Search Results

Ask a specific question about this device

Ask a specific question about this device

Ask a specific question about this device

The Erbe Electrosurgical Unit (ESU/Generator) model VIO 3n with instruments and accessories is intended to deliver high frequency (HF) electrical current for the cutting and/or coagulation of tissue.

The Erbe ESU Model VIO® 3n is an electrosurgical unit (ESU) that delivers high-frequency (HF) electrical current for cutting and/or coagulation of tissue. The unit can be mounted/secured to a cart/system carrier or on a ceiling mount. Different footswitches are available for activating the ESU. The ESU VIO® 3n has several clearly defined monopolar and bipolar cutting and coagulation modes with different electrical waveforms and electrical parameters that are programmed with defined effect levels. Each effect level corresponds to a defined maximum power output and a voltage limitation. In combination with the compatible argon plasma coagulation unit APC 3 (K191234), it offers monopolar modes for argon plasma coagulation and argon-supported modes. The ESU has a touchscreen monitor that provides the user with an onscreen tutorial as well as settings and operational information. It also provides a small number of physical controls, such as the power switch, instrument sockets and a neutral electrode receptacle. Connections for the central power supply, for footswitches, for potential equalization of the operating theatre and Erbe Communication Bus (ECB) connections to other Erbe modules are located at the rear. The ESU emits sounds when instruments are activated, and messages are signaled. The actual application is carried out using compatible electrosurgical instruments that are connected to the generator. The VIO® 3n can be combined with matching Erbe devices and modules, instruments, and accessories.

To address various clinical needs, the ESU is available in 5 different configurations which are called "Fire", "Metal", "Stone", "Water" and "Timber". Whereas the configuration "Fire" includes all available modes and functionalities, the other configurations only offer a reduced number of modes and functionalities.

The provided FDA 510(k) clearance letter and summary for the Erbe ESU Model VIO® 3n with Accessories do not contain the detailed information necessary to fully answer all aspects of your request regarding acceptance criteria and a specific study proving the device meets those criteria, particularly for an AI/software as a medical device (SaMD).

This document pertains to an electrosurgical unit, which is a hardware device for cutting and coagulating tissue using high-frequency electrical current. The "software" mentioned in the document refers to the operating software of the ESU itself, not an AI or diagnostic algorithm, and thus the type of performance metrics, ground truth, and study designs you're asking about (e.g., MRMC, standalone performance, expert consensus on diagnostic images) are not applicable to this type of device submission.

Therefore, I cannot provide a table of acceptance criteria and device performance in the context of an AI/SaMD, nor detailed information on test set sample sizes, data provenance, number of experts for ground truth, adjudication methods, MRMC studies, or specific training set details, because this document describes a hardware device.

However, I can extract the information that is present about the non-clinical performance testing and what it aims to demonstrate:

1. Table of Acceptance Criteria and Reported Device Performance

As this is a hardware electrosurgical unit, the "acceptance criteria" are generally related to compliance with electrical safety, EMC, and functional performance standards for tissue cutting/coagulation. The document does not provide specific quantitative acceptance criteria values or detailed performance metrics in a table. It states that the device "performs as intended per the product specifications and requirements."

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

• Test Set Sample Size: Not specified for any of the non-clinical tests.
• Data Provenance: Not specified, but the tests were performed "non-clinical," implying laboratory or bench testing rather than clinical patient data. The manufacturer is Erbe Elektromedizin GmbH (Germany).

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

• This question is not applicable to the non-clinical testing of an electrosurgical hardware device. Ground truth, in the context of AI/SaMD, usually refers to labeled diagnostic data. For this device, "ground truth" would be the measurable physical parameters and effects on tissue.

4. Adjudication method for the test set

• This question is not applicable. Adjudication methods like 2+1 or 3+1 are used for expert consensus on ambiguous diagnostic cases in AI/SaMD studies. For an ESU, performance is measured against engineering specifications and observed physical effects.

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, an MRMC study was not done. This type of study is relevant for diagnostic AI tools that assist human readers (e.g., radiologists interpreting images). The Erbe ESU Model VIO® 3n is an interventional hardware device, not a diagnostic AI.

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

• The term "standalone performance" for an AI algorithm is not directly applicable here. However, the non-clinical performance testing (functional, EMC, electrical safety) can be considered "standalone" in the sense that the device's technical capabilities were tested independently against specifications without a human operator's diagnostic interpretation loop. The device directly performs an action (cutting/coagulation) rather than providing information for human interpretation.

