The Edwards Lifesciences Acumen Hypotension Prediction Index (HPI) feature provides the clinician with physiological insight into a patient's likelihood of future hypotensive events (defined as mean arterial pressure < 65 mmHg for at least one minute in duration) and the associated hemodynamics. The Acumen HPI feature is intended for use in operating room (OR) patients receiving advanced hemodynamic monitoring. The Acumen HPI feature is considered to be additional quantitative information regarding the patient's physiological condition for reference only and no therapeutic decisions should be made based solely on the Hypotension Prediction Index (HPI) parameter.

Device Description

The Acumen Hypotension Prediction Index Feature ("the device") consists of software running on the Edwards Lifesciences EV1000 Platform (previously cleared under K100709, K110597, K131892. K140312, and K160552) paired with the FloTrac IQ extravascular blood pressure transducer (K152980) and a radial arterial catheter. The device includes the Hypotension Prediction Index (HPI), the Dynamic Arterial Elastance Parameter (Eagyn), the Left Ventricular Contractility Parameter (dP/dt), and additional graphical user interface features.

HPI is an index related to the likelihood of a patient experiencing a hypotensive event (defined as mean arterial pressure (MAP) <65 mmHg for one minute in duration) within fifteen minutes, where zero (0) indicates low likelihood and one hundred (100) indicates high likelihood. The EV1000 Platform initiates a high priority alarm (red) when HPI exceeds 85. The Hypotension Prediction Index, HPI, should not be used exclusively to treat the patients. A review of the patient's hemodynamics is recommended prior to initiating treatment.

Eadm is a physiologic parameter related to left ventricular afterload relative to the left ventricular elastance. It is calculated by dividing Pulse Pressure Variation (PPV) by Stroke Volume Variation (SVV), or Eadyn = PPV/SVV.

dP/dt is a physiologic parameter related to the change in contractility of the left ventricle. It is calculated as the maximal first derivative of the arterial pressure waveform with respect to time.

Additional graphical user interface features include the HPI High Alert Popup, which displays when HPI exceeds 85 for two consecutive 20-second updates or reaches 100 at any time, and the HPI Secondary Screen, which consolidates hemodynamic parameters into a single screen.

AI/ML Overview

1. Table of Acceptance Criteria and Reported Device Performance

Metric	Acceptance Criteria (Implicit from Clinical Validation)	Reported Device Performance (N=52 Study)	Reported Device Performance (N=204 Study)
Sensitivity	High enough to be clinically useful	83.7% [81.5, 86.0]%	65.8% [63.7, 67.9]%
Specificity	High enough to avoid excessive false positives	99.8% [99.4, 100.0]%	99.4% [99.2, 99.7]%
AUC	High enough to indicate good discrimination	0.95	0.88
Positive Predictive Value (PPV)	(Not explicitly stated as AC, but evaluated)	99.9% [99.7, 100.0]%	98.3% [97.6, 99.0]%
Negative Predictive Value (NPV)	(Not explicitly stated as AC, but evaluated)	75.1% [71.9, 78.4]%	84.9% [83.9, 86.0]%

Note: The document does not explicitly state numerical acceptance criteria for sensitivity, specificity, and AUC. However, the reported performance metrics from the clinical validation studies demonstrate a level of accuracy deemed acceptable by the FDA for de novo classification. The high specificities and AUC values, along with the detailed performance table for different HPI ranges, suggest that the device's ability to predict hypotension within the 15-minute timeframe was considered sufficient. The acceptance criteria for usability testing (at least 80% of participants agree or strongly agree) are explicitly stated in the Usability Testing section.

2. Sample Size Used for the Test Set and Data Provenance

The "test set" for the HPI algorithm's performance evaluation was derived from two retrospective patient databases:

First Database (Edwards Lifesciences):
- Sample Size: 52 subjects (OR patients)
- Data Provenance: Global clinical sites, collected via prospective, IRB/EC approved clinical protocols with informed consent for each patient. (Retrospective analysis of prospectively collected data).
Second Database (University Hospital):
- Sample Size: 204 subjects (OR patients)
- Data Provenance: From a university hospital, includes OR patients. (Retrospective analysis of an arterial waveform database).

