FDA 510(k) Search - By Innolitics (SaMD and AI Experts)

If the person is an infant or child younger than eight years old or weighs if the person is an thant of child Johnsylange. If the child appears less than 55 lbs (20 kg), aco (and/Child Key. Do not delay treatment to oldemarger, do not as act age or weight. If in doubt, do not use the Infant/Child Key.

Device Description

The Philips HeartStart FRx Defibrillator is an automated external defibrillator (AED) for the treatment of ventricular fibrillation, the most common cause of sudden cardiac arrest (SCA). Features of the Philips HeartStart FRx Defibrillator include estimated exponential therapy impedance-compensating biphasic waveform, SMART Analysis System (PAS) for determining if a shock is required and integrated human factors designs for use by lay responders and pre-connected electrodes.

A non-rechargeable lithium manganese dioxide battery powers the Philips HeartStart FRx Defibrillator with a minimum capacity of 200 shocks or 4 hours of operating time.

The HeartStart FRx Defibrillator issues voice instructions appropriate to the stage of the rescue and keeps pace with the user's actions. The defibrillator incorporates a shock-delivery protocol that pauses at predefined intervals to allow users to deliver CPR and otherwise attend to the patient. The defibrillator continuously and automatically analyzes the patient's ECG to determine if a shock is required. The defibrillator incorporates technologies that assess the ECG validity using both common mode and differential mode analysis. These technologies were designed to ensure that a shock is not advised unless the defibrillator is applied to a patient in a shockable heart rhythm.

The HeartStart FRx Defibrillator utilizes the same biphasic, impedance-compensating exponential waveform used in previous-generation Philips AEDs. The HeartStart FRx Defibrillator delivers 150J shocks (nominal) when the user presses the shock button as instructed by the defibrillator (50J nominal with Infant/Child Key). The HeartStart FRx Defibrillator offers no manual-shock capability.

AI/ML Overview

Here's an analysis of the provided text regarding the Philips HeartStart FRx Defibrillator, focusing on acceptance criteria and supporting studies:

It's important to note that the provided text is a 510(k) summary for a defibrillator, not an AI or medical imaging device. Therefore, many standard AI/ML study components like "test set," "ground truth," "experts," "adjudication," "MRMC," and "training set" are not applicable in the context of this traditional medical device submission. The focus here is on functional performance and substantial equivalence to a predicate device.

Acceptance Criteria and Reported Device Performance

The provided document doesn't explicitly list "acceptance criteria" in a structured, quantitative table as one might find for a more complex diagnostic device or AI algorithm. Instead, the "acceptance criteria" for this defibrillator are implicitly met by demonstrating substantial equivalence to a legally marketed predicate device (Philips HeartStart OnSite M5066A Defibrillator) and by showing that it performs in a similar manner and introduces no new safety or efficacy issues.

The performance characteristics are described qualitatively and through the statement that testing demonstrates substantial equivalence.

Acceptance Criteria (Implicit)	Reported Device Performance
Safety and Efficacy (Overall): No new issues of safety or efficacy compared to the predicate device.	"Testing demonstrates that the FRx performs in a manner substantially equivalent to the M5066A predicate and demonstrates that the introduction of the FRx does not raise and new issues of safety or efficacy."
"The introduction of the HeartStart FRx Defibrillator does not present new issues of safety or effectiveness."
Fundamental Scientific Technology: Employs the same core technology for sensing and delivering therapy.	"The HeartStart FRx Defibrillator employs the same fundamental scientific technology as the commercially available Philips HeartStart OnSite M5066A Defibrillator."
"The HeartStart FRx Defibrillator utilizes the same biphasic, impedance-compensating PHILIPS waveform used in previous-generation Philips AEDs."
Shock Delivery: Delivers effective therapy (e.g., 150J nominal).	"The HeartStart FRx Defibrillator delivers 150J shocks (nominal)..."
Analysis System: Continuously and automatically analyzes patient ECG to determine if a shock is required, ensuring validity.	"The defibrillator continuously and automatically analyzes the patient's ECG to determine if a shock is required and integrated human factors designs...
The defibrillator incorporates technologies that assess the ECG validity using both common mode and differential mode... designed to ensure that a shock is not advised unless the defibrillator is applied to a patient in a shockable heart rhythm."
Battery Capacity: Minimum capacity for operations.	"A non-rechargeable lithium manganese dioxide battery powers the Philips HeartStart FRx Defibrillator with a minimum capacity of 200 shocks or 4 hours of operating time."
Intended Use: Applicable for persons suspected to be in sudden cardiac arrest (unresponsive, not breathing normally).	This is the stated indication for use.
Infant/Child Key Functionality: Guidance for use with pediatric patients.	"If the person is an infant or child younger than eight years old or weighs less than 55 lbs (25 kg), use the Infant/Child Key." (This implies the device functions correctly in this mode.)

