Search Results

EFAI NEUROSUITE CT MIDLINE SHIFT ASSESSMENT SYSTEM (EFAI MLSCT) is a software workflow tool designed to aid in prioritizing the clinical assessment of non-contrast head CT cases with features suggestive of midline shift (MLS) in individuals aged 18 years and above. EFAI MLSCT analyzes cases using deep learning algorithms to identify suspected MLS findings. It makes case-level output available to a PACS/workstation for worklist prioritization or triage.

EFAI MLSCT is not intended to direct attention to specific portions of an image or to anomalies other than MLS. Its results are not intended to be used on a stand-alone basis for clinical decision-making nor is it intended to rule out MLS or otherwise preclude clinical assessment of CT studies.

EFAI NEUROSUITE CT MIDLINE SHIFT ASSESSMENT SYSTEM (EFAI MLSCT) is a radiological computer-assisted triage and notification software system. The software uses deep learning techniques to automatically analyze non-contrast head CTs and alerts the PACS/RIS workstation once images with features suggestive of MLS are identified.

Through the use of EFAI MLSCT, a radiologist is able to review studies with features suggestive of MLS earlier than in standard of care workflow.

The device is intended to provide a passive notification through the PACS/workstation to the radiologists indicating the existence of a case that may potentially benefit from the prioritization. It does not mark, highlight, or direct users' attention to a specific location on the original non-contrast head CT. The device aims to aid in prioritization and triage of radiological medical images only.

Here's an analysis of the acceptance criteria and study details for the EFAI Neurosuite CT Midline Shift Assessment System (MLS-CT-100), based on the provided text:

Acceptance Criteria and Device Performance

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Size and Data Provenance

• Test Set Sample Size: 300 cases (102 positive for MLS, 198 negative for MLS). Each case included only one CT study.
• Data Provenance: Retrospective, consecutively collected from multiple clinical sites across the United States (U.S.). The U.S. cases were solely collected for this study.

3. Number and Qualifications of Experts for Ground Truth (Test Set)

• Number of Experts: Three (3)
• Qualifications: U.S. board-certified radiologists.

4. Adjudication Method (Test Set)

• Adjudication Method: Majority agreement between the three experts established the reference standard (ground truth).

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

• Was it done? No. The document describes a "standalone performance validation study" and mentions "Reader comparison analysis" for overall safety & effectiveness, but does not detail an MRMC comparative effectiveness study where human readers' performance with and without AI assistance was evaluated for an effect size. The study described focuses on the standalone performance of the AI.

6. Standalone Performance Study

• Was it done? Yes. The document explicitly states: "The observed results of the standalone performance validation study demonstrated that EFAI MLSCT by itself, in the absence of any interaction with a clinician, can provide case-level notifications with features suggestive of MLS with satisfactory results."

7. Type of Ground Truth Used

• Type of Ground Truth: Expert consensus (majority agreement of three U.S. board-certified radiologists).

8. Sample Size for the Training Set

• The document states that the "model development and validation utilized cases from Taiwan," but it does not specify the sample size for the training set. It only mentions that the U.S. validation cases were not used for model development or analytical validation testing.

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

• The document indicates that the model was developed and validated using cases from Taiwan, but it does not describe how the ground truth for these training cases was established.

Ask a specific question about this device

The HEALTH LINE CT MIDLINE CATHETER is indicated for short term (less than 30 days) access to the peripheral venous system for infusion, intravenous therapy and blood sampling. The HEALTH LINE CT MIDLINE CATHETER is suitable for use with power injectors.

The HEALTH LINE CT MIDLINE CATHETER is a family of peripherally inserted peripheral catheters made from specially formulated biocompatible medical grade materials. Catheters are packaged in a tray with accessories necessary for a percutaneous micro introducer introduction (Modified Seldinger or Seldinger technique). The device is intended for short term (less than 30days) vascular access.