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts

The document does not specify the "number of experts" or their "qualifications" used to establish the ground truth for the test set.

Instead, the ground truth for hypotensive events was defined objectively: "mean arterial pressure (MAP) < 65 mmHg for at least one minute in duration." The databases used for validation contained "annotated hypotensive (defined as MAP <65 mmHG for at least 1 minute) and non-hypotensive events." This implies that the ground truth was established based on these objective physiological measurements rather than expert consensus on individual cases.

4. Adjudication Method for the Test Set

Not applicable. The ground truth was based on objective physiological measurements (MAP < 65 mmHg for at least one minute), not expert adjudication requiring consensus or multiple readings.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

No, a multi-reader multi-case (MRMC) comparative effectiveness study was not reported. The device is intended as an adjunctive predictive cardiovascular indicator, providing quantitative information, not as a diagnostic aid that directly replaces or assists human readers in interpreting complex images or clinical scenarios requiring reader performance comparison. The study focused on the algorithm's standalone performance.

6. Standalone Performance Study (Algorithm Only Without Human-in-the-Loop Performance)

Yes, a standalone performance study was done. The reported sensitivity, specificity, and AUC values (83.7%, 99.8%, 0.95 for N=52 study; 65.8%, 99.4%, 0.88 for N=204 study) represent the performance of the HPI algorithm itself in predicting hypotensive events from extracted FloTrac IQ measurements. The device is explicitly stated as an "adjunctive predictive cardiovascular indicator" and "not intended to independently direct therapy," but its performance metrics are presented in a standalone context.

7. Type of Ground Truth Used

The type of ground truth used was objective physiological outcomes data, specifically:

Hypotensive event: Defined as mean arterial pressure (MAP) < 65 mmHg for at least one minute in duration.

This objective definition was used to annotate the events in the retrospective arterial waveform databases.

8. Sample Size for the Training Set

The document states: "HPI uses features extracted from FloTrac IQ measurements... to a data-driven model developed from retrospective analysis of an arterial waveform database collected from ICU and OR patients containing annotated hypotensive... and non-hypotensive events."

However, it does not explicitly state the sample size of the training set. It only mentions that the model was "developed from retrospective analysis" of the overall databases, and the reported clinical validation results (N=52 and N=204 studies) were presumably used as test sets to evaluate the performance of this already developed model. The training and test sets might have been derived from the same larger pool of data.

9. How the Ground Truth for the Training Set Was Established

The ground truth for the model development (training) "was established" in the same manner as the validation ground truth:

Hypotensive event: Defined as mean arterial pressure (MAP) < 65 mmHg for at least one minute in duration.

The training data came from "an arterial waveform database collected from ICU and OR patients containing annotated hypotensive (defined as MAP <65 mmHG for at least 1 minute) and non-hypotensive events." This indicates that the ground truth for both training and testing was based on these objective, physiologically defined annotations of hypotensive events.

Summary

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

DE NOVO CLASSIFICATION REQUEST FOR ACUMEN HYPOTENSION PREDICTION INDEX FEATURE SOFTWARE

REGULATORY INFORMATION

FDA identifies this generic type of device as:

Adjunctive predictive cardiovascular indicator. The adjunctive predictive cardiovascular indicator is a prescription device that uses software algorithms to analyze cardiovascular vital signs and predict future cardiovascular status or events. This device is intended for adjunctive use with other physical vital sign parameters and patient information and is not intended to independently direct therapy.

