Search Results

Ask a specific question about this device

The Ion™ Endoluminal System (Model IF1000) assists the user in navigating a catheter and endoscopic tools in the pulmonary tract using endoscopic visualization of the tracheobronchial tree for diagnostic and therapeutic procedures. The Ion™ Endoluminal System enables fiducial marker placement. It does not make a diagnosis and is not for pediatric use.

The PlanPoint™ Software uses patient CT scans to create a 3D plan of the lung and navigation pathways for use with the Ion™ Endoluminal System.

The Ion Endoluminal System, Model IF1000, is a software-controlled, electro-mechanical system designed to assist qualified physicians to navigate a catheter and endoscopic tools in the pulmonary tract using endoscopic visualization of the tracheobronchial tree for diagnostic and therapeutic procedures. It consists of a Planning Laptop with PlanPoint Software, a System Cart with System Software, a Controller, Instruments, and Accessories. The IF1000 Instruments include the Ion Fully Articulating Catheter, the Ion Peripheral Vision Probe, and the Flexision Biopsy Needles.

The Planning Laptop is a separate computer from the System Cart and Controller. A 3D airway model is generated from the patient's chest CT scan using the PlanPoint Software.

The System Cart contains the Instrument Arm, electronics for the follower portion of the servomechanism, and two monitors. The System Cart allows the user to navigate the Catheter Instrument with the Controller, which represents the leader-follower relationship. For optimal viewing, the physician can position the monitors in both vertical and horizontal axes.

The Controller is the user input device on the Ion Endoluminal System. It provides the controls to command insertion, retraction, and articulation of the Catheter. The Controller also has buttons to operate the Catheter control states.

The IF1000 System and PlanPoint Software are modified to enable Remote Software Updates from the Intuitive server via secure network communication.

The provided text does not contain specific acceptance criteria or details of a study setup (like sample sizes, expert qualifications, or ground truth establishment) to prove that the device meets defined acceptance criteria for its clinical performance.

The document is a 510(k) summary, which focuses on demonstrating substantial equivalence to a predicate device rather than providing a detailed clinical study report with specific performance metrics against pre-defined acceptance criteria.

The key points from the provided text are:

• Device: Ion Endoluminal System (IF 1000)
• Purpose: Assists users in navigating catheters and endoscopic tools in the pulmonary tract for diagnostic and therapeutic procedures, including fiducial marker placement. It does not make a diagnosis.
• Key Modification (subject of this 510(k)): Added support for Remote Software Updates.
• Claim: The subject device is "substantially equivalent" to its predicate device (K232984).

Here's a breakdown of why the requested information cannot be fully provided from the given text:

1. Table of Acceptance Criteria and Reported Device Performance:

• Missing: The document does not list specific clinical performance acceptance criteria (e.g., accuracy, sensitivity, specificity, or navigation success rates) for the device regarding its primary function (navigation in the pulmonary tract).
• Instead, it states: "The performance testing data confirmed that the device performs as intended to its specifications and meets its intended use." This is a general statement, not a reporting of specific performance metrics against quantitative acceptance criteria.
• The "performance data" section primarily discusses verification and validation (V&V) of the software (including cybersecurity) and animal testing for system design validation. It doesn't present clinical performance outcomes.

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

• Missing for clinical performance: The document mentions "simulated animal models" for "in-vivo animal testing" but does not specify the number of animals or cases in this test set.
• Data Provenance: The animal testing implies prospective data collection, but no country of origin is mentioned.

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

• Missing: Since no specific clinical performance study with human subjects (or a detailed animal study) requiring expert interpretation for ground truth is described with quantitative results, this information is not present. The animal study was performed to "assess the system performance" generally, not against a pre-established expert-adjudicated ground truth for a specific diagnostic or therapeutic outcome.

4. Adjudication Method for the Test Set:

• Missing: Not applicable as detailed expert-adjudicated clinical performance testing for the device's primary function is not described.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done:

• No: The document does not mention an MRMC study. The device's clearance is based on substantial equivalence, primarily addressing a software update feature (remote software updates), rather than a comparative effectiveness study of its core functionality or human-AI interaction.
• The document implies that "Changes to the subject device do not affect previously identified critical tasks," and usability testing refers back to the predicate device's data. This suggests no new human factors or clinical performance studies related to reader improvement were conducted for this specific 510(k).

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

• Not explicitly stated for the core navigation functionality: The device is an "Endoluminal System" that "assists the user," implying a human-in-the-loop system. The PlanPoint™ Software creates a 3D plan, which is a software function, but its performance metrics (e.g., accuracy of path planning) are not detailed as standalone acceptance criteria. The software V&V confirms it "meets design specifications and user needs," but doesn't break out standalone quantitative performance.

7. The Type of Ground Truth Used:

• Implied for Animal Testing (Design Validation): The animal testing was for "design validation" and to "assess the system performance." It doesn't specify how "ground truth" was established for precise navigation outcomes within the animal models (e.g., post-mortem pathology, direct visualization, etc.). The focus seems to be on whether the system performed "effectively" generally, rather than hitting a specific, pre-quantified ground truth target.

8. The Sample Size for the Training Set:

• Missing: The document refers to "software verification and validation testing" including "unit, subsystem integration, and system level testing" and "regression testing." This refers to software development and testing phases, not typically a separate "training set" in the context of deep learning or AI model development that would require a distinct sample size. While the PlanPoint software creates 3D plans from CT scans, there's no mention of a machine learning component that requires a specific training dataset and its associated ground truth.

