Search Results

The DUO Microcatheter is intended for the selective placement of devices and/or fluids, such as contrast media, into the peripheral, coronary, and neuro vasculature during diagnostic and/or therapeutic procedures.

The DUO Microcatheter is a disposable, single use, sterile device. The DUO Microcatheter is a single-lumen, variable stiffness catheter with radiopaque marker(s) on the distal end and a luer hub on the proximal end. The catheter shaft has a hydrophilic coating on the distal 80 cm to reduce friction during use. The radiopaque shaft and distal marker(s) facilitate fluoroscopic visualization. Device dimensions and configuration are shown on the product label. A steam shaping mandrel and a peel away introducer are provided with each microcatheter.

N/A

Ask a specific question about this device

The Duoblade Plus SE (Models: DB1EP, DB1EP-T, DB1EP-H, DB1EP-TH), and Duoblade Prime (Models: DB1P, DB1P-T, DB1P-H, DB1P-TH) are intended for general electrosurgical applications, including cutting and coagulation. These models are designed without shaft extension functionalities. The Model: DB1EP, DB1EP -T, DB1EP-H, DB1EP-TH are compatible with the smoke evacuation system, removing smoke generated by electrosurgery when used in conjunction with an effective smoke evacuation system.

The Electrosurgical Cutting and Coagulation Device and Accessories (Model: Duoblade Plus SE, Duoblade Prime) is a single-use, monopolar RF device designed to be used with a qualified Generator as part of the Surgery System. It uses high-frequency energy (RF Monopolar Energy) to generate heat for tissue cutting and coagulation. It can be operated using the integrated hand switch or a qualified Footswitch. The device's design simplifies functionality by excluding shaft extension features. The models of Duoblade Plus SE and Duoblade Prime are identified according to with/without a suction function (removing smoke), and a swivel function.

• Suction & swivel function (Duoblade Plus SE): DB1EP, DB1EP-T, DB1EP-H, DB1EP-TH
• No Suction & swivel function (Duoblade Prime): DB1P, DB1P-T, DB1P-H, DB1P-TH
  The scope of the submission only includes the addition of model without functions, such as swivel function, shaft extension function and appearance change for marketing purpose.

The provided FDA 510(k) clearance letter and summary are for an electrosurgical device (Duoblade Plus SE, Duoblade Prime), not an AI/software device that would involve a test set, ground truth experts, or MRMC studies. The document primarily focuses on demonstrating substantial equivalence to a predicate device through comparison of features, materials, and established non-clinical tests relevant to electrosurgical devices (e.g., biocompatibility, sterility, electrical safety, thermal effects on tissue).

Therefore, I cannot extract the information required by your prompt regarding acceptance criteria, test set details, ground truth establishment, or human reader effectiveness studies, as these concepts are not applicable to the type of device described in this 510(k) submission.

The document states:

• "No clinical studies were considered for this submission." This directly indicates that there was no human-in-the-loop performance study, nor any evaluation of "how human readers improve with AI vs without AI assistance" because there's no AI component.
• "The thermal effects of a subject device are the same as the predicate device." This highlights that the performance demonstration relies on equivalence to a previously cleared device, not on new independent performance metrics against a defined acceptance criterion of the type you've outlined. The non-clinical test mentioned ("Thermal effects on tissue") is a comparative study against a positive control device, not a test with a specific quantitative acceptance criterion for the new device on its own.

In summary, because this 510(k) submission is for a physical electrosurgical device and not an AI/software product, the requested information about acceptance criteria for AI performance, test sets, ground truth experts, and MRMC studies is not present in the provided text.

Ask a specific question about this device

The DUO Sensors are USB driven intraoral sensors which are intended to acquire intraoral radiographic images. The DUO Sensors shall be operated by trained healthcare professionals, who are educated and competent to perform the acquisition of intraoral radiographs.

The DUO Sensors can be used either in combination with special positioning devices to facilitate positioning and alignment with the X-ray beam or they may also be positioned by hand with the assistance of the patient.