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

• For the functional testing, the "ground truth" would be the observable physical effects on tissue (e.g., degree of cutting, coagulation depth, eschar formation) and measured electrical parameters (power output, voltage, current) compared to established engineering specifications and the performance of predicate devices.
• For safety and EMC, the "ground truth" is compliance with international standards (e.g., IEC 60601 series).

8. The sample size for the training set

• This question is not applicable. The Erbe ESU Model VIO® 3n is an electrosurgical hardware device. It does not use a "training set" in the machine learning sense to learn and develop an algorithm. Its operating software is developed through traditional software engineering processes, not machine learning model training.

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

• This question is not applicable as there is no machine learning training set for this device.

Ask a specific question about this device

RO handpiece, AGNES (F) RF handpiece and AGNES (B) RF handpiece of RFMagik are intended for use in dermatologic and general surgical procedures for electrocoagulation and hemostasis.

RFMagik is a medical device combined with RF current, to function as an electrosurgical device for use in dermatology and general surgical procedures. It is possible to select and change modes, parameters, outputs, etc. using the panel on the main body. It consists of the main device, LCD screen, two handpieces, single use electrodes, electrode pad, NE pad cable, food switch.

There are three handpieces. RO handpiece, AGNES (F) RF handpiece and AGNES (B) RF handpiece that delivers RF energy through the disposable electrode in the handpiece.

This document is an FDA 510(k) clearance letter for an RF Electrosurgical Device (RFMagik). It states that the device is substantially equivalent to legally marketed predicate devices.

However, the provided document does NOT contain information about acceptance criteria, device performance results, sample sizes, expert ground truth establishment, or clinical study details. The section on "Clinical Testing" explicitly states: "Clinical testing is not a requirement and has not been performed."

The document focuses on:

• Regulatory details: Device classification, product codes, indications for use.
• Technological comparison: Detailed comparison of the subject device (RFMagik) with a primary predicate device (RFMagik Lite) and a reference device (AGNES). This comparison highlights similarities and differences in handpieces, electrodes, output power, etc., and explains why these differences do not affect substantial equivalence.
• Non-clinical testing: Biocompatibility, sterility, shelf-life, and performance bench testing. An "Ex Vivo Study" was conducted on tissue types (liver, skin, muscle) for thermal testing.

Therefore, I cannot fulfill your request for a table of acceptance criteria, device performance, sample sizes for the test set, data provenance, number/qualifications of experts, adjudication methods, MRMC study details, standalone performance, type of ground truth, training set sample size, or how training ground truth was established. This information is typically found in specific study reports or sections of a 510(k) submission that go beyond what is published in the clearance letter itself.

The document indicates that the substantial equivalence was primarily demonstrated through bench testing and comparison to predicate devices, rather than clinical trials or extensive human-in-the-loop performance studies.

Summary of what CANNOT be provided from the given document:

1. Table of acceptance criteria and reported device performance: Not present.
2. Sample size for the test set and data provenance: No clinical test set. Ex vivo study mentioned, but specific sample sizes are not detailed.
3. Number of experts and qualifications for ground truth: Not applicable as no clinical study with expert ground truth review was performed.
4. Adjudication method for the test set: Not applicable.
5. MRMC comparative effectiveness study: Not conducted.
6. Standalone (algorithm only) performance: Not applicable as this is a physical electrosurgical device, not an AI algorithm.
7. Type of ground truth used: Not applicable for a clinical study. Ex vivo study used physical tissue, but no "ground truth" akin to medical image labeling.
8. Sample size for the training set: Not applicable as there is no mention of an AI/ML algorithm requiring a training set.
9. How ground truth for the training set was established: Not applicable.

Ask a specific question about this device

The Venclose System (Venclose digiRF Generator with EVSRF Catheter) is intended for endovascular coagulation of blood vessels in patients with superficial vein reflux.

The Venclose™ digiRF Generator is a multi-voltage energy delivery system with touchscreen control that automatically sets the non-adjustable treatment parameters for the catheter to be used with the generator (time, temperature, etc.), which is connected via a triaxial catheter connector port. The Venclose™ digiRF Generator is intended to be used with Venclose™ RF Catheter(s) (either the Venclose™ EVSRF Catheter or the Venclose™ Maven Catheter) as a system. The Venclose™ RF System uses resistive radiofrequency ablation via energy delivery to heat the wall of an incompetent vein with temperature-controlled RF energy to cause irreversible luminal occlusion, followed by fibrosis and ultimately resorption of the vein.

The scope of this 510(k) is only the Venclose™ digiRF Generator as the generator software has been modified. The Venclose™ Maven Catheter is not in the scope of this submission as the changes discussed within this submission are only applicable to the Venclose™ digiRF Generator as used with the Venclose™ EVSRF Catheter. There is no change to the Venclose™ EVSRF Catheter, as previously cleared via K160754.

