K Number
K091561
Date Cleared
2010-09-23

(483 days)

Product Code
Regulation Number
870.5310
Panel
CV
Reference & Predicate Devices
Predicate For
N/A
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The ZOLL AED Plus external defibrillator is intended to be used by personnel who are qualified by training in basic life support, or advanced life support, or other physician authorized emergency medical response to defibrillate victims of cardiac arrest. Use the AED when a suspected cardiac arrest victim has an apparent LACK OF CIRCULATION as indicated by:

  • Unconsciousness and .
  • Absence of normal breathing and ●
  • Absence of a pulse or signs of circulation .

When a victim is a child or infant less than 8 years of age, or less than 55 lbs (25kg), the ZOLL AED Plus should be used with the ZOLL AED Plus Pediatric Electrodes. Therapy should not be delayed to determine the patient's exact age or weight.

Device Description

The ZOLL AED Plus is a lightweight, portable, battery-powered semi-automatic external defibrillator that utilizes the ZOLL Rectilinear Bi-Phasic defibrillation waveform to guide a user through a cardiac arrest rescue. The device is designed to be used by trained emergency responders for the treatment of cardiac arrest.

When connected with ZOLL AED Plus defibrillation electrodes to a patient, the device will analyze the electrocardiographic (ECG) rhythm of the patient and detect whether the rhythm is shockable or non-shockable. If the device detects a shockable rhythm, the device charges the capacitor, enables the "Shock Button", and issues the warning "Don't Touch Patient". The user can then press the treatment button to deliver defibrillation therapy to the patient. If the patient is not in a shockable rhythm, CPR may be advised and administered after automatically repeated analyses of the patient's heart rhythm.

The ZOLL AED Plus is lightweight. It can easily be transported to any rescue site. It is rugged and ready to use at a moment's notice. The device automatically performes a periodic self-test and continually indicates its state of readiness to the user.

When the ZOLL AED Plus is used in conjunction with the ZOLL AED Plus Pediatric Electrodes, the device can be used on patients less than 8 years of age. Labeling and packaging of the electrodes is designed to promote a clear visual distinction between adult and pediatric electrodes.

AI/ML Overview

Here's an analysis of the provided text regarding the ZOLL AED Plus (V5.32 Software Release) and its FDA 510(k) clearance (K091561), focusing on acceptance criteria and study details.

It's important to note that the provided 510(k) summary does not contain detailed performance criteria or a standalone study proving the device meets specific acceptance criteria in the way a typical AI/software device submission would today. This 510(k) clearance is from 2010 for a software update to an existing AED, and the focus is on demonstrating "substantial equivalence" to the previously cleared version, rather than setting and meeting new, quantitative performance objectives.

However, I will extract the information available and highlight where specific details you requested are not present in the document.


Acceptance Criteria and Device Performance

Acceptance Criteria CategorySpecific Criteria (Implicit/Explicit)Reported Device Performance
Functional EquivalenceDevice performs as well as the indicated predicate device."Extensive performance testing ensures that the ZOLL AED Plus (with software version 5.32) performs as well as the indicated predicated predicate device and meets all of its functional requirements and performance specifications."
Safety EquivalenceDevice complies with applicable sections of recognized industry and safety standards."Safety testing assures that the device complies with applicable sections of recognized industry and safety standards."
Performance SpecificationsMeets all functional requirements and performance specifications (of the predicate)."Extensive performance testing ensures that the ZOLL AED Plus (with software version 5.32) ... meets all of its functional requirements and performance specifications."
Pacing/Defibrillation TherapyDelivers appropriate defibrillation therapy when a shockable rhythm is detected."If the device detects a shockable rhythm, the rhythm is classified as 'shockable' or 'non-shockable.' If the device detects a shockable rhythm, the device charges the capacitor, enables the 'Shock Button.' The user can then press the treatment button to deliver defibrillation therapy to the patient." (Describes functionality, but no quantitative performance metric provided for detection accuracy or treatment delivery success rates.)
Pediatric UseFunctions correctly with pediatric electrodes for patients less than 8 years of age or less than 55 lbs (25kg)."When the ZOLL AED Plus is used in conjunction with the ZOLL AED Plus Pediatric Electrodes, the device can be used on patients less than 8 years of age. Labeling and packaging of the electrodes is designed to promote a clear visual distinction between adult and pediatric electrodes." (Describes intended use and distinction, but no specific performance criteria for pediatric detection/therapy.)
Self-Test/ReadinessPerforms periodic self-tests and indicates readiness."The device automatically performes a periodic self-test and continually indicates its state of readiness to the user."

