Search Results

EzVu Visual Vasopressor Injector (EV-19) is intended to inject vasopressor solution into the uterine musculature during laparoscopic surgery.

EzVu Visual Vasopressor Injector (EV-19) is a 330 mm long and 5 mm diameter hollow bore laparoscopic instrument, used to enable laparoscopic flashback visualization before injecting Vasopressor drug into the uterine musculature during laparoscopic surgery. It consists of a stainless steel needle at the distal end, securely connected to a hub, an elongated shaft with transparent window at the distal end and stopcock with luer connection at the proximal end onto which a syringe can be attached. The shaft is made of transparent plastic tube, surrounded by a stainless steel tube along the proximal portion of the injector to provide stability. The stainless steel tube around the transparent plastic tube is wrapped in a heat shrink. The injector is available in one needle size (19 gauge).

Here's a breakdown of the acceptance criteria and the study details for the EzVu Visual Vasopressor Injector (EV-19), based on the provided FDA 510(k) summary:

1. Table of Acceptance Criteria and Reported Device Performance

Secondary Endpoint:

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

• Sample Size:
  • Clinical Study (Patients): 13 women
  • Injections: 24 injections across the 13 patients.
  • Blood Aspiration Cases: 25 cases (Note: this number is slightly different from the 24 injections mentioned earlier in the text for detection of blood aspirate).
• Data Provenance: The study was a "multi-center, prospective observational study." The country of origin is not explicitly stated, but the sponsor is located in Navi Mumbai, Maharashtra, India.

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

• Number of Experts: 5
• Qualifications: "trained laparoscopic gynecological surgeons"

4. Adjudication Method for the Test Set

The document does not explicitly describe an adjudication method for the clinical study's primary and secondary endpoints. It appears that the observations (visibility of blood aspirate, leakage/breakage, compatibility, and usability ratings) were collected directly from the surgical procedures and surgeon feedback.

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

There is no indication that a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was done, nor is there any mention of AI assistance or its effect size on human readers. This device is a physical injector, not an AI-powered diagnostic tool.

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

This question is not applicable. The EzVu Visual Vasopressor Injector is a physical medical device, not an algorithm, and does not operate without human interaction. Its performance is intrinsically linked to its use by a surgeon.

7. The Type of Ground Truth Used

The ground truth for the clinical study was established through direct observation during surgical procedures by trained laparoscopic gynecological surgeons and their subjective feedback via Likert scales for usability. For the primary endpoint, it was the actual presence/absence of blood aspirate and device integrity as observed by the surgeon, and for the secondary endpoint, it was the surgeons' qualitative assessment of performance and compatibility.

8. The Sample Size for the Training Set

The document does not mention a training set, as this is a physical medical device and not an AI/machine learning algorithm that requires a training phase. The described studies are for validation of the fully developed device.

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

This question is not applicable, as there is no mention of a training set for this device.

Ask a specific question about this device

The Angiography Injector is intended to aspirate and inject contrast media in the interventional procedure. It can also be used to inject fluids into, or withdraw fluids from the body.

The Angiography Injector is intended to provide the function of aspirating and injecting contrast media in the interventional procedure. It can also be used to inject fluids into, or withdraw fluids from the body. The proposed device is intended for single use and is provided sterile using EO sterilization.

The Angiography Injector consists of six components: 1) Piston, 2) Plunger cap, 3) Push-button 4) Barrel, 5) Plunger and 6) Adapter (rotating or fixed). The proposed device is available in volume of 6mL, 8mL, 10mL and 12mL.

The primary package is blister package and plastic paper package. The blister package and plastic paper package all consist of PE film and Tyvek®2FS paper.

The provided text is a 510(k) summary for a medical device called "Angiography Injector." This document describes the device, its intended use, comparison to a predicate device, and the non-clinical testing performed to demonstrate substantial equivalence.

However, the 510(k) summary does not contain information related to a study proving the device meets specific acceptance criteria in the context of AI/ML performance, human reader studies (MRMC), or a detailed setup for establishing ground truth as typically observed in AI/ML medical device submissions.