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

• Missing: Not applicable since a "training set" for an AI or machine learning model, with its corresponding ground truth establishment, is not described.

Summary of what is present:

• Acceptance Criteria Mention (General): The document generally states that "performance testing data demonstrates that the subject device is substantially equivalent to the predicate device and that the design output meets the design input requirements."
• Study Types Mentioned:
  • Software Verification and Validation (including unit, subsystem integration, system level, and regression testing).
  • Cybersecurity Testing.
  • Animal Testing (in-vivo, simulated use conditions) for "system design validation."
  • Usability Testing (references prior study for predicate as no new critical tasks identified).
• Rationale for Substantial Equivalence: The primary rationale for this 510(k) is that the subject device has the "same intended use, indications for use, operating principles, and similar technological characteristics" as the predicate device, with the key modification being a remote software update feature that "does not raise different questions of safety and effectiveness." The testing performed (software V&V, cybersecurity, and animal testing) was to confirm this, not to prove specific clinical performance metrics against quantitative acceptance criteria for navigation efficacy or diagnostic accuracy.

Ask a specific question about this device

The Ion™ Endoluminal System (Model IF1000) assists the user in navigating a catheter and endoscopic tools in the pulmonary tract using endoscopic visualization of the tracheobronchial tree for diagnostic and therapeutic procedures. The Ion™ Endoluminal System enables fiducial marker placement. It does not make a diagnosis and is not for pediatric use.

The Flexision™ Biopsy Needle is used with the Ion™ Endoluminal System to biopsy tissue from a target area in the lung.

The PlanPoint™ Software uses patient CT scans to create a 3D plan of the lung and navigation pathways for use with the Ion™ Endoluminal System.

The Ion™ Endoluminal System (hereinafter referred to as the Ion System) is a software-controlled, electromechanical system designed to assist qualified physicians to navigate a catheter and endoscopic tools in the pulmonary tract using endoscopic visualization of the tracheobronchial tree for diagnostic and therapeutic procedures. It consists of a Planning Laptop with PlanPoint™ Software, a System Cart with System Software, a Controller, Instruments, and Accessories. The Ion System Instruments include the Ion™ Fully Articulating Catheter, the Ion™ Peripheral Vision Probe, and the Flexision™ Biopsy Needles. Accessories such as the Catheter Guide, Vision Probe Adapter, Suction Adapter, Swivel Connector, and Vision Probe Bag facilitate use of the Ion System Instruments.

The provided FDA 510(k) summary for the Ion™ Endoluminal System (Ion™ Fully Articulating Catheter) (IF1000) focuses on demonstrating substantial equivalence for an increase in the device's use life from 5 to 8 uses. This is not a typical submission for a novel AI/ML-based medical device where performance data relates to diagnostic accuracy, sensitivity, or specificity of an AI algorithm.

Therefore, the information required for explaining an AI device's acceptance criteria and proven performance (specifically sections regarding AI/ML performance, sample sizes for test/training sets, expert consensus, MRMC studies, etc.) is not present in this document. This submission primarily relies on bench testing, cleaning validation, and biocompatibility studies to justify the increased reprocessing cycles.

However, I can extract the acceptance criteria and the reports of meeting those criteria based on the information provided, framed within the context of a device durability/reuse validation:

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size: Not explicitly stated in terms of number of units tested. The documentation refers to "testing" in general.
• Data Provenance: Not applicable in the context of clinical data for AI performance. The tests are laboratory/bench-based.

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

• Not Applicable: This submission does not involve human expert interpretation of data to establish ground truth for a diagnostic AI. The "ground truth" here is the adherence to engineering and safety standards validated through laboratory testing.

4. Adjudication Method for the Test Set

• Not Applicable: There is no adjudication process described as this is not a study assessing human perception or diagnostic accuracy. Performance is determined by passing predefined engineering and biological safety standards.

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

• No: An MRMC study was not performed as this is not a submission for an AI-assisted diagnostic or therapeutic device that impacts human reader performance.

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

• No (Not Applicable): This is not a submission for an AI algorithm. The "System Software" mentioned is likely operating software for the robotic system, not a diagnostic AI.

7. The Type of Ground Truth Used

• Engineering and Safety Standards: The "ground truth" for this device's performance validation is its adherence to established engineering specifications (functional performance over repeated uses) and recognized safety standards (cleaning efficacy, biocompatibility).

8. The Sample Size for the Training Set

• Not Applicable: This document describes validation testing for an increased use life, not the development or training of an AI model.

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

• Not Applicable: No AI training set is discussed or implied.

Summary of why the requested AI-specific information is not present:

The FDA 510(k) submission K240135 for the Ion™ Endoluminal System (Ion™ Fully Articulating Catheter) (IF1000) is specifically for an increase in the device's reusability/use life (from 5 to 8 uses) of an existing cleared device. It primarily relies on non-clinical performance data (bench testing, cleaning validation, biocompatibility) to demonstrate that increasing the use life does not introduce new safety or effectiveness concerns. This is fundamentally different from a submission for a novel AI/ML-based medical device that would require extensive clinical performance data, ground truth establishment, and often comparative studies with human readers.

Ask a specific question about this device

The Ion™ Endoluminal System (Model IF1000) assists the user in navigating a catheter and endoscopic tools in the pulmonary tract using endoscopic visualization of the tracheobronchial tree for diagnostic and therapeutic procedures. The Ion™ Endoluminal System enables fiducial marker placement. It does not make a diagnosis and is not for pediatric use.

