(169 days)
Not Found
Yes
The device description explicitly states that the software uses "deep learning techniques" to analyze the radiographs, and the intended use also mentions using "deep learning techniques". Deep learning is a subset of machine learning.
No
The device is designed to aid in the analysis of bone age assessment by quantifying bone age from radiographs, not to treat or alleviate a medical condition.
Yes
The device aids in the analysis of bone age assessment, which is a diagnostic activity. It helps quantify bone age from radiographs, even though the results should not be solely relied upon for diagnostic decisions.
Yes
The device description explicitly states "The device is a software designed to aid the quantification of bone age". There is no mention of any accompanying hardware components being part of the device itself.
Based on the provided information, this device is not an IVD (In Vitro Diagnostic).
Here's why:
- IVD Definition: In Vitro Diagnostics are tests performed on samples taken from the human body, such as blood, urine, or tissue, to detect diseases, conditions, or infections.
- Device Function: The EFAI BONESUITE XR BONE AGE PRO ASSESSMENT SYSTEM analyzes radiographic images (X-rays), which are external imaging data, not biological samples taken from the body.
- Intended Use: The intended use is to "view and quantify bone age from 2D Posterior Anterior (PA) view of left-hand radiographs," which is an image analysis task, not a diagnostic test performed on a biological sample.
Therefore, while this device is a medical device that aids in diagnosis, it falls under the category of medical image analysis software rather than an In Vitro Diagnostic.
No
The letter does not explicitly state that the FDA has reviewed and approved or cleared a PCCP for this specific device.
Intended Use / Indications for Use
EFAI BONESUITE XR BONE AGE PRO ASSESSMENT SYSTEM (EFAI BAPXR) is designed to view and quantify bone age from 2D Posterior Anterior (PA) view of left-hand radiographs using deep learning techniques to aid in the analysis of bone age assessment of patients between 2 to 16 years old for pediatric radiologists. The results should not be relied upon alone by pediatric radiologists to make diagnostic decisions. The images shall be with left hand and wrist fully visible within the field of view, and shall be without any major bone destruction, deformity, fracture, excessive motion, or other major artifacts.
Product codes
QIH
Device Description
The device is a software designed to aid the quantification of bone age for patients between 2 to 16 years old. The software uses deep learning techniques to analyze posterior-anterior (PA) radiographs of the left-hand according to the Greulich-Pyle (GP) method.
Mentions image processing
Yes
Mentions AI, DNN, or ML
Yes
Input Imaging Modality
X-ray
Anatomical Site
Left hand and wrist
Indicated Patient Age Range
2 to 16 years old
Intended User / Care Setting
Pediatric radiologist; Healthcare facility/Hospital
Description of the training set, sample size, data source, and annotation protocol
During the process of model development, a total of 26,222 cases were retrospectively collected from Taiwan and the United States (U.S.). These cases were subsequently divided into training and testing datasets, consisting of 23.578 and 2.644 cases, respectively. Ground-truthing was the average of the bone age assessment independently done by three board-certified radiologists.
Description of the test set, sample size, data source, and annotation protocol
The test data comprised 600 cases aged 2-16 years, acquired from 27 locations across multiple states and multiple clinical organizations in the United States. The study population contained 50.0% males and 50.0% females, with a mean chronological age of cases was 9.2 years old and 120 cases in each three-year age interval. The race or ethnicities of cases include White, Hispanic, Black, Asian, Multiple, etc. The X-Ray scanner manufacturers of images include Samsung Electronics, Carestream Health, Kodak, GE Healthcare, Siemens, Konica Minolta, etc. None of the cases was used as part of the EFAI BAPXR model training or development. The ground truth (GT) was generated through a truthing process based on the current standard of care, with the addition of multiple checkpoints to ensure consistency and consensus among four U.S. board-certified expert radiologists reviewing the radiographs when comparing them to the Greulich-Pyle Atlas.
Summary of Performance Studies (study type, sample size, AUC, MRMC, standalone performance, key results)
Nonclinical Tests:
- Study type: Internal validation test
- Sample size: 2,644 cases (from the 26,222 total collected cases)
- Key Results: Deming regression analysis showed a good correlation between GT and EFAI BAPXR's output. The intercept was -0.06 with a 95% CI of [-0.09, -0.03] and the slope was 1.00 with a 95% CI of [1.00, 1.01]. The CIs of both measures fell within the highest acceptable bias.
