Search Results

ENLIGHT 1810 is a non-invasive, non-radiation medical device that provides information of local impedance variation 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 adult patients in a hospital setting, whose thorax perimeter is within the range of 78-122 cm.

Device Description

ENLIGHT 1810 is a non-invasive, radiation free medical device intended to provide information on the regional distribution of ventilation in a cross-sectional slice of the thorax.

As the total variation in impedance for the thorax corresponds to the total tidal volume, ENLIGHT 1810 can estimate the percentage of tidal volume in regions of interest (ROI) breath by breath, measuring the contribution of the impedance variation of that ROI to the total impedance of the lung.

Electrical impedance tomography (EIT) is a technique in which the electrical properties of tissues are estimated from surface electrode voltage measurements and used to provide information on Local Impedance Variation (LIV) within a cross section of a patient's thorax. Considerable electrical impedance variations are imposed on lung tissue by variations in the lung's air content. There is a linear relationship between the variations in air content and the percentage change in lung tissue impedance. This linear relationship is explored in Electrical Impedance Tomography, supporting its use as a tool to support the user's assessment of the variations in regional air content within a cross section of a patient's lungs.

The device may be used on adult patients undergoing either fully controlled or assisted mechanical ventilation in the ICU environment.

AI/ML Overview

Acceptance Criteria and Study for ENLIGHT 1810

The ENLIGHT 1810 is a ventilatory electrical impedance tomograph intended to be an adjunctive tool to other clinical information to support the user's assessment of variations in regional air content within a cross-section of a patient's lungs. As such, the device's acceptance criteria primarily focus on its ability to qualitatively measure regional ventilation distribution and its safety and performance under various conditions.

1. Table of Acceptance Criteria and Reported Device Performance

The direct "acceptance criteria" for clinical performance are not explicitly stated in quantitative metrics (e.g., specific accuracy thresholds) for the human studies. Instead, the studies aim to demonstrate agreement and the qualitative utility of the device in assessing regional ventilation distribution compared to gold standards (CT). The bench tests, however, do have specific quantitative performance parameters.

Acceptance Criterion (Category)	Specific Measure/Performance Parameter	Acceptance Threshold (Implicit/Explicit)	Reported Device Performance (Bench Study)	Reported Device Performance (Clinical Studies)
Safety & Biocompatibility	Biocompatibility (patient-contacting components)	Pass all tests (Cytotoxicity, Sensitization, Irritation, Intracutaneous reactivity, Extractables & leachables)	All tests passed	N/A (addressed in non-clinical)
Shelf Life/Reprocessing/Sterility	Reprocessing Validation (single patient use components)	50 reprocessing cycles without impact on functionality	Data supported 50 reprocessing cycles did not impact device functionality	N/A (addressed in non-clinical)
EMC & Electrical Safety	Compliance with AAMI ANSI ES60601-1, ANSI AAMI IEC 60601-1-2	Conformance with standards	Conformed with specified standards	N/A (addressed in non-clinical)
Software	Software functionality and cybersecurity	Met design, implementation, and cybersecurity specifications	Met design, implementation, and cybersecurity specifications	N/A (addressed in non-clinical)
Non-clinical Performance: EIT System Parameters	Signal to Noise Ratio	Not explicitly stated as acceptance, but specification: 45 dB-80 dB	45 dB-80 dB	N/A
	Voltage Accuracy	Not explicitly stated as acceptance, but specification: 99.45%-100%	99.45%-100%	N/A
	Drift	Not explicitly stated as acceptance, but specification: Allan variance converges to zero	Allan variance converges to zero	N/A
	Reciprocity Accuracy	Not explicitly stated as acceptance, but specification: 93%-100%	93%-100%	N/A
	Amplitude Response	Not explicitly stated as acceptance, but specification: 88%-102%	88%-102%	N/A
	Position Error	Not explicitly stated as acceptance, but specification: <5% of radius	<5% of radius	N/A
	Ringing	Not explicitly stated as acceptance, but specification: 2-5 02	2-5 02	N/A
Non-clinical Performance: Plethysmogram Accuracy	Percentage error of plethysmogram	Below 5%	Below 5%	N/A
Non-clinical Performance: Real-time LIV Display	Display of real-time local impedance variation	Display information or error message if not possible	Yes, demonstrated	N/A
Non-clinical Performance: Defibrillation Safety	Safe after defibrillation shocks if belts/electrodes not disconnected	Safety confirmed, but simulation indicated need to disconnect patient	Simulation indicated need to disconnect patient to avoid loss of treatment efficacy. Defibrillator verified energy drawn and safety.	N/A
Clinical Performance (Qualitative Utility)	Agreement for anterior/posterior regional ventilation with CT (healthy volunteers)	Qualitative agreement indicated by small bias and narrow limits of agreement	N/A	Anterior/posterior bias: -0.1, LoA: -0.11-0.1 (healthy volunteers)
	Agreement for right/left regional ventilation with CT (healthy volunteers)	Qualitative agreement indicated by small bias and narrow limits of agreement	N/A	Right/left ROI bias: -0.02, LoA: -0.09 to 0.06 (healthy volunteers)
	No device-related serious adverse events observed in clinical studies	No serious adverse events observed	N/A	No device-related serious adverse events observed
	Qualitative ability to assess regional distribution of ventilation as an "adjunctive tool"	Clinical studies "support the use of the subject device as a qualitative tool"	N/A	Supported by all three human clinical studies