The PlanPoint™ Software uses patient CT scans to create a 3D plan of the lung and navigation pathways for use with the Ion™ Endoluminal System.

The Ion™ Endoluminal System, Model IF1000, is a software-controlled, electromechanical system designed to assist qualified physicians to navigate a catheter and endoscopic tools in the pulmonary tract using endoscopic visualization of the tracheobronchial tree for diagnostic and therapeutic procedures. It consists of a Planning Laptop with PlanPoint™ Software, a System Cart with System Software, a Controller, Instruments, and Accessories. The IF1000 Instruments include the Ion™ Fully Articulating Catheter, the Ion™ Peripheral Vision Probe, and the Flexision™ Biopsy Needles.

The Planning Laptop is a separate computer from the System Cart and Controller. A 3D airway model is generated from the patient's chest CT scan using the PlanPoint™ Software.

The System Cart contains the Instrument Arm, electronics for the follower portion of the servomechanism, and two monitors. The System Cart allows the user to navigate the Catheter Instrument with the Controller, which represents the leader-follower relationship. For optimal viewing, the physician can position the monitors in both vertical and horizontal axes.

The Controller is the user input device on the Ion™ Endoluminal System. It provides the controls to command insertion, retraction, and articulation of the Catheter. The Controller also has buttons to operate the Catheter control states.

The Ion Endoluminal System enables optional Network and Virtual Reference features, streamlined mid-procedure restart, and enhances the control algorithm to provide an additional safety margin.

The provided text is a 510(k) summary for the Ion Endoluminal System (Model IF1000). While it describes software verification and validation, cybersecurity testing, and animal testing to demonstrate substantial equivalence to a predicate device, it does not contain specific acceptance criteria or detailed study results for an AI/algorithm's performance.

The device is primarily an electromechanical system with software for navigation and planning. The "PlanPoint™ Software" uses patient CT scans to create 3D plans, which is a software function, but the document does not treat it as a standalone AI algorithm that makes diagnoses or performs automated tasks requiring specific performance metrics like sensitivity, specificity, or AUC against a defined ground truth.

Therefore, I cannot provide the requested information in the format of a table outlining acceptance criteria and reported device performance for an AI algorithm, nor can I detail specific ground truth establishment, sample sizes for training/test sets, or information regarding multi-reader multi-case studies, as this information is not present in the provided document.

The document focuses on demonstrating that modifications to an existing device (adding support for optional network and virtual reference features, and streamlining mid-procedure restart) do not raise new questions of safety or effectiveness, and that the subject device remains substantially equivalent to its predicate.

In summary, the document you provided does not describe the kind of AI performance study details you are asking for.

Ask a specific question about this device

The Ion™ Endoluminal System (Model IF1000) assists the user in navigating a catheter and endoscopic tools in the pulmonary tract using endoscopic visualization of the tracheobronchial tree for diagnostic and therapeutic procedures. The Ion™ Endoluminal System enables fiducial marker placement. It does not make a diagnosis and is not for pediatric use.

The Flexision™ Biopsy Needle is used with the Ion™ Endoluminal System to biopsy tissue from a target area in the lung.

The PlanPoint™ Software uses patient CT scans to create a 3D plan of the lung and navigation pathways for use with the Ion™ Endoluminal System.

The Ion™ Endoluminal System, Model IF1000, is a software-controlled, electromechanical system designed to assist qualified physicians to navigate a catheter and endoscopic tools in the pulmonary tract using endoscopic visualization of the tracheobronchial tree for diagnostic and therapeutic procedures. It consists of a Planning Laptop with PlanPoint™ Software, a System Cart with System Software, a Controller, Instruments, and Accessories. The IF1000 Instruments include the Ion™ Fully Articulating Catheter, the Ion™ Peripheral Vision Probe, and the Flexision™ Biopsy Needles.

The Planning Laptop is a separate computer from the System Cart and Controller. A 3D airway model is generated from the patient's chest CT scan using the PlanPoint™ Software.

The System Cart contains the Instrument Arm, electronics for the slave portion of the servomechanism, and two monitors. The System Cart allows the user to navigate the Catheter Instrument with the Controller, which represents the master slave relationship. For optimal viewing, the physician can position the monitors in both vertical and horizontal axes.

The Controller is the user input device on the Ion™ Endoluminal System. It provides the controls to command insertion, retraction, and articulation of the Catheter. The Controller also has buttons to operate the Catheter control states.

The IF1000 System software is modified to optionally receive an intra-procedural cone beam CT image to enhance the virtual target location based on user input.

The provided text is a 510(k) summary for the Intuitive Surgical Ion™ Endoluminal System (Model IF1000). This document focuses on demonstrating substantial equivalence to a predicate device (K202370) rather than presenting a detailed clinical study for a novel AI algorithm's performance against specific acceptance criteria.

Therefore, much of the requested information regarding "acceptance criteria," "study that proves the device meets the acceptance criteria," "sample size for the test set and data provenance," "number of experts and their qualifications," "adjudication method," "MRMC study," "standalone performance," "type of ground truth," "training set sample size," and "ground truth for training set" is not explicitly available in the provided document.

The document primarily discusses software verification and validation, cybersecurity testing, and animal testing to demonstrate that the modified device is still substantially equivalent to the predicate device and performs as intended. It does not describe a clinical study measuring the performance of an AI-driven diagnostic or assistive algorithm against specific clinical endpoints or human expert performance.