Clinical Tests:
- Study type: Standalone performance study
- Sample size: 600 cases
- Key Results: EFAI BAPXR can provide bone age assessments with satisfactory results, with over 88% of cases having a difference less than 0.5 years between GT and EFAI BAPXR's output. The intercept of the Deming regression result was -0.07 with a 95% Confidence Interval (95% CI) of [-0.13, -0.01] and slope of 1.00 with a 95% CI of [0.99, 1.00]. The device performance met the performance goal compared with the GT. The 95% limits of agreement for bone age assessment between GT and EFAI BAPXR's output ranged from -0.517 to 0.743, indicating high consistency. Subgroup analysis showed consistent and reliable performance across gender, age, race or ethnicity, clinical organization, X-ray manufacturer, cases with radiologic findings, and cases with image quality issues.
Key Metrics (Sensitivity, Specificity, PPV, NPV, etc.)
Not Found
Predicate Device(s)
Reference Device(s)
Not Found
Predetermined Change Control Plan (PCCP) - All Relevant Information
Not Found
§ 892.2050 Medical image management and processing system.
(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).
0
Image /page/0/Picture/0 description: The image contains the logos of the Department of Health & Human Services and the Food and Drug Administration (FDA). The Department of Health & Human Services logo is on the left, and the FDA logo is on the right. The FDA logo includes the agency's name, "U.S. Food & Drug Administration," in blue text.
Ever Fortune.AI Co., Ltd. Ti-Hao Wang Chief Technology Officer Rm. D, 8F. No. 573, Sec. 2 Taiwan Blvd. West Dist. Taichung City, 403020 Taiwan
June 7, 2024
Re: K234042
Trade/Device Name: EFAI Bonesuite XR Bone Age Pro Assessment System (BAP-XR-100) Regulation Number: 21 CFR 892.2050 Regulation Name: Medical Image Management And Processing System Regulatory Class: Class II Product Code: QIH Dated: May 24, 2024 Received: May 24, 2024
Dear Ti-Hao Wang:
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.
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).
1
2
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 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-reportingcombination-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.
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-device-safety/medical-device-reportingmdr-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/medicaldevices/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-device-advice-comprehensive-regulatoryassistance/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.
Jessica Lamb
Jessica Lamb Assistant Director Imaging Software Team DHT8B: Division of Radiologic Imaging Devices and Electronic Products OHT8: Office of Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health
2
Indications for Use
Submission Number (if known)
Device Name
EFAI BONESUITE XR BONE AGE PRO ASSESSMENT SYSTEM (BAP-XR-100)
Indications for Use (Describe)
EFAI BONESUITE XR BONE AGE PRO ASSESSMENT SYSTEM (EFAI BAPXR) is designed to view and quantify bone age from 2D Posterior Anterior (PA) view of left-hand radiographs using deep learning techniques to aid in the analysis of bone age assessment of patients between 2 to 16 years old for pediatric radiologists. The results should not be relied upon alone by pediatric radiologists to make diagnostic decisions. The images shall be with left hand and wrist fully visible within the field of view, and shall be without any major bone destruction, deformity, fracture, excessive motion, or other major artifacts.
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 PRAStaff(@fda.hhs.gov
"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."
3
Image /page/3/Picture/0 description: The image shows the logo for Ever Fortune AI. The logo consists of a teal-colored icon that resembles a person with a globe as their head, followed by the text "EVER FORTUNE.AI" in a matching teal color. The globe icon is made up of interconnected dots, suggesting a network or connection.