The document discusses "acceptance criteria" only in the general sense of meeting design specifications and regulatory standards for a conventional angiography injector (e.g., biocompatibility testing results showing acceptance criteria met, performance tests meeting ISO 7886 requirements). It specifically states: "No clinical study is included in this submission."

Therefore, based on the provided text, I cannot answer the questions about:

• A table of acceptance criteria and reported device performance related to AI/ML or human reader studies.
• Sample sizes for test sets (for AI/ML).
• Data provenance.
• Number of experts and their qualifications for ground truth.
• Adjudication method for test sets.
• MRMC comparative effectiveness study or human reader improvement with AI.
• Standalone (algorithm only) performance.
• Type of ground truth used (expert consensus, pathology, outcomes data, etc.) for AI/ML.
• Sample size for the training set (for AI/ML).
• How ground truth for the training set was established.

This is because the device described is a physical medical instrument (an angiography injector and syringe), not an AI/ML-driven diagnostic or assistive software. The "performance testing" mentioned refers to engineering and safety bench tests (e.g., force to operate piston, freedom from air/liquid leakage, sterility, biocompatibility etc.), not diagnostic performance on medical images.

In summary, the provided document does not support a response to the specific questions regarding AI/ML device performance or clinical study methodologies.

Ask a specific question about this device

Use of the RELIEEV Uterine Manipulator Injector is indicated in Diagnostic Laparoscopy, Minilaparotomy, Fertility Exams, and Salpingoplasty procedures where manipulation of the uterus is required.

The "RELIEEV" Uterine Manipulator Injector is intended to be used during medical procedures where manipulation of the uterus or injection of fluids into the uterine lumen are needed. This device is a sterile, single use product consisting of a plastic (PVC) insertion tube that includes two lumens, one for inflation of a 10 mL intrauterine balloon (cuff) at the distal end of the insertion tube via the inflation valve using the provided 10 mL syringe and the other for injection of fluid through a distal end-port using a user-provided syringe via the Leur fitting. The device also includes a movable/removable rigid handle that allows alteration of the device insertion depth and includes a cervical stop, laser etched depth markings to aid in setting the insertion depth, and a pilot balloon to assess maintenance of cuff inflation. The device is curved to facilitate forward uterine manipulation. The device has an overall length of 36 cm and an outer diameter of the catheter component of 5.0 mm. When inflated with 10 mL of air, the balloon has a diameter of 23.0-24.9 mm.

This document is an FDA 510(k) summary for the "RELIEEV" Uterine Manipulator Injector. It describes the device and claims substantial equivalence to a predicate device, the Panpac Uterine Manipulator Injector, Model Umi 4.5 (K092980).

Based on the provided text, the device in question is a medical instrument, not an AI/software device. Therefore, the questions related to AI/software performance, ground truth, human readers, and training/test sets are not applicable to this document.

The acceptance criteria and study proving the device meets them are related to the physical and biological safety and performance of the Uterine Manipulator Injector, rather than an AI algorithm.

Here's the information extracted from the document, tailored to the type of device described:

Acceptance Criteria and Device Performance for "RELIEEV" Uterine Manipulator Injector

This device is a physical medical instrument, and its performance evaluation focuses on its physical characteristics, sterility, biocompatibility, and mechanical integrity, comparing it to a legally marketed predicate device.

1. Table of Acceptance Criteria and Reported Device Performance

The document details various tests performed to ensure the device meets safety and performance standards for a physical medical device. The "acceptance criteria" are implied by the successful completion of these tests per the referenced standards and the statement that "all predetermined acceptance criteria were met."

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

The document does not explicitly state the sample sizes for the various tests. It refers to established testing standards (e.g., ISO, ASTM, USP), which would specify appropriate sample sizes for each test type. The data provenance is from bench testing and laboratory evaluations conducted by the manufacturer (LI Medical Corporation LTD.) to support regulatory submission. This is a prospective assessment of newly manufactured devices under controlled conditions.

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

This concept is not applicable to the assessment of a physical medical device like a uterine manipulator. "Ground truth" in this context refers to the defined acceptable parameters for physical and biological performance, which are established by international standards and regulatory guidelines, not by individual experts evaluating images or clinical data.

4. Adjudication Method for the Test Set

Not applicable for a physical medical device. Performance is judged against specified engineering, material, and biological safety standards, not through adjudication of expert opinions.

