(305 days)
Cardioskin is intended to aid the diagnostic evaluation for cardiac disorders by recording patient's ECG signals allowing to condition and monitor these signals. ECG data is stored, transferred and displayed for a review by a physician. Cardioskin is designed to be used by a patient to transmit multiple-lead ECG signal to enable review at a physician's office, hospital or other remote locations under medical supervision. Cardioskin target population is adults.
Cardioskin is a wireless and wearable medical device.
It enables acquisition, recording, storage, transmission and display of 3-12 leads electrocardiogram (ECG) to analyze potential cardiac pathological abnormalities from adult patients in healthcare facility, at home or clinical research environment. It is intended to be used by trained patients and healthcare professionals only.
Cardioskin is composed of a garment, Cardioskin Textile, which is a T-Shirt where textilebased electrodes made of silver yarns are knitted and only functions on Cardioskin Battery and in association with a Cardioskin Recorder.
Cardioskin functioning is coupled with a smartphone/tablet compatible with an iOS or Android system, and a mobile application, the Cardioskin App.
A web-based information system, the Cardioskin Cloud, receives the ECG signals from the Cardioskin Recorder through a paired Wi-Fi connection for its long-term storage and display the signals in the web interface. The medical expert specialist, who prescribes the use of this device, should monitor its use and confirm the proper functioning of signal recording thanks to Cardioskin Cloud.
The provided text describes the Cardioskin device, its indications for use, and a comparison to predicate devices, but it primarily focuses on regulatory approval (510(k) summary) and does not contain detailed acceptance criteria or a specific study demonstrating direct performance against those criteria.
Instead, the document mentions that "Support for the substantial equivalence of Cardioskin was provided as a result of risk management and testing which included electrical and biological safety, performance and software tests." It also states, "Testing has provided reasonable assurance of safety and effectiveness for the intended use and supports the substantial equivalence demonstration." However, it does not elaborate on what these performance tests entailed, what the acceptance criteria were, or the specific results of those tests.
Therefore, many of the requested items cannot be definitively answered from the provided text.
Here is an attempt to answer the questions based only on the information available:
-
A table of acceptance criteria and the reported device performance
- Acceptance Criteria: Not explicitly stated in the document. The document refers to "requirements for safety, function and intended use" and compliance with specific IEC and ISO standards (IEC 60601-1, IEC 60601-1-2, ISO 14971, IEC 62304, IEC 60601-2-47). These standards imply certain performance criteria, but the specific thresholds or metrics for "acceptance" of the Cardioskin's ECG performance (e.g., accuracy of heart rate detection, signal-to-noise ratio) are not detailed.
- Reported Device Performance: The document only makes a general statement: "The results of the verification and validation activities demonstrate that the software meets the requirements for safety, function and intended use." No specific performance metrics or quantitative results for ECG signal acquisition and analysis are provided.
-
Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- The document refers to "non-clinical and limited clinical testing" but does not specify the sample size for any test set or the data provenance.
-
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)
- Not specified.
-
Adjudication method (e.g. 2+1, 3+1, none) for the test set
- Not specified.
-
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
- Not specified, and it's unlikely given the nature of an ECG recording device where the primary output is the raw data for physician review, rather than an AI interpretation tool being evaluated for reader improvement.
-
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- The device "records patient's ECG signals allowing to condition and monitor these signals. ECG data is stored, transferred and displayed for a review by a physician." This indicates a human-in-the-loop system, as the physician performs the review. There is no mention of a standalone algorithm for diagnosis.
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc)
- Not specified.
-
The sample size for the training set
- Not specified. This device is primarily for data acquisition and display, and while it has a "Cardioskin Cloud" that stores and displays signals, the document doesn't indicate extensive AI model training in the diagnostic sense that would require a large training set for a "ground truth" establishment.
-
How the ground truth for the training set was established
- Not specified.
Summary of what can be inferred or directly stated from the text regarding performance and testing:
- Type of tests conducted: Electrical and biological safety, performance (general statement), software verification and validation, electromagnetic compatibility, and compliance with specific medical device standards (IEC 60601-1, IEC 60601-1-2, ISO 14971, IEC 62304, IEC 60601-2-47).
- Biocompatibility tests: Irritation and Sensitization, based on ISO 10993 for skin contact limited to 12 hours.
- Software tests: Verification and validation according to IEC 62304:2006 and FDA Guidance "General Principles for Software Validation."
- Outcome of tests: The tests provide "reasonable assurance of safety and effectiveness for the intended use" and demonstrate that "the software meets the requirements for safety, function and intended use." Compliance with recognized standards was demonstrated.
The document primarily serves as a 510(k) summary, which focuses on demonstrating substantial equivalence to predicate devices and meeting general regulatory safety and effectiveness requirements, rather than providing detailed performance study results against specific, quantified acceptance criteria for diagnostic performance.
§ 870.2920 Telephone electrocardiograph transmitter and receiver.
(a)
Identification. A telephone electrocardiograph transmitter and receiver is a device used to condition an electrocardiograph signal so that it can be transmitted via a telephone line to another location. This device also includes a receiver that reconditions the received signal into its original format so that it can be displayed. The device includes devices used to transmit and receive pacemaker signals.(b)
Classification. Class II (performance standards).