The DUO sensors are intended for any dental practice that uses X-ray equipment for intraoral diagnostic purposes. DUO sensors can be used by trained dental professionals for patients receiving intraoral X-ray examinations and procedures for capturing digital X-ray images. Captured digital X-ray images can be used for examinations and diagnostic purposes with the help of optional image analysis software. The optional image analysis software is not part of this submission. DUO sensors can be used with dental positioning devices and holders to assist with aligning an X-ray source beam with the sensor and anatomy.

The DUO sensors are USB-driven digital X-ray sensors designed for health care professionals who are already acquainted with the standard procedures for acquiring dental intraoral radiographs. Digital X-ray imaging is an aide for diagnosis and should always be confirmed by the doctor using appropriate additional diagnostic aides, professional judgment, and experience.

The DUO Sensors are indirect converting X-ray detectors. A scintillating material converts the incident Xrays into visible light, this light is coupled optically to a CMOS technology light detection imager, and then converted to digital data.

The design of the sensor assembly supports the automatic detection of incident X-rays to generate digital images for intraoral applications, once armed via a software command. The digital image created is immediately visible on the screen of a personal computer connected to the DUO sensor through the standard USB port. For DUO sensors to be used in a dental practice, an optional image analysis software will be necessary. Image analysis software is not part of the submission. DUO captured X-ray images are suitable for recognition of normal anatomical structures, dental pathologies, and abnormal conditions.

The DUO sensors support USB2.0 connectivity to computers using a dedicated electronic assembly and a sensor software driver. Functions of the DUO sensors are controlled by software drivers and utilities support sensor activation and settings.

The DUO sensors are manufactured with the same device firmware as the predicate device, Brasseler GEM.

This submission describes a dental digital X-ray sensor, DUO1 and DUO2, which is substantially equivalent to the predicate device, Brasseler GEM.

Here's the breakdown of the acceptance criteria and supporting study details:

1. Table of Acceptance Criteria and Reported Device Performance

The FDA submission for K241649 is a 510(k) premarket notification, which relies on demonstrating substantial equivalence to a legally marketed predicate device rather than setting specific quantifiable acceptance criteria for novel claims. Therefore, the "acceptance criteria" here refer to demonstrating comparable performance to the predicate device (Brasseler GEM) for key technical aspects.

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

• Test Set Description: The document refers to "clinical images captured with both the devices in a performance testing report which were evaluated by US dentists."
• Sample Size: The exact number of patients or images in the clinical performance test set is not specified in the provided text.
• Data Provenance: The images were evaluated by "US dentists." It is not explicitly stated whether the data was retrospective or prospective. Given the clinical image evaluation, it suggests real-world acquisition but the exact study design (e.g., controlled prospective collection vs. retrospective existing images) is not detailed.

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

• Number of Experts: The document states that the clinical images "...were evaluated by US dentists." The exact number of dentists is not specified.
• Qualifications of Experts: The experts are described as "US dentists." Specific qualifications such as years of experience, subspecialty (e.g., board-certified oral and maxillofacial radiologists), or academic affiliations are not provided.

4. Adjudication Method for the Test Set

• Adjudication Method: The document only states that images "were evaluated by US dentists." It does not describe any specific adjudication method (e.g., 2+1, 3+1 consensus, independent reads with no consensus).

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

• A formal MRMC comparative effectiveness study that quantifies improvements in human reader performance (e.g., AUC, sensitivity, specificity) with AI versus without AI assistance was not performed or described. The clinical performance testing involved dentists evaluating images from both devices, implying a comparative visual assessment, but not a controlled MRMC study in the context of AI assistance. The device itself is an intraoral sensor, not an AI diagnostic tool.

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study

• This device (DUO sensors) is a hardware component for acquiring images, not an AI algorithm for image analysis. Therefore, a standalone algorithm performance study is not applicable in the traditional sense. The submission states, "Image analysis software is not part of the submission" and "The optional image analysis software is not part of this submission."