510(k) Summary
General Information 1.
| 510(k) Sponsor | Ever Fortune.AI Co., Ltd. |
|---|---|
| Address | Rm. D, 8F. No. 573, Sec. 2 Taiwan Blvd. |
| West Dist. | |
| Taichung City 403020 | |
| TAIWAN | |
| Applicant | Joseph Chang |
| Contact Information | 886-04-23213838 #216 |
| joseph.chang@everfortune.ai | |
| Correspondence Person | Ti-Hao Wang |
| Contact Information | 886-04-23213838 #168 |
| thothwang@gmail.com | |
| tihao.wang@everfortune.ai | |
| Date Prepared | October, 2023 |
2. Proposed Device
| Proprietary Name | EFAI Bonesuite XR Bone Age Pro Assessment System (BAP-XR-100 |
|---|---|
| Common Name | EFAI BAPXR |
| Classification Name | System, Image Processing, Radiological |
| Regulation Number | 21 CFR 892.2050 |
| Regulation Name | Medical Image Management and Processing System |
| Product Code | QIH |
| Regulatory Class | II |
3. Predicate Device
| Proprietary Name | Medo Aria |
|---|---|
| Premarket Notification | K200356 |
4
Image /page/4/Picture/0 description: The image contains a logo for a company called "EVER FORTUNE.AI". The logo consists of two parts: a stylized human figure on the left and the company name on the right. The human figure is teal and has a green circle with a network of white dots for a head. The company name is written in teal, with "EVER" on top and "FORTUNE.AI" below.
| Classification Name | System, Image Processing, Radiological | |
|---|---|---|
| Regulation Number | 21 CFR 892.2050 | |
| Regulation Name | Medical Image Management and Processing System | |
| Product Code | QIH | |
| Regulatory Class | II |
Device Description 4.
The device is a software designed to aid the quantification of bone age for patients between 2 to 16 years old. The software uses deep learning techniques to analyze posterior-anterior (PA) radiographs of the left-hand according to the Greulich-Pyle (GP) method.
Intended User Population
The intended users of EFAI BAPXR are pediatric radiologists.
When a clinician accesses the patient radiographs in a picture archiving and communication system (PACS) client or a workstation, both the EFAI BAPXR quantification and the original unaltered radiographs are available in the same patient study, allowing for concurrent reading.
EFAI BAPXR is an adjunct tool and is not intended to replace a clinician's review of the radiograph or his or her clinical judgment. Clinicians must not use the software generated output as the primary interpretation.
Intended Patient Population
The target population of the device are patients between 2 and 16 years old that require a bone age assessment.
Description of output
The algorithm outputs a standard JSON message, to ensure consistent interpretation and simple integration across systems. The result contains structured information in regards to the estimated bone age in years and the data can be transferred and processed by RIS/HIS/PACS and other workstations.
5. Intended Use
EFAI BONESUITE XR BONE AGE PRO ASSESSMENT SYSTEM (EFAI BAPXR) is designed to view and quantify bone age from 2D Posterior (PA) view of left-hand radiographs using deep learning techniques to aid in the analysis of bone age assessment of
5
Image /page/5/Picture/0 description: The image contains a logo for a company called "EVER FORTUNE.AI". The logo consists of a stylized human figure in teal, with a green circle containing a network of white dots as its head. To the right of the figure, the company name is written in teal, with "FORTUNE.AI" appearing below "EVER" in a slightly smaller font size. The overall design is clean and modern, suggesting a focus on technology and innovation.
patients between 2 to 16 years old for pediatric radiologists. The results should not be relied upon alone by pediatric radiologists to make diagnostic decisions. The images shall be with left hand and wrist fully visible within the field of view, and shall be without any major bone destruction, deformity, fracture, excessive motion, or other major artifacts.