NEW REGULATION NUMBER: 21 CFR 870.2210

CLASSIFICATION: II

PRODUCT CODE: QAQ

BACKGROUND

DEVICE NAME: Acumen Hypotension Prediction Index (HPI) Feature Software

SUBMISSION NUMBER: DEN160044

DATE OF DE NOVO: September 26, 2016

Edwards Lifesciences LLC CONTACT: One Edwards Way Irvine, CA 92614

INDICATIONS FOR USE

LIMITATIONS

The sale, distribution, and use of the Acumen Hypotension Prediction Index Feature are restricted to prescription use in accordance with 21 CFR § 801.109.

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

Inaccurate FloTrac/Cardiac Output (FT-CO) measurements can be caused by factors such as:

Improperly zeroed and/or leveled sensor/transducer ●
o Over- or under-damped pressure lines
0 Excessive variations in blood pressure. Some conditions that cause BP variations include, but are not limited to:
- 0 Intra-aortic balloon pumps
o Any clinical situation where the arterial pressure is deemed inaccurate or not representative of aortic pressure, including but not limited to:
- 0 Extreme peripheral vasoconstriction which results in a compromised radial arterial pressure waveform
- o Hyperdynamic conditions as seen in post liver transplant
o Excessive patient movement
Electrocautery or electrosurgical unit interference
Aortic valve regurgitation may cause an over estimation of Stroke Volume / Cardiac ● Output calculated depending on the amount of valvular disease and the volume lost back into the left ventricle.

The Hypotension Prediction Index, HPI, should not be used exclusively to treat the patients. A review of the patient's hemodynamics is recommended prior to initiating treatment.

Exercise caution when using dP/dt in patients with severe aortic stenosis, since the stenosis may reduce the coupling between the left ventricle and the afterload.

PLEASE REFER TO THE LABELING FOR A MORE COMPLETE LIST OF WARNINGS, PRECAUTIONS AND CONTRAINDICATIONS.

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

DEVICE DESCRIPTION

HPI is not defined by a single equation. HPI uses features extracted from FloTrac IQ measurements, some compared to an initial base value determined over the first 10 minutes of the patient monitoring session, to a data-driven model developed from retrospective analysis of an arterial waveform database collected from ICU and OR patients containing annotated hypotensive (defined as MAP <65 mmHG for at least 1 minute) and non-hypotensive events. The sensitivity, specificity, and area under the receiver operating characteristic for the first database of 52 subjects were 83.7%. 99.8%. and 0.95 respectively. The sensitivity, specificity, and area under the receiver operating characteristic for the second database of 204 subjects were 65.8%, 99.4%, and 0.88 respectively.

The accuracy of the presented measurements are based on several factors: the arterial line is reliable (not damped), the pressure sensor is well aligned and the arterial line zeroed properly is connected to the device, and patient demographics (age, gender, height, and weight) have been entered into the device. Usability testing demonstrated that users recognize that HPI is an adjunctive parameter.

dP/dt is a physiologic parameter related to the change in contractility of the left ventricle. It is calculated as the maximal first derivative of the arterial pressure waveform with respect to time.

{3}------------------------------------------------

Image /page/3/Picture/0 description: The image shows a medical monitor displaying various physiological parameters. The Hypotesion Prediction Index (HPI) is displayed in multiple locations, with values of 95/100, 96/100, and 16/100. Other parameters include MAP (86 mmHg), CO (5.3 L/min), SVR (892 dyne-s/cm), PR (69 bpm), SV (76 mL/b), SVV (13%), dP/dt (743 mmHg/sec), and Eadyn (1.4). The monitor also displays the date and time as 11:00:33 am on 09/08/2016.

