Bunkerhill ECG-EF

K250649 · BunkerHill Health · QYE · Sep 19, 2025 · Cardiovascular

Device Facts

• Record ID: K250649
• Device Name: Bunkerhill ECG-EF
• Applicant: BunkerHill Health
• Product Code: QYE · Cardiovascular
• Decision Date: Sep 19, 2025
• Decision: SESE
• Submission Type: Traditional
• Regulation: 21 CFR 870.2380
• Device Class: Class 2
• Attributes: AI/ML, Software as a Medical Device

Intended Use

Bunkerhill ECG-EF is software intended to aid in screening for Left Ventricular Ejection Fraction (LVEF) less than or equal to 40% in adults at risk for, but not already diagnosed with low LVEF. Bunkerhill ECG-EF is not intended to be a stand-alone diagnostic device for cardiac conditions, should not be used for monitoring of patients, and should not be used on ECGs with a paced rhythm. A positive result may suggest the need for further clinical evaluation in order to establish a diagnosis of Left Ventricular Ejection Fraction (LVEF) less than or equal to 40%. Additionally, if the patient is at high risk for the cardiac condition, a negative result should not rule out further non-invasive evaluation. Bunkerhill ECG-EF is adjunctive and must be interpreted in conjunction with the clinician's judgment, the patient's medical history, symptoms, and additional diagnostic tests. For a final clinical diagnosis, further confirmatory testing, such as echocardiography, is required.

Device Story

Bunkerhill ECG-EF is a software-only device using deep learning to analyze 10-second 12-lead ECG waveform snippets. It identifies patients at risk for heart failure by detecting LVEF ≤ 40%. Used in primary, urgent, and emergency care settings by clinicians, the software integrates with EMR or ECG management systems to display results (Positive, Negative, or Error) on smartphones, tablets, or PCs. It serves as an adjunctive screening tool; results are not diagnostic and must be interpreted alongside clinical judgment and confirmatory testing like echocardiography. The device benefits patients by facilitating early identification of low LVEF in settings where imaging may be unavailable or difficult to operate.

Clinical Evidence

Retrospective study of 15,994 patient records across 5 U.S. sites. Ground truth established via echocardiogram (Simpson's Biplane) within 15 days of ECG. Results: Sensitivity 82.66% (95% CI: 80.90-84.30), Specificity 83.20% (95% CI: 82.60-83.80), PPV 37.20% (95% CI: 35.70-38.76), NPV 97.54% (95% CI: 97.28-97.83). Primary endpoints met. Subgroup analysis showed performance variation by age and specific medical history (MI, revascularization, AFib), but no statistically significant heterogeneity by clinical site, sex, race, or ECG device manufacturer.

Technological Characteristics

SaMD packaged in a Docker container. Inputs: 12-lead ECG digital waveforms (500Hz). Processing: Deep learning algorithm. Output: Binary classification (Low EF detected/not detected) via API to third-party EMR/EMS. No native GUI. Validated for use with specific ECG systems (Philips PageWriter TC70, GE Dash 3000, GE MAC 5500 HD, GE MAC VU360) using Ag-AgCl electrodes.

Indications for Use

Indicated for adults at risk for, but not already diagnosed with, low LVEF (≤ 40%). Contraindicated for use on ECGs with a paced rhythm.

Regulatory Classification

Identification

Viz HCM is a cardiovascular machine learning-based notification software intended to be used in parallel to the standard of care to analyze 12-lead ECG recordings from patients 18 years of age or older. It detects signs associated with hypertrophic cardiomyopathy (HCM) and allows the user to view the ECG and analysis results. It is not intended for use on patients with implanted pacemakers, does not replace standard diagnostic methods, and is not intended to rule out HCM or be used in lieu of a full patient evaluation.

