Search Results

Morgan Scientific's ComPAS2 is a software application intended to be used to compatible Morgan Scientific or thirdparty devices to acquire, analyze, view, store, export, and print the device outputs including measurements of flow, volume, pressure, and gas concentrations. The product is designed for use on adults and pediatrics 4 years and older, in a variety of healthcare environments such as, but not limited to, primary care, hospitals, and research health centers under the supervision of a healthcare provider.

ComPAS2 is a software application designed to provide a secure PC based medical device for creating, adding/recalling subjects, and performing cardio-pulmonary function testing on those subjects. ComPAS2 will interface and link to compatible Morgan Scientific and third-party devices to read, analyze, and display their output to allow the information to be retained with the subject. Current compatible approved devices: TransAir (K953990), SpiroAir (K042595), Body Plethysmograph (K022636), WristOx2 (K102350), tremoFlo (K170185), Pneumotrac (K142812), Micro (K160253), Model 9100 PFT/D1CO (K221030). Data can be reported directly to a printer or communicated with hospital information systems/electronic medical records. All data are preserved in an SQL database, with key sub-systems of ComPAS2 interacting with the database through an API (Application Program Interface).

ComPAS2 is designed to operate with compatible cardio-pulmonary function testing hardware by manufacturers offering the capability to measure key pulmonary functions including, but not limited to: static and dynamic spirometry, bronchial challenge, maximum voluntary ventilation, respiratory muscle strength, cough peak flow, lung volume sub-divisions (such as but not limited to helium dilution, nitrogen washout and plethysmography), single breath diffusion, airway resistance, distribution with lung clearance index closing volume. Other features include: a task manager to manage patient data for reporting; manual entry to input additional information; and historical data review to analyze data for trending and reporting.

The ComPAS2 device, a software application for diagnostic spirometry, was found to be substantially equivalent to its predicate device, ComPAS2 v2019.1.0 (K190568). The primary "study" proving this substantial equivalence was non-clinical performance testing of the software.

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

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state acceptance criteria in a typical quantitative pass/fail format for each performance metric, but rather highlights that performance testing demonstrated that the subject device met its acceptance criteria. The "reported device performance" is implied to be equivalent to the predicate device's performance, as the core functionality and technical characteristics remain largely the same, and the software was validated against the predicate's results.

However, based on the comparison table and the general description, we can infer some performance aspects:

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

• Test Set Sample Size: Not explicitly stated as a number of patients or cases. The testing involved "developing test cases and test runs for the performance of end-to-end testing with both biological and mechanical controls." This suggests a series of functional tests and expected outcomes rather than a traditional patient-based clinical study with a specific sample size.
• Data Provenance: The document does not specify the country of origin for any data used in this non-clinical testing. The nature of the testing (bench testing, software validation) suggests it's primarily synthetic or controlled data generated internally, or data from mechanical/biological controls (e.g., spirometer calibration syringes, simulated lung models). The testing was against "existing results from ComPAS2 v2019.1.0," indicating a retrospective comparison to previously established performance.

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

Not applicable. The ground truth for this software validation was established by comparing the results of the ComPAS2 v2022.1.0 software to the "existing results from ComPAS2 v2019.1.0," the predicate device, and ensuring compliance with recognized standards (ATS/ERS guidelines). Expertise would have been in the form of engineers, quality assurance personnel, and potentially pulmonologists for clinical interpretation of the standards and expected outputs, but the document does not specify a panel of experts for "ground truth" establishment in the sense of a diagnostic interpretation study.

4. Adjudication Method for the Test Set

Not applicable. This was a software verification and validation study, not a clinical study requiring adjudication of diagnostic outcomes. Validation involved ensuring consistency and accuracy of the new software's outputs against the predicate and established standards.

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 comparative effectiveness study was done or described. The device is a software application intended to acquire, analyze, view, store, export, and print device outputs, not to provide AI-assisted diagnoses that impact human reader performance.