7. Type of Ground Truth Used

• For the clinical performance testing, the ground truth was based on the visual evaluation and judgment of US dentists comparing images from DUO sensors to those from the predicate Brasseler GEM. This can be considered a form of expert consensus/reader judgment on image quality and diagnostic utility, but specific "ground truth" for disease presence/absence (like pathology or outcomes data) is not explicitly detailed as this is not an AI diagnostic device. The statement "DUO captured X-ray images are suitable for recognition of normal anatomical structures, dental pathologies, and abnormal conditions" implies the images were assessed for their ability to show such features.

8. Sample Size for the Training Set

• The provided text does not mention a training set for the DUO sensors. As this is a hardware device (sensor) and not an AI diagnostic algorithm, a "training set" in the context of machine learning is not applicable here. The device uses established CMOS and scintillator technologies and is compared against a predicate device.

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

• Since there is no mention of a training set for an AI algorithm, the concept of establishing ground truth for a training set is not applicable to this submission.

Ask a specific question about this device

The Duo Hands-free breast pump is a powered breast pump to be used by lactating women to express and collect milk from their breasts.

The Duo Hands-free breast pump is intended for a single user.

The breast pump is intended to be used in a home environment.

The Duo Hands-Free breast pump is an electrically powered breast pump to be used in a home environment by a single user. The device is provided non-sterile and can be used on one breast (single pumping) or on both breasts at the same time (double pumping).

The device consists of the pump unit, two Hands-free Collection Cups (breast shields, membranes, outer shells), and tubing. The breast pump provides wireless connectivity via a Bluetooth Low Energy (BLE) 4.2 compliant protocol and is compatible with the Medela Family mobile application. The BLE component does not offer control of the breast pump and is only meant to store the information sent from the breast pump (such as session length, phases and vacuum intensity levels) and log additional information related to their pumping session. The device has four buttons allowing the user to power the device on/off, select between two pumping modes (expression, and stimulation), and control vacuum strength within each mode (9 levels of vacuum strength in each mode). The pump is powered by an internal, non-replaceable, rechargeable lithium-ion battery which is charged using the included AC power supply and cable. The subject device can be operated while plugged into AC power.

The Duo Hands-free breast pump utilizes a microcontroller executing embedded software to interpret user inputs and modulate the voltage applied to a DC motor and a solenoid to produce a negative vacuum pressure applied to the user. The vacuum is generated by turning on the motor, incrementally drawing air out of the pump set on each rotation and expelling it into the atmosphere. When the cycle is complete, the solenoid valve is opened, relieving the vacuum. Vacuum generated by the breast pump unit is applied to the membrane in the Hands-free Collection Cup pump set causing it to displace away from the breast and to apply vacum to the breast. Vacuum applied to the breast will cause milk to be expressed and to accumulate on the milk valve. Once the vacuum is relieved by the solenoid valve, milk will fall through the milk valve into the outer shells, and the cycle is repeated.

All milk contacting components are compliant with 21 CFR 174-179.

The Duo Hands-Free Breast Pump, described in the provided 510(k) summary, is a Class II medical device, and the information provided does not directly detail a clinical study involving human patients or complex AI algorithms requiring extensive acceptance criteria beyond basic device functionality and safety. The document focuses on bench testing and regulatory compliance.

However, based on the non-clinical performance testing conducted, we can infer some "acceptance criteria" related to the device's functionality and safety, and the "study" that proves it.

Here's the breakdown of the available information:

1. A table of acceptance criteria and the reported device performance

Since specific numerical acceptance criteria (e.g., "vacuum level must be within +/- 5 mmHg") are not explicitly stated in the summary, we will infer the performance criteria from the types of tests conducted and their stated purpose. The "reported device performance" is essentially that the device "meets its design requirements and performs as intended."

2. Sample size used for the test set and the data provenance

The document does not provide details on the specific sample sizes for the non-clinical tests (e.g., how many units were tested for vacuum level, how many cycles for use-life, etc.). These are typically bench tests conducted on a sufficient number of manufactured units as determined by the manufacturer's internal quality assurance procedures and risk management. The data provenance is internal manufacturer testing (Medela LLC). These are prospective tests conducted on the manufactured device.

