Intended Use: The HeartStart XL + is intended for use in a hospital setting by qualified medical personnel trained in the operation of the device and qualified by training in basic life support, advanced life support, or defibrillation. It must be used by or on the order of a physician.

When operating as a semi-automatic external defibrillator in AED Mode, the HeartStart XL+ is suitable for use by medical personnel trained in basic life support that includes use of an AED.

When operating in Monitor, Manual Defib or Pacer Mode, the HeartStart XL+ is suitable for use by healthcare professionals trained in advanced life support.

Indications for Use: The HeartStart XL+ is a defibrillator monitor. The device is for use by qualified medical personnel trained in the operation of the device and certified by training n basic life support, advanced life support or defibrillation. It must be used by or on the order of a physician.

AED Therapy: AED Mode is used in the presence of a suspected cardiac arrest on patients that are unresponsive, not breathing and pulseless.

Manual Defibrillation: Asynchronous defibrillation is the initial treatment for ventricular fibrillation and ventricular tachycardia in patients that are pulseless and unresponsive.

Synchronous defibrillation (cardioversion) is indicated for termination of atrial fibrillation.

Non-Invasive External Pacing: The pacing option is indicated for treating patients with symptomatic bradycardia.

Pulse Oximetry: The SpO2 option is indicated for use when it is beneficial to assess the patient's oxygen saturation level.

Non-invasive Blood Pressure Monitoring: The NBP option is indicated for non-invasive measurement of a patient's arterial blood pressure.

ECG Monitoring: The ECG monitoring option is indicated to be used for monitoring, alarming, and recording of the patient's heart rate and morphology.

Device Description

The HeartStart XL+ is a lightweight, portable defibrillator/monitor. It provides four clinical modes of operation: Monitor, Manual Defibrillator, AED and Pacer (optional).

In Monitor Mode, depending on the ECG inputs being used (pads, paddles, ECG cable), you can monitor up to 3 different ECG waveforms at one time. Using a 3-lead ECG cable you can view Lead I, II or III. With a 5-Lead ECG cable, you can view two leads from Leads I, III, avR, avF or V. Optional monitoring of SpO2 or NBP is available using existing and previously cleared technology as references in the predicate device comparison of the summary. Measurements are presented on the display and alarms are available to alert you to a change in the patient's condition. You can also display the Vital Signs Trending Report to view all key parameters and their measurements at a glance.

Manual Defibrillation Mode provides simple 1-2-3 defibrillation. You analyze the patient's ECG and, if appropriate: 1) select an energy setting; 2) charge; and 3) deliver the shock. Defibrillation is performed using paddles (internal or external) or multifunction electrode pads. You can also perform synchronized cardioversion in Manual Defibrillation Mode. The HeartStart XL+ incorporates Philips' low energy SMART Biphasic waveform for defibrillation which has been in use for over a decade.

In AED Mode, the HeartStart XL+ analyzes the patient's ECG and determines whether a shock is advised. Voice prompts guide you through the 2-step defibrillation process, with easy-to-follow instruction and patient information. Voice prompts are reinforced by messages on the display.

Optional Pacer Mode offers non-invasive transcutaneous pacing therapy. Pace pulses are delivered through multifunction electrode pads.

AI/ML Overview

The provided text describes the Philips HeartStart XL+ Defibrillator Monitor, a medical device. The submission primarily focuses on establishing substantial equivalence to predicate devices rather than presenting a performance study with explicit acceptance criteria for a new AI algorithm.

Therefore, the requested information regarding acceptance criteria, reported device performance, sample sizes, ground truth establishment, expert involvement, and MRMC studies, as they relate to a new AI algorithm or a distinct performance study, is not present in the provided document. The device is a defibrillator/monitor, and its "performance" is primarily assessed through compliance with recognized consensus standards and comparison to existing predicate devices.

However, I can extract information related to the device's technical specifications and the general approach to validating its equivalence.

Here's a breakdown of the available information in relation to your request:

1. A table of acceptance criteria and the reported device performance

This information is not explicitly stated as quantitative acceptance criteria for a new algorithm's performance in the document. Instead, the document focuses on compliance with established medical device standards and demonstrating equivalence to predicate devices. The "performance data" section states:

"Testing for performance was done according to applicable FDA recognized consensus standards for electrical defibrillation, ECG monitoring, SPO2 monitoring, and NBP monitoring."
"Additional standards testing beyond the list of FDA recognized standards was also performed."
"Small feature changes have been made to align the design with the 2010 AHA Resuscitation Guidelines. The previous product had only been evaluated against the 2005 AHA guidelines."