Special Controls

In combination with the general controls of the FD&C Act, cardiovascular machine learningbased notification software is subject to the following special controls:

Predicate Devices

• Low Ejection Fraction AI-ECG Algorithm (K232699)

Reference Devices

• Eko Low Ejection Fraction Tool (ELEFT) (K233409)

Submission Summary (Full Text)

{0}

FDA U.S. FOOD & DRUG ADMINISTRATION

September 19, 2025

BunkerHill Health
% John Smith
Partner
Hogan Lovells LLP
555 Thirteenth Street, NW
Washington, District of Columbia 20004

Re: K250649
Trade/Device Name: Bunkerhill ECG-EF
Regulation Number: 21 CFR 870.2380
Regulation Name: Cardiovascular Machine Learning-Based Notification Software
Regulatory Class: Class II
Product Code: QYE
Dated: March 3, 2025
Received: March 4, 2025

Dear John Smith:

We have reviewed your section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (the Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database available at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.

If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.

U.S. Food & Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993
www.fda.gov

{1}

K250649 - John Smith
Page 2

Additional information about changes that may require a new premarket notification are provided in the FDA guidance documents entitled "Deciding When to Submit a 510(k) for a Change to an Existing Device" (https://www.fda.gov/media/99812/download) and "Deciding When to Submit a 510(k) for a Software Change to an Existing Device" (https://www.fda.gov/media/99785/download).

Your device is also subject to, among other requirements, the Quality System (QS) regulation (21 CFR Part 820), which includes, but is not limited to, 21 CFR 820.30, Design controls; 21 CFR 820.90, Nonconforming product; and 21 CFR 820.100, Corrective and preventive action. Please note that regardless of whether a change requires premarket review, the QS regulation requires device manufacturers to review and approve changes to device design and production (21 CFR 820.30 and 21 CFR 820.70) and document changes and approvals in the device master record (21 CFR 820.181).

Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting (reporting of medical device-related adverse events) (21 CFR Part 803) for devices or postmarketing safety reporting (21 CFR Part 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reporting-combination-products); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR Part 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR Parts 1000-1050.

All medical devices, including Class I and unclassified devices and combination product device constituent parts are required to be in compliance with the final Unique Device Identification System rule ("UDI Rule"). The UDI Rule requires, among other things, that a device bear a unique device identifier (UDI) on its label and package (21 CFR 801.20(a)) unless an exception or alternative applies (21 CFR 801.20(b)) and that the dates on the device label be formatted in accordance with 21 CFR 801.18. The UDI Rule (21 CFR 830.300(a) and 830.320(b)) also requires that certain information be submitted to the Global Unique Device Identification Database (GUDID) (21 CFR Part 830 Subpart E). For additional information on these requirements, please see the UDI System webpage at https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-assistance/unique-device-identification-system-udi-system.

Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-devices/medical-device-safety/medical-device-reporting-mdr-how-report-medical-device-problems.

For comprehensive regulatory information about medical devices and radiation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-

{2}

K250649 - John Smith
Page 3

assistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email ([e-mail]) or phone [phone] or 301-796-7100).

Sincerely,

Jackson Hair-S
Digitally signed by Jackson Hair-S
Date: 2025.09.19 13:41:37 -04'00'

for
LCDR Stephen Browning
Assistant Director
Division of Cardiac Electrophysiology,
Diagnostics, and Monitoring Devices
Office of Cardiovascular Devices
Office of Product Evaluation and Quality
Center for Devices and Radiological Health