6. Comparison of Technological Characteristics with Predicate Device
| Feature/
Function | Proposed Device:
EFAI BAPXR
(K234042) | Predicate Device:
Medo Aria
(K200356) |
|-----------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Intended
Use/Indication for
Use | EFAI BONESUITE XR BONE AGE
ASSESSMENT SYSTEM PRO
(EFAI BAPXR) is designed to view
and quantify bone age from 2D
Posterior Anterior (PA) view of
left-hand radiographs using deep
learning techniques to aid in the
analysis of bone age assessment of
patients between 2 to 16 years old for
pediatric radiologists. The results
should not be relied upon alone by
pediatric radiologists to make
diagnostic decisions. The images
shall be with left hand and wrist fully
visible within the field of view, and
shall be without any major bone
destruction, deformity, fracture,
excessive motion, or other major
artifacts. | MEDO ARIA is designed to view
and quantify ultrasound image data
using machine learning techniques
to aid trained medical professionals
in diagnosis of developmental
dysplasia of the hip (DDH). The
device is intended to be used on
neonates and infants, aged 0 to 12
months. |
| Environment of Use | Healthcare facility/Hospital | Healthcare facility/Hospital |
| Intended user | Pediatric radiologist | Radiologist |
| Clinical condition | Bone age assessment | developmental dysplasia of the hip
(DDH) |
| Image Input | Complies with DICOM standard | Complies with DICOM standard |
| Scan Type | X-ray | 2D and 3D Ultrasound |
| Body Part | Left hand and wrist | Hip |
| Image display mode | Static | Static |
| Artificial Intelligence
Algorithm | Yes | Yes |
| Image navigation and
manipulation
tools | No | Adjust image brightness and
contrast, slice-scroll, pane
layout, reset |
| 2D image review | No | Yes, capable of reviewing all
frames of multi-frame
(multi-slice) image |
| Manual landmark
placement | No | Yes |
| Semi-automatic
landmark
placement | No | Yes, user-modifiable |
| Quantitative analysis | Bone age assessment (years) | ● Angle (alpha angle)
● Distance ratio (coverage) |
| Report creation | No | Yes |
6
Image /page/6/Picture/0 description: The image shows the logo for Ever Fortune AI. The logo consists of a stylized human figure in teal, with a green circle containing a network of white dots above its head. To the right of the figure, the word "EVER" is written in large, teal letters. Below "EVER", the words "FORTUNE.AI" are written in smaller, teal letters, with a green circle containing a network of white dots replacing the "O" in "FORTUNE".
Performance Data 7.
Performance of the EFAI BAPXR has been evaluated and verified in accordance with software specifications and applicable performance standards through software verification and validation testing. Additionally, the software validation activities were performed in accordance with IEC 62304:2006/A1:2016 - Medical device software - Software life cycle processes, in addition to the FDA Guidance documents, "Content of Premarket Submissions for Device Software Functions" and "Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions."
To establish the performance of EFAI BAPXR, the performance was validated by nonclinical and clinical tests.
Nonclinical Tests
During the process of model development, a total of 26,222 cases were retrospectively collected from Taiwan and the United States (U.S.). These cases were subsequently divided into training and testing datasets, consisting of 23.578 and 2.644 cases, respectively.
An internal validation test was conducted to assess the performance of the EFAI BAPXR. Ground-truthing was the average of the bone age assessment independently done by three board-certified radiologists.
Overall, the Deming regression analysis result showed a good correlation between GT and EFAI BAPXR's output. The intercept of the regression line was -0.06 with a 95% CI of [-0.09, -0.03]
7
Image /page/7/Picture/0 description: The image contains the logo for Ever Fortune AI. The logo consists of a stylized human figure with a green circle containing a network of white dots above its head. To the right of the figure, the words "EVER" and "FORTUNE.AI" are written in a sans-serif font, with the word "EVER" stacked above "FORTUNE.AI". The color scheme is primarily teal and green.
and the slope was 1.00 with a 95% CI of [1.00. 1.01]. By confirming that the Cls of both measures fall within the highest acceptable bias.
Clinical Tests
EFAI conducted a standalone performance study with the proposed device EFAI BAPXR with a pre-determined primary endpoint and performance goal to evaluate the software's performance on left-hand X-ray images in PA view. The test data comprised 600 cases aged 2-16 years, acquired from 27 locations across multiple states and multiple clinical organizations in the United States. The study population contained 50.0% males and 50.0% females, with a mean chronological age of cases was 9.2 years old and 120 cases in each three-vear age interval.The race or ethnicities of cases include White, Hispanic, Black, Asian, Multiple, etc. The X-Ray scanner manufacturers of images include Samsung Electronics, Carestream Health, Kodak, GE Healthcare, Siemens, Konica Minolta, etc. None of the cases was used as part of the EFAI BAPXR model training or development.
The study design measured the performance of EFAI BAPXR against the ground truth (GT) from four U.S. board-certified expert radiologists. As shown in the following figure A) for the ground truthing workflow, the ground truthing was generated through the truthing process based on the current standard of care, with the addition of multiple checkpoints to ensure consistency and consensus among all readers reviewing the radiographs when comparing them to the Greulich-Pyle Atlas.