The HEALTH LINE CT MIDLINE CATHETER is indicated for dwell times shorter than 30 days. The HEALTH LINE CT MIDLINE CATHETER product line will have catheters in 3Fr, 4 Fr and 5 Fr single lumen, and 4 Fr and 5 Fr dual lumen. The HEALTH LINE CT MIDLINE CATHETER's are supplied in two lengths, approximately 10 and 20 cm long. All catheters are attached to an injectionmolded polyurethane hub that has extension legs with Luer lock fittings for access attachment.

This document is a 510(k) summary for the Health Line CT Midline Catheter (K200263). The core argument for its substantial equivalence relies on its technological identity to a predicate device, the NEXUS MIDLINE CT CATHETER (K140270). Therefore, the "acceptance criteria" here refers to the equivalence to the predicate device, especially in performance, rather than a separate set of numerical thresholds for a new, independent study.

Here's a breakdown of the requested information based on the provided text:

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

The acceptance criterion for this device is substantial equivalence to the predicate device (NEXUS MIDLINE CT CATHETER, K140270). The "reported device performance" is the claim of identity or sameness with the predicate device for all critical performance aspects.

The document states changes only include a name change, added priming instructions in the IFU, and a catheter trim tool in the kit, none of which impact the core functional characteristics used for demonstrating substantial equivalence to the predicate product.

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

This FDA 510(k) summary does not describe a specific "test set" in the context of an AI/algorithm performance study. Instead, it relies on the "technological identity" of the new device to an already cleared predicate device.

Therefore:

• Sample size for test set: Not applicable, as there was no independent clinical/performance test set for this device beyond demonstrating it is identical to the predicate. Performance data was "leveraged from the predicate device."
• Data provenance: Not applicable in the context of a new test set. The provenance of the predicate device's data would be from its original clearance. The changes made to this device were assessed through a risk analysis, which found "no risks... identified with these changes."

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

Not applicable. This is not a study involving expert-established ground truth for an AI/algorithm-based diagnostic device. It's a medical device clearance based on substantial equivalence to an existing device.

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

Not applicable. No test set requiring adjudication was performed as this is a substantial equivalence submission for a physical medical catheter, not an AI/diagnostic algorithm.

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

Not applicable. This is not an AI-assisted diagnostic device.

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

Not applicable. This is a physical medical device (catheter), not an algorithm.

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

Not applicable. The "ground truth" for this submission is the established performance and safety of the legally marketed predicate device (NEXUS MIDLINE CT CATHETER, K140270), to which the new device is claimed to be technologically identical. The assessment relies on a comparison of specifications, materials, and intended uses.

8. The sample size for the training set

Not applicable. This is not an AI/machine learning 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

The Arch-Flo CT Midline is indicated for Short-Term peripheral venous system for selected intravenous therapies, blood sampling, and power injection of contrast media. This catheter may be inserted via basilic, cephalic, or median cubital vein.

The Arch-Flo'™ CT Midline is available in a 4F Single Lumen configuration. The catheter lumen terminates through an extension to a female luer-lock connector. The extension has an in-line clamp to control fluid flow and is marked POWER INJECTABLE MIDLINE along with the lumen gauge size. The transition between lumen and extension is housed within a molded hub. The hub is marked MIDLINE to identify that the catheter is not centrally placed. The tip of the lumen is notched to increase the exposed area of the lumen. The outside diameter of the lumen increases gradually near the hub to aid in kink resistance and to provide a mechanical obstruction to bleeding from the venotomy. The lumen is marked with depth marks every centimeter.

The provided text describes a 510(k) premarket notification for a medical device called "Arch-Flo CT Midline." This document primarily focuses on establishing substantial equivalence to a predicate device through comparison and performance testing. It does not contain information about acceptance criteria and studies related to the performance of an AI/algorithm-based device.

The device in question is an "Intravascular Catheter," which is a traditional medical device, not an AI or software-based application. Therefore, the specific questions regarding AI device performance (like the number of experts for ground truth, MRMC studies, standalone performance with AI, training set details, etc.) are not applicable to the content provided.

However, I can extract the general "acceptance criteria" (or performance data) for the physical device based on the bench/performance data and comparison to the predicate device.

