LOGIQ Fortis is intended for use by a qualified physician for ultrasound evaluation of Fetal/Obstetrics; Abdominal (including Renal, Gynecology/Pelvic); Pediatric; Small Organ (Breast, Testes, Thyroid); Neonatal Cephalic; Adult Cephalic; Cardiac (Adult and Pediatric); Peripheral Vascular; Musculo-skeletal Conventional and Superficial; Urology (including Prostate); Transrectal; Transvaginal; Transesophageal and Intraoperative (Abdominal and Vascular).

Modes of operation include: B, M, PW Doppler, CW Doppler, Color Doppler, Color M Doppler, Power Doppler, Harmonic Imaging, Coded Pulse, 3D/4D Imaging mode, Elastography, Shear Wave Elastography, Attenuation Imaging and Combined modes: B/M, B/Color, B/PWD, B/Color/PWD, B/Power/PWD.

The LOGIQ Fortis is intended to be used in a hospital or medical clinic.

Device Description

The LOGIQ Fortis is a full featured, Track 3, general purpose diagnostic ultrasound system which consists of a mobile console approximately 575 mm wide (keyboard), 925 mm deep and 1300 mm high that provides digital acquisition, processing and display capability. The user interface includes a digital keyboard (physical keyboard as an option), specialized controls, 12-inch high-resolution color touch screen and 23.8-inch High Contrast LED LCD monitor (or 23.8-inch High Resolution LED LCD monitor as an option).

AI/ML Overview

Here's a breakdown of the acceptance criteria and study details for the AI features of the LOGIQ Fortis Ultrasound System, based on the provided FDA 510(k) clearance letter:

AI Features Analyzed:

Auto Abdominal Color Assistant 2.0
Auto Aorta Measure Assistant
Auto Common Bile Duct (CBD) Measure Assistant
Ultrasound Guided Fat Fraction (UGFF)

1. Auto Abdominal Color Assistant 2.0

1.1. Acceptance Criteria and Reported Device Performance:

Acceptance Criteria (Expected)	Reported Device Performance (Achieved)
Detection accuracy $\ge$ 80% (0.80)	Accuracy: 94.8%
Sensitivity (True Positive Rate): $\ge$ 80% (0.80)	Sensitivity: 0.91
Specificity (True Negative Rate): $\ge$ 80% (0.80)	Specificity: 0.98
DICE Similarity Coefficient (Segmentation Accuracy): $\ge$ 0.80 (for Aorta, Kidney, Liver/Spleen/IVC, GB/Urinary Bladder, Pancreas, Air view)	DICE score: 0.82

1.2. Sample Size and Data Provenance (Test Set):

Number of individual subjects: 49
Number of annotation images: 1186
Country: USA (100%)
Retrospective/Prospective: Not explicitly stated, but the description "Before the process of data annotation, all information displayed on the device is removed and performed on information extracted purely from Ultrasound B-mode images" and "Readers to ground truth the 'anatomy' visible in static B-Mode image" suggests retrospective analysis of collected images.

1.3. Number and Qualifications of Experts for Ground Truth (Test Set):

Number of Experts: Not specified ("Readers to ground truth the 'anatomy'").
Qualifications: Not specified (generally, these would be qualified ultrasonographers or radiologists).

1.4. Adjudication Method (Test Set): Not specified.

1.5. MRMC Comparative Effectiveness Study: No, this study evaluates the standalone performance of the AI model.

1.6. Standalone Performance: Yes, this study was done to evaluate the algorithm's performance in detecting abdominal structures.

1.7. Type of Ground Truth Used: Expert consensus on "anatomy" visible in static B-Mode images.

1.8. Sample Size for Training Set: Not explicitly stated, but implied to be separate from the test set.

1.9. How Ground Truth for Training Set Was Established: Not explicitly stated, but implied to be similar to the test set, with experts annotating B-mode images.