Image /page/7/Figure/5 description: The image shows a flowchart describing a ground truthing workflow. The workflow is divided into four phases: Bone Age Assessment, Consensus Via Grading, Majority Voting, and Final Adjudication. Each phase involves a decision-making process based on criteria such as differences in bone age assessments, grades, and votes. The flowchart outlines the steps to determine the ground truth (GT) based on the readers' assessments.
Figure A. Ground Truthing Workflow
EFAI BAPXR Traditional 510(k)
8
Image /page/8/Picture/0 description: The image contains a logo for a company called "EVER FORTUNE.AI". The logo consists of a stylized human figure with a green globe-like head, connected by lines and dots, and a teal body. To the right of the figure, the word "EVER" is written in large, teal letters, with "FORTUNE.AI" written in smaller letters below it, also in teal.
The primary endpoint was the intercept and slope of a Deming regression between GT and EFAI BAPXR's output. The acceptance criteria were met if both the intercept and slope of the regression line had fallen within the range of the highest acceptable bias.
The observed results of the standalone performance validation study demonstrated that EFAI BAPXR can provide bone age assessments with satisfactory results including over 88% of the cases with a difference less than 0.5 years between GT and EFAI BAPXR's output. The intercept of the Deming regression result was -0.07 with a 95% Confidence Interval (95% CI) of [-0.13, -0.01] and slope of 1.00 with a 95% CI of [0.99, 1.00]. Overall, the device performance met the performance goal compared with the GT, thus reaching the primary endpoint. In addition, as shown in the following Bland-Altman plot (Figure B), the 95% limits of agreement (red solid lines) for bone age assessment between GT and EFAI BAPXR's output ranged from -0.517 to 0.743 (with corresponding CIs in gray dashed lines), indicating high consistency.
Image /page/8/Figure/3 description: This image is a Bland-Altman plot of the EFAI BAPXR. The x-axis represents the average of GT and EFAI BAPXR's output in years, ranging from 0 to 20. The y-axis represents the difference between GT and EFAI BAPXR's output in years, ranging from -4 to 4. The plot shows a scatter of points around the zero line, with two dashed lines indicating the limits of agreement.
As shown in the table below, we also evaluated the performance of EFAI BAPXR in various clinical subgroups to see if these factors systematically affect the device performance, including gender, age, race or ethnicity, clinical organization, X-ray manufacturer, input image with radiologic findings (including epiphyseal, finger, carpal/ metacarpal, radius/ ulna, others, and multiple), and image quality issues (including poor image quality, poor position, foreign body, artifact, and multiple).
9
Image /page/9/Picture/0 description: The image shows the logo for Ever Fortune AI. The logo consists of a stylized human figure with a green globe as its head, and the text "EVER FORTUNE.AI" in a teal color. The globe has a network pattern on it, suggesting a connection or global reach.
| Intercept (95% CI) | Slope (95% CI) | |
|---|---|---|
| Gender | ||
| Female | 0.01 (-0.07, 0.09) | 0.99 (0.98, 1.00) |
| Male | -0.14 (-0.23, -0.04) | 1.00 (0.99, 1.01) |
| Age | ||
| Pre-puberty | 0.03 (-0.07, 0.13) | 0.98 (0.96, 0.99) |
| Early & Mid-puberty | -0.06 (-0.25, 0.13) | 0.99 (0.98, 1.01) |
| Late-puberty | -1.10 (-1.46, -0.74) | 1.07 (1.04, 1.09) |
| Race or Ethnicity | ||
| White | -0.05 (-0.14, 0.04) | 0.99 (0.99, 1.00) |
| Hispanic | 0.05 (-0.12, 0.22) | 0.98 (0.97, 1.00) |
| Black or African | -0.17 (-0.55, 0.20) | 1.01 (0.98, 1.04) |
| Asian | -0.12 (-0.28, 0.04) | 0.99 (0.98, 1.01) |
| Multiple | -0.19 (-0.36, -0.01) | 1.00 (0.98, 1.02) |
| Other Races or Ethnicities | -0.07 (-0.31, 0.17) | 0.99 (0.97, 1.01) |
| Clinical Organization | ||
| Org A | 0.12 (-0.13, 0.37) | 0.97 (0.94, 1.01) |
| Org B | -0.24 (-0.69, 0.21) | 1.01 (0.97, 1.05) |
| Org C | -0.11 (-0.24, 0.02) | 0.99 (0.98, 1.00) |
| Org D | -0.07 (-0.15, 0.01) | 1.00 (0.99, 1.01) |