The document implies that the device "performs" by successfully meeting these standards and aligning with clinical guidelines, but it doesn't provide a table of numerical acceptance criteria or specific performance metrics (e.g., sensitivity, specificity for an AI component) in the way one would expect for a novel algorithmic claim.

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

This information is not provided in the document. The testing mentioned refers to conformance with applicable standards, which typically involves laboratory testing and potentially some clinical evaluation, but no details on specific sample sizes for a "test set" are given.

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)

This information is not provided in the document. Given the nature of the device (defibrillator/monitor) and the focus on standards compliance and predicate device equivalence, the concept of "ground truth established by experts" in the context of an algorithm's diagnostic performance (like in AI studies) doesn't directly apply here. Clinical validation would involve qualified medical personnel, but this is not detailed.

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

This information is not provided in the document.

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

An MRMC study is not mentioned in the document. This is a medical device approval for a physical defibrillator/monitor, not an AI-assisted diagnostic tool for human readers.

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

While the device includes internal algorithms (e.g., the HeartStream Patient Analysis System (PAS) Algorithm for AED mode), the document does not describe a "standalone" algorithmic performance study in the context of evaluating a new AI component. The algorithms integrated are existing and previously reviewed technologies, with the focus being on their integration into the new device and compliance with standards.

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

This information is not explicitly stated in the document in the context of a new algorithm's performance. For a device like this, "ground truth" would implicitly come from established physiological measurements, validated clinical conditions (e.g., actual cardiac arrest for AED function), and adherence to recognized medical guidelines (AHA Resuscitation Guidelines).

8. The sample size for the training set

This information is not provided. The document does not describe the development or training of a new algorithm that would require a dedicated training set. It leverages existing, previously cleared algorithms like the HeartStream Patient Analysis System (PAS) Algorithm.

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

This information is not provided. As above, the document focuses on integration of existing, cleared technologies rather than the development of a novel algorithm from scratch.

Summary

{0}------------------------------------------------

K110825

pg 1 of 7

FEB 16 2012

FEB 1 6 2012

5.0 510(k) Summary

As required by 21 CFR 807.87(h), a 510(k) Summary for this Premarket Notification submission is provided below. A 510(k) statement is therefore not required.

510(k) SUMMARY OF SAFETY AND EFFECTIVENESS

Philips Defibrillator Monitor

Submitter's Name and Address

Submitter's Name:	Philips Medical Systems
Division:	Emergency Care Solutions
Address:	3000 Minuteman Road
City, State, and Zip:	Andover, MA 01810
Contact Name:	Paul Schrader, Senior Regulatory Affairs Manager
Telephone / Fax:	(978) 659-2404 / 978-659-3610
510(k) Summary Date	October 28, 2011

Manufacturers' Information: Establishment Registration Number

Establishment name:	Philips Medical Systems
Address:	3000 Minuteman RoadAndover, MA 01810
Establishment Registration No.	1218950

{1}------------------------------------------------

||||0825

Image /page/1/Picture/1 description: The image shows a handwritten note on a white background. The note says "pg 2 of 7". The handwriting is somewhat cursive, and the ink appears to be dark. The image is simple and focuses solely on the handwritten text.

Device Details:

Proprietary or Trade Name:	HeartStart XL +
Common Name:	ALS Defibrillator Monitor
Device Class:	III for AED mode (MKJ), II for theremaining applicable ProCodes / CFRclassifications
Device ProCodes:	MKJ, LDD, DRO, DQA, DXN
Device CFR:	Several see table below
Classification Panel:	Cardiovascular
21 CFR Classification Name /Description	Several see table below

Classification	ProCode	Classification Description
870.5310-III	MKJ	Defibrillators, Automatic, External
870.5300-II	LDD	Low-energy defibrillator1
870.5550-II	DRO	External Transcutaneous Pacemaker(Non-invasive)
870.2700-II	DQA	Pulse Oximeter
870.1130-II	DXN	Non-Invasive Blood Pressure
870.1025-II	MHX	Arrhythmia detector and alarm

{2}------------------------------------------------

Device Name: Philips XL+ Defibrillator Monitor