2. Auto Aorta Measure Assistant

2.1. Acceptance Criteria and Reported Device Performance:

Acceptance Criteria (Expected)	Reported Device Performance (Achieved)
Long View Aorta Keystrokes Reduction (AI vs. Manual): Not explicitly stated as a numerical criterion.	Average keystrokes: 4.132 $\pm$ 0.291 (without AI) vs. 1.236 $\pm$ 0.340 (with AI)
Short View Aorta Keystrokes Reduction (AI vs. Manual): Not explicitly stated as a numerical criterion.	Average keystrokes: 7.05 $\pm$ 0.158 (without AI) vs. 2.307 $\pm$ 1.0678 (with AI)
Long View AP Measurement Accuracy: Not explicitly stated as a numerical criterion.	Average accuracy: 87.2% (95% CI +/- 1.98%)Average absolute error: 0.253 cm (95% CI 0.049 cm)Limits of Agreement: (-0.15, 0.60) cm (95% CI (-0.26, 0.71) cm)
Short View AP Measurement Accuracy: Not explicitly stated as a numerical criterion.	Average accuracy: 92.9% (95% CI +/- 2.02%)Average absolute error: 0.128 cm (95% CI 0.037 cm)Limits of Agreement: (-0.21, 0.36) cm (95% CI (-0.29, 0.45) cm)
Short View Trans Measurement Accuracy: Not explicitly stated as a numerical criterion.	Average accuracy: 86.9% (95% CI +/- 6.25%)Average absolute error: 0.235 cm (95% CI 0.110 cm)Limits of Agreement: (-0.86, 0.69) cm (95% CI (-1.06, 0.92) cm)

2.2. Sample Size and Data Provenance (Test Set):

Long View Aorta:
- Subjects: 36 (11 Male, 25 Female)
- Country: 16 Japan, 20 USA
Short View Aorta:
- Subjects: 35 (11 Male, 24 Female)
- Country: 15 Japan, 20 USA
Retrospective/Prospective: Not explicitly stated, but "Validation images were collected on LOGIQ Fortis" and the truthing process suggests retrospective analysis of collected images.

2.3. Number and Qualifications of Experts for Ground Truth (Test Set):

Number of Experts: Not specified ("Readers to ground truth...").
Qualifications: Not specified.

2.4. Adjudication Method (Test Set): An "arbitrator to select most accurate measurement among all readers" was used. This suggests a form of adjudication, possibly 2+1 or similar, where the arbitrator acts as the tie-breaker/final decision-maker.

2.5. MRMC Comparative Effectiveness Study: Yes, this study directly compares human performance with and without AI assistance by measuring keystrokes and accuracy.

Effect Size (Keystrokes):
- Long View Aorta: Reduction of ~2.896 keystrokes (4.132 - 1.236)
- Short View Aorta: Reduction of ~4.743 keystrokes (7.05 - 2.307)
  (While not a traditional effect size like AUC improvement, this quantifies human workflow improvement).

2.6. Standalone Performance: Partially. The accuracy measurements compare AI baseline against an arbitrator's selected measurement, indicating standalone algorithm accuracy, but the primary focus is on human-in-the-loop efficiency.

2.7. Type of Ground Truth Used: Expert consensus on measurements, with an arbitrator for final selection.

2.8. Sample Size for Training Set: Not explicitly stated, but independence from the test set is ensured by "exam site origin."

2.9. How Ground Truth for Training Set Was Established: Not explicitly stated, but implied to be similar to the test set, with experts performing measurements.

3. Auto Common Bile Duct (CBD) Measure Assistant

3.1. Acceptance Criteria and Reported Device Performance:

Acceptance Criteria (Expected)	Reported Device Performance (Achieved)
Keystrokes Reduction (AI vs. Manual): Not explicitly stated as a numerical criterion.	Average reduction: 1.62 $\pm$ 0.375
Porta Hepatis measurement accuracy without segmentation scroll edit: Not explicitly stated as a numerical criterion.	Average accuracy: 59.85% (95% CI +/- 17.86%)Average absolute error: 1.66 mm (95% CI 1.02 mm)Limits of Agreement: (-4.75, 4.37) mm (95% CI (-6.17, 5.79) mm)
Porta Hepatis measurement accuracy with segmentation scroll edit: Not explicitly stated as a numerical criterion.	Average accuracy: 80.56% (95% CI +/- 8.83%)Average absolute error: 0.91 mm (95% CI 0.45 mm)Limits of Agreement: (-1.96, 3.25) mm (95% CI (-2.85, 4.14) mm)

3.2. Sample Size and Data Provenance (Test Set):

Subjects: 25 (11 Male, 14 Female)
Countries: USA (40%), Japan (60%)
Retrospective/Prospective: Not explicitly stated, but "Validation images were collected on LOGIQ Fortis" and the truthing process suggests retrospective analysis of collected images.

3.3. Number and Qualifications of Experts for Ground Truth (Test Set):

Number of Experts: Not specified ("Readers to ground truth...").
Qualifications: Not specified.

3.4. Adjudication Method (Test Set): An "arbitrator to select most accurate measurement among all readers" was used.

3.5. MRMC Comparative Effectiveness Study: Yes, this study directly compares human performance with and without AI assistance by measuring keystrokes and accuracy (specifically, accuracy with and without segmentation scroll edit, which implies human interaction with AI).

Effect Size (Keystrokes): Average reduction of 1.62 keystrokes.