{3}

FORM FDA 3881 (8/23)
Page 1 of 1
PSC Publishing Services [phone]
EF

| DEPARTMENT OF HEALTH AND HUMAN SERVICES Food and Drug Administration Indications for Use | Form Approved: OMB No. 0910-0120 Expiration Date: 07/31/2026 See PRA Statement below. |
| --- | --- |
| 510(k) Number (if known) K250649 | |
| Device Name Bunkerhill ECG-EF | |
| Indications for Use (Describe) Bunkerhill ECG-EF is software intended to aid in screening for Left Ventricular Ejection Fraction (LVEF) less than or equal to 40% in adults at risk for, but not already diagnosed with low LVEF. Bunkerhill ECG-EF is not intended to be a stand-alone diagnostic device for cardiac conditions, should not be used for monitoring of patients, and should not be used on ECGs with a paced rhythm. A positive result may suggest the need for further clinical evaluation in order to establish a diagnosis of Left Ventricular Ejection Fraction (LVEF) less than or equal to 40%. Additionally, if the patient is at high risk for the cardiac condition, a negative result should not rule out further non-invasive evaluation. Bunkerhill ECG-EF is adjunctive and must be interpreted in conjunction with the clinician's judgment, the patient's medical history, symptoms, and additional diagnostic tests. For a final clinical diagnosis, further confirmatory testing, such as echocardiography, is required. | |
| Type of Use (Select one or both, as applicable) ☑ Prescription Use (Part 21 CFR 801 Subpart D) ☐ Over-The-Counter Use (21 CFR 801 Subpart C) | |
| CONTINUE ON A SEPARATE PAGE IF NEEDED. | |
| This section applies only to requirements of the Paperwork Reduction Act of 1995. *DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.* | |
| The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to: Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff [e-mail] | |
| "An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number." | |

{4}

K250649 - BunkerHill ECG-EF - Low Ejection Fraction AI-ECG Algorithm

# 510(K) SUMMARY

# Bunkerhill ECG-EF

Bunkerhill, Inc. 436 Bryant Street

San Francisco CA 94107

Phone: [phone]

Contact Person: Eren Alkan

Date Prepared: September 19, 2025

Proposed Device

| Proprietary Name | Bunkerhill ECG-EF |
| --- | --- |
| Cardiovascular Machine Learning-Based Notification Software | Cardiovascular Machine Learning-Based Notification Software |
| Regulation Number | 21 CFR 870.2380 |
| Product Code | QYE |
| Regulatory Class | II |

Predicate Device

| Proprietary Name | Low Ejection Fraction AI-ECG Algorithm |
| --- | --- |
| Premarket Notification | K232699 |
| Classification Name | Cardiovascular Machine Learning-Based Notification Software |
| Regulation Number | 21 CFR 870.2380 |
| Product Code | QYE |
| Regulatory Class | II |

Reference Device

| Proprietary Name | Eko Low Ejection Fraction Tool (ELEFT) |
| --- | --- |
| Premarket Notification | K233409 |
| Classification Name | Cardiovascular Machine Learning-Based Notification Software |
| Regulation Number | 21 CFR 870.2380 |
| Product Code | QYE |
| Regulatory Class | II |

{5}

K250649 - BunkerHill ECG-EF - Low Ejection Fraction AI-ECG Algorithm

# Device Description

ECG-EF is a software-only medical device that employs deep learning algorithms to analyze 12-lead ECG data for the detection of low left ventricular ejection fraction (LVEF < 40%). The algorithm processes 10-second ECG waveform snippets, providing predictions to assist healthcare professionals in the early identification of patients at risk for heart failure.

ECG-EF algorithm receives digital 12-lead ECG data and processes it through its machine learning model. The output of the analysis is transmitted to integrated third-party software systems, such as Electronic Medical Records (EMR) or ECG Management Systems (EMS). The results are displayed by the third-party software on a device such as a smartphone, tablet, or PC.

ECG-EF algorithm produces a result indicating "Low EF Screen Positive - High probability of low ejection fraction based on the ECG", "Low EF Screen Negative - Low probability of low ejection fraction based on the ECG" or "Error - device input criteria not met" for cases that do not meet data input requirements. These results are not intended to be definitive diagnostic outputs but rather serve as adjunctive information to support clinical decision-making. A disclaimer accompanies the output, stating: "Not for diagnostic use. The results are not final and must be reviewed alongside clinical judgment and other diagnostic methods."

The Low Ejection Fraction AI-ECG Algorithm device is intended to address the unmet need for a point-of-care screen for LVEF less than or equal to 40% and is expected to be used by cardiologists, front-line clinicians at primary care, urgent care, and emergency care settings, where cardiac imaging may not be available or may be difficult or unreliable for clinicians to operate. Clinicians will use the Low Ejection Fraction AI-ECG Algorithm to aid in screening for LVEF less than or equal to 40% and making a decision for further cardiac evaluation.