Figure 1: (top, left) HPI displayed as a Key Parameter; (bottom, left) HPI High Alert Popup; (right) HPI Secondary Screen

SUMMARY OF NONCLINICAL/BENCH STUDIES

ELECTROMAGNETIC COMPATIBILITY AND ELECTRICAL SAFETY

The device is a software feature installed on the EV1000 Platform. The EV1000 Platform conforms with FDA-recognized standards for basic safety and essential performance of Medical Electrical Equipment. These standards include:

IEC 60601-1:2005 + CORR. 1 (2006) + CORR. 2 (2007) with report of US National . Differences - Medical Electrical Equipment, Part 1: General requirements for basic safety and essential performance
IEC 60601-1-2:2007 - Medical Electrical Equipment, Part 1-2: General requirements for safety - Collateral Standard: Electromagnetic compatibility - Requirements and tests.
IEC 60601-1-6:2010 Medical Electrical Equipment, Part 1-6: General requirements ● for safety and essential performance - Collateral Standard: Usability.
IEC 62366:2007 Medical Devices Application of usability engineering to medical ● devices.
IEC 60601-1-8:2006 - Medical Electrical Equipment, Part 1-8: General requirements

{4}------------------------------------------------

for basic safety and essential performance – Collateral Standard: General requirements, tests, and guidance for alarm systems in medical electrical equipment and medical electrical systems.

IEC 60601-2-49:2011 Medical electrical equipment Part 2-49: Particular ● requirements for the basic safety and essential performance of multifunction patient monitoring equipment
o IEC 60068-2-13:1985 - Basic environmental testing procedures - Part 2-13: Tests -Test M: Low air pressure

Electromagnetic compatibility information was provided in accordance with the FDA Guidance Document, "Information to Support a Claim of Electromagnetic Compatibility (EMC) of Electrically-Powered Medical Devices - Guidance for Industry and Food and Drug Administration Staff' (issued July 11, 2016).

SOFTWARE

Software documentation was provided in accordance with the FDA Guidance Document, "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices," (issued May 11, 2005) for a Moderate Level of Concern (LOC). A Moderate LOC is deemed appropriate as malfunction of the device software or a latent design flaw in the device software may lead to an erroneous diagnosis or a delay in the delivery of appropriate medical care, which would likely result in minor injury but would likely not result in serious injury or death due to the availability of other patient vital signs.

Regression testing was performed to demonstrate that the device software does not adversely impact the performance of the cleared EV1000 Platform.

Translation testing was performed to demonstrate that movement of the device software from the development environment to the EV1000 Platform does not adversely impact the intended performance of the EV1000 Platform.

Algorithm unit testing was performed to demonstrate that the device software meets its software requirements. This testing was performed using publicly available and privately collected patient data. Additional details are provided in the "Summary of Clinical Information" section.

Cybersecurity information was provided in accordance with the FDA Guidance Document, "Content of Premarket Submissions for Management of Cybersecurity in Medical Devices - Guidance for Industry and Food and Drug Administration Staff" (issued October 02, 2014).

USABILITY TESTING

Usability testing was necessary to mitigate the risk of delayed or incorrect treatment due

{5}------------------------------------------------

to user misinterpretation or overreliance on the indicator. Test reports were provided in accordance with the FDA Guidance Document, "Applying Human Factors and Usability Engineering to Medical Devices - Guidance for Industry and Food and Drug Administration Staff' (issued February 02, 2016). Fifteen (15) clinical participants, including anesthesiologists, intensivists, Certified Registered Nurse Anesthetists (CRNAs), and Intensive Care Unit (ICU) nurses participated in the testing. Testing was performed in a simulated use environment using a sequence of tasks, including monitoring initiation, configuration of the screen, response to high alert, and end of case. Specifically, users were assessed for the understanding that after a high HPI result, other physiologic parameters should be considered before taking clinical action. Interview questions were administered to assess user understanding of the monitor features and the meaning of a different HPI values. At least 80% of participants met the acceptance criteria of agree or strongly agree for all items, including when separating subjects by clinical profession and years of experience.