3.6. Standalone Performance: Partially. The measurement accuracy with and without segmentation scroll edit provides insight into the algorithm's performance and the benefit of human refinement, but the primary focus is on human-in-the-loop efficiency and accuracy.

3.7. Type of Ground Truth Used: Expert consensus on measurements, with an arbitrator for final selection.

3.8. Sample Size for Training Set: Not explicitly stated, but independence from the test set is ensured by "exam site origin."

3.9. How Ground Truth for Training Set Was Established: Not explicitly stated, but implied to be similar to the test set, with experts performing measurements.

4. Ultrasound Guided Fat Fraction (UGFF)

4.1. Acceptance Criteria and Reported Device Performance:

Acceptance Criteria (Expected)	Reported Device Performance (Achieved)
Correlation with MRI-PDFF (Primary Study - Japan): Not explicitly stated as a numerical criterion.	Correlation coefficient: 0.87 (strong correlation)
Bland-Altman LOA with MRI-PDFF (Primary Study - Japan): Not explicitly stated.	Offset: -0.32%LOA: -6.0% to 5.4%91.6% patients had differences smaller than the LOA (within $\pm$8.4%)
Correlation with MRI-PDFF (Confirmatory Study - US/EU): Not explicitly stated as a numerical criterion.	Correlation coefficient: 0.90 (strong correlation)
Bland-Altman LOA with MRI-PDFF (Confirmatory Study - US/EU): Not explicitly stated.	Offset: -0.1%LOA: -3.6% to 3.4%95.0% patients had differences smaller than the LOA (within $\pm$4.6%)
Correlation with UDFF (Siemens) (Confirmatory Study - EU): Not explicitly stated as a numerical criterion.	Correlation coefficient: 0.88 (strong correlation)
Bland-Altman LOA with UDFF (Siemens) (Confirmatory Study - EU): Not explicitly stated.	Offset: -1.2%LOA: -5.0% to 2.6%100% patients had differences smaller than the LOA (within $\pm$4.7%)

4.2. Sample Size and Data Provenance (Test Set): This section describes the clinical studies used for validation of the UGFF index, rather than a traditional AI test set.

Primary Study (Development/Validation of UGFF Index):
- Subjects: 582 participants
- Country: Japan
- Retrospective/Prospective: "external clinical study in Japan" implies prospective data collection, with subsequent analysis.
Second Confirmatory Study:
- Subjects: 15 US patients, 5 EU patients (Total 20)
- Country: US and EU
- Retrospective/Prospective: Not specified.
Third Confirmatory Study (Comparison with Predicate):
- Subjects: 24 EU patients
- Country: EU
- Retrospective/Prospective: Not specified.

4.3. Number and Qualifications of Experts for Ground Truth (Test Set):

UGFF Study: The ground truth is established by a reference imaging modality (MRI-PDFF) and a comparison device (UDFF), not directly by human experts interpreting ultrasound images for the purpose of the study. The study involves acoustic property measurements.

4.4. Adjudication Method (Test Set): Not applicable, as the ground truth is based on MRI-PDFF and UDFF, not human interpretation requiring adjudication.

4.5. MRMC Comparative Effectiveness Study: No, this is a clinical validation against a reference standard and a comparative study against a predicate device.

4.6. Standalone Performance: Yes, the UGFF index is an algorithm-generated value based on acoustic properties, and its performance is evaluated in a standalone manner against established reference methods (MRI-PDFF) and a legally marketed predicate (UDFF).

4.7. Type of Ground Truth Used: Quantitative measurements from a reference imaging modality (MRI Proton Density Fat Fraction - MRI-PDFF %) and a comparative device (Ultrasound-Derived Fat Fraction (UDFF, Siemens)).

4.8. Sample Size for Training Set: The UGFF index is based on a least squares fit (estimation) between acoustic property measurements and MRI-PDFF measurements from the primary 582-subject study. This study effectively serves as the "training" dataset for establishing the correlation and the estimation model.

4.9. How Ground Truth for Training Set Was Established: MRI-PDFF measurements were obtained from the liver of these 582 participants.

Summary

FDA 510(k) Clearance Letter - LOGIQ Fortis Ultrasound System

Page 1

January 7, 2026

GE Medical Systems Ultrasound and Primary Care Diagnostics
Lee Bush
Regulatory Affairs Director
3200 N Grandview Blvd
Waukesha, Wisconsin 53188

Re: K253366
Trade/Device Name: LOGIQ Fortis
Regulation Number: 21 CFR 892.1550
Regulation Name: Ultrasonic Pulsed Doppler Imaging System
Regulatory Class: Class II
Product Code: IYN, IYO, ITX, QIH
Dated: December 4, 2025
Received: December 4, 2025

Dear Lee Bush:

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.