Study Details

  1. Sample size used for the test set and the data provenance:

    • Test Set Sample Size: Not explicitly stated. The document refers to "extensive performance testing" but does not provide details on the sample size of cases or patients used for this testing.
    • Data Provenance: Not explicitly stated. The document doesn't specify the country of origin of the data, nor whether the data was retrospective or prospective. Given the nature of AED testing, it likely involves simulated cardiac rhythms and possibly animal or human subject testing under controlled conditions, but no specifics are provided.
  2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

    • Number of Experts: Not applicable/Not mentioned. For an AED's rhythm analysis, ground truth is typically established based on well-defined ECG characteristics and established medical standards for shockable vs. non-shockable rhythms, rather than expert consensus on individual cases. The document does not describe human experts establishing ground truth for a test set in the context of rhythm analysis.
  3. Adjudication method (e.g., 2+1, 3+1, none) for the test set:

    • Adjudication Method: Not applicable/Not mentioned. As the ground truth is likely based on objective ECG criteria and a "gold standard" for rhythm classification in AEDs, a human adjudication process for individual cases (like 2+1 or 3+1 for imaging datasets) is not typically performed or described for this type of device.
  4. 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:

    • MRMC Study: No. This device is an automated external defibrillator; its primary function is to analyze ECG and deliver shocks independently, guiding a human user rather than assisting a human "reader" in making a diagnostic decision in the same way an AI for medical imaging would. The "human readers" in this context (trained emergency responders) are following explicit device instructions (e.g., "Press Shock Button") rather than interpreting data with AI assistance. Therefore, an MRMC study comparing human reader performance with and without this AI (algorithm) assistance is not relevant to this device's function and was not performed or described.
  5. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:

    • Standalone Performance: Yes, implicitly. The core function of the AED, specifically its rhythm analysis (detecting "shockable" or "non-shockable" rhythms), is a standalone algorithm operation. The document states: "the device will analyze the electrocardiographic (ECG) rhythm of the patient and detect whether the rhythm is shockable or non-shockable." This analysis is performed by the algorithm (software version 5.32) without human intervention in the analysis process itself. The human-in-the-loop aspect comes from the user pressing the shock button after the device has made its determination and verbalized instructions. However, no specific performance metrics (e.g., sensitivity, specificity for shockable rhythm detection) are provided for this standalone algorithm.
  6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

    • Type of Ground Truth: Implicitly, established medical standards and objective ECG interpretations. For rhythm analysis in AEDs, the ground truth for what constitutes a "shockable" rhythm (e.g., Ventricular Fibrillation, Pulseless Ventricular Tachycardia) is based on universally accepted electrocardiographic criteria and international resuscitation guidelines. This is not typically "expert consensus" on specific cases but rather adherence to predefined diagnostic criteria.
  7. The sample size for the training set:

    • Training Set Sample Size: Not applicable/Not mentioned. This document describes a software update (V5.32) to an existing AED for "substantial equivalence." While the original development of an AED's rhythm analysis algorithm would have involved training data, this specific 510(k) does not mention a training set or its size. The focus is on demonstrating that the updated software performs equivalently and safely to the predicate device, not on validating a newly developed AI model from scratch.
  8. How the ground truth for the training set was established:

    • Ground Truth for Training Set: Not applicable/Not mentioned. Similar to point 7, this information is typically relevant for initial algorithm development. For a software update demonstrating substantial equivalence, the specific details of the original training set ground truth establishment are not typically re-evaluated or documented in the 510(k) summary. It would have been based on established ECG classification standards and medical guidelines.

Summary of Limitations in the Document:

The provided 510(k) summary for the ZOLL AED Plus (V5.32) is primarily focused on demonstrating "substantial equivalence" to a previously cleared predicate device (K033474 from 2005) following a software update. As such, it highlights functional and safety equivalence rather than presenting new, detailed performance studies with quantitative acceptance criteria, extensive test sets, or ground truth establishment methods typical of a novel AI device submission. The FDA clearance is based on the assertion that the updated device performs "as well as" and meets the "functional requirements and performance specifications" of the legally marketed predicate device, without detailing those specific metrics for the updated device in this summary.

§ 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.