PERFORMANCE TESTING - ANIMAL

Device performance was evaluated in five swine using a hemorrhagic model and a vasodilation model. In the hemorrhagic model, swine were bled by venous catheter insertion at 5-20 cc/min after baseline stabilization was established, then held at a MAP of 60 mm/hg for 15 minutes. In the vasodilation model, swine at a MAP of 85 mm/hg were slowly administered nitroprusside (NTP) to reduce MAP to less than 65 mm/hg for 15 minutes. Device outputs (HPI. Eadyn, and dP/dt) were recorded during execution of both models. The device outputs were compared to animal status and proposed Indications for Use.

{6}------------------------------------------------

SUMMARY OF CLINICAL INFORMATION

Clinical validation of the HPI index used both publicly and privately collected data. Data utilized in the validation of the HPI Algorithm originated from two databases. The first database, the Edwards Lifesciences database, has archived data that were all collected via prospective, IRB/EC approved clinical protocols with informed consent for each patient. This database archive contains acute care OR patients (N=52) with wide ranges of procedures and with various acute conditions collected from global clinical sites. The patient data used for validation were all collected via prospective protocols. The second database came from a university hospital and included OR patients (n=204). The sensitivity, specificity, and area under the receiver operating characteristic for the first database were 83.7%, 99.8%, and 0.95 respectively. The sensitivity, specificity, and area under the receiver operating characteristic for the second database were 65.8%, 99.4%, and 0.88 respectively.

Pediatric Extrapolation

In this De Novo request, existing clinical data were not leveraged to support the use of the device in a pediatric patient population.

LABELING

The labeling includes the following elements:

a. A description of what the device measures and outputs to the user;
"Acumen Hypotension Prediction Index (HPI) software, when active and when using a FloTrac IQ sensor, connected to a radial arterial catheter, provides the clinician with information regarding the likelihood of a patient trending toward a hypotensive vent, defined as mean arterial pressure (MAP) < 65 mmHg for at least one minute."

"HPI uses features extracted from FloTrac IQ measurements, some compared to an initial base value determined over the first 10 minutes of the patient monitoring session, to a data-driven model developed from retrospective analysis of an arterial waveform database collected from ICU and OR patients containing annotated hypotensive (defined as MAP <65 mmHG for at least 1 minute) and non-hypotensive events. HPI is displayed as an integer value between 0 and 100."

b. Warnings identifying sensor acquisition factors that may impact measurement results;

{7}------------------------------------------------

Image /page/7/Picture/0 description: This image shows a caution notice regarding inaccurate FT-CO measurements. The notice states that inaccurate measurements can be caused by factors such as improperly zeroed sensors, over- or under-damped pressure lines, and excessive variations in blood pressure. Other factors include intra-aortic balloon pumps, clinical situations where arterial pressure is inaccurate, extreme peripheral vasoconstriction, hyperdynamic conditions, excessive patient movement, electrocautery interference, and aortic valve regurgitation. The notice references Chapter 7 and Chapter 16.

"The accuracy of the presented measurements are based on several factors: the arterial line is reliable (not damped), the pressure sensor is well aligned and the arterial line zeroed properly is connected to the device, and patient demographics (age, gender, height, and weight) have been entered into the device."

C. Guidance for interpretation of the measurements, including a statement that the output is adjunctive to other physical vital sign parameters and patient information;