Page 2

K253366 - Lee Bush 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-

Page 3

K253366 - Lee Bush Page 3

assistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).

Sincerely,

YANNA S. KANG -S

Yanna Kang, Ph.D.
Assistant Director
Mammography and Ultrasound Team
DHT8C: Division of Radiological
Imaging and Radiation Therapy Devices
OHT8: Office of Radiological Health
Office of Product Evaluation and Quality
Center for Devices and Radiological Health

Enclosure

Page 4

Indications for Use

Please type in the marketing application/submission number, if it is known. This textbox will be left blank for original applications/submissions. K253366

Please provide the device trade name(s). LOGIQ Fortis

Please provide your Indications for Use below.

The LOGIQ Fortis is intended to be used in a hospital or medical clinic.

Please select the types of uses (select one or both, as applicable):
☑ Prescription Use (Part 21 CFR 801 Subpart D)
☐ Over-The-Counter Use (21 CFR 801 Subpart C)

Page 5

GE HealthCare 510(k) Premarket Notification Submission

510(k) Summary – K253366

In accordance with 21 CFR 807.92 the following summary of information is provided:

Date: January 7, 2026

Submitter: GE Medical Systems Ultrasound and Primary care Diagnostics, LLC
3200 N Grandview Blvd
Waukesha, WI 53188 USA

Manufacturer: GE Ultrasound Korea, Ltd.
9, Sunhwan-ro 214 beon-gil, Jungwon-gu,
Seongnam-si, Gyeonggi-do, 13204 Republic of Korea

Primary Contact Person: Lee Bush
Regulatory Affairs Director
GE HealthCare
T:(262)309-9429

Alternate Contact Person: Qingmeng Chen
Regulatory Affairs Leader
GE HealthCare
T: +86-18180590723

Device Trade Name: LOGIQ Fortis

Common / Usual Name: Diagnostic Ultrasound System

Classification Names: Class II

Product Code: IYN (primary), IYO, ITX, QIH (secondary)
Ultrasonic Pulsed Doppler Imaging System. 21CFR 892.1550, 90-IYN;
Ultrasonic Pulsed Echo Imaging System, 21CFR 892.1560, 90-IYO;
Diagnostic Ultrasound Transducer, 21 CFR 892.1570, 90-ITX;
Medical Image Management and Processing System, 21 CFR 892.2050, 90-QIH

Primary Predicate Device: K231989 LOGIQ E10s, LOGIQ Fortis Diagnostic Ultrasound System

Reference Device(s):

K232381 LOGIQ Totus Diagnostic Ultrasound System
K231301 Vscan Air
K201768 Voluson E10
K220882 Vivid E80, Vivid E90, Vivid E95
K183575 Siemens Acuson S3000/S2000

Page 6

Device description:

Intended Use / Indications for Use:

The LOGIQ Fortis is intended to be used in a hospital or medical clinic.

Technology:

The LOGIQ Fortis employs the same fundamental scientific technology as its predicate device(s).

Determination of Substantial Equivalence:

The proposed LOGIQ Fortis is substantially equivalent to the predicate LOGIQ Fortis (K231989) with regards to intended use, imaging capabilities, technological characteristics, imaging modes, hardware, and safety effectiveness.

The systems are all intended for diagnostic ultrasound imaging and fluid flow analysis.

The proposed LOGIQ Fortis and the predicate LOGIQ Fortis (K231989) have the same clinical indications for use.

The proposed LOGIQ Fortis employs the same fundamental scientific technology as its predicate device.

The proposed LOGIQ Fortis and the predicate LOGIQ Fortis (K231989) have the same imaging modes.

Page 7

The proposed LOGIQ Fortis is manufactured with materials which have been evaluated and found to be safe for the intended use of the device.

The proposed LOGIQ Fortis has acoustic power levels which are below the applicable FDA limits.

The proposed LOGIQ Fortis and the predicate LOGIQ Fortis (K231989) have similar capability in terms of performing measurements, capturing digital images, reviewing and reporting studies.

The proposed LOGIQ Fortis has been designed in compliance with approved electrical and physical safety standards.

The following is an overview of the differences between the proposed LOGIQ Fortis and the predicate LOGIQ Fortis (K231989).

Probes:

The probes supported in proposed LOGIQ Fortis and the predicate LOGIQ Fortis (K231989) are identical except:

Addition of new probe 12S-D and 9L-D (migrated from LOGIQ Totus K232381).
Addition of clinical application of Small Parts on existing L4-20t-D probe.
Addition of Shear Wave Elastography on existing RIC5-9-D probe under clinical application of Urology.
Addition of 4D Contrast on existing RIC5-9-D probe.