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, as this is not an AI/software device.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

Not applicable, as this is not an AI/software device.

7. The Type of Ground Truth Used

The "ground truth" for this device's performance is based on established industry standards and regulatory requirements for medical device safety and efficacy. This includes:

• Physical and mechanical properties (e.g., dimensions, tensile strength, inflation capabilities).
• Sterility assurance (e.g., EtO residuals).
• Biocompatibility (e.g., cytotoxicity, sensitization, irritation, systemic toxicity, pyrogenicity).
• Packaging integrity.

These are quantitative metrics or pass/fail criteria derived from validated test methods.

8. The Sample Size for the Training Set

Not applicable, as this is not an AI/software device. There is no "training set" in the context of a physical medical device's performance validation; rather, there are samples tested according to predefined standards.

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

Not applicable, as this is not an AI/software device.

Ask a specific question about this device

The Disposable Pen Injector Assembly is a disposable pen injector designed for single patient use by diabetics for the subcutaneous self-injection of a desired dose insulin. The disposable pen injector assembly uses 3 mL cartridge of HUMALOGTM (U-100, insulin lispro for injection), and a single use detachable and disposable insulin pen needle (supplied separately). The pen injector allows the user to dial the desired dose up to 80 units in 1 unit increments. It is intended for general population.

The Disposable Pen Injector Assembly is a disposable single-patient use pen injector capable of injecting a dose of up to 80 units of insulin in 1 unit increments. The pen injector is intended for use with 3mL insulin cartridges and single-use, disposable insulin pen needles (supplied separately). After the intended insulin cartridge is used up, the Disposable Pen Injector Assembly should be disposed. The Disposable Pen Injector Assembly is intended for single user only and provided non-sterile.

This document describes the FDA's decision regarding the 510(k) premarket notification for the "Disposable Pen Injector Assembly" from Wuxi NEST Biotechnology Co., Ltd. It outlines the device's characteristics, comparison to a predicate device, and performance data used to establish substantial equivalence.

Here's an analysis of the acceptance criteria and study information provided:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria for the Disposable Pen Injector Assembly are primarily based on meeting the requirements of ISO 11608-1:2022 Needle-based injection systems for medical use - Requirement and test methods - Part 1: Needle-based injection systems.

Ask a specific question about this device

The Pen Injector is a re-usable pen injector designed for single patient use by diabetics for the self-injection of a desired dose of insulin. The Pen Injector uses HUMALOG (insulin lispro) injection (U-100) available in 3 mL cartridges, and a single use detachable and disposable insulin pen needle (supplied separately, needle sizes including: 32G4mm, 31G4mm, 31G5mm, and 31G6mm).

The Pen Injector is a reusable mechanical pen-injector capable of injecting a dose of up to 80 units of insulin, in 1 unit increments. The Pen Injector consists of a pen injector body, a push block, a injection button, a dose display window, a dose adjustment knob, a reservoir and a pen injector cap. The intended dose is mechanically set by rotating a dose adjustment knob. The insulin is injected by depressing the knob which mechanical coupling causes the piston in the insulin cartridge to move forward thereby expelling the intended dose. The Pen Injector is intended for single user and provided for non-sterile.

The provided document describes the FDA 510(k) clearance for the Wuxi NEST Biotechnology Co., Ltd. Pen Injector (K240774). The acceptance criteria and supporting studies are primarily focused on performance testing to demonstrate substantial equivalence to the predicate device, NovoPen Echo® (K182387).

Here's a breakdown of the requested information:

1. Table of Acceptance Criteria and Reported Device Performance

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

The document does not specify the exact sample sizes (e.g., number of devices, cartridges, or test repetitions) used for each individual performance test (dose accuracy, injection force, injection time, biocompatibility, shelf life, service life, transportation). It generally states that "corresponding performance tests were conducted" or "aging studies have been conducted."

The provenance of the data is from Wuxi NEST Biotechnology Co., Ltd. in China, and the studies are prospective in nature, conducted specifically to demonstrate the performance of the Pen Injector for this submission.

