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

The samaritan® PAD 450P is intended for use by personnel who have been trained in its operation. Users should have received training in basic life support / AED, advanced life support or a physician-authorized emergency medical response training program.

The samaritan® PAD 450P is indicated for use on patients greater than 8 years old or over 55 lbs (25 kg) when used with the adult samaritan® Pad-Pak (Pad-Pak-01 or Pad-Pak-07). The samaritan® PAD 450P is indicated for use on children between 1 and 8 years of age or up to 55 lbs (25 kg) when used with the samaritan® Pediatric-Pak (Pad-Pak-02).

Device Description

Like the SAM 350P predicate device, the SAM 450P is a small, lightweight portable battery operated Automated External Defibrillator (AED) designed to treat victims of a cardiac arrest. The SAM 450P incorporates a simple user interface of voice and text/icon prompts to guide the user in the use of the device.

Like the SAM 350P predicate device, the SAM 450P incorporates an audible metronome to guide the user as to the correct rate at which chest compressions should be administered in accordance with current AHA resuscitation quidelines. However, in addition to the metronome provided in the SAM 350P, the SAM 450P also includes a proprietary impedance cardiogram (ICG) analysis algorithm to determine the rate at which CPR compressions are being administered. The SAM 450P uses the measured CPR compression rate to provide both audible and visual feedback prompts to the user to quide them to administer compressions at a rate within the current AHA resuscitation quidelines (i.e., 100-120 compressions per minute). The SAM 450P's audible and visual feedback prompts take the form of voice prompts such as "Push Faster", "Push Slower", and "Good Speed" and LEDs in red, amber and green being lit on the device cover to indicate if the speed at which the compressions are being delivered is too fast, too slow or within the guideline recommendations.

Like the SAM 350P predicate device, the proprietary SAM 450P ECG analysis algorithm automatically determines whether a victim has a shockable or nonshockable rhythm and advises a shock when appropriate. If a shock is required, the SAM 450P will automatically charge to the appropriate energy level and prompt the user to press the illuminated shock button. This enables the delivery of therapeutic energy to the patient.

Like the SAM 350P predicate device, an escalating, truncated exponential biphasic waveform pulse is delivered to the patient via two disposable defibrillator electrodes. This waveform is known as SCOPE® (Self-compensating Output Pulse Envelope). A 150 Joule, 150 Joule, 200 Joule escalating energy sequence is used in accordance with current AHA resuscitation quidelines.

After initial analysis and shock delivery (if appropriate), the SAM 450P will advise that CPR may be commenced via a number of voice prompts such as "Begin CPR" and "It is safe to touch the patient" in addition to emitting an audible metronome.

Like the SAM 350P predicate device, the SAM 450P records the patient's electrocardiogram (ECG) and the patient's ICG (Impedance Cardiogram). The ECG can be viewed using HeartSine's Saver EVO® software.

The Pad-Pak is a combined battery and electrode unit which is single use. The electrodes used with the SAM 450P are two non-sterile, single-use, self-adhesive, conductive gelled defibrillation electrodes. The Pad-Pak is available in three versions: an adult version, a paediatric version, and an adult version meeting FAA temperature, shock and flammability requirements for use on commercial aircraft. The Pad-Paks are identical to those cleared under K123881 for the SAM 350P.

Like the SAM 350P predicate device, the SAM 450P incorporates the following features:

. Controls for Power ON/OFF and Shock
Automated charging at escalating energies of 150J, 150J, 200J ●
Automated self-tests and LED status indicator ●
Combined, disposable battery and electrodes (Pad-Pak™)
Electrode placement guidance voice prompts and LED/icon indicators
CPR voice prompts and metronome ●
Paediatric function for victims between the ages of 1 and 8 years at non-● escalating energy of 50 J
Integral event data recording .

