(483 days)
Not Found
The Burdick Eclipse 4 performs the same functions and meets the same performance standards as the Marquette MAC PC. This version of the Burdick GRI interpretative program and Marquette s interpretative program used in the MAC PC both provide adult and pediatric resting ECGs on patients ranging in age from birth to 99 years. Both programs analyze 10 seconds of data simultaneously from the 12 standard leads and identify essentially the same set of abnormalities.
Here's an analysis of the provided text regarding the acceptance criteria and study for the K94681 device, an enhancement to an ECG interpretative program:
This submission (K94681) is specifically about a pediatric enhancement to an existing ECG interpretative program. The core claim is that this enhancement performs the same functions and meets the same performance standards as another established device (Marquette MAC PC) with its pediatric interpretation.
Since this is an enhancement to an existing program and a claim of equivalence, the "acceptance criteria" are implicitly tied to demonstrating that the pediatric interpretation performs comparably to a predicate device.
1. A table of acceptance criteria and the reported device performance
The document does not explicitly state quantitative "acceptance criteria" in the typical sense (e.g., "sensitivity must be >X%"). Instead, the primary acceptance criteria appear to be:
| Acceptance Criteria (Inferred) | Reported Device Performance |
|---|---|
| Functional Equivalence: The pediatric enhancement performs the same functions as the predicate device's pediatric interpretation (Marquette MAC PC). | "The Burdick Eclipse 4 performs the same functions... as the Marquette MAC PC. This version of the Burdick GRI interpretative program and Marquette’s interpretative program used in the MAC PC both provide adult and pediatric resting ECGs on patients ranging in age from birth to 99 years. Both programs analyze 10 seconds of data simultaneously from the 12 standard leads and identify essentially the same set of abnormalities." |
| Performance Standard Equivalence: The pediatric enhancement meets the same performance standards as the predicate device's pediatric interpretation. | "The Burdick Eclipse 4... meets the same performance standards as the Marquette MAC PC." (No specific quantitative standards are detailed in this summary.) |
| Safety: The addition of pediatric interpretation does not introduce new safety risks. | "The addition of pediatric interpretation does not change the analysis of potential risks as outlined in the Eclipse 4 510(k) submittal (# K943959) concerning electrical shock, misrepresentation of the patient's ECG, inability of the operator to successfully record an ECG, mechanical pinch points and device falling." |
| "Burdick conducted a review of the literature pertaining to safety of pediatric interpretative capabilities in electrocardiographs." | |
| "Appropriate safeguards have been incorporated in the design of the Eclipse 4." | |
| "The device labeling includes instructions for safe and effective use. It includes warnings, cautions, and guidance for installation and maintenance." |
2. Sample size used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective)
- Sample Size: The underlying basis for the pediatric criteria (developed by Dr. MacFarlane) is "a large study of 2,196 neonates, infants and children." This number likely refers to the dataset used to develop or validate the pediatric criteria itself, which is then incorporated into the Burdick Eclipse 4. It's not explicitly stated as a separate "test set" for the K94681 submission, but rather the foundation for the expert criteria being adopted.
- Data Provenance: The criteria were developed at the University of Glasgow, Department of Cardiology, Glasgow Royal Infirmary (GRI), Glasgow, Scotland. This indicates the data originated from Scotland.
- Retrospective or Prospective: Unspecified.
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)
The ground truth or "pediatric criteria" was "developed by Dr. Peter MacFarlane." The text implies he was the primary expert involved in its development, drawing on his extensive experience: "Dr. MacFarlane has been involved in computerized ECG interpretation since its inception in the 1960s." It's not specified if other experts were involved in the development of the GRI criteria or in establishing a "ground truth" for a specific test set related to this 510(k) submission.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
The document does not describe an adjudication method for a specific test set. The pediatric criteria itself was developed by a single expert (Dr. MacFarlane) based on a large study. The submission focuses on the incorporation of this established criteria and its functional equivalence to a predicate device.
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
- Was an MRMC study done? No. The document does not describe an MRMC study involving human readers with and without the AI (interpretive program) assistance. The focus is on the program's standalone functional and performance equivalence.
- Effect size: Not applicable, as no such study was described.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
Yes, implicitly. The submission focuses on the "pediatric enhancement to the interpretative program" and states it "performs the same functions and meets the same performance standards as the Marquette MAC PC." This implies a comparison of the algorithm's performance (standalone) to that of the predicate device's algorithm, specifically in identifying "essentially the same set of abnormalities."
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
The ground truth for the underlying pediatric criteria is expert-developed criteria based on a large clinical study. Dr. MacFarlane, a long-standing expert in computerized ECG interpretation, developed these criteria based on data from 2,196 pediatric patients. This is essentially expert consensus or expert-defined criteria derived from clinical observation.
8. The sample size for the training set
The text states the GRI pediatric criteria is "based on a large study of 2,196 neonates, infants and children." This 2,196 sample size likely represents the dataset used to develop and train (in a broader sense of "training" a set of expert rules or algorithms) the pediatric criteria. It's not explicitly labeled as a "training set" in the context of modern machine learning, but it served that function for the development of the expert system.
9. How the ground truth for the training set was established
The ground truth for this "training set" (the 2,196 patients) was established through the expertise and extensive clinical research of Dr. Peter MacFarlane and potentially his team at the University of Glasgow. He "developed" the criteria, implying he analyzed the data from these patients to define the diagnostic rules and parameters that constitute the pediatric interpretation logic. This would involve a deep understanding of pediatric electrophysiology and ECG patterns.
N/A