What is the FDA product code for Acumen Hypotension Prediction Index (HPI) Feature Software?

QAQ. It is classified under 21 CFR 870.2210 as a Class 2 device in the Cardiovascular panel.

What is the regulatory pathway for Acumen Hypotension Prediction Index (HPI) Feature Software?

De Novo classification (submission type: Direct).

Does Acumen Hypotension Prediction Index (HPI) Feature Software use AI or machine learning?

Yes. Acumen Hypotension Prediction Index (HPI) Feature Software (DEN160044) is flagged as an AI/ML-enabled medical device in the FDA's AI/ML device list.

Who can help prepare an FDA De Novo submission like Acumen Hypotension Prediction Index (HPI) Feature Software?

Innolitics — a medical-device software consultancy — provides regulatory and engineering support for FDA De Novo submissions. See https://innolitics.com/services/regulatory/ or contact https://innolitics.com/contact.

Can an AI/ML device like Acumen Hypotension Prediction Index (HPI) Feature Software get a guaranteed FDA De Novo clearance?

Yes. Innolitics offers a guaranteed FDA De Novo classification engagement for AI/ML Software as a Medical Device — combining engineering and regulatory execution under one agreement with a guaranteed clearance outcome. Eligibility: the device must be an AI/ML Software as a Medical Device (SaMD), and its performance must meet the criteria Innolitics determines during an initial regulatory strategy engagement to be necessary for FDA clearance. See https://innolitics.com/services/end-to-end-samd/ or contact https://innolitics.com/contact.

Acumen Hypotension Prediction Index (HPI) Feature Software

Q: Who is the manufacturer of Acumen Hypotension Prediction Index (HPI) Feature Software?

Edwards Lifesciences, LLC filed the De Novo classification request for Acumen Hypotension Prediction Index (HPI) Feature Software (DEN160044).

DEN160044 · Edwards Lifesciences, LLC · QAQ · Mar 16, 2018 · Cardiovascular

Device Facts

Record ID	DEN160044
Device Name	Acumen Hypotension Prediction Index (HPI) Feature Software
Applicant	Edwards Lifesciences, LLC
Product Code	QAQ · Cardiovascular
Decision Date	Mar 16, 2018
Decision	DENG
Submission Type	Direct
Regulation	21 CFR 870.2210
Device Class	Class 2
Attributes	AI/ML, Software as a Medical Device, Real-World Evidence

Real-World Evidence

Submission	Device	Sponsor	RWD Sources	RWE Use Summary	Key Tags
DEN160044 · Mar 16, 2018	Acumen Hypotension Prediction Index (HPI) Feature Software	Edwards Lifesciences, LLC	Retrospective arterial waveform database (ICU and OR patients)	Retrospective clinical data were used to develop the data-driven model for the Hypotension Prediction Index (HPI) and to validate the algorithm's performance (sensitivity, specificity, and AUC).	Retrospective analysis; Algorithm development; Clinical validation; Arterial waveform database

Clinical Evidence

Study Design	Population	Comparator	Key Endpoints
Edwards Lifesciences Database; Retrospective analysis	Acute care OR patients; Sample Size: 52; Number of Sites: Global clinical sites	Not applicable for this study	Sensitivity, specificity, and area under the receiver operating characteristic (AUC)
University Hospital Database; Retrospective analysis	OR patients; Sample Size: 204; Number of Sites: 1	Not applicable for this study	Sensitivity, specificity, and area under the receiver operating characteristic (AUC)

AI Performance

Output	Algorithm	Acceptance	Observed	Dev DS	Dev Readers	Test DS	Test Readers
Hypotension Prediction Index	Data-driven model developed from retrospective analysis of arterial waveforms	—	Database 1 (N=52): Sensitivity 83.7%, Specificity 99.8%, AUC 0.95; Database 2 (N=204): Sensitivity 65.8%, Specificity 99.4%, AUC 0.88	Database 1: 52 OR patients; Database 2: 204 OR patients	—	—	—

Indications for Use

The Edwards Lifesciences Acumen Hypotension Prediction Index 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 Story

Software feature for hemodynamic monitoring; analyzes cardiovascular vital signs to predict future hypotensive events; provides clinician with quantitative index (HPI) and associated hemodynamic data; used in operating room; intended for adjunctive use alongside other vital signs and patient information; not for independent therapeutic decision-making; assists clinicians in identifying potential patient instability; enables proactive clinical intervention.

Clinical Evidence

Retrospective validation using two databases (N=52 and N=204) of OR patients. Primary endpoints: sensitivity, specificity, and AUC for predicting hypotension (MAP < 65 mmHg for ≥ 1 min) within 15 minutes. Database 1 (N=52): sensitivity 83.7%, specificity 99.8%, AUC 0.95. Database 2 (N=204): sensitivity 65.8%, specificity 99.4%, AUC 0.88. Animal studies (N=5 swine) using hemorrhagic and vasodilation models confirmed device output correlation with physiological status.

Technological Characteristics

Software-based predictive cardiovascular indicator; analyzes cardiovascular vital signs; provides quantitative index; requires integration with compatible hemodynamic monitoring sensors; subject to software verification, validation, and hazard analysis; requires human factors/usability assessment.

Indications for Use

Indicated for patients in the operating room (OR) receiving advanced hemodynamic monitoring to provide insight into the likelihood of future hypotensive events (MAP < 65 mmHg for at least one minute).

Regulatory Classification

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.

Special Controls

*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.

Submission Summary (Full Text)

{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 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. #### 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 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. 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. 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. {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 Display Elements | Audible | General Interpretation | 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 Priority Alarm 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 for 2 continuous readings (40 seconds) | Red (Flashing) Popup | High Priority Alarm 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 Acknowledge popup by chosen method | | HPI = 100 | Red (Flashing) Popup | High Priority Alarm 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 action Acknowledge 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 Validation Study (N=52) | Clinical Validation Study (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* | Clinical Validation Study | HPI Threshold | PPV [confidence interval] | NPV [confidence interval] | Specificity (%) [95% confidence interval] | # True negative/ # nonevents | Sensitivity (%) [95% confidence interval] | # True positive/ # 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 to erroneous device output resulting from software malfunction or algorithm error | Software verification, validation, and hazard analysis Non-clinical performance testing Clinical performance testing Labeling | | Delayed or incorrect treatment due to user misinterpretation or overreliance on indicator | Usability assessment Labeling | # 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. - 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. {12}------------------------------------------------ - 4. 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. - 5. 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

Acumen Hypotension Prediction Index (HPI) Feature Software

Device Facts

Real-World Evidence

Clinical Evidence

AI Performance

Indications for Use

Device Story

Clinical Evidence

Technological Characteristics

Indications for Use

Regulatory Classification

Identification

Special Controls

Submission Summary (Full Text)

Panel 1

Section Matches

Product Code Matches

Special Control Matches

My Alerts

Acumen Hypotension Prediction Index (HPI) Feature Software

Device Facts

Real-World Evidence

Clinical Evidence

AI Performance

Indications for Use

Device Story

Clinical Evidence

Technological Characteristics

Indications for Use

Regulatory Classification

Identification

Special Controls

Submission Summary (Full Text)

Panel 1

Section Matches

Product Code Matches

Special Control Matches

My Alerts

Create Alert

Search Filters

Agent Token

Welcome

Check your email

Welcome!