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

Yes, the performance testing described is a standalone evaluation of the ComPAS2 software application. The "Bench" section explicitly states "software testing activities" and "system level testing to ensure that the product is capable of meeting the intended use." This indicates the algorithm's performance (i.e., the software's ability to process and display data) was tested independently. The software interfaces with hardware devices that generate the raw data, but its own function of processing and presenting that data was evaluated as described.

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

The ground truth used for the validation of ComPAS2 v2022.1.0 was primarily:

• Existing results from the predicate device (ComPAS2 v2019.1.0): The new software's outputs were compared against the established, cleared performance of the previous version.
• Current standards for Lung Function Testing: Compliance with standards issued by the American Thoracic Society (ATS) and European Respiratory Society (ERS) (e.g., Laszlo, 2006; Macintyre et al., 2005; Miller, Crapo, Hankinson, et al., 2005; Pellegrino, et al., 2005; Wanger et al., 2005; ERS/ATS 2017 & 2019 standards).

8. The Sample Size for the Training Set

Not applicable. This is a software update to an existing device, and the testing described is primarily verification and validation against established standards and the predicate's performance. There is no mention of a machine learning or AI component requiring a "training set" in the context of this submission. The software performs calculations and displays data based on established algorithms in pulmonary function testing.

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

Not applicable, as there is no mention of a training set for machine learning or AI.

Ask a specific question about this device

The ComPAS2 software is intended to operate with the Screenstar pneumotachograph spirometer, Morgan Transflow test PFT system and the Morgan transfer test benchmark PFT system. ComPAS2 uses flow and volume from each of the devices to display the flow and volume information measured directly from patient effort. ComPAS2 also utilizes gas analyzer readings from the Transfer test benchmark to display helium dilution lung volume data and single breath diffusion data measured directly from patient effort. This information is for use in pulmonary function testing and reports.

ComPAS2 is designed to interface with various pieces of hardware (previously cleared pulmonary function testing devices, K142812, K042595, K022636, K953990, K013752) to capture clinical data in the performance of clinical testing. Those data can be reported directly to a printer or communicated with hospital information systems/electronic medical records. All data are preserved in an SOL database, with key sub-systems of ComPAS2 interacting with the database through an API (Application Program Interface).

ComPAS2 is designed to operate with pulmonary function testing hardware by manufacturers offering the capability to measure key pulmonary functions including: static and dynamic spirometry, bronchial challenge, maximum voluntary ventilation (MVV), respiratory muscle strength, cough peak flow, lung volume sub-divisions (by helium dilution, nitrogen washout and plethysmography), single breath diffusion, airway resistance, distribution with lung clearance index closing volume. Other features include a task manager in order to manage patient data for reporting, manual entry in order to input additional information and historical data in order to analyze data for trending and reporting.

The user performs daily quality checks/calibrations prior to performing any tests. Once the test subject enters the Pulmonary Function Testing lab, foundation biographical information (Unique ID, Name, DOB) are either entered by the user, recalled or received in and order via Health Level 7(HL7) message from the information system. The functionality of ComPAS2 software remains the same as the predicate and provides the end user with the same experience.

Encounter information is added at the time of testing such as height, weight, diagnosis and physician. Test capability depends upon the Pulmonary Function Testing device being employed. Completed test information can be printed and handed to the physician for interpretation or data can be routed to the EMR (Electronic Medical Record).

ComPAS2 software connects using USB-powered desktop pulmonary function testing devices for the purpose of creating, adding and recalling subjects and performing pulmonary function testing on those subjects to aid in the measuring of the effect of lung disease on pulmonary function.

The ComPAS2 software is intended to interface with existing pulmonary function testing hardware to capture and display clinical data related to static and dynamic spirometry, bronchial challenge, maximum voluntary ventilation, respiratory muscle strength, cough peak flow, lung volume sub-divisions, single breath diffusion, airway resistance, and distribution with lung clearance index closing volume, for use in pulmonary function testing and reports.