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

This section is not applicable in the context of this device and its testing. The "ground truth" for non-clinical performance and safety tests is established by recognized international standards (e.g., IEC, ISO) and the device's design specifications. The experts involved would be the engineers and quality assurance personnel at Medela LLC, qualified in electrical engineering, mechanical engineering, software development, and quality systems, who designed, built, and tested the device against these standards and specifications. No external expert panel was used to establish a "ground truth" in the way it might be for an AI-powered diagnostic device.

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

This is not applicable. Adjudication methods like 2+1 or 3+1 are used for clinical studies involving interpretation of medical images or data by multiple readers to establish a consensus "ground truth." The tests described are objective, non-clinical performance tests against pre-defined specifications and standards.

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 is not applicable. The device is a breast pump, not an AI-assisted diagnostic tool. No MRMC study was performed.

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

This is not applicable. The device is a breast pump, not an AI algorithm. While it contains embedded software to control its operation, there's no "standalone algorithm" performance assessed in the context of diagnostic accuracy.

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

For the non-clinical performance tests, the "ground truth" is defined by:

• International Standards: e.g., IEC 60601 series for electrical safety and EMC, ISO 10993-1 for biocompatibility.
• Device Design Specifications: Internal specifications set by Medela LLC for vacuum levels, cycle rates, battery life, and durability.
• Regulatory Requirements: 21 CFR 174-179 for milk-contacting materials.

8. The sample size for the training set

This is not applicable. This device does not use machine learning or AI that requires a "training set" of data.

9. How the ground truth for the training set was established

This is not applicable, as there is no training set for this device.

Ask a specific question about this device

The Duoblade is intended for general electrosurgical applications, including cutting and coagulation, and (Models: DB1SEP, DB1SEP-H, DB1SEP-T, DB1SEP-TH) for removing smoke generated by electrosurgery when used in conjunction with an effective smoke evacuation system.

The Electrosurgical Cutting and Coagulation Device and Accessories (Model: Duoblade) is a single-use, monopolar RF device. It is designed to be used with the qualified Generator as part of the Surgery System. It can be operated with the integrated hand switch or a qualified Footswitch. The Duoblade consists of a single blade and telescoping shaft that can be configured in both standard and extended length. The finger grip also incorporates a suction lumen for the evacuation of smoke and fluids.

The models of of Duoblade are identified according to with/without a suction function (removing smoke).

• Suction function (Removing smoke): DB1SEP, DB1SEP-H, DB1SEP-T, DB1SEP-TH
• No Suction function (No removing smoke): DB1SP, DB1SP-H, DB1SP-T, DB1SP-TH

The provided document is a 510(k) summary for the Duoblade electrosurgical device. It is a submission for regulatory clearance and focuses on demonstrating substantial equivalence to a predicate device, not on proving device performance against specific acceptance criteria for an AI/ML algorithm.

Therefore, the document does not contain the information requested regarding acceptance criteria and the study proving the device meets those criteria for an AI/ML product. The questions asked are typically relevant for AI/ML device clearances where performance metrics like sensitivity, specificity, AUC, etc., are established and validated through specific study designs.

The Duoblade is an electrosurgical cutting and coagulation device, which is a physical medical device, not an AI/ML algorithm. The "Performance Test - Thermal effects on tissue" described in section 12 is a physical performance test, not a study evaluating an algorithm's performance.

In summary, none of the requested information (acceptance criteria table, sample sizes for test/training sets, data provenance, expert qualifications, adjudication methods, MRMC study, standalone performance, ground truth types, etc.) can be extracted from this document because it pertains to a different type of medical device lacking an AI/ML component.

Ask a specific question about this device

The Duo™ Expandable Interbody Fusion System is indicated for intervertebral body fusion at one level or two contiguous levels in the lumbar spine from L2 to L5 in patients with degenerative disc disease (DDD) with up to Grade I spondylolisthesis at the involved level(s). DDD is defined as back pain of discogenic origin with degeneration of the disc confirmed by patient history and radiographic studies. These patients should be skeletally mature and have had six months of non-operative treatment. The Duo device is designed for use with autograft comprised of cancellous and/or corticocancellous bone graft as an adjunct to fusion and is intended for use with supplemental fixation systems cleared by the FDA for use in the lumbar spine.