Software:

The software features supported in proposed LOGIQ Fortis and the predicate LOGIQ Fortis (K231989) are identical except:

Addition of new software features:
- Auto Abdominal Color Assistant 2.0 for adult imaging (Auto Abdominal Color Assistant 1.0 cleared on K231989)
- Auto Abdominal Measure Assistant (AI) consists of:
  - Auto Renal Measure Assistant (Cleared on LOGIQ Fortis K231989)
  - Auto Aorta Measure Assistant
  - Auto Common Bile Duct (CBD) Measure Assistant
- Ultrasound Guided Fat Fraction (UGFF) for adult imaging (Similar to Siemens UDFF feature cleared on Acuson S3000/S2000 K183575)
- AppAPI RoundTrip (AppAPI cleared on K231989)
- Viewpoint on LOGIQ (Viewpoint 6 cleared on K241300)
- Send Images via Email (migrated from Voluson E10 K201768)

Page 8

RFID Reader Login
KOIOS Lite (KOIOS DS cleared on K242130)
Auto EF without ECG (migrated from Vivid E80 / Vivid E90 / Vivid E95 K220882)
Other minor software modifications/improvements:
- Data Streaming Color Flow Support.
- Public SR Template for Urology, Small Parts and Pediatrics.
- DICOM SR Support for Viewpoint Measurements.
- DICOM tags for AI support.
- Clean Pixel Tag.
- Image Tagging.
- Additional OB Measurements/Charts: added support for authors Acharya (UMB A), Schaffer (Uterine A, UMB A, MCA), and Chitty (HL).
- Qt UI framework for the touch panel.
- Ez Touchpanel 2.0.
- Improvements to CTO (Continuous Tissue Optimization)/CATO (Continuous Auto Tissue Optimization): Improvements of functionality already available on previous clearance K231989.
- Adding availability of ACE (Adaptive Contrast Enhancement) to Thyroid application: Expansion of functionality already available on previous clearance K231989.
- Adding PW mode to the Vscan Air CL probe cleared on K231301.
- Expanded redesigned Color Flow.
- Added raw data collection for Shear Wave Elastography.
- Verisound Fleet Detailed Restore: improved based on Device Mgmt cleared on K231989.
- E-delivery of base image and application software together.
- Advanced Anonymization.
- Removed Tricefy.

Hardware:

The hardware in proposed LOGIQ Fortis and the predicate LOGIQ Fortis (K231989) are identical except:

GPU replacement due to end-of-life.
Key cap variation: added new keys for new software features for LOGIQ Fortis R5.

Page 9

Accessory

Addition of new accessory: Radio Frequency Identification (RFID) Reader and Uninterruptible Power Supply (UPS).

Compatible device:

Addition of PW mode to Vscan Air CL probe (Device itself cleared with K231301; Cleared on Predicate LOGIQ Fortis K231989).

AI Testing Summary:

Auto Abdominal Color Assistant 2.0:

Summary test statistics or other test results including acceptance criteria or other information supporting the appropriateness of the characterized performance	• The overall model detection accuracy (sensitivity and specificity) and DICE score for the Aorta, Kidney, Liver/Spleen/inferior vena cava (IVC), Gallbladder (GB)/Urinary Bladder, Pancreas, and Air view is expected to be as follows: Detection accuracy ≥ 80% (0.80) Sensitivity (True Positive Rate): ≥ 80% (0.80) Specificity (True Negative Rate): ≥ 80% (0.80) DICE Similarity Coefficient (Segmentation Accuracy): ≥ 0.80• The number of individual subjects: 49• The number of annotation images: 1186• The model achieved accuracy of 94.8%, with sensitivity of 0.91, specificity of 0.98, and a DICE score of 0.82, all of which meet the predefined acceptance criteria.
Information about clinical subgroups and confounders present in the dataset	• Gender: Male 24.2% (8), Female 75.8% (25)• Age: 60 ±15.7 (average and standard deviation) (24 Min, 83 Max)• BMI: 27±5.6 (average and standard deviation) (16 Min, 38 Max)• Ethnicity: not hispanic 96.4% (27), hispanic 3.6% (1)• Race : Asian 12.9% (4), White 77.4% (24), Black 9.7% (3)• Country: USA (100%)
Information about equipment and protocols used to collect images	Mix of data from across three different probe models and three different Console variants. The data collection protocol was standardized.
Information about how the reference standard was derived from the testing dataset (i.e. the "truthing" process)	• Before the process of data annotation, all information displayed on the device is removed and performed on information extracted purely from Ultrasound B-mode images.

Page 10

Readers to ground truth the "anatomy" visible in static B-Mode image. (Before running AI)
Ran AI and created confusion matrix of ground truth vs AI predictions.
Calculated the accuracies of the algorithm against each class.