Here's an analysis of the acceptance criteria and study information provided:

1. Table of Acceptance Criteria and Reported Device Performance

The provided document does not explicitly list "acceptance criteria" in a typical quantitative format for device performance. Instead, it details that the ComPAS2 device has identical functionality and indications for use as its predicate device, ComPAS (K021200). The comparison table highlights that key functional performance parameters are the same between ComPAS and ComPAS2. Since ComPAS was already cleared by the FDA, the demonstration of identical functionality and adherence to the same established standards (ATS/ERS) serves as the basis for substantial equivalence.

Note: The key "acceptance criterion" implicitly demonstrated is that ComPAS2 functions identically and adheres to the same established performance standards as the predicate device (ComPAS K021200), which was already cleared. The minor changes (updated operating system compatibility and localization support) are considered not to introduce new risks or alter the fundamental performance.

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

The document states that ComPAS2 software testing involved "developing test cases and test runs for the performance of end to end testing with both biological and mechanical controls." It specifically mentions "results from ComPAS2 testing of the American Thoracic Society's 26 waveform loops for flow/volume validation (Hankinson & Crapo, 1995)".

Sample Size:

• For flow/volume validation, 26 waveform loops from the American Thoracic Society were used.
• The document does not specify a distinct 'test set' sample size in terms of patient data but rather focuses on testing the software's ability to process and display data in congruence with existing hardware and standards.

Data Provenance:

• The 26 waveform loops are derived from a standard set (American Thoracic Society). The original provenance (country of origin, retrospective/prospective) of these standardized waveforms is not detailed in this document, but they represent a recognized benchmark for spirometry validation.

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

The document does not mention the use of human experts to establish "ground truth" for the test set in the context of this software clearance. The validation relies on standardized waveforms and comparison with the predicate device's existing results. The "ground truth" for the performance metrics (e.g., flow accuracy, volume accuracy) is inherently established by the widely accepted ATS/ERS standards and the performance of the predicate device.

4. Adjudication Method for the Test Set

Not applicable. There was no mention of an adjudication process by multiple experts for establishing ground truth for the software's performance, as the validation relied on standardized waveforms and comparison to predicate device performance.

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

No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not performed. This type of study typically assesses how AI assistance impacts human reader performance (e.g., radiologists interpreting images). The ComPAS2 software is a data acquisition and display system for pulmonary function tests, not an AI-driven interpretive aid for human readers. Its validation focuses on accurate data processing and display, matching the predicate device.

6. Standalone Performance Study

Yes, a standalone performance study was implicitly conducted, focused on the software's ability to accurately process and display data. The "ComPAS2 software testing activities consisted of developing test cases and test runs for the performance of end to end testing with both biological and mechanical controls." The results were "validated against existing results from ComPAS, the aforenamed predicate device." This indicates the software was tested independently to ensure its calculations and outputs matched expected results based on the predicate and established standards.

7. Type of Ground Truth Used

The ground truth used for validating ComPAS2's performance appears to be a combination of:

• Established industry standards: Specifically, the American Thoracic Society and European Respiratory Society's Standardization for Lung Function Testing (ATS/ERS 2005, and later updates from 2017). These standards define acceptable accuracy and performance for spirometry.
• Standardized mechanical and biological controls/waveforms: The mention of "26 waveform loops for flow/volume validation (Hankinson & Crapo, 1995)" points to using standardized, known input data against which the software's outputs are compared.
• Predicate device results: The software's output was validated against "existing results from ComPAS," implying that the previously cleared and validated performance of the predicate serves as a benchmark for equivalence.

8. Sample Size for the Training Set

The document does not mention a "training set" because ComPAS2 is not described as a machine learning or AI algorithm in the context of typical AI device development that requires a training set. It is a software redesign of an existing pulmonary function testing application. Its development involves standard software engineering practices rather than algorithmic training on a dataset.

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

Not applicable, as there was no mention of a training set or machine learning algorithm.

Ask a specific question about this device