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

This information is not applicable to the reported studies. The performance tests rely on objective measurements against established international standards (ISO, ASTM) and not on human expert interpretation or ground truth establishment in a medical context.

4. Adjudication Method for the Test Set

Not applicable. The tests are based on direct physical and chemical measurements against pre-defined thresholds from international 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

Not applicable. This device is a mechanical pen injector, not an AI-powered diagnostic or imaging device, so MRMC studies or human reader performance with AI assistance are not relevant.

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

This refers to the core performance testing of the device (dose accuracy, injection force, etc.) which demonstrates the standalone capabilities of the Pen Injector mechanism without human-in-the-loop performance evaluation in a clinical setting. The tests confirm the device's inherent mechanical functionalities meet the specified standards.

7. The Type of Ground Truth Used

The "ground truth" for the performance tests outlined is defined by:

• International Standards: ISO 11608-1:2022 (for injection system performance), ISO 10993 series (for biocompatibility), ASTM F1980-16 (for accelerated aging/shelf life), and ASTM D4169:2022 (for transportation).
• Device Specifications: The inherent design parameters and intended performance of the Pen Injector (e.g., maximum dose, dial increments, service life).

8. The Sample Size for the Training Set

Not applicable. This device is a mechanical medical device, not an AI/machine learning model, so there is no concept of a "training set."

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

Not applicable, as no training set is involved for this type of device.

Ask a specific question about this device

The ProSeal™ Closed System drug Transfer Device (CSTD) mechanically prohibits environmental contaminants from entering the system and the escape of drug or vapor concentrations from thereby minimizing individual and environmental exposure to drug vapor, aerosols, and spills. The ProSeal™ system also prevents the introduction of microbial contaminants into the drug or fluid path for up to 168 hours or 7 days, when used as intended.

The ProSeal™ Injector Plus is a component of the ProSeal™ CSTD system intended for connection to a standard Luer lock syringe. It is one variant of the cleared ProSeal™ Injector, a component device of the ProSeal™ CSTD system. Just like the ProSeal™ Injector, a nonlatex elastomeric membrane covers the liquid transfer cannula tip of the ProSeal™ Injector Plus. It incorporates a clamp mechanism that reversibly connects to the other component devices of the ProSeal™ CSTD system. The ProSeal™ Injector Plus, like the ProSeal™ Injector includes a stainless steel cannula that is always shielded: during preparation, use and disposal. The ProSeal™ Injector Plus is supplied with a protective cap.

The provided text is a 510(k) premarket notification for a medical device called "ProSeal™ Injector Plus (Model no. 421050)". It details the device's description, indications for use, comparison to a predicate device, and performance data supporting substantial equivalence.

However, the document does not contain any information about acceptance criteria or a study proving the device meets those criteria in the context of an AI/ML model for medical image analysis, which is what your request is about. The device is an "Intravascular Administration Set" and does not appear to involve AI.

Therefore, I cannot fulfill your request for:

1. A table of acceptance criteria and reported device performance (for an AI/ML model): This is a hardware device, not an AI/ML model.
2. Sample size used for the test set and data provenance: No AI/ML test set is described.
3. Number of experts used to establish ground truth and qualifications: No ground truth establishment for AI/ML is mentioned.
4. Adjudication method for the test set: Not applicable for a hardware device.
5. Multi Reader Multi Case (MRMC) comparative effectiveness study: Not applicable for a hardware device.
6. Standalone (algorithm-only) performance: Not applicable for a hardware device.
7. Type of ground truth used: Not applicable for a hardware device.
8. Training set sample size: No AI/ML training set is mentioned.
9. How ground truth for the training set was established: No AI/ML training set is mentioned.

The document focuses on:

• Functional performance: Bench performance verifications and validations against ISO standards (e.g., fluid leakage, air leakage, stress cracking, resistance to separation, drop test, flexural force test, tensile force test, compression force test, sharps access, device leakage integrity, needle bonding strength, sharps injury protection, cap removal force).
• Biocompatibility: Conformance to ISO 10993-1, with tests like cytotoxicity, sensitization, systemic toxicity, hemolysis, pyrogenicity, and chemical characterization.
• Sterility, Shipping, and Shelf-Life: Conformance to ISO 11135 and other standards for sterilization, endotoxin testing, accelerated aging, seal strength, and ethylene oxide residuals.