Here's a breakdown of what can be gleaned from the text, and where information is missing:

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

• Acceptance Criteria: Not explicitly stated as quantifiable metrics for clinical performance (e.g., sensitivity, specificity, accuracy). The acceptance criteria mentioned are related to software verification and validation, cybersecurity, and the general demonstration that the "design output meets the design input requirements" and "the System performs effectively according to its intended use."
• Reported Device Performance: Instead of performance metrics, the document reports:
  • "The software testing results demonstrate the System meets design specifications and user needs."
  • "The cybersecurity verification and validation test results demonstrate the adequacy of the implemented cybersecurity controls."
  • "The test results demonstrate that the System performs effectively according to its intended use and does not raise different questions of safety or effectiveness."

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

• Test Set Sample Size: Not specified for any performance evaluation in terms of patient numbers or clinical cases. The "animal testing" refers to an "in-vivo animal testing" but doesn't quantify the number of animals or trials.
• Data Provenance: The animal testing is described as a "simulated animal model." There's no mention of human patient data, its origin (country), or whether it was retrospective or prospective for performance testing.

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

• Not applicable/Discussed. This document does not describe a study where ground truth was established by human experts for the purpose of validating an AI's performance.

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

• Not applicable/Discussed.

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 is described. The device assists in navigation and tool placement, it is not an AI diagnostic tool that human readers would interpret assisted by AI.

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

• The device is a system that "assists the user in navigating," implying human-in-the-loop operation. No standalone algorithm performance is described. The software V&V confirms the system meets design specifications, but not in terms of standalone clinical performance metrics.

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

• Not explicitly defined in the context of clinical performance. The validation relies on "design specifications," "user needs," and "intended use" verified through software testing and animal models.

8. The sample size for the training set:

• Not applicable/Discussed. This document is about a 510(k) submission for a modified device, not the development and training of a novel AI algorithm with a training set. The device uses "System Software" and "PlanPoint™ Software" but the document doesn't detail their development or training data.

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

• Not applicable/Discussed.

In summary, the provided 510(k) summary focuses on demonstrating substantial equivalence of a modified medical device to a previously cleared predicate device. It does so by describing software verification and validation, cybersecurity testing, and limited animal testing to show the modifications do not raise new questions of safety or effectiveness. It does not provide the type of detailed performance study data typically associated with the rigorous evaluation of a novel AI algorithm against specific clinical acceptance criteria, expert ground truth, or human performance metrics.

Ask a specific question about this device

The Ion™ Endoluminal System (Model IF1000) assists the user in navigating a catheter and endoscopic tools in the pulmonary tract using endoscopic visualization of the tracheobronchial tree for diagnostic and therapeutic procedures. The Ion™ Endoluminal System enables fiducial marker placement. It does not make a diagnosis and is not for pediatric use.

The Flexision™ Biopsy Needle is used with the Ion™ Endoluminal System to biopsy tissue from a target area in the lung.

The PlanPoint™ Software uses patient CT scans to create a 3D plan of the lung and navigation pathways for use with the Ion™ Endoluminal System.

The Ion™ Endoluminal System (Model IF1000) is a software-controlled, electromechanical system designed to assist qualified physicians to navigate a catheter and endoscopic tools in the pulmonary tract using endoscopic visualization of the tracheobronchial tree for diagnostic and therapeutic procedures. It consists of a Planning Laptop with PlanPoint™ Software, a System Cart with System Software, a Controller, Instruments, and Accessories. The Model IF1000 Instruments include the Ion™ Fully Articulating Catheter, the Ion™ Peripheral Vision Probe, and the Flexision™ Biopsy Needles. Accessories such as the Catheter Guide, Vision Probe Adapter, Suction Adapter, Swivel Connector, and Vision Probe Bag facilitate use of the Model IF1000 Instruments.

The provided document is a 510(k) summary for the Ion™ Endoluminal System (specifically the Ion™ Fully Articulating Catheter and the Ion™ Peripheral Vision Probe). The submission primarily focuses on changes to the reprocessing methods for these devices, introducing an alternative automated cleaning process and reducing rinsing steps for the existing manual cleaning process. It does not describe a study involving an AI algorithm in the traditional sense of diagnostic or predictive performance.

Therefore, the requested information regarding acceptance criteria and study details for AI performance (such as sample size for test sets, data provenance, expert qualifications, adjudication methods, MRMC studies, standalone performance, and training set information) is largely not applicable to this document. The "device" in this context refers to the physical medical instruments, and the "performance" being evaluated is related to their reprocessability and safety after cleaning, not an AI's analytical capabilities.

However, I can extract the acceptance criteria and performance data related to the reprocessing validation and biocompatibility aspects, as these are the core performance assessments presented in this 510(k) summary.

Acceptance Criteria and Device Performance (Related to Reprocessing and Biocompatibility)

The device in question is the Ion™ Endoluminal System (Ion™ Fully Articulating Catheter and Ion™ Peripheral Vision Probe). The study described relates to validating new reprocessing methods (automated cleaning and reduced manual rinsing steps) for these devices.

Due to the nature of this 510(k) submission, which focuses on device reprocessing validation, many of the typical AI-related study components (like expert ground truth, MRMC, training sets) are not present.