# Intended Use / Indications for Use

Bunkerhill ECG-EF is software intended to aid in screening for Left Ventricular Ejection Fraction (LVEF) less than or equal to 40% in adults at risk for, but not already diagnosed with low LVEF.

Bunkerhill ECG-EF is not intended to be a stand-alone diagnostic device for cardiac conditions, should not be used for monitoring of patients, and should not be used on ECGs with a paced rhythm. A positive result may suggest the need for further clinical evaluation in order to establish a diagnosis of Left Ventricular Ejection Fraction (LVEF) less than or equal to 40%.

Additionally, if the patient is at high risk for the cardiac condition, a negative result should not rule out further non-invasive evaluation.

Bunkerhill ECG-EF is adjunctive and must be interpreted in conjunction with the clinician's judgment, the patient's medical history, symptoms, and additional diagnostic tests. For a final clinical diagnosis, further confirmatory testing, such as echocardiography, is required.

{6}

K250649 - BunkerHill ECG-EF - Low Ejection Fraction AI-ECG Algorithm

Table 1: Indications for Use Comparison

| | Proposed Device: Bunkerhill ECG-EF Algorithm | Predicate Device: Low Ejection Fraction AI-ECG Algorithm (K232699) | Reference Device: Eko Low Ejection Fraction Tool (K233409) |
| --- | --- | --- | --- |
| Intended use / Indications for use | Bunkerhill ECG-EF is software intended to aid in screening for Left Ventricular Ejection Fraction (LVEF) less than or equal to 40% in adults at risk for, but not already diagnosed with low LVEF.Bunkerhill ECG-EF is not intended to be a stand-alone diagnostic device for cardiac conditions, should not be used for monitoring of patients, and should not be used on ECGs with a paced rhythm. A positive result may suggest the need for further clinical evaluation in order to establish a diagnosis of Left Ventricular Ejection Fraction (LVEF) less than or equal to 40%.Additionally, if the patient is at high risk for the cardiac condition, a negative result should not rule out further non-invasive evaluation.Bunkerhill ECG-EF is adjunctive and must be interpreted in conjunction with the clinician's judgment, the patient's medical history, symptoms, and additional diagnostic tests. For a final clinical diagnosis, further confirmatory testing, such as echocardiography, is required. | The Anumana Low Ejection Fraction AI-ECG Algorithm is software intended to aid in screening for Left Ventricular Ejection Fraction (LVEF) less than or equal to 40% in adults at risk for heart failure. This population includes, but is not limited to:• patients with cardiomyopathies• patients who are post-myocardial infarction• patients with aortic stenosis• patients with chronic atrial fibrillation• patients receiving pharmaceutical therapies that are cardiotoxic, and• postpartum women.Anumana Low Ejection Fraction AI-ECG Algorithm is not intended to be a stand- alone diagnostic device for cardiac conditions, should not be used for monitoring of patients, and should not be used on ECGs with a paced rhythm.A positive result may suggest the need for further clinical evaluation in order to establish a diagnosis of Left Ventricular Ejection Fraction (LVEF) less than or equal to 40%. Additionally, if the patient is at high risk for the cardiac condition, a negative result should not rule out further non-invasive evaluation.The Anumana Low Ejection Fraction AI-ECG Algorithm should be applied jointly with clinician judgment. | Eko Low Ejection Fraction Tool (ELEFT) is a software intended to aid clinicians in identifying individuals with Left Ventricular Ejection Fraction (LVEF) less than or equal to 40%. ELEFT takes as input ECG and heart sounds and is intended for use on patients at risk for heart failure. This population includes, but is not limited to, patients with: coronary artery disease; diabetes mellitus; cardiomyopathy; hypertension; and obesity.The interpretations of heart sounds and ECG offered by the software are meant only to assist healthcare providers in assessing Left Ventricular Ejection Fraction ≤ 40%, who may use the result in conjunction with their own evaluation and clinical judgment. It is not a diagnosis or for monitoring of patients diagnosed with heart failure. This software is for use on adults (18 years and older). |

{7}

K250649 - BunkerHill ECG-EF - Low Ejection Fraction AI-ECG Algorithm

The intended use of the Bunkerhill ECG-EF is the same as that of the Anumana Low Ejection Fraction AI-ECG Algorithm, and reference device, Eko Low Ejection Fraction Tool (ELEFT) as the devices are software tools designed to aid in screening for Left Ventricular Ejection Fraction (LVEF) $\leq 40\%$ in adults at risk for heart failure.

