(203 days)
The ClinDataLinkTM Version 1.0 for Spirometry is an application software that will collect spirometry data for clinical research studies in male/females, pediatrics to adults, and measure FVC, MVV, and SVC, in a hospital, clinic, or home use environment. Prescription device by a physician.
ClinDataLink Version 1.0 is a software application that will be used to collect spirometry data for clinical research studies using QRS Diagnostics, LLC Type II PCMCIA cards and software development kit. ClinDataLink will capture demographic data, spirometry data (FVC, SVC, and MVV) and time/date of visits based upon Protocol Wizard.
The provided text describes a software application, ClinDataLink Version 1.0 for Spirometry, but it is lacking the specific details required to answer many of your questions, particularly regarding acceptance criteria and a detailed study proving device performance in the way you've outlined.
The document is a 510(k) summary, which focuses on demonstrating substantial equivalence to a legally marketed predicate device rather than presenting detailed performance efficacy data for a novel device. As such, it highlights system verification and validation but doesn't delve into clinical performance metrics or studies in the manner typical for an AI/ML device.
Here's an attempt to answer your questions based on the available information, with direct statements about missing information where applicable:
1. A table of acceptance criteria and the reported device performance
This information is not explicitly stated or presented in the provided document. The document discusses "extensive validations of the four operating systems via standard verification/validation activities" to ensure compatibility and functionality, but it does not define specific performance acceptance criteria (e.g., accuracy, sensitivity, specificity for diagnostic tasks) nor report clinical performance data against such criteria.
The device's function is to collect spirometry data, not to interpret or diagnose. Therefore, typical diagnostic performance metrics wouldn't apply in the same way they would for an AI-driven diagnostic tool. The "performance" here refers more to reliable data capture and management.
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
This information is not provided in the document. The 510(k) summary does not detail specific test sets or clinical data used to validate the data collection capabilities of ClinDataLink. It refers to the use of "QRS Diagnostics, LLC Type II PCMCIA cards and software development kit" and the FDA-cleared "ORS SpiroCard" for data collection, implying that the core spirometry measurements are handled by the QRS hardware/software, and ClinDataLink's role is in collecting and managing that 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)
This information is not provided in the document. Since the device's primary function is data collection and management, the concept of "ground truth" for diagnostic performance in the context of expert review isn't directly applicable to its stated purpose.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
This information is not provided in the document. Adjudication methods are typically used in studies where expert consensus is needed to establish ground truth for diagnostic or evaluative tasks, which is not the primary function of this data collection software.
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
This information is not applicable/provided. The ClinDataLink device is a data collection and management software for spirometry data, not an AI-assisted diagnostic tool. Therefore, an MRMC study comparing human readers with and without AI assistance is not relevant to its stated function or described validation.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
This information is not applicable/provided. ClinDataLink is an application software for data collection, not a standalone diagnostic algorithm. Its performance is implicitly tied to its ability to accurately capture and manage data from the QRS SpiroCard system, which itself is a diagnostic spirometer requiring human operation.
7. The type of ground truth used (expert concensus, pathology, outcomes data, etc)
This information is not provided in the document. Given the device's function as data collection software, the "ground truth" would likely relate to the accuracy and integrity of the data it collects compared to the raw output from the connected QRS SpiroCard. However, details of such comparisons or any specific ground truth definition are not included.
8. The sample size for the training set
This information is not provided in the document. As ClinDataLink is a software application for data collection and management, not an AI/ML model, the concept of a "training set" in the context of machine learning is not applicable here. Its development would involve software engineering and testing principles rather than machine learning training.
9. How the ground truth for the training set was established
This information is not applicable/provided. As noted above, the concept of a "training set" for an AI/ML model doesn't apply to this software.
§ 868.1840 Diagnostic spirometer.
(a)
Identification. A diagnostic spirometer is a device used in pulmonary function testing to measure the volume of gas moving in or out of a patient's lungs.(b)
Classification. Class II (performance standards).