These are standard hardware device tests, not related to AI/ML performance.

Ask a specific question about this device

The ACCUJECT™ REFRA Injector is a device intended to fold and insert STAAR Surgical Collamer Phakic One Piece Intraocular Lenses, Model EVO/EVO+ VISIAN® Implantable Collamer® Lens, for surgical placement in the human eye.

The Medicel ACCUJECT™ REFRA Injector System, Model AR2900 is to be used by an ophthalmic surgeon and is intended to facilitate the loading, folding and insertion of the STAAR Surgical Collamer Phakic One Piece Intraocular Lenses, Model EVO/EVO+ VISIAN® Implantable Collamer® Lens, for surgical placement in the human eye. The ACCUJECTTM REFRA is a single use device designed specifically to deliver the STAAR Surgical Implantable Collamer® Lenses.

The provided text describes a 510(k) premarket notification for a medical device called the ACCUJECT™ REFRA Injector. This type of submission establishes substantial equivalence to a legally marketed predicate device, rather than proving performance against specific clinical acceptance criteria in the same way a de novo or PMA submission might.

Therefore, the information you've requested about acceptance criteria, study design, expert involvement, and ground truth establishment, which are typical for studies validating AI/ML-based diagnostic or prognostic devices, is largely not applicable to this 510(k) submission.

This submission focuses on demonstrating that the new injector device (ACCUJECT™ REFRA Injector) is as safe and effective as a previously cleared predicate device (Visian nanoPOINT™ 2.0 Injector) for the same intended use by comparing their technical characteristics and performing non-clinical (laboratory/bench) tests.

Here's a breakdown based on the information available:

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

   Acceptance Criteria	Reported Device Performance
   Functional Performance (in accordance with ISO 11979-3:2012 Ophthalmic implants -- Intraocular lenses -- Part 3: Mechanical properties and test methods, Section 5: Recovery of Properties following simulated surgical manipulation)	Result: Intraocular lenses recovered to specifications after being folded and deformed by the Injector.

Conclusion: "The change in injector design does not impact the performance characteristics of the injector cartridge or lens." (Implies meeting the recovery specifications, which are the acceptance criteria from ISO 11979-3). |
| Biocompatibility (in accordance with ISO 10993-1:2018, Biological evaluation of medical devices - Part 1: Evaluation and testing within a risk management process) | Result: "The biocompatibility tests performed on the modified injector met all acceptance criteria." (Implies meeting the acceptance criteria defined by applying ISO 10993-1, which would involve various tests like cytotoxicity, sensitization, irritation depending on body contact and duration). |
| Particulate Testing | Result: "The particulate testing performed on the modified injector met all acceptance criteria." (Implies meeting acceptance criteria for particulate matter release, likely defined internally or by relevant standards to prevent complications in the eye). |
| Substantial Equivalence to Predicate Device (K101134) | Conclusion: "The ACCUJECT™ REFRA Injector is substantially equivalent to the predicate device." This is the overarching "performance" reported from the comparative analysis and non-clinical testing, meaning it performs as safely and effectively as the predicate for its intended use, despite minor technological differences (e.g., changes in materials, absence of a spring, presence of a silicone buffer, operating principle including twisting). |

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

   • The document does not explicitly state "sample size" in terms of number of devices or number of lenses tested for each functional, biocompatibility, or particulate test.
   • The study is a non-clinical (bench/laboratory) study, not a clinical study involving human patients or real-world data. Therefore, "data provenance" in terms of country of origin or retrospective/prospective is not applicable in the typical sense. The testing was conducted in a controlled laboratory environment.

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

   • This is not applicable. The ground truth is established by objective measurements and standardized test methods (e.g., ISO standards) for mechanical performance, biocompatibility, and particulate matter. There isn't a "ground truth" established by human experts in the context of interpreting images or clinical outcomes for this type of device submission.

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

   • This is not applicable. Adjudication methods are relevant for subjective human assessments, especially in clinical trials or studies involving expert consensus on diagnostic interpretations. This submission relies on objective, quantifiable non-clinical testing.