AI/ML Overview

Here's an analysis of the provided text regarding the acceptance criteria and supporting studies for the HeartSine samaritan® PAD 450P, formatted as requested:

Acceptance Criteria and Device Performance

Acceptance Criteria	Reported Device Performance
CPR Compression Rate Feedback Accuracy: Provide audible and visual prompts to guide the user to administer CPR at a rate between 100-120 compressions per minute.	Demonstrated in a GLP animal study comparing the accuracy and appropriateness of the SAM 450P's CPR rate feedback to actual compression rate (determined by video) and a legally marketed device (Philips MRx with Q-CPR).
Arrhythmia Diagnostic Algorithm Performance: Diagnose shockable/non-shockable rhythms accurately.	Extensively validated using standardized AHA, MIT, and CU databases. (Algorithm is unchanged from predicate device).
Electrical Safety: Compliance with relevant international standards.	Tested in accordance with IEC 60601-1.
Electromagnetic Compatibility (EMC): Compliance with relevant international standards.	Tested in accordance with IEC 60601-1-2.
Environmental Testing: Withstand various environmental conditions.	Tested in accordance with MIL-STD 810F.
Software Validation: Appropriate for a major level of concern device.	Carried out.
Device Specifications: Overall performance in accordance with device specifications.	Validation included testing on key device subassemblies and performance testing of the device as a whole.
Time to First Shock: Acceptable performance in terms of time to first shock.	Demonstrated in a Usability Study.
Usability of CPR Feedback Prompts: Acceptable usability of the new CPR feedback prompts.	Demonstrated in a Usability Study.

Study Details

2. Sample size used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective):

Arrhythmia Diagnostic Algorithm Validation: Standardized AHA, MIT, and CU databases were used. The document does not specify the sample size (number of ECGs) from these databases or their specific provenance.
CPR Rate Feedback (Animal Study): The document does not specify the sample size (number of animals or data points). It was a GLP (Good Laboratory Practice) animal study, implying prospective data collection under controlled conditions. The country of origin for the data is not specified.
Usability Study: The document does not specify the sample size (number of participants/users). It was a usability study, implying prospective data collection. The country of origin for the data is not specified.

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):

Arrhythmia Diagnostic Algorithm: For standardized databases like AHA, MIT, and CU, ground truth is typically established by multiple cardiologists or experts in electrophysiology through consensus based on detailed ECG review, sometimes supplemented by clinical outcomes. The document does not specify the number or qualifications of experts involved in the creation of these databases, only that the databases were used.
CPR Rate Feedback (Animal Study): Ground truth for actual CPR compression rate was determined by "video recordings." The document does not mention human experts establishing this ground truth, implying direct measurement from video.
Usability Study: Ground truth for time to first shock and usability of CPR feedback prompts would be based on observational data and potentially user feedback/surveys. The document does not specify experts establishing ground truth, rather it's data collected during the study.

4. Adjudication method (e.g., 2+1, 3+1, none) for the test set:

The document does not describe a specific adjudication method for any of the studies, particularly concerning expert review of data. Ground truth for the algorithm validation relied on pre-existing standard databases.

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 focusing on human readers improving with AI assistance was not explicitly described or performed based on the provided text.
The usability study assessed the "usability of the new CPR feedback prompts," which implies assessing human performance with the device's feedback guidance, but it's not described as a formal MRMC study comparing performance with and without AI (or the device's specific CPR feedback).

6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:

Yes, a standalone evaluation of the arrhythmia diagnostic algorithm was done. The document states it was "extensively validate[d]... using standardised AHA, MIT and CU databases." This is a validation of the algorithm's performance independent of a human user.
The CPR rate feedback algorithm component's accuracy was also evaluated in the animal study by comparing its output to actual compression rates determined by video recordings, suggesting a standalone assessment of its accuracy.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

Arrhythmia Diagnostic Algorithm: Ground truth was established by the standardized AHA, MIT, and CU databases, which typically rely on expert consensus over detailed ECG analysis and sometimes clinical correlation.
CPR Rate Feedback (Animal Study): Ground truth for the actual CPR compression rate was determined by "video recordings" of the compressions.
Usability Study: Ground truth for "time to first shock" and "usability" would be directly observable metrics and subjective feedback from participants.

8. The sample size for the training set:

The document does not specify the sample size for any training set. It refers to validation of an algorithm (arrhythmia detection) that is "unchanged from the predicate device," implying its development and training (if any) occurred previously. For the CPR feedback algorithm, training specifics are not provided.

9. How the ground truth for the training set was established:

The document does not provide details on how the ground truth for any training set was established, as it does not explicitly describe a training phase for a new algorithm in detail. The arrhythmia diagnostic algorithm was carried over from the predicate device, implying its ground truth establishment (if it was a machine learning algorithm) occurred during the development of the predicate device or a previous iteration. The CPR feedback algorithm is described as a "proprietary impedance cardiogram (ICG) analysis algorithm" but details on its training and ground truth establishment are absent.

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.