Search Results

Coagulation (thermo-ablation) of soft tissue. Not for use in cardiac procedures.

HS AMICA devices family is a fully featured soft tissue ablation system that is intended for coagulation (thermo-ablation) of soft tissues. Not for use in cardiac procedures.
AMICA-GEN is available in the following different models: AMICA-GEN AGN (Microwave generator only), AMICA-GEN AGN-R (Radiofrequency generator only), and AMICA-GEN AGN-H (Hybrid Microwave and Radiofrequency generator). The MW and RF outputs can never be activated simultaneously. The actual energy source in use depends on the applied part type, RF or MW, connected to the generator.
There are several available variants of PROBE (i.e. the applied parts for direct energy delivery into the patient's body for percutaneous or intra-operative use): AMICA-PROBE (disposable device for MW energy delivery) and RF AMICA-PROBE (monopolar, straight, stainless steel electrode for RF energy delivery).
HS AMICA devices family consists of non-sterile reusable electronic parts, and sterile disposable applied parts. The sterilization method used for all the sterile components is Ethylene Oxide.
The microwave devices can be operated in continuous and PULSE mode. The PULSE mode is new operational mode with a duty cycle of 40% and a max output power of 190 Watts.

The provided text is a 510(k) Summary for a medical device (HS AMICA devices family) seeking clearance from the FDA. It primarily focuses on comparing the new device to a predicate device and demonstrating substantial equivalence through various tests and compliance with standards.

However, the document does not describe an AI/ML-based medical device. The "AI" term in the prompt implies such a device. This document describes an "Electrosurgical Cutting and Coagulation Device and Accessories," which uses microwave and radiofrequency energy for thermo-ablation of soft tissues. The software update mentioned (Rev. 1.7.1) appears to be a general software update for device control, not an AI/ML algorithm for diagnostic or prognostic purposes.

Therefore, the specific information requested about acceptance criteria and studies for an AI/ML device (e.g., sample size for test set, data provenance, number of experts for ground truth, MRMC study, standalone performance, training set details) is not present in the provided text as it pertains to an AI/ML aspect.

The document does mention "Performance Data" and "Thermal Effects performance tests" with ex-vivo bovine liver, kidney, and muscle as part of the verification and validation studies. It states that "the system passed all pre-determined acceptance criteria identified in the test plan." However, it does not explicitly list these acceptance criteria or the reported performance in a quantitative, granular way as would be expected for an AI/ML model's output metrics (e.g., sensitivity, specificity, AUC). The nearest it comes to a performance claim is that "PULSE mode ablations allowed for slightly more spherical ablations."

Based on the provided text, I cannot fulfill the request for information regarding AI/ML device acceptance criteria and study details because the device described is not an AI/ML device.

If the question were rephrased to be about the non-AI medical device described in the document, here's what could be extracted, though it would still be limited:

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

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

• The document mentions "Thermal Effects tests with ex-vivo bovine liver, kidney and muscle." No specific sample sizes (number of tissue samples or experiments) are provided.
• Data provenance: Ex-vivo bovine tissues.

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

• Not applicable/Not mentioned, as this is a performance test on tissue, not an AI ground truth establishment.

4. Adjudication method for the test set:

• Not applicable/Not mentioned.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done:

• No, an MRMC study was not done as this is not an AI/ML device for interpretation.

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

• The device itself is a standalone electrosurgical system. The performance tests were of the device's ability to ablate tissue.

7. The type of ground truth used:

• The "ground truth" for the performance tests was the observable thermal ablation effects on ex-vivo bovine tissues (e.g., size and shape of ablation zone).

8. The sample size for the training set:

• Not applicable, as this is not an AI/ML device requiring a training set.

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

• Not applicable.

Ask a specific question about this device

Coagulation (thermoablation) of soft tissue. Not for use in cardiac procedures.

HS AMICA devices family is an integrated system for thermoablation of tissues through controlled emission of non-ionizing electromagnetic radiations in the microwave and radiofrequency ranges. Especially the HS AMICA family consists of 3 devices and relative accessories emitting: 1. Only microwaves (MW) or 2. Only radiofrequency waves (RF) or 3. Either microwaves or radiofrequency waves (not simultaneously). The three devices emit the specific wavelength through their applicators (probes) that are inserted into the human body and deliver electromagnetic energy through their emitting tip, causing the thermoablation. Briefly, the HS AMICA devices family consists of two main components: 1) the generator; 2} the applicator (probe). The generator of the electromagnetic energy is available in the following variants, depending on the specific electromagnetic emission: 1. AMICA GEN AGN-H. This variant is characterized by both the MW and RF modules that must be selected by the physician. When the MW function is selected, the RF emission is disabled and viceversa and thus the modules operate in mutually exclusive fashion 2. AMICA GEN AGN. This variant has only the MW module. 3. AMICA GEN AGN-R This variant has only the RF module. In all cases, the AMICA GEN is provided with an electronic control unit (EC), for data exchange with the patient applied parts, the interpretation of user's commands through front panel controls or external peripherals (such as the footswitch for remote energy start/stop), the continuous update of the machine indicators, and the control of the energy generation modules MW and/or RF. The applicator (probe) is disposable and consists of the following variants, to be used for the MW or RF thermoablation: 1. AMICA PROBE. This variant is a microwave coaxial antenna of asymmetric dipole type allowing the emission of the MW energy 2. RF AMICA-PROBE. This variant is used for radiofrequency energy delivery through monopolar interstitial electrode.

