Search Results

ScreenDx is a software-only device that receives and analyzes lung computed tomography (CT) imaging data in order to assess for interstitial lung findings compatible with interstitial lung disease. The device supplements the standard-of-care workflow by providing a qualitative output of imaging findings based on pattern recognition, in order to provide adjunctive information as part of a referral pathway to an appropriately qualified clinician. Patients with positively identified patterns may undergo assessment for lung fibrosis, but ScreenDx does not replace the current standard of care methods for diagnosis of lung fibrosis and the results of the device are not intended to rule-out or rule-in lung fibrosis. The results of ScreenDx are intended to be used only by clinicians qualified in the care of lung disease, in conjunction with the patient's clinical history, symptoms, and other diagnostic tests, as well as the clinician's professional judgment.

The input to ScreenDx is a DICOM-compliant lung CT scan. Clinical case eligibility includes the following criteria:
Age > 22 years old.

ScreenDx is a computer-assisted analysis software device. The software analyzes lung computed tomography (CT) imaging data to provide a qualitative output assessing for interstitial lung findings compatible with interstitial lung disease. The software system is based on a software algorithm component and connection Application Programing Interface (API) to enable image transfer and notifications. The device consists of the following 3 components:

• (1) Image Receiver API for image acquisition;
• (2) Ingestion Pipeline and Analysis System for image processing; and
• (3) Output API for notification transmission.
• (1) The Image Receiver API is accessed via any technologically compliant system (e.g., DICOM, PACS). The case is submitted to the device through the API directly. The API passes the data to the Ingestion Pipeline and Analysis System.
• (2) The Ingestion Pipeline and Analysis System accepts the images, selects cases appropriate for processing, processes the images for analyses, analyzes the images, and stores the images. This system includes the analysis algorithm that identifies lung abnormalities in the case. No diagnostic information is generated from the software.
• (3) The Output API transmits the result of interstitial lung findings compatible with interstitial lung disease to an assigned set of users in the hospital or clinic, specialists who will then review the case. The Output API is integrated into the hospital or clinic notification software (e.g., EHR, messaging system).

The Analysis System is composed of a 3-D deep learning algorithm trained to identify interstitial lung findings compatible with interstitial lung disease. The training dataset included >3,000 lung CT cases from five different data sources from numerous clinical facilities. The algorithm takes in the ingested CT scan, runs it through the locked model, and classifies whether interstitial lung findings compatible with interstitial lung disease appear to be present. The average patient age was 63 years with male and females representing 51.5% and 48.5% of the patient population respectively. All major CT manufacturers were included, and prevalence of positive cases was 24%.

The software output is a binary Positive (Suggestive of ILD)/Negative result for interstitial lung findings compatible with interstitial lung disease. The output is stored for all cases run. Workflow for managing the output is customizable and under the control of the hospital or clinic making use of the device. For example, one workflow can include configuring the output to list Positive cases in a worklist for clinician review (e.g. a dedicated clinician within the pulmonary clinic environment). Another workflow may include integration with dedicated 3rd party software for workflow management of Positive cases. Regardless of method for case list management, cases with a Positive result will be reviewed for consideration of whether additional work-up is clinically indicated.

No analyzed images or other visually assessed features are output by the device. No regions of interest are either input or provided as an output. Additionally, the software does not provide localization information and there is no filtering, post processing, or annotations. The device is designed to not interrupt standard workflows and operates only in parallel, identifying patients who may benefit from additional follow-up for possible lung fibrosis, based on interstitial lung findings compatible with interstitial lung disease.

The Imvaria ScreenDx device is a software-only device designed to analyze lung CT imaging data for interstitial lung findings compatible with interstitial lung disease (ILD). It provides a qualitative output (Positive/Negative) to supplement standard-of-care workflow as part of a referral pathway to a qualified clinician.

1. Table of Acceptance Criteria and Reported Device Performance

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

• Pivotal Study Test Set: 3,018 unique patients.
  • Data Provenance: Multiple datasets from multiple clinical sites. The report does not specify the country of origin but states it was a retrospective, multicenter study.
• Additional Independent Validation Study Test Set: 2,482 cases.
  • Data Provenance: Collected prospectively by an independent organization. The report does not specify the country of origin.