{8}------------------------------------------------

HPI Value	Graphical DisplayElements	Audible	GeneralInterpretation	User Action
HPI ≤ 85	White	None	Patient hemodynamics indicate that there is a low to moderate likelihood of a hypotensive event occurring. A low HPI value does not exclude a hypotensive event from occurring in the next 5-15 minutes regardless of MAP value	Continue monitoring patient hemodynamics. Remain vigilant with respect to changing patient hemodynamics using the primary monitoring screen, HPI secondary screen, HPI, and trends in parameters and vital signs
HPI > 85	Red (Flashing)	High PriorityAlarm Tone	Patient has a high likelihood of experiencing a hypotensive event within 15 minutes	Check patient hemodynamics using the secondary screen and other primary screen parameters in order to investigate the potential cause of the high likelihood of hypotension in order to inform a potential course of action
HPI > 85 and persists for2 continuous readings(40 seconds)	Red (Flashing)Popup	High PriorityAlarm Tone	Patient has a high likelihood of experiencing a hypotensive event within 15 minutes	Check patient hemodynamics using the secondary screen and other primary screen parameters in order to investigate the potential cause of the high likelihood of hypotension in order to inform a potential course of actionAcknowledge popup by chosen method
HPI = 100	Red (Flashing)Popup	High PriorityAlarm Tone	Patient is hypotensive	Check patient hemodynamics using the secondary screen and other primary screen parameters in order to investigate the potential cause of the hypotension in order to inform a potential course of actionAcknowledge popup by chosen method

Table 16-2 HPI Value Graphical and Audible Display Elements

Note: If HPI is displayed in the Information Bar, the graphical display element changes will not change color nor alarm Instead, the user will only be notified when HP exceeds 85 for consecutive updates by displaying the HPJ High Alert Popup

"The Hypotension Prediction Index, HPI, should not be used exclusively to treat the patients. A review of the patient's hemodynamics is recommended prior to initiating treatment."

"The Acumen HPI feature is considered to be additional quantitative information regarding the patient's physiological condition for reference only and no therapeutic decisions should be made based solely on the Hypotension Prediction Index (HPI) parameter."

d. A specific time or a range of times before the predicted patient status or clinical event occurs, accounting for differences in patient condition and environment;
"Patient has a high likelihood of experiencing a hypotensive event within 15 minutes"
e. Key assumptions made during calculation of the output;
"The HPI parameter uses data from the first ten minutes of monitoring to establish a 'base value'. Device performance during these first ten minutes may differ as a result."

{9}------------------------------------------------

The type(s) of sensor data used, including specification of compatible sensors for data f. acquisition;
"Acumen Hypotension Prediction Index (HPI) software, when active and when using a FloTrac IQ sensor, connected to a radial arterial catheter, provides the clinician with information regarding the likelihood of a patient trending toward a hypotensive vent, defined as mean arterial pressure (MAP) < 65 mmHg for at least one minute."
g. The expected performance of the device for all intended use populations and environments; and

HPI Range	Event Rate (%)	Time-to-Event in minutes:Median [10th percentile,90th percentile]
10-14	14.2	8.0 [4.7, 12.7]
15-19	16.6	6.7 [3.3, 12.6]
20-24	15.4	7.0 [3.3, 14.0]
25-29	16.9	7.8 [3.7, 13.4]
30-34	22.5	9.0 [3.7, 14.0]
35-39	27.4	8.0 [3.3, 13.3]
40-44	31.8	8.3 [3.0, 13.7]
45-49	40.4	8.3 [3.3, 13.7]
50-54	43.4	7.7 [2.7, 13.3]
55-59	44.3	7.3 [3.0, 13.1]
60-64	57.0	6.7 [2.7, 12.8]
65-69	56.8	5.7 [2.3, 12.3]
70-74	67.2	5.7 [2.0, 11.7]
75-79	81.0	4.7 [2.0, 11.0]
80-84	84.2	5.0 [1.7, 12.3]
85-89	92.9	4.0 [1.7, 10.3]
90-94	95.8	3.7 [1.3, 10.0]
95-99	97.6	1.3 [0.3, 8.0]

Table 16-8 Clinical Validation (N=52)

"The Acumen HPI feature is intended for use in OR patients receiving advanced hemodynamic monitoring."