Based on the provided 510(k) Clearance Letter, the device in question is the "Venclose digiRF Generator" and the modifications are related to its software when used with the "Venclose EVSRF Catheter." The clearance letter states that the scope of this 510(k) is only the Venclose digiRF Generator as the generator software has been modified, and there is no change to the Venclose EVSRF Catheter.

The document explicitly states that the device is an "Electrosurgical Cutting And Coagulation Device And Accessories" and the testing performed was "Software Verification and Validation." There is no mention of a study involving human subjects, interpretation of medical images by experts, or any kind of diagnostic performance evaluation typically seen with AI/ML-based diagnostic devices.

Therefore, many of the requested criteria regarding acceptance criteria for diagnostic performance, ground truth establishment, expert adjudication, MRMC studies, and training/test set details for AI/ML models are not applicable to this submission. This is a clearance for a software modification to an electrosurgical generator, not a medical imaging AI/ML diagnostic aid.

Here's the breakdown of what can be gathered from the provided text, addressing the points where information is available and indicating where it is not applicable or not provided.

Device: Venclose digiRF Generator (VCRFG1) with Venclose EVSRF Catheter (VC10A256F60, VC10A256F100)
Type of Modification: Software Modification to the Venclose digiRF Generator.

1. Table of Acceptance Criteria and Reported Device Performance

Given that this is a software modification to an electrosurgical generator, the acceptance criteria are not related to diagnostic performance metrics like sensitivity, specificity, or AUC, but rather to software functionality, safety, and effectiveness. The document states that internal risk assessments procedures were used.

Note: Specific numerical acceptance values are not detailed in this public 510(k) summary, as they are typically proprietary and part of detailed engineering and software validation reports submitted to the FDA.

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

This is not applicable in the context of an AI/ML diagnostic performance test set. The "test set" here refers to the software verification and validation activities. The document does not specify exact "sample sizes" (e.g., number of test cases or iterations) for the software testing. Data provenance is also not applicable in the context of clinical data for AI/ML, as the testing relates to engineering and software validation.

• Software Verification and Validation: This typically involves rigorous testing against defined requirements, including unit testing, integration testing, system testing, and perhaps regression testing. The "sample size" would relate to the number of test cases executed, input parameters varied, and error conditions simulated. Specific numbers are not provided in this summary.
• Data Provenance: Not applicable as no clinical data for diagnostic performance was used in this clearance for a software modification to an electrosurgical device.

3. Number of Experts Used to Establish Ground Truth and Qualifications

Not applicable. Ground truth, in the sense of expert annotation of medical data, is not established for an electrosurgical generator's software modification. The "ground truth" for this device's performance would be its adherence to engineering specifications and its ability to safely and effectively deliver RF energy for its intended purpose, as measured by calibrated equipment and functional tests.

4. Adjudication Method for the Test Set

Not applicable. Adjudication methods (e.g., 2+1, 3+1) are for consensus building among human experts for ground truth label generation in diagnostic studies. This process is not part of software verification and validation for an electrosurgical device.

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

No. An MRMC study is relevant for evaluating the impact of an AI/ML diagnostic device on human reader performance. This 510(k) is for a software modification to an electrosurgical generator, not a diagnostic AI/ML device. Therefore, no MRMC study was performed or reported.

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

No. "Standalone performance" refers to the diagnostic accuracy of an AI/ML algorithm by itself. This device is an electrosurgical generator. Its performance is measured by its ability to generate and deliver RF energy according to specifications, not by its diagnostic capabilities. The software's "performance" was evaluated through verification and validation activities.

7. The Type of Ground Truth Used

Not applicable in the AI/ML diagnostic sense. For this device, the "ground truth" for software validation would be derived from:

• Design Specifications: The documented requirements and expected behavior of the software and the device.
• Predicate Device Performance: The existing performance characteristics of the previously cleared predicate devices, to which the modified device is being compared for substantial equivalence.
• Engineering Standards and Measurements: Data from calibrated test equipment, electrical measurements, temperature readings, and time controls.

8. The Sample Size for the Training Set

Not applicable. This device is not an AI/ML algorithm that requires a training set. The software was likely developed using traditional software engineering methodologies.

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

Not applicable. As there is no AI/ML training set, there is no ground truth to establish for such a set.

Ask a specific question about this device

Ask a specific question about this device

The XERF is intended for use in dermatologic and general surgical procedures for electrocoagulation and hemostasis.