- Both devices assist certified medical professionals with analyze 12-lead ECG data for the rapid detection of low left ventricular ejection fraction (LVEF $\leq 40\%$).
- Both subject and predicate devices are not intended to be used stand-alone, can be used optionally by the physician and do not provide a definitive diagnosis. Both devices require the physician to use this information to decide next steps and/or additional diagnostic work up.
- Verification and validation testing, including performance assessment demonstrates that the Bunkerhill ECG-EF Device is as safe and effective as its predicate device.

## Summary of Technological Characteristics

There are no major changes to technological characteristics in the subject device compared to the predicate device. Both the predicate and the subject device A) use machine learning algorithms to analyze 12-lead ECG data for the rapid detection of low left ventricular ejection fraction (LVEF $\leq 40\%$). Both the algorithms process 10-second ECG waveform snippets, providing predictions to assist healthcare professionals in the early identification of patients at risk for heart failure. However, they do not replace clinical evaluation and do not alter the standard of care.

The subject device and the predicate device are Software as a Medical Device (SaMD) provided as a software module packaged in a Docker container. The Algorithms do not provide a graphical user interface (GUI) of their own. They are integrated with other medical systems such as Electronic Medical Record (EMR) systems or ECG Management Systems (EMS). The third-party integrating software furnishes a 12-lead ECG digital waveform as input to the Low Ejection Fraction AI-ECG Algorithm and records the algorithm output for display via the integrated medical system or for printing in an offline report.

There are no major differences between subject device and reference device as well. The reference device can also analyze PCG signals when available. Any minor differences in the technology characteristics do not raise different questions of safety and effectiveness.

{8}

K250649 - BunkerHill ECG-EF - Low Ejection Fraction AI-ECG Algorithm

Table 2: Technological Comparison

| | Proposed Device: Bunkerhill ECG-EF Algorithm | Predicate Device: Low Ejection Fraction AI-ECG Algorithm (K232699) | Reference Device: Eko Low Ejection Fraction Tool (K233409) | Summary |
| --- | --- | --- | --- | --- |
| Product code | QYE | QYE | QYE | Same |
| Regulation number | 21 CFR 870.2380 | 21 CFR 870.2380 | 21 CFR 870.2380 | Same |
| Regulation Name | Cardiovascular machine learning-based notification software | Cardiovascular machine learning-based notification software | Cardiovascular machine learning-based notification software | Same |
| Operational Mode | Spot Check | Spot Check | Spot Check | Same |
| Patient population | Adults | Adults | Adults 18 and older | Same |
| Environment of Use | Primary care, urgent care, and emergency care settings | Primary care, urgent care, and emergency care settings | Primary care, urgent care, and emergency care settings | Same- Both devices are to be used in professional healthcare settings |
| Algorithm | Machine learning based algorithm | Machine learning based algorithm | Machine learning based algorithm | Same |
| Algorithm Calculation and Output | Detection of LVEF (Left Ventricular Ejection Fraction less than or equal to 40%) from an ECG signal | Detection of LVEF (Left Ventricular Ejection Fraction less than or equal to 40%) from an ECG signal | The Eko Low Ejection Fraction Tool (ELEFT) to identify individuals with Left Ventricular Ejection Fraction (LVEF) less than or equal to 40% by analyzing ECG and heart sounds from patients at risk for heart failure. | Same |
| Ground Truth for Model Training | Transthoracic echocardiogram (TTE) with disease | Transthoracic echocardiogram (TTE) with disease | gold standard echocardiogram | Same- Both devices rely upon established clinical diagnostic methods as ground truth |
| Physiological Parameter Inputs | 12-Lead ECG waveform in digital format | 12-Lead ECG waveform in digital format | ECG recording signals from single lead PCG recording signals (when available) | Same- Both devices utilize ECG digital waveforms as input |
| Data Displayed | Algorithm output is provided to third party software that displays the result to clinicians. Output provided for each ECG is “Low LVEF Detected” “Low | Algorithm output is provided to third party software that displays the result to clinicians. Output provided for each ECG is “Low LVEF Detected” “Low LVEF Not Detected” | Application Programming Interface (API) only, no user interface | Same- Both devices provide data suggesting the likelihood of the same cardiovascular disease or condition for further referral or diagnostic follow-up. |