Here's the information that can be extracted, interpreted based on the context of a traditional medical device submission:

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

The document describes performance data for the Arch-Flo CT Midline and compares it to the predicate device, CT Midline (K141151). The "acceptance criteria" are implied by the standards the device was tested against and by demonstrating similar or superior performance to the predicate device.

Ask a specific question about this device

The CT Midlines are indicated for Short-Term peripheral access to the peripheral venous system for selected intravenous therapies, blood sampling, and power injection of contrast media. The maximum recommended infusion rate varies by catheter French size and is printed on the catheter.

The CT Midline Catheter is designed for peripheral vein catheterization and power injection of contrast media. The lumen is an open-ended design comprised of a soft radiopaque polyurethane material with barium sulfate for radiopacity. The lumen is connected to the extensions via a soft pliable hub with suture wing for secure placement. Clamps are provided on the extension tubes to prevent air/fluid contamination. Female luer connectors provide the connection for intravenous administration.

The CT Midline Catheter is available in a 4Fx20cm single-lumen, or 5Fx20cm double-lumen configuration. The outside diameter of the lumen has a reverse taper increasing gradually near the hub to aid in kink resistance and to provide a mechanical obstruction to bleeding from the venotomy. The lumen has depth marks every centimeter and numerical marks every fifth centimeter. The CT Midline is packaged sterile with the necessary accessories to facilitate insertion.

The provided document is a 510(k) premarket notification for a medical device (CT Midline) and primarily discusses its substantial equivalence to a predicate device, rather than presenting a study of the device's performance against specific acceptance criteria.

The submission states that the purpose of this particular 510(k) is to "remove a contraindication that was once cited in the Journal of Infusion Nursing but has since been revised." This is a change to the labeling, not a new performance claim or a new device design that would necessitate a comprehensive performance study with acceptance criteria and reported results.

Therefore, the document does not contain the detailed information requested regarding acceptance criteria and a study proving the device meets those criteria.

Here's a breakdown of why each point cannot be thoroughly answered from the provided text:

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

   • The document implies that the device's performance (e.g., flow rates for power injection) is identical to the predicate device K141151.
   • Table 5.1 "Design Comparison Matrix" lists "Performance Testing" with "Power Injection: 5cc/sec (4F), 7cc/sec (5F)" for both the proposed and predicate devices, stating "Identical, no change." This indicates the expected performance, but not explicit acceptance criteria, nor the results of a new study designed to meet those criteria for this specific submission. It's a statement of equivalence.

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

   • No test set is described for evaluating new performance. The comparison is based on the predicate device's existing performance data.

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

   • Not applicable as no new performance test set requiring expert ground truth is described.

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

   • Not applicable.

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

   • Not applicable. This device is an intravascular catheter, not an AI-powered diagnostic tool.

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

   • Not applicable.

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

   • Not applicable. The "ground truth" here is the established performance of the predicate device, against which the proposed device is declared equivalent.

8. The sample size for the training set:

   • Not applicable as this is a physical medical device, not an algorithm requiring a training set.

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

   • Not applicable.

Summary from the document:

The submission explicitly states under "Bench / Performance Data / Non-Clinical Testing":
"No performance testing was required for the revision to the instructions in conjunction with the substantial equivalence claims, effectively demonstrate the proposed device, CT Midline, is equivalent to the predicate device, CT Midline (K141151)."

The basis for equivalence is that the "Proposed CT Midline is substantially equivalent to the predicate device. CT Midline (K141151), in all aspects, including but not limited to, indications for use, intended use, anatomical location, basic design, dimensions, lengths performance, biocompatibility, materials, manufacturing process and method of sterilization." The only difference is a "revision to the instructions for use (labeling)" to remove a contraindication.

Therefore, for this specific 510(k) submission (K170770), no new study was conducted to prove the device meets performance acceptance criteria, because the device itself and its performance characteristics are deemed identical to a previously cleared predicate device. The change is solely in the labeling information, specifically removing a contraindication.

Ask a specific question about this device

The CT Midlines are indicated for Short-Term peripheral access to the peripheral venous system for selected intravenous therapies, blood sampling, and power injection of contrast media. The maximum recommended infusion rate varies by catheter French size and is printed on the catheter.

