIC readings to a gold standard laboratory method, not by comparing human reader performance.


    6. Standalone (Algorithm Only) Performance

    This concept is applicable, and the study provided details on the standalone performance of the MTS Sulbactam-Durlobactam device. The "performance data" table (Essential Agreement, Category Agreement, and Error Rates) directly refers to the device's ability to accurately determine MIC values and susceptibility categories when compared to the reference method, essentially its "algorithm-only" performance in the context of an IVD. There is no "human-in-the-loop" component for interpretation; the user manually reads the MIC from the strip.


    7. Type of Ground Truth Used

    The ground truth used for this study was reference broth microdilution MIC method, conducted according to CLSI M7-A11 guidelines. This is a well-established and standardized laboratory method for determining antimicrobial minimum inhibitory concentrations, considered the gold standard for AST.


    8. Sample Size for the Training Set

    The document does not specify a separate "training set" sample size for the development of the MTS Sulbactam-Durlobactam device. For IVDs like AST systems, the "training" typically refers to the initial development and optimization of the test strip's design, antimicrobial gradient, and manufacturing process to reliably produce specific drug concentrations and diffusion patterns. This is primarily a chemical and engineering development process, not a machine learning training process with a distinct data set. The 588 isolates discussed are for the performance validation (test set) rather than initial model training.


    9. How Ground Truth for the Training Set Was Established

    As noted above, a distinct "training set" and associated "ground truth establishment" in the machine learning sense are not described for this type of medical device. The "ground truth" for the performance validation was established by the CLSI broth microdilution reference method. For the initial development and optimization phase of such a device, the "ground truth" would implicitly be the accurate and precise measurement of drug concentration gradients and their biological effect on various bacterial strains, guided by established AST principles and drug properties.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 227