Description of how independence of test data from training data was ensured	The exams used for test/training validation purpose are separated from the ones used during training process and there is no overlap between the two.

Auto Aorta Measure Assistant:

Summary test statistics or other test results including acceptance criteria or other information supporting the appropriateness of the characterized performance	Long View Aorta:• The average keystrokes to obtain the Anteroposterior (AP) measurement (diameter) of the aorta in the long view is 4.132 +/- 0.291 without AI and 1.236 +/-0.340 with AI.Short View Aorta:• The average keystrokes to obtain the AP and Trans measurement (diameter) of the aorta in the short view is 7.05 +/-0.158 without AI and 2.307 +/- 1.0678 with AI.Long View AP Measurement Accuracy:• Average accuracy is 87.2% with 95% CI of +/- 1.98% and average absolute error of 0.253 cm and 95% CI of 0.049 cm.• Limits of Agreement in centimeters are (-0.15, 0.60) with 95% CI of (-0.26, 0.71).Short View AP Measurement Accuracy:• Average accuracy is 92.9% with a 95% CI of +/- 2.02% and an average absolute error of 0.128 cm and 95% CI of 0.037 cm.• Limits of Agreement in centimeters are (-0.21, 0.36) with 95% CI of (-0.29, 0.45).Short View Trans Measurement Accuracy:• Average accuracy is 86.9% with 95% CI of +/- 6.25% and average absolute error of 0.235 cm and 95% CI of 0.110 cm.• Limits of agreement in centimeters are (-0.86, 0.69) with 95% CI (-1.06, 0.92).
Information about clinical subgroups and confounders present in the dataset	Long View Aorta:• Gender: 11 Male, 25 Female• Country: 16 Japan, 20 USA• Age: 60.50 ±14.24 (average and standard deviation) (23 Min – 81 Max)

Summary test statistics or other test results including acceptance criteria or other information supporting the appropriateness of the characterized performance

Long View Aorta:• The average keystrokes to obtain the Anteroposterior (AP) measurement (diameter) of the aorta in the long view is 4.132 +/- 0.291 without AI and 1.236 +/-0.340 with AI.Short View Aorta:• The average keystrokes to obtain the AP and Trans measurement (diameter) of the aorta in the short view is 7.05 +/-0.158 without AI and 2.307 +/- 1.0678 with AI.Long View AP Measurement Accuracy:• Average accuracy is 87.2% with 95% CI of +/- 1.98% and average absolute error of 0.253 cm and 95% CI of 0.049 cm.• Limits of Agreement in centimeters are (-0.15, 0.60) with 95% CI of (-0.26, 0.71).Short View AP Measurement Accuracy:• Average accuracy is 92.9% with a 95% CI of +/- 2.02% and an average absolute error of 0.128 cm and 95% CI of 0.037 cm.• Limits of Agreement in centimeters are (-0.21, 0.36) with 95% CI of (-0.29, 0.45).Short View Trans Measurement Accuracy:• Average accuracy is 86.9% with 95% CI of +/- 6.25% and average absolute error of 0.235 cm and 95% CI of 0.110 cm.• Limits of agreement in centimeters are (-0.86, 0.69) with 95% CI (-1.06, 0.92).

Information about clinical subgroups and confounders present in the dataset

Long View Aorta:• Gender: 11 Male, 25 Female• Country: 16 Japan, 20 USA• Age: 60.50 ±14.24 (average and standard deviation) (23 Min – 81 Max)

Page 11

BMI: 25.11 ±5.69 (average and standard deviation) (16.65 – 37.60)

Short View Aorta:

Gender: 11 Male, 24 Female
Country: 15 Japan, 20 USA
Age: 61.11 ±14.46 (average and standard deviation) (23 Min – 81 Max)
BMI: 25.24 ±5.97 (average and standard deviation) (16.65 – 37.60)

Information about equipment and protocols used to collect images	Validation images were collected on LOGIQ Fortis with the C1-6 probe with a standardized protocol.
Information about how the reference standard was derived from the testing dataset (i.e. the "truthing" process)	• Before the process of data annotation, all information displayed on the device is removed and performed on information extracted purely from Ultrasound B-mode images.• Readers to ground truth the AP measurement of the aorta long view and the AP and Trans measurement of the aorta short view – Number of keystrokes measured.• Readers to ground truth the AP measurement of the aorta long view and the AP and Trans measurement of the aorta short view using AI - Number of keystrokes measured.• Number of Keystrokes with and without AI is compared for each reader.• Arbitrator to select most accurate measurement among all readers.• Arbitrator selected measurement is compared to AI baseline measurement with and without on segmentation editing for accuracy.
Description of how independence of test data from training data was ensured	The exams used for regulatory validation purpose are separated from the ones used during model development process by exam site origin ensuring there is no overlap between the two.