The CT Midlines are designed for peripheral vein catheterization and power injection of contrast media, available in 4Fx20cm single-lumen or 5Fx20cm double-lumen configurations. Fundamentally, the proposed device is physically identical to the predicate K 121094 aside from the clamp, which is now colored purple to indicate power injection.

The provided document is a 510(k) summary for the Medcomp CT Midline device, indicating that it is being submitted for substantial equivalence to existing predicate devices, K121094 (Midline) and K091953 (Pro-PICC CT). The primary focus of the submission is to demonstrate that the CT Midline, while otherwise identical to predicate K121094, is also safe and effective for power injection, an indication shared with predicate K091953.

Here's an analysis of the acceptance criteria and the study that proves the device meets them:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are not explicitly labeled as such but are derived from the performance data presented for the proposed CT Midline and compared against the predicate devices, particularly the Pro-PICC CT (K091953) for power injection capabilities. The document asserts that the proposed device is "substantially equivalent" to predicate devices. For mechanical performance, specifically power injection, the CT Midline is compared to the Pro-PICC CT.

Study Proving Device Meets Acceptance Criteria:

The study proving the device meets the acceptance criteria is a nonclinical performance test study. It specifically focused on the power injection capabilities, as this was the key performance difference between the proposed CT Midline and the primary predicate (K121094).

The document states: "The following tests were performed to establish the device's equivalence to the relevant predicate device: o Power Injection Flow Rate o Max Static Burst. These tests highlight the relevant difference between the proposed device and predicate K121094 by testing for the safety and effectiveness of the proposed device with regard to the expanded indication for use of power injection."

The reported performance data for the CT Midline in the table above demonstrates that for both 4F and 5F configurations, the proposed device achieved equal or higher flow rates and burst pressures compared to the predicate Pro-PICC CT (K091953) for power injection. This indicates that the CT Midline meets or exceeds the power injection performance of the predicate device with that indication.

For air leakage, liquid leakage, biocompatibility, and sterility, the claims of substantial equivalence are based on either being identical in materials to a cleared predicate or passing relevant ISO standards, which implies meeting the acceptance criteria set by those standards.

The remaining information requested is largely not applicable (NA) or not explicitly provided in the given excerpts, as this is a 510(k) summary for a medical device (catheter), not an AI/software device or a clinical study in the typical sense that would involve human readers, ground truth consensus, or training data for an algorithm.

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

• Sample Size: The exact sample sizes for the power injection and static burst tests are not explicitly stated as "n=X". However, for the Max Static Burst, the standard deviation and range are provided (e.g., "302±5psi," "range of burst pressures was 292-312 psi"), which implies multiple tests were performed on multiple units to generate an average and range. Without the full Section 18 (reference testing summaries and protocols), the specific number of units tested is unknown.
• Data Provenance: This is an in-vitro nonclinical performance test, conducted by the manufacturer (Medcomp). Therefore, it is a prospective test conducted on manufactured devices, likely in a laboratory setting. Country of origin of the data is the US, where Medcomp is located.

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):

• NA. This is a hardware device performance test. There are no human experts establishing ground truth for image interpretation or diagnosis. The "ground truth" is defined by the physical properties of the device and its performance under specified testing conditions as measured by instruments.

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

• NA. There is no adjudication method as this is a physical performance test, not a subjective judgment task.

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:

• NA. This is not an AI or imaging device subject to MRMC studies.

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

• NA. This is not an algorithm. Standalone performance refers to the device's functional attributes (e.g., flow rate, burst pressure) under test conditions as measured by equipment.

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

• For the nonclinical performance tests (power injection, static burst, leakage, biocompatibility), the "ground truth" is defined by the measured physical properties and performance characteristics of the device under controlled laboratory conditions, verified against established ISO standards and the performance of legally marketed predicate devices.

8. The sample size for the training set:

• NA. This is a physical device, not an algorithm that requires a training set.

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

• NA. This is a physical device, not an algorithm that requires a training set and its associated ground truth establishment.

Ask a specific question about this device