Study Details (Applicable to Traditional Device Submissions)

For a device like a defibrillator submitting via 510(k), the "study" is primarily focused on bench testing, validation against existing standards, and comparison to the predicate device's established performance. It's not a clinical trial in the sense of an AI algorithm, but rather a demonstration of functional and safety equivalence.

Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- Test Set (Patient Data/ECGs): The document does not specify a "test set" in terms of patient ECGs or clinical cases. The testing would involve simulated rhythms, performance under various electrical and environmental conditions, and comparison of waveforms to the predicate. The "data provenance" (country of origin, retrospective/prospective) for such engineering bench tests is not typically detailed in this type of summary.
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 Applicable. For a defibrillator, "ground truth" isn't established by expert consensus on diagnostic images or data. The "truth" is whether the device accurately detects shockable rhythms (e.g., ventricular fibrillation) and delivers the specified energy, which is verified through engineering tests against known electrical signals.
Adjudication method (e.g. 2+1, 3+1, none) for the test set
- Not Applicable. As there's no "ground truth" set by human experts, there's no adjudication process. Performance is objectively measured against electrical standards and the predicate device.
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 Applicable. This is a standalone medical device, not an AI-assisted diagnostic tool. There are no human "readers" or AI assistance involved in its primary function.
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Yes, in spirit. The defibrillator's core function (analyzing ECG, determining shock advisability) is an "algorithm only" process before human intervention to press the shock button. The device autonomously decides if a shock is needed. This is implicitly what the "testing demonstrates" refers to in terms of the analysis system.
The type of ground truth used (expert consensus, pathology, outcomes data, etc)
- "Ground truth" for a defibrillator involves adherence to electrical and performance standards. This includes:
  - Known Electrical Rhythms: Testing with simulated ECGs representing shockable (e.g., VF) and non-shockable rhythms, generated by specialized equipment.
  - Energy Output Measurement: Verification that the device delivers the specified joules.
  - Impedance Testing: Performance across a range of patient impedances.
  - Environmental Testing: Performance under various temperature, humidity, and vibration conditions.
The sample size for the training set
- Not Applicable. This device doesn't employ a machine learning algorithm in the sense of a "training set" for classification or prediction. Its "algorithm" is based on established signal processing and pattern recognition rules for cardiac rhythms.
How the ground truth for the training set was established
- Not Applicable. See point 7.

Summary of the Study (as described in the 510(k)):

The study primarily involved engineering and bench testing to demonstrate that the Philips HeartStart FRx Defibrillator is substantially equivalent to its predicate device, the Philips HeartStart OnSite M5066A Defibrillator. This equivalence was demonstrated by showing that:

It uses the same fundamental scientific technology.
It has similar performance characteristics.
It performs in a similar manner.
Its introduction does not raise new issues of safety or efficacy.

This type of submission relies heavily on a comparison to a device already cleared by the FDA, rather than novel clinical trial data for new technology.

Summary

Regulation Number and Section

§ 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.