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

The ground truth for the test set was established via clinical diagnosis derived directly from the data sources. These methodologies for clinical diagnosis were via combined clinical, radiological, laboratory, and/or pathological assessments. The document does not specify the number of experts or their specific qualifications (e.g., "radiologist with 10 years of experience") but implies that the diagnoses were established by qualified clinicians.

4. Adjudication Method for the Test Set

The document states that diagnostic information had been recorded independently for each case via combined clinical, radiological, laboratory, and/or pathological assessments. It does not mention a specific adjudication method like "2+1" or "3+1" for expert review of the test set by the study authors. The ground truth was based on pre-existing clinical diagnoses from various sources.

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

No MRMC comparative effectiveness study was performed or reported. The study focuses on the standalone performance of the algorithm. Therefore, there is no reported effect size of how much human readers improve with AI vs. without AI assistance.

6. Standalone Performance

Yes, a standalone performance study was done. The pivotal study and the additional independent validation study evaluated the algorithm's performance without a human-in-the-loop, reporting sensitivity and specificity metrics.

7. Type of Ground Truth Used

The ground truth used was expert consensus clinical diagnosis (derived from combined clinical, radiological, laboratory, and/or pathological assessments). The presence or absence of the pattern assessed by ScreenDx was intended to correlate with a clinical diagnosis that included lung fibrosis (e.g., IPF, fibrotic NSIP, and other related diagnoses).

8. Sample Size for the Training Set

The algorithm was trained on a dataset that included >3,000 lung CT cases from five different data sources from numerous clinical facilities. Data checks were completed to ensure no overlap between training and test sets.

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

The document states that the training dataset included cases used to identify interstitial lung findings compatible with interstitial lung disease. While specific details on how the ground truth for the training set was established are not explicitly provided, it is highly likely that similar methodologies as for the test set (clinical diagnosis via combined clinical, radiological, laboratory, and/or pathological assessments) were employed, as this is standard practice for medical imaging AI development based on clinical outcomes. However, the document does not definitively state this for the training set.

Ask a specific question about this device

Fibresolve is a software-only device that receives and analyzes lung computed tomography (CT) imaging data in order to provide a diagnostic subtype classification in suspected cases of interstitial lung disease (ILD). The device supplements the standardof-care workflow by providing a qualitative, diagnostic classification output of imaging findings based on machine learning pattern recognition, in order to provide adjunctive information as part of a referral pathway to an appropriate Multidisciplinary Discussion (MDD) or as part of an MDD. Specifically, the tool is used to serve as an adjunct in the diagnosis of idiopathic pulmonary fibrosis (IPF) prior to invasive testing. The results of Fibresolve are intended to be used only by clinicians qualified in the care of lung disease, specifically in caring for patients with ILD, in conjunction with the patient's clinical history, symptoms, and other diagnostic tests, as well as the clinician's professional judgment.

The input to Fibresolve is a DICOM-compliant lung CT scan. Clinical case eligibility includes the following criteria:

Age > 22 years old.

Pulmonary symptoms suggestive of possible ILD including IPF.

Fibresolve is a Software as a Medical Device (SaMD) for the qualitative disease assessment of DICOM-compliant chest computed tomography (CT) imaging for the detection of image content consistent with patterns found in patients with idiopathic pulmonary fibrosis (IPF). Fibresolve uses a deep learning algorithm that assesses CT images for patterns consistent with specific disease diagnosis, identifying patterns consistent with IPF among cases of Interstitial Lung Disease (ILD). Fibresolve produces a binary output ("Suggestive of IPF" or "Inconclusive"). Fibresolve does not provide any visual aid to the clinician to assist in interpreting the image.

The device consists of the following 3 components: (1) Image Receiver application programming interface (API) for image acquisition in the cloud; (2) Ingestion Pipeline and Analysis System for image processing and analysis; and (3) Output API for device output transmission.

(1) The Image Receiver API is accessed via any DICOM-compliant system (e.g., PACS). Images are submitted through the API by the hospital or clinic, or by the manufacturer. The API passes the images to the Ingestion Pipeline and Analysis System (2). The input to the device is a single stack of axial slice, DICOM-compliant, 3 mm thickness or less lung CT images from a list of validated device manufacturers.