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. An MRMC study is relevant for evaluating the performance of AI-assisted diagnostic devices in a clinical setting with human readers. The ACCUJECT™ REFRA Injector is a surgical instrument for delivering an intraocular lens, not an AI diagnostic device. There is no AI component or human reader interaction with AI.

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

   • This is not applicable. As explained above, this product is a mechanical medical device, not an AI algorithm.

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

   • The "ground truth" for the non-clinical tests is established by:
     • Standardized specifications: For functional recovery, the specifications would likely be derived from the requirements of ISO 11979-3.
     • Standardized biological safety criteria: For biocompatibility, the criteria are defined by ISO 10993-1 and related sub-parts.
     • Pre-defined acceptance limits: For particulate matter, specific limits for particle size and count would be established, often based on internal specifications, industry standards, or regulatory guidance for sterile medical devices.

8. The sample size for the training set:

   • This is not applicable. There is no "training set" as this device does not involve machine learning or AI.

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

   • This is not applicable. As there is no training set.

Ask a specific question about this device

The CORE-INJECTOR is to be used in conjunction with an endoscope to perform endoscopic injections, such as the treatment of esophageal and gastric varices and for submucosal dye marking in the GI tract.

The CORE-INJECTOR, the disposable endoscope injection needle is a disposable device for injecting medicine and medical supplies into a mucous membrane or blood vessel to stop the bleeding or for hardening the vessel during endoscopic procedure. The device consists of a stainless steel needle attached to sheath and handle where a syringe with solution for injection can be attached. It is available in various sizes and working lengths. The needle sizes are 23 gauge and the needle length is 4.0mm. The working length includes 1,200mm, 1,600mm, 1,800mm, 2,300mm. The operating time is less than 1 hour. it contacts with mucosa of the human digestive tract. The proposed product is packed in a sealed pouch following EO Sterilization (SAL 10°). This device is supplied sterile for single-patient use and shall be not reused or re-sterilized.

The provided document describes the non-clinical performance testing for the CORE-INJECTOR device to demonstrate its substantial equivalence to a predicate device. It does not contain information about a comparative effectiveness study (MRMC) or a standalone (algorithm-only) study for a medical imaging AI device. The device in question is an endoscope injection needle, not an AI or imaging device. Therefore, many of the requested fields are not applicable.

Here's the information that can be extracted from the document:

1. Table of Acceptance Criteria and Reported Device Performance

Ask a specific question about this device

The MicroDose Injector is indicated for low volume ophthalmic injections into the subretinal space.

The MicroDose Injector is designed for low volume ophthalmic injection into the subretinal space. It consists of one (1)1mL syringe and one (1) connector, which is joined to VFC tubing that is attached to a pneumatic air source, enabling a surgeon control for administering subretinal injections. The device is supplied sterile and intended for single-use only and cannot be reused or resterilized.

This document is a 510(k) summary for the MedOne Surgical, Inc. MicroDose™ Injector. As such, it focuses on demonstrating substantial equivalence to a predicate device rather than presenting a detailed study proving the device meets specific acceptance criteria in terms of clinical performance or diagnostic accuracy.

Therefore, many of the requested sections (sample size for test/training sets, data provenance, expert qualifications, adjudication methods, MRMC studies, standalone performance, ground truth types) are not applicable or cannot be extracted from this type of regulatory submission, as they pertain to studies involving performance metrics like sensitivity, specificity, or reader agreement, which are not the subject of this 510(k). This submission primarily covers technical, safety, and functionality aspects to establish equivalence.

Here's an analysis of the available information:

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

The document does not provide a table of acceptance criteria in the typical sense of numerical performance targets (e.g., sensitivity > X%, specificity > Y%). Instead, it establishes equivalence based on meeting various technical, safety, and functional testing requirements.

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

This information is not applicable/available from the 510(k) summary. The "tests" performed are engineering and laboratory tests (biocompatibility, sterilization, shelf-life, package testing), not clinical or diagnostic performance studies with patient data.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

This information is not applicable/available. Ground truth as understood in AI/diagnostic studies (e.g., expert consensus on medical images) is not relevant to the types of tests conducted for this device.

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

This information is not applicable/available. Adjudication methods are typically used in clinical studies involving human interpretation or consensus, which are not presented here.