{9}

K250649 - BunkerHill ECG-EF - Low Ejection Fraction AI-ECG Algorithm

| | Proposed Device: Bunkerhill ECG-EF Algorithm | Predicate Device: Low Ejection Fraction AI-ECG Algorithm (K232699) | Reference Device: Eko Low Ejection Fraction Tool (K233409) | Summary |
| --- | --- | --- | --- | --- |
| | LVEF Not Detected" or "Error - device input criteria not met"). | or "Error"). | | |
| Hardware | Compatible 12-Lead diagnostic ECG machines with 500Hz digital output | Compatible 12-Lead diagnostic ECG machines with 500Hz digital output | ECG recording signals from single lead PCG recording signals (when available) | Same |
| Software | Bunkerhill proprietary algorithm and application | Bunkerhill proprietary algorithm and application | proprietary algorithm and application | Same |
| Type of Interpretation | Adjunctive information | Adjunctive information | Same | Type of Interpretation |
| Intended User | Appropriately trained medical specialists such as cardiologists, front-line clinicians at primary care, urgent care, and emergency care settings | Appropriately trained medical specialists such as cardiologists, front-line clinicians at primary care, urgent care, and emergency care settings | Same | Intended User |
| Rx or OTC | Rx | Rx | Same | Rx or OTC |

# Performance Data

Safety and performance of the Bunkerhill ECG-EF algorithm has been evaluated and verified in accordance with software specifications and applicable performance standards through Software Development and Validation & Verification Process to ensure performance according to specifications, User Requirements and Federal Regulations and Guidance documents, "Content of Premarket Submissions for Device Software Functions" and a thorough cybersecurity assessment was performed per FDA Guidance "Cybersecurity in medical devices: Quality System Considerations and Content of Premarket Submissions".

The performance of the ECG-EF algorithm was validated through a retrospective study involving 15,994 patient records sourced from two health systems across the United States. The study aimed to assess the diagnostic accuracy of the algorithm in identifying patients with an ejection fraction (EF) $< 40\%$ within a clinically and demographically diverse population. The study sample was representative of the U.S population and was $65.5\%$ White, $18.8\%$ Hispanic, $5.7\%$ American Indian or Alaska Native, $3.9\%$ Asian, $3.0\%$ Black/African American, and $2.8\%$ Other. The sample consisted of $53\%$ Male and $47\%$ Female. The pivotal dataset was be curated from 5 sites geographically distributed throughout the United

{10}

K250649 - BunkerHill ECG-EF - Low Ejection Fraction AI-ECG Algorithm

States. The ground truth was established from an echocardiogram using the Simpson's Biplane measurement method taken less than 15-days apart from the ECG scan.