| X-ray Manufacturer | ||
| Samsung Electronics | -0.17 (-0.33, -0.01) | 1.00 (0.99, 1.01) |
| Carestream Health | -0.03 (-0.16, 0.10) | 0.99 (0.98, 1.00) |
| Kodak | -0.17 (-0.28, -0.07) | 1.01 (1.00, 1.02) |
| GE Healthcare | 0.01 (-0.23, 0.25) | 0.99 (0.96, 1.01) |
| Siemens | 0.05 (-0.10, 0.20) | 1.00 (0.99, 1.02) |
| Konica Minolta | 0.12 (-0.10, 0.35) | 0.97 (0.94, 1.00) |
| Other Manufacturers | 0.05 (-0.29, 0.39) | 0.99 (0.96, 1.02) |
| Cases with Radiologic Findings | -0.03 (-0.14, 0.08) | 0.99 (0.98, 1.01) |
| Cases with Image Quality Findings | -0.04 (-0.19, 0.11) | 1.00 (0.98, 1.01) |
Table. Subgrouping Analysis Results of EFAI BAPXR
Pre-puberty: female ages [2 - 7) & male ages [2 - 9).
Early & Mid-puberty: female ages [7 - 13) & male ages [9 - 14).
Late-puberty: female ages [13 - 16] & male ages [14 - 16].
Other races or ethnicities include American Indian/Alaska Native, Pacific Islander/Native Hawaiian, others and unreported.
Other manufacturers include Fujifilm Corporation, Canon Inc., and Hologic, Inc..
10
Image /page/10/Picture/0 description: The image shows the logo for Ever Fortune AI. The logo consists of a teal-colored icon on the left, resembling a person with a globe as their head. To the right of the icon, the words "EVER" and "FORTUNE.AI" are written in teal. The logo appears to be for a company that specializes in artificial intelligence.
Overall, we found the device performs consistently and reliably under these circumstances, this concludes the performance demonstrated that the EFAI BAPXR device is as safe and effective as the predicate device Medo Aria.
Safety & Effectiveness 8.
EFAI BAPXR has been designed, verified and validated in compliance with 21 CFR, Part 820.30 requirements. The device has been designed to meet the requirements associated with ISO 14971:2019 Medical devices - Application of risk management to medical devices. The EFAI BAPXR performance has been validated using retrospective data from case data and through the use of Reader comparison analysis.
Substantial Equivalence 9.
The EFAI BAPXR has minor differences compared to the predicate device. These differences are related to the Intended Use and to the Quantitative Analysis features.
The Medo Aria predicate is intended to quantify ultrasound images to support diagnosis of development dysplasia of the hip (DDH) based on Graf. The EFAI BAPXR is intended to quantify bone age based on an image atlas. Although the intended uses are different, the principle of operation is the same as both devices use artificial intelligence algorithms to view and quantify radiograph images and provide results based on an established reference or standard. Both devices have similar risks and are mitigated by similar special controls. Both devices rely on labeling and clinical performance testing as mitigations to address risks related to the use of the devices. Therefore, although the intended uses are not exactly the same, the risks and technology used by both devices are the same and are mitigated similarly and thus the proposed device does not raise new questions of safety or efficacy as no new risks are introduced.
The predicate device consists of a user interface in which end users are able to interact with images using typical image navigation and manipulation tools, including landmark placement. The proposed device does not consist of a typical user interface which allows users to interact with images using typical image navigation and manipulation tools, including landmark placement. However, this difference does not raise new questions of safety or efficacy and does not add new or significant risk to the device as the differences are workflow related and the end users are able to still access the original image to interpret the image according to standard practices.
10. Conclusion
Based on the information submitted in this premarket notification, and based on the indications for use, technological characteristics, and performance testing, the EFAI BAPXR raises no new questions of safety and effectiveness and is substantially equivalent to the predicate device in terms of safety, efficacy, and performance.