The provided text is a 510(k) Summary for the HS AMICA devices family, an electrosurgical cutting and coagulation device. It primarily focuses on demonstrating substantial equivalence to predicate devices (K083157 and K053290) through a comparison of technological characteristics and performance data.

However, the document does not contain the level of detail typically required to fully answer a request for acceptance criteria and a study proving a software/AI-based device meets those criteria, especially regarding clinical study design elements like sample sizes, expert qualifications, ground truth establishment, or multi-reader multi-case studies for AI performance.

The "Performance Data" section discusses:

• Electrical safety
• Electromagnetic compatibility
• Software verification and validation (developed and validated according to FDA guidance and IEC 62304:2006, but no specific performance criteria or results are given beyond "compliance")
• Biocompatibility
• Performance test-bench: This is the closest to device performance, focusing on physical ablation size on ex-vivo tissues for both microwave and radiofrequency components, compared to predicate devices.

Therefore, many parts of your request for "acceptance criteria and the study that proves the device meets the acceptance criteria" cannot be fully answered as the document describes a traditional electrosurgical device, not an AI/software-driven diagnostic or assistive system with the types of performance metrics you've outlined.

However, I can extract the information that is present and indicate where information is missing based on the context of the document.

Acceptance Criteria and Device Performance (Based on available information for a physical device, not AI)

Detailed Study Information (Based on a typical AI/Software Device Request vs. Provided Document)

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

   • Provided: For the "Performance test-bench" (ablation size), the data provenance is "ex-vivo tissues (muscle, liver, lung and kidney)". No specific number or type of "samples" (e.g., number of tissue blocks, number of ablation procedures) is given, nor is the origin country. This is not a clinical test set in the context of AI.
   • Missing for AI: No information on test set size (e.g., number of images, cases) or data provenance (e.g., retrospective/prospective, number of sites/patients, country of origin) for AI performance evaluation.

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

   • Provided: Not applicable. The "ground truth" for the performance test was the physical measurement of ablation size on ex-vivo tissues. This was a physical measurement, not an expert-derived truth.
   • Missing for AI: No information on expert involvement or their qualifications.

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

   • Provided: Not applicable. Ground truth was direct measurement for the physical performance test.
   • Missing for AI: No information.

4. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

   • Provided: No. This study was not an MRMC comparative effectiveness study involving human readers. It was a comparative performance test of a physical device against its predicates on ex-vivo tissue concerning ablation size and general safety/EMC standards.
   • Missing for AI: No information.

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

   • Provided: Not applicable. This device is an electrosurgical unit, not an algorithm performing a standalone diagnostic or assistive function on its own data inputs (like images). The "software verification and validation" mentioned refers to the embedded software that controls the hardware, not an AI algorithm for autonomous decision-making or analysis.
   • Missing for AI: No information.

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

   • Provided: For the "Performance test-bench," the ground truth was the physical measurement of the size (depth, width, length) of the ablation zone created on ex-vivo tissues.
   • Missing for AI: Not applicable in the context of this device.

7. The sample size for the training set:

   • Provided: Not applicable. This device is not an AI model that undergoes a "training set" in the machine learning sense. The "training" relates to the design and testing process of the engineering.
   • Missing for AI: No information.

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

   • Provided: Not applicable. See point 7.
   • Missing for AI: No information.

In summary, the provided document from the FDA is a 510(k) summary for a traditional electrosurgical device, not an AI-powered diagnostic or assistive medical device. As such, it details engineering and safety performance (electrical safety, EMC, biocompatibility, and physical ablation size) relative to predicate devices, rather than the complex clinical validation and ground truth establishment methods typical for AI/ML-based software products.

Ask a specific question about this device

HS AMICA is intended for coagulation (thermoablation) of soft tissues. Not for use in cardiac procedures.

HS AMICA (Apparatus for MICrowave Ablation) is an integrated system for interstitial thermoablation of soft tissues through controlled emission of microwaves. The system is composed by three interactive devices, namely: AMICA-GEN: a digitally controlled microwave power source, operating at 2450 MHz and delivering up to 100 W CW (continuous wave); it features a single output channel. AMICA-PROBE: an interstitial single-use coaxial microwave applicator, fed by AMICA--GEN. AMICA-PUMP: a peristaltic pump for convective applicator cooling through continuous circulation of liguid coolant, fully controlled by AMICA-GEN.

The provided text is a 510(k) summary for the HS AMICA Microwave Tissue Coagulation System. It describes the device's technical characteristics, its intended use, and its substantial equivalence to a predicate device. However, it does not contain any information regarding acceptance criteria, specific device performance data (like sensitivity, specificity, accuracy), sample sizes for test or training sets, data provenance, expert qualifications, ground truth establishment, or multi-reader multi-case (MRMC) studies.

The "Performance testing" mentioned on page 3 is a general statement: "Performance testing was executed to ensure that HS AMICA functions as intended and meets design specifications. Sufficient data were obtained to show that the device meets safety and effectiveness criteria and is substantially equivalent to the predicate device." This statement, while confirming testing was done, does not provide any of the quantitative details requested.

Therefore, I cannot fulfill your request for:

1. A table of acceptance criteria and the reported device performance
2. Sample sized used for the test set and the data provenance
3. Number of experts used to establish the ground truth for the test set and qualifications
4. Adjudication method
5. MRMC comparative effectiveness study details
6. Standalone performance details
7. Type of ground truth used
8. Sample size for the training set
9. How the ground truth for the training set was established

Ask a specific question about this device