1. Table of Acceptance Criteria and Reported Device Performance

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

• Reprocessing Validation (Cleaning Efficacy): The document does not specify the exact "sample size" in terms of number of devices tested for cleaning efficacy. It states that "AER equipment were validated" and "Testing was performed on the Model IF1000 devices subjected to the automated cleaning process."
• Biocompatibility (TOC Testing): Similar to reprocessing, the exact number of devices tested for TOC is not specified, but it was performed "on the Model IF1000 devices."
• Usability Testing: The document does not specify the number of users or sessions in the human factors study.
• Data Provenance: The studies described are prospective validation studies conducted by the manufacturer for the specific purpose of this submission. The origin of "data" in terms of patient information is not relevant here as these are laboratory and human factors studies, not clinical trials on patient data.

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

This information is not applicable as the "test set" in this context refers to devices undergoing reprocessing and human factors testing, not an AI algorithm being evaluated against expert-annotated medical image data. The "ground truth" for cleaning validation is objective laboratory measurement against standards, and for usability, it's successful task completion by trained users.

4. Adjudication Method for the Test Set

This information is not applicable for the reasons stated above. Adjudication methods like 2+1 or 3+1 typically apply to resolving discrepancies in expert labeling for AI ground truth, which is not relevant here.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, and the effect size of how much human readers improve with AI vs without AI assistance

No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not done. This document does not describe the evaluation of an AI algorithm assisting human readers. It focuses on the reprocessing of physical instruments.

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

No, a standalone algorithm performance study was not done. This submission does not pertain to an AI algorithm.

7. The type of ground truth used

• Reprocessing Validation: The ground truth for cleaning efficacy was established through objective laboratory measurements of residual soil levels (e.g., proteins, hemoglobin) against pre-defined limits, as guided by AAMI standards (TIR12, TIR30).
• Biocompatibility: The ground truth for biocompatibility was established through objective laboratory measurements of Total Organic Carbon (TOC) residuals, evaluated against acceptable limits defined by ISO 10993-1.
• Usability Testing: The ground truth was based on participants successfully and safely completing the specified reprocessing tasks as described in the updated instructions.

8. The Sample Size for the Training Set

This information is not applicable. This document does not describe an AI system, and therefore there is no "training set" in the context of machine learning.

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

This information is not applicable as there is no AI training set discussed in this document.

Ask a specific question about this device

The Ion™ Endoluminal System (Model IF1000) assists the user in navigating a catheter and endoscopic tools in the pulmonary tract using endoscopic visualization of the tracheobronchial tree for diagnostic and therapeutic procedures. The Ion™ Endoluminal System enables fiducial marker placement. It does not make a diagnosis and is not for pediatric use.

The Flexision™ Biopsy Needle is used with the Ion™ Endoluminal System to biopsy tissue from a target area in the lung,

The PlanPoint™ Software uses patient CT scans to create a 3D plan of the lung and navigation pathways for use with the Ion™ Endoluminal System.

The Ion™ Endoluminal System, Model IF1000, is a software-controlled, electromechanical system designed to assist qualified physicians to navigate a catheter and endoscopic tools in the pulmonary tract using endoscopic visualization of the tracheobronchial tree for diagnostic and therapeutic procedures. It consists of a Planning Laptop with PlanPoint™ Software, a System Cart with System Software, a Controller, Instruments, and Accessories. The IF1000 Instruments include the Ion™ Fully Articulating Catheter, the Ion™ Peripheral Vision Probe, and the Flexision™ Biopsy Needles.

The Planning Laptop is a separate computer from the System Cart and Controller. A 3D airway model is generated from the patient's chest CT scan using the PlanPoint™ Software.

The System Cart contains the Instrument Arm, electronics for the slave portion of the servomechanism, and two monitors. The System Cart allows the user to navigate the Catheter Instrument with the Controller, which represents the master slave relationship. For optimal viewing, the physician can position the monitors in both vertical and horizontal axes.

The Controller is the user input device on the Ion™ Endoluminal System. It provides the controls to command insertion, retraction, and articulation of the Catheter. The Controller also has buttons to operate the Catheter control states.

The Ion™ Endoluminal System enables automatic device logs retrieval via the network and connects to a hospital networked Picture Archiving and Communication System (PACS).

The provided document describes a 510(k) submission for the Ion™ Endoluminal System, Model IF1000, which has undergone modifications from its predicate device (K182188). The key changes relate to networking capabilities for automatic log retrieval and accessing CT scans directly from hospital networked PACS.

Here's an analysis of the acceptance criteria and supporting studies based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state quantitative acceptance criteria or assign a specific "device performance" metric for the modified features in a structured table. Instead, it relies on demonstrating compliance with standards and successful completion of verification and validation activities. The primary acceptance criteria for the modifications (network communication and PACS access) are implied to be functional correctness, reliability, and security, as demonstrated through various tests.

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

• Software Verification and Validation, Bench Testing, Cybersecurity Testing: The document does not specify a numerical sample size for these tests. The nature of these tests (e.g., unit tests, integration tests, system tests, penetration tests for cybersecurity) typically involves comprehensive coverage rather than a statistical sample size of cases in the way that clinical studies do.
• Animal Testing: The document mentions "animal testing was performed," but does not specify the number of animals or the type of animal used. The provenance is implied to be experimental (simulated use conditions).
• The document does not mention the use of retrospective or prospective data sets from human patients for the evaluation of the new features. The evaluation focuses on technical performance and safety of the modified system.

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

The document does not describe the use of experts to establish "ground truth" for the test sets in the context of diagnostic accuracy, as the modifications are related to system functionality, networking, and safety rather than a diagnostic algorithm. The ground truth for functional tests would be the expected system behavior, and for cybersecurity, it would be adherence to security best practices and robustness against identified threats.