The Duo Expandable Interbody Fusion System is an intervertebral implant designed to provide mechanical support of the intradiscal space as an adjunct to fusion. The device is made of PEEK-OPTIMA® LT-1, titanium alloy, polyethylene terephthalate (PET), and tantalum or OsteoSync™ titanium, titanium alloy, and PET. The Duo implant is available in varying lengths, widths, heights, lordotic angles and is provided sterile. The implant is designed with a porous central cavity for graft containment, a rounded nose to aid in implant insertion, and rigid teeth to resist migration.

This document (K210155) is a 510(k) premarket notification for a medical device called the "Duo™ Expandable Interbody Fusion System," specifically a line extension of implants and implant trials. It describes the device, its intended use, and non-clinical testing performed to demonstrate substantial equivalence to legally marketed predicate devices.

However, the provided text does not contain any information regarding acceptance criteria, device performance results against those criteria, sample sizes for test or training sets, ground truth establishment, expert qualifications, adjudication methods, or multi-reader multi-case studies generally associated with AI/ML-based medical devices or diagnostic tools.

The document primarily focuses on demonstrating mechanical and performance equivalence through benchtop ASTM testing for an intervertebral body fusion device, which is a physical implant, not a software or AI/ML diagnostic tool. Therefore, the requested information about AI/ML performance metrics, expert reviews, and data provenance typical for software validation studies is not applicable to this submission.

Based on the provided text, I cannot complete the table or answer the specific questions about acceptance criteria for an AI/ML device, as this device is a physical implant and the testing described is related to its mechanical and material properties.

If there's an assumption that this is an AI/ML device based on the prompt structure, that assumption is incorrect when applied to the provided content. The document describes a traditional medical device submission for a spinal implant.

Ask a specific question about this device

The Nextremity Solutions DuoHex™ CH Cannulated Hammertoe System is intended for small bone reconstruction limited to inter-phalangeal repair and fusion of the lesser toes.

The DuoHex™ CH Cannulated Hammertoe System consists of a two-part cannulated bone screw implant construct. The screw implants are provided in various sizes. The proximal screw implant diameters range from 2.75mm to 4.2mm. The middle screw implant diameters range from 2.75mm to 5.0mm in increments of 0.75mm. The proximal and distal screw implants are manufactured from Ti-6Al-4V ELI conforming to ASTM F136. The system offers an optional fixation method using a Kirschner wire (K-wire) in conjunction with the screw implants for additional fixation and temporary stabilization. The K-Wire is intended to be removed at the discretion of the physician upon joint fusion. The k-wires provided are manufactured from 316 Stainless Steel conforming to ASTM F138. The system includes the necessary surgical site preparation and insertion instruments.

This document describes a medical device, the DuoHex™ CH Cannulated Hammertoe System, and its clearance by the FDA based on substantial equivalence to predicate devices. It does not present clinical performance data or studies against specific acceptance criteria for AI/ML-driven medical devices.

Therefore, I cannot provide the details requested in your prompt for acceptance criteria and study data for an AI/ML device. The provided text is a 510(k) summary for a non-AI/ML medical device (bone screw system) and primarily relies on mechanical testing and comparison to existing products for substantial equivalence.

Here's a breakdown of why I cannot fulfill your request based on the provided text:

• The document explicitly states: "Clinical testing was not necessary to demonstrate substantial equivalence of the DuoHex™ CH Cannulated Hammertoe System to the predicate device." This means no clinical study was performed to "prove the device meets the acceptance criteria" in the way you've described for an AI/ML system.
• The device is a "Bone Screw System" for hammertoe correction, a mechanical implant, not an AI/ML diagnostic or therapeutic guidance tool.
• The "Non-Clinical Testing" section describes mechanical and material tests (axial pull-out strength, torque to failure, static/dynamic 3-point bend tests) and endotoxin testing, not performance metrics like sensitivity, specificity, or AUC as would be relevant for an AI/ML system.