XERF is an electrosurgical unit which uses high frequency electrical currents for treatment. When high frequency is irradiated on the skin, the treated skin tissue is heated, resulting in coagulation. This equipment generates high frequency of 2 MHz and 6.78 MHz and is delivered non-invasively into skin through the tip of the handpiece. There are a total of 12 types of active electrode tips compatible with the handpiece; the different tips are intended for various applications and treatment zones. The system also includes a return pad corresponding to the neutral electrode which is intended to be attached to the patient's back to disperse the generated energy. For adjustment of treatment parameter, data can be used by adjusting the operator interface through LCD touch screen. Treatment is conducted using foot switch or finger switch after ready when applied treatment parameter is output to the tissue.

The provided FDA 510(k) Clearance Letter for the XERF device does not contain the kind of detailed information about acceptance criteria and a study proving the device meets them that your request outlines. This document is a clearance letter, which means the FDA has already assessed the sufficiency of the submitted information, including performance data, and found the device substantially equivalent to a predicate.

Specifically, the document states:

• "No clinical tests were included as part of this submission." This immediately tells us there was no study involving human subjects to demonstrate the device meets acceptance criteria in a clinical setting.
• The "Performance" section describes ex-vivo thermal studies. While these are performance tests, they are not clinical studies with acceptance criteria based on human outcomes or expert assessment of clinical images, as typically implied by your request.

Therefore, for aspects like "Table of acceptance criteria and reported device performance," "Sample size used for the test set," "Number of experts," "Adjudication method," "MRMC comparative effectiveness study," "Standalone performance," "Type of ground truth," "Sample size for training set," and "How ground truth for training set was established," the provided text does not contain this information. These details would typically be found in the more comprehensive 510(k) submission itself, rather than in the final clearance letter summary.

However, I can extract the available information from the "Performance" section regarding the ex-vivo studies.

Summary of Device Performance and Related Information from the Provided Text:

1. Table of Acceptance Criteria and Reported Device Performance

• Acceptance Criteria (Implicit from study goal): Achieving coagulation, uniform coagulation, and thermal performance equivalent to predicate device.
• Reported Device Performance:
  • Study 1 (Ex-vivo thermal study - tissue effects): "Coagulation was observed when treatment was performed with five stacked pulses with the interval of 200ms (within the same treatment spot without moving the tip). Coagulation surface correlated to the perimeter of the RF tip treatment surface. Uniform coagulation at entire perimeter and depth was observed in tested tissues."
  • Study 2 (Ex-vivo thermal study - temperature-time curves): "The ex-vivo dermal temperature testing confirmed that the XERF device's thermal performance is equivalent to that of the Thermage FLX device in terms of time-dependent heating and cooling behavior."

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

• Sample Size: Not explicitly stated for the ex-vivo studies.
• Data Provenance: Ex-vivo (not human/clinical) tissues: kidney, liver, and skin. No country of origin mentioned for the tissues.

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

• Not applicable as no clinical ground truth was established. The tissue analysis involved standard H&E histology performed on biopsy samples. The expertise of those analyzing the histology (e.g., pathologist) is not specified.

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

• Not applicable as no clinical ground truth was established by experts.

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 MRMC study was done. This device is an electrosurgical unit, not an AI diagnostic/imaging device.

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

• Not applicable. This is a medical device, not an algorithm, and its performance was assessed ex-vivo.

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

• For the ex-vivo tissue study: Histology (H&E staining and analysis under light microscope) was used to assess coagulation.
• For the ex-vivo thermal curve study: Direct temperature measurements using fiber optic sensors.

8. The sample size for the training set:

• Not applicable. The device is not an AI/ML algorithm that requires a training set in the conventional sense. The studies described are performance validation tests for the device itself.

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

• Not applicable.

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 InbellaMAX System with the BellaXL 810 Black is intended for hair removal and permanent hair reduction defined as the stable, long-term reduction in hair counts at 6, 9, or 12 months following a treatment regime. The BellaXL 755/810 Black and the BellaXL 810/1064 Black are intended for hair removal.

The InbellaMAX System with the BellaVlaze Black is intended for the treatment of vascular lesions, including angiomas, hemangiomas, telangiectasia, port wine stains, leg veins and other benign vascular lesions.

The InbellaMAX System with the Bella515 and Bella580 Black Applicators are indicated for use for the following treatments:

• The treatment of benign pigmented epidermal lesions, including dyschromia, hyperpigmentation, melasma, ephelides (freckles);
• The treatment of benign cutaneous vascular lesions, including port wine stains, facial, truncal and leg telangiectasias, rosacea, erythema of rosacea, angiomas and spider angiomas, poikiloderma of Civatte, superficial leg veins and venous malformations.

