K Number
K101078
Date Cleared
2010-05-10

(21 days)

Product Code
Regulation Number
870.2910
Panel
CV
Reference & Predicate Devices
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The purpose of the TCx-I Remote Care Management System is to collect and transmit medical information such as weight, blood pressure and pulse rate, and blood glucose from the patients on completion of their testing and transmit these results to their healthcare provider at another facility. The system supports videoconferencing, multimedia education and messages. This system is installed by or with support from trained professionals. This device is not intended to provide time sensitive data or alarms. This system may not be used as a substitute for direct medical intervention or emergency care. Interpretation of the information collected and transmitted requires clinical judgment by an experienced medical professional.

Device Description

TCx-I Remote Care Management system collects and transmits measurement information such as weight, blood pressure and pulse rate, and Blood Glucose data from the patients on completion of their testing and transmit these results to their healthcare provider at another facility.

AI/ML Overview

The BL Healthcare Inc. TCx-I Remote Care Management System (RCMS) is a telemedicine system designed to collect and transmit medical information (weight, blood pressure, pulse rate, blood glucose) from patients to healthcare providers. The provided document is a 510(k) summary and submission acceptance letter, which details its regulatory approval based on demonstrating substantial equivalence to predicate devices, rather than a full clinical study with specific acceptance criteria and performance metrics for an AI algorithm.

Therefore, much of the requested information regarding detailed acceptance criteria, specific performance metrics, sample sizes for test/training sets, ground truth establishment methods, expert qualifications, adjudication methods, MRMC studies, and standalone performance for an AI-powered device is not applicable or not provided in this document. The device described here is a data collection and transmission system, not an AI diagnostic or assistive tool in the way current AI medical devices are typically evaluated.

Here's what can be extracted from the document based on your questions:

1. Table of acceptance criteria and the reported device performance

Based on the document, there are no specific numeric acceptance criteria or reported device performance metrics in terms of accuracy, sensitivity, specificity, etc., as typically associated with AI performance. The "acceptance criteria" here relate to regulatory compliance and the system's ability to correctly transmit data.

Acceptance Criteria CategorySpecific Criteria (as inferred)Reported Device Performance (as inferred)
Data Collection & TransmissionEnsure data is collected and transmitted correctly to the server.Non-clinical substantial equivalency testing and Risk-based verification testing performed per FDA guidance "General Principles of Software Validation; Final Guidance for Industry and FDA Staff" demonstrated correct data collection and transmission.
Safety and EffectivenessDevice is as safe and effective as predicate devices.Non-clinical testing met required objectives, demonstrating safety and effectiveness comparable to predicate devices.
Regulatory ComplianceConforms to relevant FDA recognized standards.Conforms to IEC60601-1-1 and IEC60601-1-2. Labeling conforms to FDA guidance "Guidance on Medical Device Patient labeling" April 19, 2001.
Technological CharacteristicsSame fundamental technology as predicate devices.The TCx-I Remote Care Management system has the same fundamental technology as the predicate devices.

2. Sample size used for the test set and the data provenance

  • Sample size for test set: Not applicable/Not provided. The evaluation was based on non-clinical software validation and risk-based verification testing, not a clinical "test set" of patient data in the context of an AI algorithm.
  • Data provenance: Not applicable/Not provided in the context of an AI algorithm's test data. The testing focused on the system's functional integrity.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

Not applicable. Ground truth, in the sense of expert-labeled data for algorithm evaluation, was not established for this type of system validation. The "ground truth" implicitly was whether the system correctly collected and transmitted the input data.

4. Adjudication method for the test set

Not applicable. No adjudication method for a test set was mentioned, as it was not a study evaluating human interpretation or AI performance on medical images/signals.

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. This device is a data transmission system, not an AI-assisted diagnostic tool.

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

No standalone performance evaluation (in the context of an AI algorithm's diagnostic or predictive capabilities) was done. The focus was on the reliability of data transmission.

7. The type of ground truth used

The "ground truth" for this system's validation would be the accurate transmission and display of the measured physiological parameters (weight, BP, pulse, blood glucose). This is established through engineering and software testing protocols, verifying that what is measured at the patient end is accurately reflected at the healthcare provider end. It does not involve expert consensus, pathology, or outcomes data in the typical sense of AI evaluation.

8. The sample size for the training set

Not applicable. This device is not an AI algorithm that undergoes "training" on a dataset. Its primary function is data acquisition and transmission.

9. How the ground truth for the training set was established

Not applicable, as there is no training set for this type of device.

§ 870.2910 Radiofrequency physiological signal transmitter and receiver.

(a)
Identification. A radiofrequency physiological signal transmitter and receiver is a device used to condition a physiological signal so that it can be transmitted via radiofrequency from one location to another, e.g., a central monitoring station. The received signal is reconditioned by the device into its original format so that it can be displayed.(b)
Classification. Class II (performance standards).