To answer your request, if this were an AI/ML device, and assuming a hypothetical scenario where the document would contain the necessary information, a typical response would look like this (but again, this is NOT supported by the provided text):

Hypothetical Acceptance Criteria and Study for an AI/ML-Driven Hummer Toe Diagnostic System (Illustrative - NOT based on the provided document)

Let's imagine, for the sake of demonstrating the structure, that the DuoHex™ CH system included an AI component that diagnosed hammertoe severity from medical images.

1. Table of Acceptance Criteria and Reported Device Performance

Note: The actual document does not contain any such performance metrics as it's for a mechanical device.

2. Sample Size and Data Provenance

• Test Set Sample Size: 500 patient cases (e.g., foot X-rays)
• Data Provenance: Retrospective data collected from multiple clinical sites across the United States and Europe (e.g., Germany, UK).

Note: The actual document does not mention any test set or data provenance in this context.

3. Number and Qualifications of Experts for Ground Truth

• Number of Experts: 3 independent orthopedic radiologists.
• Qualifications: Each radiologist had at least 15 years of experience specializing in musculoskeletal imaging, with a focus on foot and ankle pathologies. All were board-certified in their respective countries.

Note: The actual document does not mention any experts for ground truth establishment.

4. Adjudication Method for Test Set

• Adjudication Method: 2+1 Adjudication. If at least two out of three experts agreed on a diagnosis (e.g., severity of hammertoe), that was considered the provisional ground truth. In cases of disagreement (e.g., 1-1-1 split), a fourth senior orthopedic surgeon (with 25+ years experience) acted as a tie-breaker/final adjudicator.

Note: The actual document does not mention any adjudication method.

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

• Was an MRMC study done? Yes.
• Effect Size of Human Reader Improvement:
  • Without AI assistance: Average diagnostic accuracy of human readers was 78%.
  • With AI assistance (AI-assisted read): Average diagnostic accuracy of human readers improved to 89%.
  • Effect Size: The AI assistance led to an average increase of 11 percentage points in diagnostic accuracy for human readers (p < 0.001, 95% CI: [9.5%, 12.5%]). This represents a significant improvement in reader performance.

Note: The actual document does not mention any MRMC study or AI assistance.

6. Standalone Algorithm Performance

• Was standalone performance done? Yes.
• Standalone Performance Metrics:
  • Sensitivity: 91.8%
  • Specificity: 86.5%
  • AUC: 0.92

Note: The actual document does not mention any standalone algorithm performance.

7. Type of Ground Truth Used

• Type of Ground Truth: Expert consensus based on clinical examination, high-resolution MRI scans, and follow-up surgical pathology reports when available for definitive confirmation of hammertoe severity and presence.

Note: The actual document does not mention any ground truth type in this context.

8. Sample Size for the Training Set

• Training Set Sample Size: 10,000 anonymized patient cases (X-rays, medical reports).

Note: The actual document does not mention any training set.

9. How Ground Truth for Training Set Was Established

• Ground Truth for Training Set: Established by an internal team of 10 experienced orthopedic specialists (orthopedic surgeons and radiologists) who labeled the image data and associated clinical information. A subset of these labels (10%) was independently reviewed by a senior specialist for quality assurance. Data was semi-automatically labeled using a pre-trained model and then manually refined and verified by the experts.

Note: The actual document does not mention ground truth for a training set.

In conclusion, the provided FDA clearance letter and 510(k) summary are for a mechanical bone screw system and do not contain any information related to AI/ML device performance, acceptance criteria, or clinical studies of the type you are asking about.

Ask a specific question about this device

The Duo-Flow Side x Side Double Lumen Catheter is intended for short-term central venous access for hemodialysis, apheresis, and infusion.

The Duo-Flow Side x Side Double Lumen Catheter is a non-implanted hemodialysis catheter with two lumens. The red adapter connects to the proximal lumen for "arterial" outflow, and the blue adapter connects to the distal lumen for "venous" return. The catheter is available in various sizes and configurations (curved or straight extensions).

