(183 days)
The M Series with Real CPR Help is intended to provide visual and audio feedback to encourage rescuers to perform chest compressions at the AHA/ERC recommended rate of 100 compressions per minute. Voice and visual prompts encourage the compression depth of greater than 1.5 to 2 inches for adult patients. The CPR monitoring function is not intended for use on paients under 8 years of age
The ZOLL M Series with Real CPR Help™ provides 'real-time' user CPR assistance when used in conjunction with ZOLL CPR-D-padz™ and CPR Stat-padz™ Multi-function Electrodes. CPR feedback is provided via ZOLL's unique sensor assembly that relays user compression data to the ZOLL. M Series. The ZOLL M Series with Real CPR Help™ provides a metronome to encourage rescuers to perform CPR at the AHA/ECR recommended rate of 100 compressions per minute (CPM). The ZOLL M Series additionally provides chest compression performance feedback to the user through displayed symbols, text messages and voice prompts.
The ZOLL M Series Defibrillator is indicated for the defibrillation, Noninvasive Transcutaneous Pacing, multi-parameter monitoring of patient vital signs, including: ECG Monitoring, Pulse Oximetry, end tidal CO2, 12-Lead ECG monitoring, non-invasive blood pressure measurement, CPR performance and data printing and recording for resting patients in critical care and transport.
The provided text describes ZOLL M Series with Real CPR Help™ and its functionalities but does not contain detailed information about acceptance criteria and a specific study proving the device meets those criteria, as typically presented in a scientific publication or a dedicated performance evaluation section.
Instead, the document is a 510(k) summary, which focuses on demonstrating substantial equivalence to a legally marketed predicate device rather than presenting a detailed performance study with specific metrics, acceptance criteria, and ground truth establishment as would be found in a clinical trial report.
However, based on the intended use and description of the device, we can infer some implicit performance goals and how the provided text generally addresses them.
Inferred Acceptance Criteria and Reported Device Performance
| Criteria Category | Specific Criteria (Inferred from Intended Use) | Reported Device Performance (from text) |
|---|---|---|
| CPR Rate Guidance | Accurately provides metronome/feedback for 100 compressions per minute (CPM). | "The ZOLL M Series with Real CPR Help™ provides a metronome to encourage rescuers to perform CPR at the AHA/ECR recommended rate of 100 compressions per minute (CPM)." |
| "The ZOLL M Series with Real CPR Help™ is intended to provide visual and audio feedback to encourage rescuers to perform chest compressions at the AHA/ERC recommended rate of 100 compressions per minute." | ||
| CPR Depth Guidance | Accurately provides feedback for a compression depth of 1.5 to 2 inches (3.8 to 5.0 cm) for adult patients. | "Voice and visual prompts encourage a compression depth of 1.5 to 2 inches (3.8 to 5.0 cm) for adult patients." |
| "Voice and visual prompts encourage the compression depth of greater than 1.5 to 2 inches for adult patients." | ||
| CPR Feedback Mechanism | Provides clear visual symbols, text messages, and voice prompts for CPR performance. | "The ZOLL M Series additionally provides chest compression performance feedback to the user through displayed symbols, text messages and voice prompts." |
| "The acquired depth and rate signals are used to provide CPR compression performance feedback to the user through displayed symbols, text messages and voice prompts which are equivalent to other ZOLL defibrillators with user CPR feedback." | ||
| Safety & Functional Integrity | Device modifications do not degrade or impact other product features, functions, or performance specifications. Compliance with applicable industry and safety standards. | "Extensive performance testing ensures that the ZOLL M Series with Real CPR Help™ performs as well as the indicated predicate devices and meets all of its functional requirements and performance specifications. Safety testing assures the device complies with applicable sections of recognized industry and safety standards." |
| "Functional testing of the device's features and functions was conducted to ensure that the modifications to the software did not degrade or impact other product features, functions or performance specifications." | ||
| Substantial Equivalence | The device performs equivalently to previously marketed ZOLL defibrillators with CPR feedback. | "The characteristics, features and functions of the Real CPR Help™ are substantially equivalent to other ZOLL Defibrillators equipped with CPR Feedback." |
| "Performance and safety testing of the ZOLL M Series with Real CPR Help™ demonstrates that its features and functions are substantially equivalent to those of the indicated commercially distributed predicate device with regard to performance, safety and effectiveness." |
Missing Information (Not provided in the document for a typical performance study):
The document does not detail a specific "study" in the traditional sense of a clinical trial or a statistically powered performance evaluation with primary and secondary endpoints, sample sizes, and ground truth methodologies that are usually associated with AI/ML device performance descriptions. Here's why and what's missing:
- Sample size used for the test set and the data provenance: This information is not provided. The document mentions "extensive performance testing" and "functional testing" but does not specify sample sizes (e.g., number of compressions evaluated, number of subjects, or data points) or the origin of any data used for these tests.