Note on Acceptance Criteria: For the clinical studies, the acceptance criteria are largely implicit, demonstrating "agreement" or "support for use as a qualitative tool" rather than specific numerical thresholds for diagnostic accuracy (e.g., sensitivity, specificity, AUC), as the device is intended as an "adjunctive tool" for qualitative assessment.

2. Sample Size for Test Set and Data Provenance

Bench Tests:

Sample Size: Not explicitly stated as a number of "samples" in the same way as human data. For the EIT system performance, an acrylic cylindrical tank filled with saline was used, with experiments involving "contrast objects" and varying conductivity.
Data Provenance: Laboratory bench testing. No specific country of origin for the data is mentioned for the bench tests.

Animal Study:

Sample Size: 7 swine animals.
Data Provenance: Not specified, but generally animal studies are prospective in design, conducted in a controlled research environment.

Clinical Studies (Human):

Study 1: Comparison between regional distribution of ventilation: EIT vs. CT
- Sample Size: 32 healthy volunteers (out of 39 initially evaluated; 7 excluded).
- Data Provenance: Not specified, but implied to be prospective collection for this study from human volunteers.
Study 2: Assessment of Regional Distribution of Ventilation: Right / Left
- Sample Size: 21 patients with lung transplants (11 single lung, 10 bilateral transplant).
- Data Provenance: Not specified, but implied to be prospective collection for this study from human patients.
Study 3: Assessment of Regional Distribution of Ventilation: Upper / Lower
- Sample Size: 39 patients.
- Data Provenance: This was a retrospective analysis.

3. Number of Experts and Qualifications for Ground Truth

Bench Tests & Animal Study:

The ground truth for bench tests was established through physical measurements using phantoms and analytical calculations.
For the animal study, the ground truth was X-ray computed tomography (CT) measurements of lung ventilation distribution. The number and qualifications of experts involved in running the CT scans or interpreting them for ground truth are not explicitly stated.

Clinical Studies (Human):

Ground Truth Method: The primary ground truth for the clinical studies was X-ray computed tomography (CT) measurements of regional ventilation distribution.
Number and Qualifications of Experts: The document does not explicitly state the number or specific qualifications (e.g., "radiologist with 10 years of experience") of the experts involved in establishing the CT ground truth for any of the human studies. However, routinely, CT interpretations for medical research would involve board-certified radiologists.

4. Adjudication Method for the Test Set

The document does not describe a formal "adjudication method" (like 2+1, 3+1 consensus) for the ground truth establishment in any of the studies (bench, animal, or human). The CT images served as the reference standard, and their interpretation is generally a standard clinical practice, though expert consensus for research purposes is often ideal. Its absence is not necessarily a flaw, especially if the CT reads were performed by appropriately qualified individuals.

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

No Multi-Reader Multi-Case (MRMC) comparative effectiveness study comparing human readers with AI assistance vs. without AI assistance was mentioned or conducted. The ENLIGHT 1810 is not described as an AI-powered diagnostic aide that assists human readers in interpreting images; rather, it provides its own "information of local impedance variation" as an adjunctive tool. The studies focus on comparing the device's output to CT, not on how human interpretation changes with or without the device.

6. Standalone Performance

The provided studies predominantly describe the standalone performance of the algorithm. The device, ENLIGHT 1810, generates information on local impedance variation and regional air content distribution. The clinical studies evaluate the direct output of the ENLIGHT 1810 system (EIT measurements of ventilation distribution) against CT. There is no mention of "human-in-the-loop" performance being tested in the context of comparative studies, only that the device is "intended for clinicians to use as an adjunctive tool to other clinical information."

7. Type of Ground Truth Used

Bench Studies: Physical measurements using saline phantoms and analytical calculations.
Animal Studies: X-ray Computed Tomography (CT) measurements of ventilation distribution.
Clinical Studies (Human): X-ray Computed Tomography (CT) measurements of regional ventilation distribution.

8. Sample Size for the Training Set

The document does not explicitly mention a "training set" in the context of algorithm development or machine learning. The studies described are performance evaluation studies, not studies related to the development or training of the device's underlying algorithms. It's plausible that proprietary data, not disclosed in this document, was used for algorithm development and training, but it is not detailed here.

9. How Ground Truth for the Training Set was Established

Since no "training set" or its size is detailed in the document, how its ground truth was established is also not provided. The document focuses on the validation of the device's performance against established clinical standards (CT) in the context of healthy volunteers and patient populations.

Ask a Question

Ask a specific question about this device

Page 1 of 1