(2) (a) The Ingestion Pipeline and (b) Analysis System accepts the images, selects cases appropriate for processing, processes the images for analyzes the images, and stores the images. This Analysis System includes the analysis algorithm that generates the assessment for the case. The device outputs a report which includes identifying information and technical details about the case data and a binary result stating whether the data are determined to be suggestive for the target disease state.

• . The Ingestion Pipeline identifies applicable CT imaging series from the case and verifies that the series is valid, completes quality checks, and confirms adequacy for analysis.
• The analysis algorithm is a 3D deep learning model developed and trained using images . from multiple facilities. No segmentation is performed as part of the Analysis Algorithm.

(3) The Output API transmits the report data for the clinician to review. The Output API is either integrated into the hospital or clinic notification software (e.g., electronic health record) for electronic transmission or the device manufacturer transmits the Report in human-readable format directly (e.g., via fax). The clinician then incorporates the device Report as part of diagnostic decision-making.

The system does not include an image viewer or produce visual output for diagnostic use.

Design Limitation: The device does not interpret images according to established clinical radiological features: the device cannot be used to infer the presence or absence of radiological features associated with the disease or condition named in the indications for use.

Here's a breakdown of the acceptance criteria and the study details for Fibresolve, as extracted from the provided text:

Acceptance Criteria and Device Performance

Study Information

1. Sample Size used for the Test Set and Data Provenance:
* Total Test Set: 300 ILD cases.
* Primary Analysis Subset (relevant for indications, slice thickness <3mm): 137 cases.
* Data Provenance: Sourced from the Lung Tissue Research Consortium (LTRC), collected from sites independent of device development. The test dataset acquisition period ranges from 2005 until 2018. The country of origin for the data is not explicitly stated but implies US-based given the FDA review. The data is retrospective.

2. Number of Experts used to establish the ground truth for the test set and the qualifications of those experts:
* Expert Panel (Primary Clinical Comparator): 5 experts.
* Qualifications: Expert pulmonologists and thoracic radiologists.
* Panel for Retrospective UIP Pattern Assignment: One expert pulmonologist and one expert radiologist pair.

3. Adjudication Method for the test set:
* Expert Panel (EP): Performed a chart review and returned a binary result ("IPF" or "not IPF") based on the 2018 ATS IPF Guidelines. It is not explicitly stated if there was an adjudication beyond the panel's consensus decision, but the description implies a single agreed-upon decision from the 5 experts.
* Reference Standard Diagnosis (Ground Truth): Assigned to each case by a Multidisciplinary Discussion (MDD) from the LTRC. This implies a consensus process among the MDD members.
* Radiological UIP Pattern Category: Retrospectively assigned by panel consensus of an expert pulmonologist and radiologist pair.

4. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:
* A comparative effectiveness study was done comparing the device's standalone performance to an Expert Panel (EP) of human readers. However, this was a standalone comparison and not a multi-reader multi-case (MRMC) study examining human readers with AI assistance versus without AI assistance. Therefore, no effect size for human reader improvement with AI assistance is provided or applicable from this study design.

5. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:
* Yes, the device's standalone performance (algorithm only) was assessed. The reported sensitivity and specificity values (e.g., 55% sensitivity and 82% specificity for <= 3mm slice thickness) are for the Fibresolve device operating in standalone mode.

6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
* The primary reference standard diagnoses for the entire dataset were established by an MDD (Multidisciplinary Discussion) from the LTRC, assessing all available clinical, imaging, laboratory, demographic, and pathologic data, with approximately 1 year of clinical information. This represents a comprehensive, expert consensus ground truth that includes pathology and outcomes data.
* For the subset of cases with slice thickness ≤3 mm, the radiological UIP pattern category was further retrospectively assigned by panel consensus of an expert pulmonologist and radiologist pair.

7. The sample size for the training set:
* The document states, "The analysis algorithm is a 3D deep learning model developed and trained using images from multiple facilities." However, the specific sample size for the training set is not provided in the given text.

8. How the ground truth for the training set was established:
* The document states the model was "developed and trained using images from multiple facilities." However, the method of establishing ground truth for the training set is not explicitly detailed in the provided text. It can be inferred that it likely followed a similar rigorous process to the test set, given the context of a medical device, but no specifics are given.

Ask a specific question about this device