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 information is not applicable/available. The MicroDose™ Injector is a physical medical device (syringe system), not an AI-powered diagnostic or assistive tool.

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

This information is not applicable/available. The device is not an algorithm.

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

The "ground truth" for the tests performed can be characterized as follows:

• Biocompatibility: Established standards and validated laboratory methodologies (e.g., cell viability assays for cytotoxicity, skin reaction assessment for sensitization, animal models for systemic toxicity).
• Sterilization: Microbiological methods to confirm the absence of viable microorganisms to the specified SAL.
• Shelf-life: Real-time or accelerated aging studies with functional testing at intervals to determine the point at which the device no longer meets specifications.
• Package integrity: Physical testing (e.g., burst strength, seal integrity) according to recognized standards.
• Functionality: Direct measurement against engineering specifications (e.g., flow rate, volume delivery accuracy).

8. The sample size for the training set

This information is not applicable/available. There is no "training set" as this device is not an AI/machine learning algorithm.

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

This information is not applicable/available. As there is no training set for an AI algorithm, there is no associated ground truth in that context.

Ask a specific question about this device

This instrument has been designed to be used with an Olympus endoscope to deliver injectable materials into the urinary bladder wall during the transurethral endoscopic procedures.

This instrument has been designed to be used with an Olympus endoscope to deliver injectable materials into the urinary bladder wall during the transurethral endoscopic procedures. The subject device is sterilized and packaged in a sterilization package.

The provided document is a 510(k) premarket notification for a medical device called the "Single Use Injector NM-221C-0427." This is a device used in conjunction with an endoscope to deliver injectable materials into the urinary bladder wall.

Based on the content, specifically Section 7 "PERFORMANCE DATA," it is clear that this submission focuses on bench testing, sterilization/shelf-life testing, and biocompatibility testing to demonstrate substantial equivalence to a predicate device. There is no mention of a study involving AI, human readers, or image analysis.

Therefore, many of the requested details about acceptance criteria and studies related to AI performance, such as MRMC studies, expert ground truth establishment, training sets, and data provenance, are not applicable to this specific device submission as described in the provided text.

However, I can extract the acceptance criteria and performance data that were provided for this traditional medical device.

1. Table of Acceptance Criteria and Reported Device Performance

For this device, the "acceptance criteria" are implied by the successful completion of the specified performance tests. The document states that the tests were conducted "to ensure that the subject device performs as intended and meet design specifications."

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

• Sample Size: Not explicitly stated for each test, but standard engineering practices for medical devices (e.g., ISO, ASTM standards) imply sufficient samples were tested to demonstrate performance and meet statistical confidence. This is not a data-driven AI model, so "test set" in the context of images or AI performance isn't applicable.
• Data Provenance: Not applicable in the context of image data. The testing was conducted by Olympus Medical Systems Corp. and Aomori Olympus Co., Ltd. (Japan) to support their 510(k) submission to the FDA (USA).

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

• Not applicable. This device is a physical instrument, not an AI or image analysis system. Ground truth is established through adherence to engineering specifications and performance standards (e.g., "Needle slidability" is assessed against a defined mechanical threshold, not expert consensus on an image).

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

• Not applicable. See point 3.

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

• No. The document explicitly states: "No clinical study was performed to demonstrate substantial equivalence." and "No animal study was performed to demonstrate substantial equivalence." This is not an AI-assisted diagnostic device.

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

• Not applicable. This is a physical medical device, not an algorithm.

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

• For physical performance characteristics (e.g., flow rate, durability, puncture performance), engineering specifications and validated testing methods serve as the "ground truth." For biocompatibility and sterilization, the "ground truth" is adherence to established international standards (e.g., ISO, ASTM, USP) and FDA guidance.

8. The sample size for the training set

• Not applicable. No training set was used as this is not an AI/machine learning device.

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

• Not applicable. See point 8.

In summary, the provided document describes the regulatory submission for a physical medical device (a single-use injector) that demonstrates substantial equivalence through bench testing, biocompatibility testing, and sterilization validation, rather than studies focused on AI performance or human reader interaction with an AI system.

Ask a specific question about this device