4. Adjudication Method for the Test Set

Not applicable, as no human-expert-based ground truth establishment or adjudication is described for the technical tests performed for this submission.

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

No MRMC comparative effectiveness study was mentioned in this document. The submission focuses on demonstrating substantial equivalence of the modified system, not on comparing reader performance with and without AI assistance.

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

While the PlanPoint™ Software uses CT scans to create 3D plans and navigation pathways, this document primarily discusses the system's ability to access these CT scans via PACS and automatic log retrieval. It does not provide details about a standalone performance study of the PlanPoint™ Software's algorithmic accuracy in path planning or 3D reconstruction. The animal testing assessed "system performance" under simulated use, which would include the integrated functionality, but not an isolated algorithm-only performance metric.

7. Type of Ground Truth Used

• For Software Verification and Validation, Bench Testing: The ground truth is implicit in the design specifications and user needs. The tests verified that the system's outputs matched the expected behavior defined by these specifications.
• For Cybersecurity Testing: Ground truth is defined by established cybersecurity standards, best practices, and the identified vulnerability landscape.
• For Animal Testing: The ground truth is the successful demonstration of the "Ion™ Endoluminal System performs according to its intended use" in a simulated environment.
• No pathology, clinical outcomes data, or expert consensus (in a diagnostic sense) ground truth is described as being used for the evaluation of the modifications in this submission.

8. Sample Size for the Training Set

The document does not describe any machine learning or AI models being "trained" as part of the modifications being evaluated. Therefore, there is no mention of a training set sample size. The PlanPoint™ Software uses patient CT scans for planning, but it's not described as a learning algorithm that requires a "training set" in the conventional AI/ML sense.

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

Not applicable, as no training set for a machine learning model is described in this document.

Ask a specific question about this device

The Ion™ Endoluminal System (Model IF1000) assists the user in navigating a catheter and endoscopic tools in the pulmonary tract using endoscopic visualization of the tracheobronchial tree for diagnostic and therapeutic procedures. The Ion™ Endoluminal System enables fiducial marker placement. It does not make a diagnosis and is not for pediatric use.

The Flexision™ Biopsy Needle is used with the Ion™ Endoluminal System to biopsy tissue from a target area in the lung.

The PlanPoint™ Software uses patient CT scans to create a 3D plan of the lung and navigation pathways for use with the Ion™ Endoluminal System.

The Ion™ Endoluminal System (Model IF1000) is a software-controlled, electromechanical system designed to assist qualified physicians to navigate a catheter and endoscopic tools in the pulmonary tract using endoscopic visualization of the tracheobronchial tree for diagnostic and therapeutic procedures. It consists of a Planning Laptop with PlanPoint™ Software, a System Cart with System Software, a Controller, Instruments, and Accessories. The Model IF 1000 Instruments include the Ion™ Fully Articulating Catheter, the Ion™ Peripheral Vision Probe, and the Flexision™ Biopsy Needles. Accessories such as the Catheter Guide, Vision Probe Adapter, Suction Adapter, and Swivel Connector facilitate use of the Model IF1000 Instruments.

This document (K201146) is a 510(k) premarket notification for a medical device (Ion Endoluminal System) and primarily addresses updates to reprocessing instructions, not the initial performance or efficacy of the device itself. Therefore, many standard elements of AI/ML device performance studies (like MRMC studies, training set details, or standalone algorithm performance) are not applicable to this submission.

The "acceptance criteria" and "study that proves the device meets the acceptance criteria" in this context refer specifically to the reprocessing validation studies.

Acceptance Criteria and Study Proving Device Meets Acceptance Criteria for Reprocessing Validation

1. Table of Acceptance Criteria and Reported Device Performance

Note: The document provides a high-level summary that "All testing passed the predetermined acceptance criteria." Specific quantitative metrics for soil/bioburden reduction or microbial inactivation are not detailed in this public summary, but would have been part of the full submission.

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

• Sample Size: Not explicitly stated for each test in the provided summary. Reprocessing validation studies typically involve a set number of device cycles (e.g., typically 50 or 100 cycles) to demonstrate cleaning and disinfection efficacy over the expected lifespan or number of uses.
• Data Provenance: The studies were laboratory-based reprocessing validation tests. No patient data or clinical data is relevant to this specific submission.

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

• Not Applicable. For reprocessing validation, "ground truth" is established by laboratory standards and established test methods (e.g., AAMI TIR12:2010, AAMI TIR30:2011/(R)2016) which define acceptable levels of residuals or microbial inactivation, not by expert consensus on clinical data. The tests are objective measurements.

4. Adjudication Method for the Test Set

• Not Applicable. As per point 3, this is laboratory testing against objective standards, not a subjective assessment requiring adjudication.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done

• No. An MRMC study is relevant for evaluating the impact of an AI system on human reader performance (e.g., radiologists interpreting images). This submission is about reprocessing instructions for a physical device, not an AI/ML algorithm.

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

• No. This is not an AI/ML algorithm submission.

7. The Type of Ground Truth Used

• For cleaning: Quantitative measurement of residual protein, hemoglobin, carbohydrates, or other organic matter (simulated soil) after cleaning.
• For disinfection: Quantitative measurement of microbial inactivation (log reduction) after the disinfection process using specified test microorganisms.
• The "ground truth" is the established scientific and regulatory thresholds for effective cleaning and disinfection, as outlined in the AAMI standards.

8. The Sample Size for the Training Set

• Not Applicable. There is no "training set" in the context of reprocessing validation as this is not an AI/ML model.