This document describes the premarket notification (510(k)) for the Medcomp® Duo-Flow® Side x Side Double Lumen Catheter. It outlines the device's characteristics, its intended use, and its substantial equivalence to a predicate device.

Key Point: The provided text does not describe an AI/ML medical device. It pertains to a physical medical device (a catheter) and therefore, the concepts of AI-specific acceptance criteria, test sets, ground truth establishment by experts, MRMC studies, standalone performance, and training sets for an AI model are not applicable.

The document primarily focuses on demonstrating the substantial equivalence of the Duo-Flow® Side x Side Double Lumen Catheter to a legally marketed predicate device (Mahurkar™ Acute Dual Lumen Catheter). This is a common pathway for medical device clearance in the US, where new devices are compared to existing ones that have already been cleared for marketing.

Instead of AI-specific performance metrics, the document details:

• Indications for Use: What the device is intended for (short-term central venous access for hemodialysis, apheresis, and infusion).
• Comparison to Predicate Device: A detailed table (Table 6.1) comparing various attributes of the subject device to the predicate device, including indications for use, definition, location of use, French size, catheter configuration, lengths, duration of use, sterilization method, number of lumens, patient population, insertion site, and kit type. The goal is to show that the new device is fundamentally similar to the predicate.
• Bench/Performance Data/Non-Clinical Testing: This section (Table 6.2) lists the applicable standards and performance testing conducted on the physical device to ensure its safety and effectiveness. These are primarily engineering and material tests, not clinical performance studies comparing diagnostic accuracy.
  • ISO 10555-1: Intravascular catheters (Air Leak, Liquid Leak, Peak Tensile Force, Gravity Flow)
  • ISO 11607-1 & -2: Packaging for terminally sterilized medical devices (Transit and Shelf Life testing)
  • ISTA 3A: Packaged products for parcel delivery system shipment (Transit Testing)
  • ISO 594-1 & -2: Conical fittings (Luer) for syringes, needles, etc. (Gauging, Liquid Leakage, Air Leakage, Separation Force, Unscrewing Torque, Ease of Assembly, Resistance to Overriding, Stress Cracking)
• Biocompatibility: Tests conducted according to ISO 10993 standards to ensure the device is safe for biological contact. These include cytotoxicity, sensitization, irritation, systemic toxicity, pyrogenicity, subacute toxicity, genotoxicity, implantation, and hemocompatibility.

Therefore, to directly answer your request based on the provided text, while acknowledging that it's not an AI device:

1. Table of acceptance criteria and the reported device performance:

Since this is a physical medical device and not an AI/ML diagnostic tool, the "acceptance criteria" are based on meeting established engineering and biocompatibility standards, and demonstrating substantial equivalence to a predicate device. Performance is measured by successful completion of these non-clinical tests.

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

For this type of device, a "test set" in the AI sense is not applicable. The sample sizes for the various bench/performance/biocompatibility tests are typically determined by the standards themselves (e.g., specific number of catheters for tensile strength, or material samples for biocompatibility), and these details are not provided in this summary. The data provenance is from non-clinical bench testing and laboratory studies by the manufacturer (Medcomp®) to ISO and ASTM standards. It is not patient data from clinical trials.

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

Not applicable. "Ground truth" in the context of an AI device relates to verified diagnostic labels. For a physical medical device, the "ground truth" is established by the specifications of the device, the requirements of the standards, and the physical measurements/observations during testing. No external expert panel is described for establishing a "ground truth" for these engineering and biocompatibility tests.

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

Not applicable. This concept applies to human reader consensus for labeling data, which is not relevant here. The tests are defined by standard protocols with clear pass/fail criteria.

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:

Not applicable. This is not an AI-assisted device. The "effectiveness" is demonstrated by meeting performance standards and clinical equivalence to a predicate device, not by improving human reader performance.

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

Not applicable. This is not an algorithm.

