(219 days)
The RHYTHMIA HDx™ Mapping System (with software Version 2.0) and accessories are indicated for catheter-based atrial and ventricular mapping. The mapping system allows real-time visualization of intracardiac catheters as well as display of cardiac maps in a number of different formats. The acquired patient signals, including body surface ECG and intracardiac electrograms, may also be recorded and displayed on the system's display screen.
The RHYTHMIA HDx™ Mapping System is a catheter-based atrial and ventricular mapping system designed to display 3D anatomical and electroanatomical maps of the human heart in real-time. The mapping system is intended to be used during electrophysiology procedures for cardiac mapping and storage of cardiac electrophysiological data. In addition, based on user-defined criteria, the system is able to acquire data over multiple cardiac beats. It is capable of real-time display through construction of maps using catheter magnetic and impedance localization technology and data from intracardiac and surface electrograms.
The Signal Station and related accessories provide data connection pathways for external input/output devices (e.g. catheters and recording systems) and serve as the data conduit to the system Workstation computer and software.
The subject device is reusable capital equipment that is intended to be used in an electrophysiology laboratory by physicians fully trained in cardiac electrophysiology.
The provided FDA 510(k) summary for the RHYTHMIA HDx™ Mapping System (with software Version 2.0) describes the device and its performance testing. However, it does not include detailed acceptance criteria in a quantitative table format nor does it directly present a "study that proves the device meets the acceptance criteria" in the way one might expect for a robust AI/ML performance evaluation. The document focuses on showing substantial equivalence to a predicate device and software validation.
Here's a breakdown of the requested information based on the provided text, and where information is not available:
1. Table of Acceptance Criteria and Reported Device Performance
The document states: "The subject RHYTHMIA HDx Mapping System software Version 2.0 passed all tests in accordance with appropriate test acceptance criteria and standards." however, it does not provide a specific table of acceptance criteria or quantitative performance metrics.
The testing described is functional and safety-oriented, rather than a performance study with specific metrics like sensitivity, specificity, or accuracy.
| Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|
| Functional Performance | |
| Accurately create 3D maps of cardiac chambers | Confirmed that incorporation of new software features does not negatively impact this ability. |
| Support visualization of magnetic and impedance tracked catheters | Confirmed that incorporation of new software features does not negatively impact this ability. |
| New software features meet functional requirements | Confirmed. |
| System level functionality under expected and worst case use conditions | Confirmed. |
| Safety | |
| No new safety concerns associated with use | Demonstrated in animal study. |
| Software verification and validation based on 'major' level of concern is complete | Passed. |
| Device performs as intended | Demonstrated in V&V, bench, and animal studies. |
2. Sample size used for the test set and the data provenance
- Test Set Sample Size: Not explicitly stated in terms of patient data or cases. The "bench performance testing" implies internal testing, but the size of data sets (e.g., number of mapping runs, number of anatomical models) is not provided. The animal study involved an unspecified number of animals to demonstrate safety, not a test set for performance metrics.
- Data Provenance: Not explicitly stated. The animal study is a pre-clinical study. For the bench testing, the origin of data is not specified.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
This information is not provided as the document does not describe a performance study involving expert-established ground truth for a test set. The evaluation is focused on functional verification and validation, as well as safety.
4. Adjudication method for the test set
This information is not provided as the document does not describe a performance study involving expert-established ground truth.
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, a multi-reader multi-case (MRMC) comparative effectiveness study is not mentioned in the document. The device is a mapping system, not specifically an AI diagnostic tool designed to augment human reader performance in a comparative study.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done
The RHYTHMIA HDx™ Mapping System is described as a "catheter-based atrial and ventricular mapping system" that provides "real-time visualization" and "display of cardiac maps." While it uses advanced software, it is not presented as a standalone AI algorithm (without human-in-the-loop performance) in the context of this document. Its function is to assist physicians during electrophysiology procedures.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
For the functional testing, the "ground truth" would likely be based on established engineering specifications and validated simulation models or physical phantoms. For the animal study, the ground truth for safety would be physiological measurements and observation of the animals. No mention of expert consensus, pathology, or outcomes data as ground truth for a performance study.
8. The sample size for the training set
This information is not applicable/provided. The document describes a software update for a medical device mapping system. It does not indicate that the system employs machine learning or a neural network that would require a "training set" in the conventional sense for AI/ML development. The software enhancements are described as "DirectSense™ feature provides real-time display of local impedance," "Enhanced CT and MRI capabilities," "Improved initial map setup," and "Support for multiple monitor displays," along with "Minor bug fixes." These are features unlikely to involve a separate training set.
9. How the ground truth for the training set was established
This information is not applicable/provided as there is no mention of an AI/ML training set.
§ 870.1425 Programmable diagnostic computer.
(a)
Identification. A programmable diagnostic computer is a device that can be programmed to compute various physiologic or blood flow parameters based on the output from one or more electrodes, transducers, or measuring devices; this device includes any associated commercially supplied programs.(b)
Classification. Class II (performance standards).