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

• Not Applicable. See point 8.

Ask a specific question about this device

The Ion™ Endoluminal System (Model IF1000) assists the user in navigating a catheter and endoscopic tools in the pulmonary tract using endoscopic visualization of the tracheobronchial tree for diagnostic and therapeutic procedures. The Ion™ Endoluminal System enables fiducial marker placement. It does not make a diagnosis and is not for pediatric use.

The Flexision™ Biopsy Needle is used with the Ion™ Endoluminal System to biopsy tissue from a target area in the lung.

The PlanPoint™ Software uses patient CT scans to create a 3D plan of the lung and navigation pathways for use with the Ion™ Endoluminal System.

The Ion™ Endoluminal System (Model IF1000) is a software-controlled, electromechanical system designed to assist qualified physicians to navigate a catheter and endoscopic tools in the pulmonary tract using endoscopic visualization of the tracheobronchial tree for diagnostic and therapeutic procedures. It consists of a Planning Laptop with PlanPoint™ Software, a System Cart with System Software, a Controller, Instruments, and Accessories. The Model IF 1000 Instruments include the Ion™ Fully Articulating Catheter, the Ion™ Peripheral Vision Probe, and the Flexision™ Biopsy Needles. Accessories such as the Catheter Guide, Vision Probe Adapter, Suction Adapter, and Swivel Connector facilitate use of the Model IF1000 Instruments.

The provided text is a 510(k) Summary for the Intuitive Surgical Ion™ Endoluminal System (Model IF1000). This submission specifically focuses on adding an alternative automated microbicidal reprocessing method for certain components (Catheter and Vision Probe) compared to the previously cleared manual method.

Therefore, the acceptance criteria and study proving the device meets them are related to demonstrating that this new reprocessing method does not negatively impact the device's safety and effectiveness and that the device, when reprocessed by the automated method, remains substantially equivalent to the device reprocessed by the manual method.

1. Table of Acceptance Criteria and Reported Device Performance:

The document broadly states that "All testing passed the predetermined acceptance criteria" for each category. Specific numerical acceptance criteria or performance metrics are not provided in this summary. Instead, the performance is reported as meeting the criteria.

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

• Reprocessing Validation: "3 automated reprocessing equipment were validated." The sample size for devices reprocessed with each equipment is not specified (e.g., number of cycles, number of devices).
• Biocompatibility: "Testing was performed on the Model IF1000 devices subjected to each representative automated reprocessing equipment." Specific sample size not detailed.
• Bench Testing: The document lists "Design Verification Testing" and "Reliability Testing" for both the Catheter and Vision Probe. Specific sample sizes for each test are not detailed.
• Usability Testing: The sample size of users involved in the human factors study is not provided.
• Data Provenance: Not explicitly stated, but implicitly, given the nature of a 510(k) submission for a US market, the testing would be conducted within a controlled environment compliant with US regulatory standards. It's a prospective study designed to validate the new reprocessing method for market clearance.

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

• Not Applicable in this Context: This submission is focused on the device's ability to withstand a new reprocessing method and maintain its original safety and performance characteristics, rather than making a diagnostic claim or requiring human expert interpretation for "ground truth" in the typical sense of an AI/ML device study.
• The "ground truth" here is objective: whether the device is successfully disinfected/sterilized, retains its functionality, and is safe for patient contact. This is established through validated testing protocols, not expert consensus on diagnostic images.

4. Adjudication Method for the Test Set:

• Not Applicable (or Implicit/Internal): Since the studies described are primarily engineering and reprocessing validation, they involve objective measurements against predetermined acceptance criteria. There's no mention of an external adjudication panel of experts for subjective interpretation, as might be found in a clinical imaging study involving human readers. Any "adjudication" would be internal to the testing process, ensuring that results consistently meet the established pass/fail criteria.

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

• No: An MRMC comparative effectiveness study was not done. This type of study is typically performed to evaluate the impact of an AI algorithm on human reader performance for diagnostic tasks. This 510(k) is for a physical device with a new reprocessing method validation, not for an AI/ML diagnostic aid.

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

• Not Applicable/Implicit: This is not an AI/ML device being evaluated for standalone performance. The "Ion Endoluminal System" does have software (PlanPoint™ and System Software), but the focus of this 510(k) is on the reprocessing of physical instruments. The software's performance itself (e.g., navigation accuracy) was likely evaluated in the original K182188 clearance. Bench testing for the physical components did evaluate their functional performance after reprocessing (which could be considered a form of "standalone" evaluation of the physical device's characteristics).

7. The Type of Ground Truth Used:

• Objective, Measured Parameters:
  • Reprocessing Validation: Microbial load reduction (e.g., sterilization/disinfection effectiveness confirmed by microbiological assays).
  • Biocompatibility: Absence of cytotoxicity (confirmed by cellular assays).
  • Bench Testing: Device functional specifications (e.g., mechanical integrity, electrical performance, dimensional accuracy) met after reprocessing (confirmed by engineering measurements and tests).
  • Usability Testing: Successful completion of tasks by intended users as per instructions (confirmed by observation and task analysis).

8. The Sample Size for the Training Set:

• Not Applicable: This submission does not pertain to an AI/ML device that requires a training set of data. The device itself is a bronchoscope system.

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 be established for it in this context.

Ask a specific question about this device

The Ion™ Endoluminal System (Model IF1000) assists the user in navigating a catheter and endoscopic tools in the pulmonary tract using endoscopic visualization of the tracheobronchial tree for diagnostic and therapeutic procedures. The Ion™ Endoluminal System enables fiducial marker placement. It does not make a diagnosis and is not for pediatric use.