Within this diverse dataset, a total of 1725 LVEF $\leq 40\%$ cases were identified based on the echocardiogram from 15,994 samples (prevalence of $10.8\%$ ). The Bunkerhill ECG-EF device achieved a sensitivity of $82.66\%$ (80.90-84.30), a specificity of $83.20\%$ (82.60-83.80), a PPV of $37.20\%$ (35.70-38.76), and NPV of $97.54\%$ (97.28-97.83). The confidence intervals are available in the table below. The confusion matrix summarizing the results are available in Figure 1: Bunkerhill ECG EF Confusion Matrix below.

| Performance Metric | Acceptance Criteria | Value | Bootstrap | Clopper-Pearson | Wilson | Pass/Fail |
| --- | --- | --- | --- | --- | --- | --- |
| Sensitivity | Se ≥ 80% | 82.66% | (80.90–84.30) | (80.80 - 84.43) | (80.81 - 84..38) | Pass |
| Specificity | Sp ≥ 80% | 83.20% | (82.60–83.80) | (82.56 - 83.80) | (82.56 - 83.79) | Pass |
| PPV | PPV ≥ 25% | 37.20% | (35.70–38.76) | (35.75 - 38.84) | (35.76 - 38.38) | Pass |
| NPV | NPV ≥ 95% | 97.54% | (97.28–97.83) | (97.25 - 97.81) | (97.25 - 97.80) | Pass |

Figure 1: Bunkerhill ECG-EF Confusion Matrix

{11}

K250649 - BunkerHill ECG-EF - Low Ejection Fraction AI-ECG Algorithm

The primary endpoint was Detection of Low Left Ventricular Ejection Fraction and the acceptance criteria were $\mathrm{Se} / \mathrm{Sp} \geq 80$ , $\mathrm{PPV} \geq 25\%$ , $\mathrm{NPV} \geq 95\%$ . All the primary acceptance criteria were successfully met. The secondary acceptance criteria for Detection of Low Left Ventricular Ejection Fraction using AUROC plot was also met.

Subgroup assessments of diagnostic performance were conducted to determine if there was heterogeneity in device performance across clinical sites, demographics, clinical characteristics, co-morbidities, ECG manufacturer and ECG devices. The findings are summarized in Table 3: Subgroup Analysis:

Table 3: Sub-group Analysis

| Subgroup Analysis | Result of Test for Heterogeneity |
| --- | --- |
| Clinical Site | Not statistically significant |
| Sex | Not statistically significant |
| Race/Ethnicity | Not statistically significant |
| Age Group | Diagnostic performance varied across age group strata (p<0.01). The diagnostic odds ratio was higher than the overall estimate in patients aged 18-49 and 70-79 while it's lower in patients age group of 60-69 and 80+. In younger patients, sensitivity was higher while specificity was lower, whereas in patients of advanced age, sensitivity was lower while specificity was higher. |
| Clinical Characteristics | Diagnostic performance varied across certain elements of medical history derived from ICD9/ICD10 codes in patient medical records. The diagnostic odds ratio was higher in patients with Myocardial Infarction (p<0.01) and lower for Coronary Revascularization (p<0.01) and Atrial Fibrillation/Flutter (p<0.01). In each of these cases, there was a higher presence of low ejection fraction, the algorithm had higher sensitivity and lower specificity, and as a result there were robust PPV and NPV results. |
| Device / Manufacturer | Not statistically significant |
| Conduction Disorder | Not statistically significant |

# Note:

This device only should be used with 12-lead ECGs acquired using Ag-AgCl electrodes in the standard lead configuration on the following validated ECG acquisition systems: Philips PageWriter TC70, GE Dash 3000, GE MAC 5500 HD, GE MAC VU360.

# Warning (Safety):

Use of non-validated ECG devices, alternative electrode types, or non-standard acquisition conditions may result in inaccurate results.

# Conclusions

The Bunkerhill ECG-EF algorithm is as safe and effective as the predicate Low Ejection Fraction AI-ECG Algorithm (K232699). The subject device has the same intended uses and similar indications,

{12}

K250649 - BunkerHill ECG-EF - Low Ejection Fraction AI-ECG Algorithm

technological characteristics, and principles of operation as its predicate device. The minor differences in indications do not alter the intended diagnostic use of the device and do not affect its safety and effectiveness when used as labeled. In summary, any minor differences between the Low Ejection Fraction AI-ECG Algorithm and the Bunkerhill ECG-EF Device do not raise any issues of safety or effectiveness.