- Number of experts used to establish the ground truth for the test set and the qualifications of those experts: This information is not provided. The device provides feedback based on AHA/ERC guidelines, which are expert-derived, but the document doesn't describe an independent expert ground truth establishment for testing the Real CPR Help's accuracy in delivering those prompts. The "ground truth" here is implied to be the established AHA/ERC guidelines themselves for target rate and depth.
- Adjudication method (e.g., 2+1, 3+1, none) for the test set: Not applicable based on the provided text, as no expert adjudication for ground truth is described.
- 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 is not provided and is not applicable in the context of this device. The device assists rescuers (not "readers") in performing CPR. The document states its intended use is to "encourage rescuers to perform chest compressions" at recommended rates and depths. It doesn't present an effectiveness study to quantify how much rescuers improve with the device vs. without it.
- If a standalone (i.e., algorithm only without human-in-the-loop performance) was done: The "Real CPR Help" feature is the algorithm, and its performance is inherently tied to providing feedback to a human-in-the-loop. The textual performance descriptions ("provides metronome," "provides feedback," "acquires signals") relate to its standalone function of processing data and generating prompts. However, a formal standalone performance study with specific metrics (e.g., accuracy of rate detection, accuracy of depth detection against a gold standard sensor) is not detailed.
- The type of ground truth used (expert consensus, pathology, outcomes data, etc.): The "ground truth" for the feedback mechanism is the AHA/ERC recommended guidelines for CPR rate (100 CPM) and depth (1.5-2 inches). The accuracy of the device would then be measured by how well its internal sensors and algorithms detect and report these parameters, and how effectively its prompts align with these guidelines. The document does not describe the specific methodology for establishing measurement ground truth (e.g., using a high-precision force/motion sensor as a gold standard to validate the device's sensor readings).
- The sample size for the training set: This information is not provided. Given the nature of medical device 510(k) submissions for non-AI/ML systems, details about "training sets" are often not explicitly mentioned. The device's functionality likely relies on established signal processing and measurement techniques rather than a "trained" machine learning model in the contemporary sense.
- How the ground truth for the training set was established: This information is not provided. Again, for a traditional medical device (before the widespread use of deep learning), a "training set" doesn't typically exist in the same way as an AI/ML model. The device is engineered to meet specific physical and physiological parameters based on established guidelines.
In summary, the provided document is a regulatory submission demonstrating substantial equivalence, not a detailed scientific paper on device performance. It attests to the device's functional integrity and adherence to intended physiological targets (AHA/ERC guidelines) through general claims of "extensive performance testing" and "functional testing" but lacks the granular data and methodological details requested for a comprehensive performance study description.
§ 870.5310 Automated external defibrillator system.
(a)
Identification. An automated external defibrillator (AED) system consists of an AED and those accessories necessary for the AED to detect and interpret an electrocardiogram and deliver an electrical shock (e.g., battery, pad electrode, adapter, and hardware key for pediatric use). An AED system analyzes the patient's electrocardiogram, interprets the cardiac rhythm, and automatically delivers an electrical shock (fully automated AED), or advises the user to deliver the shock (semi-automated or shock advisory AED) to treat ventricular fibrillation or pulseless ventricular tachycardia.(b)
Classification. Class III (premarket approval)(c)
Date PMA or notice of completion of PDP is required. A PMA will be required to be submitted to the Food and Drug Administration by April 29, 2015, for any AED that was in commercial distribution before May 28, 1976, or that has, by April 29, 2015, been found to be substantially equivalent to any AED that was in commercial distribution before May 28, 1976. A PMA will be required to be submitted to the Food and Drug Administration by April 29, 2015, for any AED accessory described in paragraph (a) that was in commercial distribution before May 28, 1976, or that has, by April 29, 2015, been found to be substantially equivalent to any AED accessory described in paragraph (a) that was in commercial distribution before May 28, 1976. Any other AED and AED accessory described in paragraph (a), shall have an approved PMA or declared completed PDP in effect before being placed in commercial distribution.