The Flexision™ Biopsy Needle is used with the Ion™ Endoluminal System to biopsy tissue from a target area in the lung.

The PlanPoint™ Software uses patient CT scans to create a 3D plan of the lung and navigation pathways for use with the Ion™ Endoluminal System.

The Ion™ Endoluminal System, Model IF1000, is a software-controlled, electromechanical system designed to assist qualified physicians to navigate a catheter and endoscopic tools in the pulmonary tract using endoscopic visualization of the tracheobronchial tree for diagnostic and therapeutic procedures. It consists of a Planning Laptop with PlanPoint™ Software, a System Cart with System Software, a Controller, Instruments, and Accessories. The IF1000 Instruments include the Ion™ Fully Articulating Catheter, the Ion™ Peripheral Vision Probe, and the Flexision™ Biopsy Needles.

The Planning Laptop is a separate computer from the System Cart and Controller. A 3D airway model is generated from the patient's chest CT scan using the PlanPoint™ Software.

The System Cart contains the Instrument Arm, electronics for the slave portion of the servomechanism, and two monitors. The System Cart allows the user to navigate the Catheter Instrument with the Controller, which represents the master/slave relationship. For optimal viewing, the physician can position the monitors in both vertical and horizontal axes.

The Controller is the user input device on the Ion™ Endoluminal System. It provides the controls to command insertion, retraction, and articulation of the Catheter. The Controller also has buttons to operate the Catheter control states.

The Catheter Instrument has a tool channel compatible with the Peripheral Vision Probe. Flexision™ Biopsy Needles, and third-party tools. The Vision Probe provides direct visualization of the patient's airways during navigation. Accessories such as the Catheter Guide, Vision Probe Adapter, Suction Adapter, and Swivel Connector facilitate use of the IF1000 Instruments.

The provided text describes the 510(k) summary for the Ion™ Endoluminal System and Flexision™ Biopsy Needle. It details performance data but does not include a specific table of acceptance criteria with reported device performance or a standalone study with quantitative metrics for accuracy, sensitivity, or specificity.

However, I can extract information related to the device's validation and the types of studies conducted.

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly provide a table of acceptance criteria with specific numerical performance metrics (e.g., sensitivity, specificity, accuracy). Instead, it states that "validation and verification testing demonstrate that the subject devices are equivalent to the predicate devices in terms of safety and effectiveness." and that "the design output meets the design input requirements" and "the System meets design specifications and user needs."

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

The document mentions "animal and cadaver testing" and a "summative validation study" for human factors.

• Animal and Cadaver Testing:

  • Sample Size: Not explicitly stated. The text notes "Cadavers" (plural) and "Live animal models" (plural).
  • Data Provenance: Prospective (simulated use conditions). No specific country of origin is mentioned, but typically, these studies are conducted within the submitting company's or collaborating research facilities.

• Human Factors Evaluation (Summative Validation Study):

  • Sample Size: Not explicitly stated. It involved "intended user groups."
  • Data Provenance: Prospective (simulated bronchoscopy suite).

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

The document does not specify the number of experts or their qualifications for establishing ground truth in the animal/cadaver testing or human factors evaluation. It implies that these studies were overseen by qualified personnel as part of the overall design verification and validation process. For the human factors study, "intended user groups" were involved, suggesting participation from physicians or clinical staff who would typically perform such procedures.

4. Adjudication Method for the Test Set

The document does not describe a formal adjudication method (e.g., 2+1, 3+1) for establishing ground truth in the performance studies mentioned. The evaluation of "safety or performance" and "accuracy" in animal/cadaver models, and the assessment of "high-risk use scenarios and essential tasks" in the human factors study, likely relied on expert observation and assessment without a multi-reader adjudication process detailed here.

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

No MRMC comparative effectiveness study is described in this document. The focus is on demonstrating the device's safety, effectiveness, and substantial equivalence to predicate devices, rather than a direct comparison of human reader performance with and without AI assistance.

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

The device is an "endoluminal system" that "assists the user in navigating a catheter and endoscopic tools." The description of the System Cart's "master/slave relationship" with the Controller and the "3D guided navigation view" indicates it is a human-in-the-loop system. While "Software Verification and Validation" was performed, a standalone algorithm-only performance study (without human-in-the-loop) for a clinical outcome is not explicitly discussed. The PlanPoint™ Software "creates a 3D plan... and navigation pathways," which is an algorithmic function, and its verification would have been part of the software testing. However, its performance as an aid to the human user is part of the integrated system.

7. The Type of Ground Truth Used

• Animal and Cadaver Testing: The ground truth for these studies would have been established through direct observation during the simulated procedures, potentially involving anatomical dissection, histological analysis of biopsied tissue (if sample quality was assessed), and clinical assessment by veterinarians or physicians during animal studies for safety and performance.
• Human Factors Evaluation: Ground truth here relates to task completion, error rates, and user interface effectiveness, observed and recorded during simulated use scenarios.

8. The Sample Size for the Training Set

The document does not provide details on sample sizes for training sets. It focuses on the validation and verification of the final product. The PlanPoint™ Software uses patient CT scans to create 3D plans, which implies an underlying model that would have been developed using a training set, but this information is not included in this submission summary.

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

Information on how the ground truth for any potential training data used for the PlanPoint™ Software (e.g., for segmentation or pathway generation models) is not provided in this document.

Ask a specific question about this device