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

Not applicable in the AI sense. The "truth" for this device's performance is derived from:

• Engineering specifications and design.
• Compliance with recognized international standards (ISO, ASTM).
• Direct physical measurements and observations during bench testing (e.g., flow rates, tensile strength, Luer taper dimensions).
• Laboratory analysis for biocompatibility endpoints.

8. The sample size for the training set:

Not applicable. This is not an AI/ML device that requires a training set.

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

Not applicable.

Ask a specific question about this device

The Duo™ Lumbar Interbody Fusion Device is indicated for intervertebral body fusion at one level or two contiguous levels in the lumbar spine from L2 to L5 in patients with degenerative disc disease (DDD) with up to Grade I spondylolisthesis at the involved level(s). DDD is defined as back pain of discogenic origin with degeneration of the disc confirmed by patient history and radiographic studies. These patients should be skeletally mature and have had six months of non-operative treatment. The Duo device is designed for use with autograft comprised of cancellous and/or corticocancellous bone graft as an adjunct to fusion and is intended for use with supplemental fixation systems cleared by the FDA for use in the lumbar spine.

The Duo Lumbar Interbody Fusion Device is an intervertebral implant designed to provide mechanical support of the intradiscal space as an adjunct to fusion. The device is made of PEEK-OPTIMA® LT-1, titanium alloy, polyethylene terephthalate (PET), and tantalum. The Duo implant is available in varying lengths and heights with two lordotic configurations and is provided sterile. The device is designed with a porous central cavity for graft containment, a rounded nose to aid implant insertion, and ridged teeth to resist migration.

The provided text is a 510(k) Summary for a medical device (Duo Lumbar Interbody Fusion Device) and does not contain information about acceptance criteria, study methodologies, or performance metrics typically associated with AI/ML-based medical devices. This document is related to a traditional medical device and focuses on demonstrating substantial equivalence to a predicate device based on design, materials, and intended use, rather than algorithmic performance.

Therefore, I cannot extract the requested information regarding acceptance criteria and a study proving a device meets them for an AI/ML product from the given text. The provided document concerns a spinal implant and its surgical instruments, not an AI/ML device.

Ask a specific question about this device

The Duo™ Lumbar Interbody Fusion Device is indicated for intervertebral body fusion at one level or two contiguous levels in the lumbar spine from L2 to L5 in patients with degenerative disc disease (DDD) with up to Grade I spondylolisthesis at the involved level(s). DDD is defined as back pain of discogenic origin with degeneration of the disc confirmed by patient history and radiographic studies. These patients should be skeletally mature and six months of non-operative treatment. The Duo device is designed for use with autograft comprised of cancellous and/or corticocancellous bone graft as an adjunct to fusion and is intended for use with supplemental fixation systems cleared by the FDA for use in the lumbar spine.

The Duo Lumbar Interbody Fusion Device is an intervertebral implant designed to provide mechanical support of the intradiscal space as an adjunct to fusion. The device is made of PEEK-OPTIMA® LT-1, titanium alloy, polyethylene terephthalate (PET), and tantalum. The Duo implant is available in varying lengths and heights with three lordotic configurations and is provided sterile. The device is designed with a porous central cavity for graft containment, a rounded nose to aid implant insertion, and ridged teeth to resist migration.

This document is an FDA 510(k) clearance letter for a medical device called the "Duo™ Lumbar Interbody Fusion Device." It does not contain information about acceptance criteria or a study proving the device meets those criteria, as typically seen for AI/ML-based medical devices or diagnostics.

The document pertains to a physical intervertebral body fusion device and focuses on establishing its substantial equivalence to a previously cleared predicate device. The "Non-Clinical Testing" section mentions mechanical testing (static and dynamic axial compression, compression-shear, subsidence, and expulsion) conducted on the primary predicate device and "engineering analysis and verification testing (expulsion testing)" that supported this implant line extension. This suggests the testing was for the physical properties and performance of the implant, not about a software device meeting specific performance metrics based on data.

Therefore, I cannot provide the requested information regarding acceptance criteria and a study proving a device meets those criteria, as this document does not describe such a study or performance metrics relevant to AI/ML or diagnostic devices.

Ask a specific question about this device