Search Results

AirTom is a non-invasive, non-radiation medical device that provides information of local impedance variations within a cross section of a patient's thorax. This information is presented to the clinician user as an adjunctive tool to other clinical information in order to support the user's assessment of variations in regional air content within a cross section of a patient's lungs.

It is intended for mechanically-ventilated patients in a professional healthcare facility, whose chest circumference is within the range of 32 ~ 130 cm.

AirTom does not measure regional ventilation of the lungs.

AirTom is a ventilatory electrical impedance tomograph that uses several electrodes (16+1) placed around the patient's thorax to assess regional impedance variations in a lung slice (tomography). It provides only relative measurements about variations in local impedance.

AirTom estimates local impedance variations, occurring in a cross section of the thorax during a breathing cycle, which are linearly related to variations in regional air content within the lungs.

The provided document, a 510(k) summary for BiLab's AirTom device, focuses primarily on establishing substantial equivalence to a predicate device (TIMPEL S.A.'s Enlight 2100) rather than presenting a detailed study proving the device meets specific acceptance criteria based on quantifiable performance metrics. The summary outlines non-clinical (bench) and clinical performance data, but these are presented as comparative results to support substantial equivalence, not as formal acceptance criteria with corresponding performance against those criteria.

Therefore, the following response will extract the relevant information regarding performance and present it in a structured way that attempts to align with the request, acknowledging where explicit "acceptance criteria" (defined as specific thresholds for success) are not provided in the document.

Acceptance Criteria and Device Performance Study for AirTom

The provided 510(k) summary for AirTom focuses on demonstrating substantial equivalence to a predicate device (ENLIGHT 2100) through a comparison of technological characteristics and performance data. While explicit "acceptance criteria" with quantitative thresholds for study success are not formally stated in the document in the format typically requested (e.g., "Accuracy > 90%"), the document does list several "Performance Characteristics - Bench Test" with corresponding reported ranges for both the subject device (AirTom) and the predicate. These can be interpreted as the performance measures that were assessed to demonstrate equivalence.

The "clinical performance data" presented are descriptive and illustrative of the device's capability to assess regional ventilation, rather than a formal validation against a set of statistical acceptance criteria.

1. Table of Acceptance Criteria and Reported Device Performance

As explicit acceptance criteria are not provided for the clinical studies, the table below lists the Performance Characteristics - Bench Test for which quantitative data is presented to support substantial equivalence. The "Acceptance Criteria" column is inferred from the ranges reported for the predicate device, as the goal is to show comparable performance.

Note: For the clinical performance sections (A, B, C), the document describes observed physiological changes in regional ventilation/impedance under different clinical conditions that are consistent with expected physiological responses or comparisons to other imaging modalities (e.g., CT). It does not provide quantitative acceptance criteria or statistical hypothesis testing results for these observations beyond p-values for differences between states.

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

The document describes three clinical "assessments" that serve as a form of test set, demonstrating the device's performance in clinical settings:

• A. Comparison of regional ventilation distributions: EIT vs. X-ray CT image

  • Sample Size: 6 patients
  • Data Provenance: Retrospective ("AirTom was used on six patients during routine clinical practice in ICU. X-ray CT or chest X-ray images were acquired...")
  • Country of Origin: Not explicitly stated, but assumed to be where the clinical practice occurred, likely in South Korea given BiLab's location.

• B. Assessment of regional ventilation distributions: Anterior and posterior regions

  • Sample Size: 53 patients
  • Data Provenance: Retrospective analysis. Patients were undergoing general anesthesia during surgery.
  • Country of Origin: Not explicitly stated.

• C. Assessment of regional ventilation distributions: With and without pneumoperitoneum

  • Sample Size: 28 patients
  • Data Provenance: Retrospective analysis. Patients were undergoing general anesthesia during laparoscopic surgery with pneumoperitoneum.
  • Country of Origin: Not explicitly stated.

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

The document does not specify the number or qualifications of experts used to establish ground truth for the clinical observations.

• For section A (EIT vs. CT), it mentions X-ray CT or chest X-ray images were acquired to identify likely regions with different tidal ventilation. This implies a clinician (likely a radiologist or intensivist) interpreted these images, but no details are provided about their number or specific qualifications.
• For sections B and C, the "ground truth" implicitly relies on established physiological understanding of lung mechanics and the expected changes under conditions like atelectasis or pneumoperitoneum, rather than a separate expert-labeled ground truth for each case for direct comparison.

4. Adjudication Method for the Test Set

The document does not describe any formal adjudication method (e.g., 2+1, 3+1) for establishing ground truth or for reviewing the outputs of the AirTom device in the context of the clinical assessments. The findings are presented as observations consistent with clinical expectations or comparisons to CT.

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

No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study comparing human readers with AI assistance versus without AI assistance was not conducted or described in this document. The AirTom device is described as providing "information of local impedance variations" to the "clinician user as an adjunctive tool to other clinical information." It is not presented as an AI-powered diagnostic tool that directly assists human readers in interpreting images in a comparative setting.

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

The document does not describe a standalone performance study of the AirTom algorithm in isolation. The device's output (tidal images, regional distribution percentages, total impedance changes) is the direct measurement from the device, which is then interpreted by clinicians. The clinical performance data sections (A, B, C) illustrate the device's ability to capture physiological phenomena, essentially demonstrating its "standalone" measurement capabilities in a clinical context against expected physiological changes or other imaging modalities like CT.

7. The Type of Ground Truth Used

• For the bench tests (Section 9, under "Performance Characteristics - Bench Test"), the ground truth is based on engineering specifications, physical phantoms, and controlled electrical measurements.
• For the clinical performance data (Section 8):
  • Section A (EIT vs. X-ray CT): The ground truth was established by comparing AirTom's visual representations of regional ventilation to X-ray CT or chest X-ray images, which are standard clinical imaging modalities for assessing lung conditions like atelectasis and pneumothorax. This represents a type of imaging ground truth.
  • Sections B & C (Regional ventilation changes with PEEP, and with/without pneumoperitoneum): The ground truth is effectively physiological ground truth/clinical understanding. The studies observed the device's ability to reflect expected physiological changes in lung ventilation/impedance under known clinical interventions (e.g., induction of anesthesia and PEEP changes influencing atelectasis, or CO2 insufflation during surgery). The statistical significance of observed changes (p-values) supports that the device is reflecting these known physiological responses.

8. The Sample Size for the Training Set

The document does not specify any training set sample sizes. This device, as described, appears to be an Electrical Impedance Tomography (EIT) device that directly measures and reconstructs impedance images based on physical principles, rather than a deep learning/AI model that requires a specific training dataset (unless inherent to the image reconstruction algorithm which is not described as a deep learning model). The "clinical performance data" presented are likely used for validation/demonstration of the final product, not for training.

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

As no training set is described (see point 8), the method for establishing ground truth for a training set is not applicable or detailed in this document.

Ask a specific question about this device