Information about equipment and protocols used to collect images

Validation images were collected on LOGIQ Fortis with the C1-6 probe with a standardized protocol.

Information about how the reference standard was derived from the testing dataset (i.e. the "truthing" process)

• Before the process of data annotation, all information displayed on the device is removed and performed on information extracted purely from Ultrasound B-mode images.• Readers to ground truth the AP measurement of the aorta long view and the AP and Trans measurement of the aorta short view – Number of keystrokes measured.• Readers to ground truth the AP measurement of the aorta long view and the AP and Trans measurement of the aorta short view using AI - Number of keystrokes measured.• Number of Keystrokes with and without AI is compared for each reader.• Arbitrator to select most accurate measurement among all readers.• Arbitrator selected measurement is compared to AI baseline measurement with and without on segmentation editing for accuracy.

Description of how independence of test data from training data was ensured

The exams used for regulatory validation purpose are separated from the ones used during model development process by exam site origin ensuring there is no overlap between the two.

Auto Common Bile Duct (CBD) Measure Assistant:

Summary test statistics or other test results including acceptance criteria or other information supporting the appropriateness of the characterized performance	• The average reduction between keystrokes for measurements (diameter) made manually and with AI is 1.62±0.375 (mean and standard deviation)Porta Hepatis measurement accuracy without segmentation scroll edit:• Average accuracy is 59.85% with 95% CI of +/- 17.86% and average absolute error of 1.66 mm and 95% CI of 1.02 mm.• Limits of Agreement in millimeters are (-4.75,4.37) with

Page 12

95% CI of (-6.17, 5.79).

Porta Hepatis measurement accuracy with segmentation scroll edit:

Average accuracy is 80.56% with a 95% CI of +/- 8.83% and an average absolute error 0.91 mm and 95% CI of 0.45 mm.
Limits of Agreement in millimeters are (-1.96, 3.25) with 95% CI of (-2.85,4.14).

Information about clinical subgroups and confounders present in the dataset	• Gender: Male 44% (11), Female 56% (14)• Age: 62 ±16.03 (average and standard deviation) (23 Min - 83 Max)• BMI: 23.48 ± 4.94 (average and standard deviation) (16.65 min – 36.73 max)• Race: Asian 64% (16), White 36% (9)• Country: USA (40%), Japan (60%)
Information about equipment and protocols used to collect images	Validation images were collected on LOGIQ Fortis with the C1-6 probe with a standardized protocol.
Information about how the reference standard was derived from the dataset (i.e. the "truthing" process)	• Before the process of data annotation, all information displayed on the device is removed and performed on information extracted purely from Ultrasound B-mode images.• Readers to ground truth the diameter of the CBD in the Porta Hepatis – Number of keystrokes measured.• Readers to ground truth the diameter of the CBD in the Porta Hepatis using AI - Number of keystrokes measured.• Number of Keystrokes with and without AI is compared for each reader.• Arbitrator to select most accurate measurement among all readers.• Arbitrator selected measurement is compared to AI baseline measurement with and without on segmentation editing for accuracy.
Description of how independence of test data from training data was ensured	The exams used for regulatory validation purpose are separated from the ones used during model development process by exam site origin ensuring there is no overlap between the two.

Summary of Non-Clinical Tests:

The device has been evaluated for acoustic output, biocompatibility, cleaning and disinfection effectiveness as well as thermal, electrical, electromagnetic and mechanical safety, and has been found to conform with applicable medical device safety standards. The LOGIQ Fortis complies with voluntary standards:

Page 13

ANSI AAMI ES60601-1:2005/(R)2012 & A1:2012, C1:2009/(R)2012 & A2:2010/(R)2012 (Cons. Text) [Incl. AMD2:2021]
Medical electrical equipment - Part 1: General requirements for basic safety and essential performance (IEC 60601-1:2005, MOD) [Including Amendment 2 (2021)]
IEC 60601-1 Edition 3.2 2020-08 CONSOLIDATED VERSION
Medical electrical equipment - Part 1: General requirements for basic safety and essential performance
IEC 60601-2-37 Edition 3.0 2024
Medical electrical equipment - Part 2-37: Particular requirements for the basic safety and essential performance of ultrasonic medical diagnostic and monitoring equipment
IEC 60601-1-2 Edition 4.1 2020-09 CONSOLIDATED VERSION
Medical electrical equipment - Part 1-2: General requirements for basic safety and essential performance - Collateral Standard: Electromagnetic disturbances - Requirements and tests
IEC 62359 Edition 2.1 2017-09 CONSOLIDATED VERSION
Ultrasonics - Field characterization - Test methods for the determination of thermal and mechanical indices related to medical diagnostic ultrasonic fields
ISO 10993-1 Fifth edition 2018-08
Biological evaluation of medical devices - Part 1: Evaluation and testing within a risk management process
ISO 14971 Third Edition 2019-12
Medical devices - Application of risk management to medical devices
NEMA PS 3.1 - 3.20 2024e
Digital Imaging and Communications in Medicine (DICOM) Set
AAMI TIR69:2017/(R2020)
Technical Information Report Risk management of radio-frequency wireless coexistence for medical devices and systems