{10}------------------------------------------------

h. Relevant characteristics of the patients studied in the clinical validation (e.g., age, gender, race/ethnicity, patient condition) and a summary of validation results

Type	Clinical ValidationStudy(N=52)	Clinical ValidationStudy(N=204)
# of Patients	52	204
Gender (Male)	29	100
Age	$58.3\pm11.3$	$56.7\pm14.4$
BSA	$1.8\pm0.2$	$1.9\pm0.3$

Table 16-6 Patient Demographics

Table 16-7 Clinical Validation Studies*

ClinicalValidationStudy	HPIThreshold	PPV[confidenceinterval]	NPV[confidenceinterval]	Specificity(%)[95%confidenceinterval]	# Truenegative/# nonevents	Sensitivity(%)[95%confidenceinterval]	# Truepositive/# events	AUC
(N=52)	85	99.9(=886/887)[99.7, 100.0]	75.1(=520/692)[71.9, 78.4]	99.8[99.4, 100.0]	520/521	83.7[81.5, 86.0]	886/1058	0.95
(N=204)	85	98.3(=1265/1287)[97.6, 99.0]	84.9(=3709/4367)[83.9, 86.0]	99.4[99.2, 99.7]	3709/3731	65.8[63.7, 67.9]	1265/1923	0.88

*Data on File at Edwards Lifesciences

{11}------------------------------------------------

RISKS TO HEALTH

The table below identifies the risks to health that may be associated with use of the adjunctive predictive cardiovascular indicator and the measures necessary to mitigate these risks.

Identified Risk	Mitigation Measures
Delayed or incorrect treatment due toerroneous device output resulting fromsoftware malfunction or algorithm error	Software verification, validation, andhazard analysisNon-clinical performance testingClinical performance testingLabeling
Delayed or incorrect treatment due touser misinterpretation or overreliance onindicator	Usability assessmentLabeling

SPECIAL CONTROLS

In combination with the general controls of the FD&C Act, the adjunctive predictive cardiovascular indicator is subject to the following special controls:

1. A software description and the results of verification and validation testing based on a comprehensive hazard analysis and risk assessment must be provided, including:
- a. A full characterization of the software technical parameters, including algorithms;
- A description of the expected impact of all applicable sensor acquisition hardware b. characteristics and associated hardware specifications;
- c. A description of sensor data quality control measures;
- d. A description of all mitigations for user error or failure of any subsystem components (including signal detection, signal analysis, data display, and storage) on output accuracy:
- e. A description of the expected time to patient status or clinical event for all expected outputs, accounting for differences in patient condition and environment; and
- The sensitivity, specificity, positive predictive value, and negative predictive f. value in both percentage and number form.
1. A scientific justification for the validity of the predictive cardiovascular indicator algorithm(s) must be provided. This justification must include verification of the algorithm calculations and validation using an independent data set.
1. A human factors and usability engineering assessment must be provided that evaluates the risk of misinterpretation of device output.

{12}------------------------------------------------

1. A clinical data assessment must be provided. This assessment must fulfill the following:
- a. The assessment must include a summary of the clinical data used, including source, patient demographics, and any techniques used for annotating and separating the data.
- The clinical data must be representative of the intended use population for the b. device. Any selection criteria or sample limitations must be fully described and justified.
- c. The assessment must demonstrate output consistency using the expected range of data sources and data quality encountered in the intended use population and environment.
- d. The assessment must evaluate how the device output correlates with the predicted event or status.
1. Labeling must include:
- a. A description of what the device measures and outputs to the user;
- b. Warnings identifying sensor acquisition factors that may impact measurement results:
- c. Guidance for interpretation of the measurements, including a statement that the output is adjunctive to other physical vital sign parameters and patient information:
- d. A specific time or a range of times before the predicted patient status or clinical event occurs, accounting for differences in patient condition and environment;
- e. Key assumptions made during calculation of the output;
- The type(s) of sensor data used, including specification of compatible sensors for f. data acquisition:
- g. The expected performance of the device for all intended use populations and environments: and
- h. Relevant characteristics of the patients studied in the clinical validation (including age, gender, race or ethnicity, and patient condition) and a summary of validation results.