The InbellaMAX System with the BellaPlus and BellaForma Handpieces are indicated for the temporary relief of minor muscle aches and pain, temporary relief of muscle spasm, and temporary improvement of local blood circulation.

The InbellaMAX System with the BellaM8 BApplicators is intended for use in dermatologic procedures where coagulation/contraction of soft tissue or hemostasis is needed. At higher energy levels greater than 62 mJ/pin, the use of the Morpheus8 Applicator is limited to Skin Types I-IV.

The InbellaMAX system is a computerized, versatile system that generates Laser, IPL, and RF energies for the treatment of several clinical indications. The device utilizes different applicators to achieve its mode of operation in accordance with the selected technology and clinical indication. The device system operates when any of the applicators are connected and enables individual adjustment of treatment parameters. The water-cooling system provides cooling for laser and IPL applicators and thermoelectric coolers (TECs). The cooling system includes a radiator, water pump, fan, water reservoir, deionizer, water filter, tissue contact temperature sensor, and water flow sensor. The system is compatible with the following applicators:

• BellaForma
• BellaPlus
• BellaM8 BApplicator and BellaM8 BDeep Applicators
• Bella515 Black
• Bella580 Black
• BellaVlaze Black
• BellaXL 755/810 Black
• BellaXL 810/1064 Black
• BellaXL 810 Black

Based on the provided FDA 510(k) Clearance Letter for the InbellaMAX System, it's important to understand that this document primarily focuses on Substantial Equivalence to a predicate device rather than presenting a performance study with detailed acceptance criteria and a test set.

The core essence of this 510(k) submission is that the InbellaMAX System is identical in all aspects to the predicate device (Optimas MAX System, K251632) except for the manufacturer and 510(k) holder. This means that the acceptance criteria and the proof of meeting those criteria would have been established and demonstrated for the predicate device, and the InbellaMAX System is simply asserting equivalence based on its identical design and function.

Therefore, the information typically found in a performance study with explicit acceptance criteria for a new, novel device is largely absent here because it's a "copy" of an already cleared device. The "study" proving it meets acceptance criteria is the demonstration that its design, technology, and intended use are identical to the predicate.

Given this, I will answer your questions as best as possible based on the provided text, highlighting where information is absent due to the nature of a substantial equivalence claim for an identical device.

Acceptance Criteria and Device Performance (Based on Substantial Equivalence Logic)

Since the device is declared "identical in all aspects" to the predicate, the "acceptance criteria" for the InbellaMAX System are implicitly that it performs exactly like the predicate device, meeting all the performance standards the predicate device met. The "reported device performance" is, by definition, the performance of the predicate device.

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

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

• Sample Size for Test Set: Not applicable/Not provided. No separate clinical or non-clinical test set data specific to the InbellaMAX system is presented because the submission relies on substantial equivalence. The "test set" for the original predicate device (Optimas MAX System, K251632) would have been used to establish its safety and effectiveness, and the InbellaMAX System is declared identical.
• Data Provenance: Not applicable/Not provided. The document does not refer to any new test data for the InbellaMAX System.

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)

• Not applicable/Not provided. This information pertains to the rigorous evaluation of a new device's performance, typically involving clinical trials or extensive non-clinical testing. For a substantial equivalence claim based on identical design, such details are not required for the subject device. This would have been part of the predicate device's clearance.

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

• Not applicable/Not provided. As no new test set is described, no adjudication method is referenced. This would have pertained to the predicate device's evaluation.

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/Not provided. This type of study (MRMC, AI assistance) is not relevant to this device, which is a laser/IPL/RF system for dermatologic procedures, not an AI-assisted diagnostic imaging device.

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

• Not applicable/Not provided. This term typically applies to AI algorithms. The InbellaMAX System is a hardware-based medical device. Its "performance" is its ability to generate laser/IPL/RF energy and function as intended, rather than producing an "output" like an AI algorithm.

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

• Not applicable/Not provided. No new "ground truth" was established for the InbellaMAX system, as it's a substantial equivalence claim based on an identical predicate device. The clinical effectiveness and safety of the predicate device would have been established through relevant data, which could have included clinical outcomes, expert observations, and other performance metrics depending on the specific indications.

8. The sample size for the training set

• Not applicable/Not provided. This term typically applies to machine learning models. The InbellaMAX System is a hardware device; it does not have a "training set" in the machine learning sense.

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

• Not applicable/Not provided. As above, this concept refers to machine learning models, which is not applicable to the InbellaMAX System.

Ask a specific question about this device