The following quality assurance measures are applied to the development of the system:

Risk Analysis
Requirements Reviews
Design Reviews
Testing on unit level (Module verification)
Integration testing (System verification)
Performance testing (Verification & Validation)
Safety testing (Verification)

Transducer materials and other patient contact materials are biocompatible.

Page 14

Summary discussion of the clinical tests submitted, referenced, or relied on for a determination of substantial equivalence.

UGFF Clinical Study: Acoustic property measurements including the Attenuation Coefficient (AC), Back Scatter Coefficient (BSC), and Signal-to-Noise Ratio (SNR) were obtained from the liver of five hundred and eighty-two (582) participants in an external clinical study in Japan. The UGFF index is based on a least squares fit (estimation) between the acoustic property measurements and the corresponding MRI Proton Density Fat Fraction (MRI-PDFF %) measurements.

Table 1 summarizes baseline demographic information from the clinical study including sex, age, BMI, race, and ethnicity. There were no adverse effects or complications in the acquisition of the ultrasound clinical data.

Table 1 Clinical patient data

Population	Asian
Age	65±14.1
Sex
Male	308
Female	274
Etiology
HBV	91
HCV	67
NAFLD	300
ALD	35
Other	89
BMI	21.0 – 30.8
Skin to Capsule Distance (SCD) [mm]	9.0 – 53.0

Strong correlation was confirmed between UFF values and MRI-PDFF. The correlation coefficient was 0.87. Bland-Altman analysis between UGFF and MRI-PDFF was conducted. The

Page 15

offset was -0.32% and the limit of agreement (LOA) was -6.0% to 5.4%. The differences between UGFF and MRI-PDFF values were within ±8.4%, and results in 91.6% patients were smaller than the LOA.

A second confirmatory study was conducted on 15 US and 5 EU patients using the same least squares fit (estimation) to ensure performance was maintained on an independent dataset.

Table 2 summarizes the demographic information from the confirmatory study conducted on US and EU patients. Demographic information on the 5 EU patients was unavailable.

Table 2 Clinical patient data (US adults)

Sex
Male	5
Female	10
BMI	21.0 – 37.5
SCD [mm]	13.9 – 26.9

Strong correlation between UFF values and MRI-PDFF (correlation coefficient: 0.90) was also demonstrated in European and American populations. Bland-Altman analysis between UGFF and MRI-PDFF was conducted. The offset was -0.1%, and the limit of agreement (LOA) was -3.6% to 3.4%. The differences between UFF and MRI-PDFF values were within ±4.6%, and results in 95.0% patients were smaller than the LOA.

A third confirmatory study comparing UGFF with Ultrasound-Derived Fat Fraction (UDFF, Siemens) was conducted on 24 EU patients using the same least squares fit (estimation) to ensure performance was maintained on an independent dataset.

Strong correlation between UGFF and UDFF (correlation coefficient: 0.88) was also demonstrated. Bland-Altman analysis between UGFF and UDFF was conducted. The offset was -1.2%, and the limit of agreement (LOA) was -5.0% to 2.6%. The differences between UFF and MRI-PDFF values were within ±4.7%, and results in all patients were smaller than the LOA.

The results of the clinical study indicate that BMI, SCD, and other demographic confounders do not have a statistically significant effect on measurements of the AC, BSC, and SNR.

Page 16

Conclusion:

Based on the equipment design similarities, conformance to recognized performance standards, and performance testing, GE HealthCare considers the LOGIQ Fortis to be as safe, effective, and performs in a substantially equivalent manner as the primary predicate LOGIQ Fortis (K231989).

Regulation Number and Section

§ 892.1550 Ultrasonic pulsed doppler imaging system.

(a)
Identification. An ultrasonic pulsed doppler imaging system is a device that combines the features of continuous wave doppler-effect technology with pulsed-echo effect technology and is intended to determine stationary body tissue characteristics, such as depth or location of tissue interfaces or dynamic tissue characteristics such as velocity of blood or tissue motion. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II.