BENEFIT/RISK DETERMINATION

The risks of the device are based on nonclinical laboratory and animal studies, as well as retrospective clinical data as described above. The primary risk would be fluid overload or subsequent treatment with vasopressor based on a false positive HPI reading when the anesthesiologist is only relying on that single reading.

The probable benefits of the device are also based on nonclinical laboratory and animal studies, as well as retrospective clinical data as described above. The primary benefit of the HPI software is that it provides the physician with a predictive score that the patient may be trending toward a hypotensive event (defined as Mean Arterial Pressure < 65 mmHg for at least one minute in duration). For most patients, increased awareness to the increased risk for a hypotensive event

{13}------------------------------------------------

may help prevent a hemodynamic deterioration by first diagnosing the underlying dysfunction and then treating it.

Patient Perspectives

This submission did not include specific information on patient perspectives for this device.

Benefit/Risk Conclusion

In conclusion, given the available information summarized above, the data support that for the intended use specified above, the probable benefits outweigh the probable risks for the Acumen Hypotension Prediction Index Feature Software. The device provides benefits and the risks can be mitigated by the use of general controls and the identified special controls.

CONCLUSION

The De Novo request for the Acumen Hypotension Prediction Index Feature Software is granted and the device is classified under the following:

Product Code: QAQ Device Type: Adjunctive predictive cardiovascular indicator Class: II Regulation: 21 CFR 870.2210

Regulation Number and Section

§ 870.2210 Adjunctive predictive cardiovascular indicator.

(a)
Identification. The adjunctive predictive cardiovascular indicator is a prescription device that uses software algorithms to analyze cardiovascular vital signs and predict future cardiovascular status or events. This device is intended for adjunctive use with other physical vital sign parameters and patient information and is not intended to independently direct therapy.(b)
Classification. Class II (special controls). The special controls for this device are:(1) A software description and the results of verification and validation testing based on a comprehensive hazard analysis and risk assessment must be provided, including:
(i) A full characterization of the software technical parameters, including algorithms;
(ii) A description of the expected impact of all applicable sensor acquisition hardware characteristics and associated hardware specifications;
(iii) A description of sensor data quality control measures;
(iv) A description of all mitigations for user error or failure of any subsystem components (including signal detection, signal analysis, data display, and storage) on output accuracy;
(v) A description of the expected time to patient status or clinical event for all expected outputs, accounting for differences in patient condition and environment; and
(vi) The sensitivity, specificity, positive predictive value, and negative predictive value in both percentage and number form.
(2) A scientific justification for the validity of the predictive cardiovascular indicator algorithm(s) must be provided. This justification must include verification of the algorithm calculations and validation using an independent data set.
(3) A human factors and usability engineering assessment must be provided that evaluates the risk of misinterpretation of device output.
(4) A clinical data assessment must be provided. This assessment must fulfill the following:
(i) The assessment must include a summary of the clinical data used, including source, patient demographics, and any techniques used for annotating and separating the data.
(ii) The clinical data must be representative of the intended use population for the device. Any selection criteria or sample limitations must be fully described and justified.
(iii) The assessment must demonstrate output consistency using the expected range of data sources and data quality encountered in the intended use population and environment.
(iv) The assessment must evaluate how the device output correlates with the predicted event or status.
(5) Labeling must include:
(i) A description of what the device measures and outputs to the user;
(ii) Warnings identifying sensor acquisition factors that may impact measurement results;
(iii) Guidance for interpretation of the measurements, including a statement that the output is adjunctive to other physical vital sign parameters and patient information;
(iv) A specific time or a range of times before the predicted patient status or clinical event occurs, accounting for differences in patient condition and environment;
(v) Key assumptions made during calculation of the output;
(vi) The type(s) of sensor data used, including specification of compatible sensors for data acquisition;
(vii) The expected performance of the device for all intended use populations and environments; and
(viii) Relevant characteristics of the patients studied in the clinical validation (including age, gender, race or ethnicity, and patient condition) and a summary of validation results.