Spectralis HRA + OCT and variants (e.g.s below), Spectralis FA+OCT, Spectralis ICGA+OCT, Spectralis OCT Blue Peak, Spectralis OCT ith Multicolor
Applicant
Heidelberg Engineering GmbH
Product Code
OBO · Ophthalmic
Decision Date
May 6, 2016
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 886.1570
Device Class
Class 2
Attributes
Real-World Evidence
Real-World Evidence
Submission
Device
Sponsor
RWD Sources
RWE Use Summary
Key Tags
K152205 · May 6, 2016
Spectralis HRA + OCT and variants (e.g.s below), Spectralis FA+OCT, Spectralis ICGA+OCT, Spectralis OCT Blue Peak, Spectralis OCT ith Multicolor
Heidelberg Engineering GmbH
Prospective, multi-center, observational study of normal subjects
The document uses data from prospective observational studies of normal subjects to establish normative reference databases for RNFL thickness and BMO-MRW (neuroretinal rim width) measurements, allowing for quantitative comparison of patient data to normal population values.
Normative database; Observational study; Reference data
Clinical Evidence
Study Design
Population
Comparator
Key Endpoints
RNFLT Reference Database Study; Prospective, multi-center, observational study
330 normal subjects (146 male, 184 female) with healthy eyes; Sample Size: 330 eyes; Number of Sites: Multi-center
Not applicable for this study
Retinal nerve fiber layer (RNFL) thickness
BMO-MRW Reference Database Study; Prospective, multi-center, observational study
368 normal subjects (165 male, 203 female) with healthy eyes; Sample Size: 368 eyes; Number of Sites: Multi-center
Not applicable for this study
BMO minimum rim width (BMO-MRW)
AI Performance
Output
Algorithm
Acceptance
Observed
Dev DS
Dev Readers
Test DS
Test Readers
Retinal Nerve Fiber Layer (RNFL) thickness
—
—
—
Prospective, multi-center, observational study: 330 eyes of 330 normal subjects.
The SPECTRALIS is a non-contact ophthalmic diagnostic imaging device. It is intended for viewing the posterior segment of the eye, including two- and three-dimensional imaging, cross-sectional imaging (SPECTRALIS HRA+OCT and SPECTRALIS OCT), fundus photography, fluorescence imaging (fluorescein angiography, indocyanine green angiography; SPECTRALIS HRA+OCT, SPECTRALIS HRA), autofluorescence imaging (SPECTRALIS HRA+OCT, SPECTRALIS HRA and SPECTRALIS OCT with BluePeak) and to perform measurements of ocular anatomy and ocular lesions. The device is indicated as an aid in the detection and management of various ocular diseases, including age-related macular degeneration, macular edema, diabetic retinopathy, retinal and choroidal vascular diseases, glaucoma, and for viewing geographic atrophy as well as changes in the eye that result from neurodegenerative diseases. The SPECTRALIS HRA+OCT and SPECTRALIS OCT include reference databases for retinal nerve fiber layer thickness and optic nerve head neuroretinal rim parameter measurements, which are used to quantitatively compare the retinal nerve fiber layer and neuroretinal rim in the human retina to values found in normal subjects.
Device Story
SPECTRALIS HRA+OCT is a non-contact ophthalmic imaging system combining optical coherence tomography (OCT) and confocal scanning laser ophthalmoscopy (cSLO). It captures simultaneous high-resolution cross-sectional OCT images and cSLO images (infrared, blue reflectance, fluorescein/indocyanine green angiography, autofluorescence). Operated by clinicians via standard PC, it displays images side-by-side. The system uses the Anatomic Positioning System (APS) to align images based on fovea-to-BMO-center axis. It provides quantitative measurements of retinal nerve fiber layer (RNFL) thickness and optic nerve head (ONH) neuroretinal rim (BMO-MRW) compared against normative databases. Enhanced Depth Imaging (EDI) mode allows visualization of deep ocular structures. Optional wide-field/ultra-widefield lenses expand the field of view. Output aids in diagnosis and management of retinal and optic nerve diseases; benefits include precise structural assessment and longitudinal monitoring of ocular pathology.
Clinical Evidence
Prospective, multi-center observational studies enrolled 330 normal subjects for RNFLT database and 368 for BMO-MRW database. Precision/agreement studies in 34 subjects (healthy and glaucoma) showed repeatability/reproducibility CVs within specified ranges. Agreement study (40 subjects) compared APS-based alignment (subject) vs. FoDi-based alignment (predicate), confirming results agree within expected thresholds.
Technological Characteristics
System combines OCT and cSLO. Class 1 laser product (IEC 60825-1). Hardware includes laser scanning camera, headrest, operation panel, power supply, and host PC. Connectivity via standard PC. Software version 6.0. APS-based alignment uses OCT images. Scan patterns include 3.5mm, 4.1mm, 4.7mm diameter circles and 48 radial scans. EDI mode for deep structure visualization.
Indications for Use
Indicated for patients requiring posterior segment eye imaging and measurement of ocular anatomy/lesions to aid in detection and management of ocular diseases including age-related macular degeneration, macular edema, diabetic retinopathy, retinal/choroidal vascular diseases, glaucoma, geographic atrophy, and neurodegenerative eye changes.
Regulatory Classification
Identification
An ophthalmoscope is an AC-powered or battery-powered device containing illumination and viewing optics intended to examine the media (cornea, aqueous, lens, and vitreous) and the retina of the eye.
Special Controls
*Classification.* Class II (special controls). The device, when it is an AC-powered opthalmoscope, a battery-powered opthalmoscope, or a hand-held ophthalmoscope replacement battery, is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 886.9.
{0}------------------------------------------------
Image /page/0/Picture/1 description: The image shows the logo for the Department of Health & Human Services - USA. The logo is a circular seal with the text "DEPARTMENT OF HEALTH & HUMAN SERVICES - USA" around the perimeter. Inside the circle is an image of three stylized human profiles facing to the right, with flowing lines beneath them.
Food and Drug Administration 10903 New Hampshire Avenue Document Control Center - WO66-G609 Silver Spring, MD 20993-0002
May 6, 2016
Heidelberg Engineering Gmbh % Ms. Diane Horwitz Mandell Horwitz Consultants LLC 2995 Steven Martin Drive Fairfax, Virginia 22031
Re: K152205
Trade/Device Name: Spectralis Hra + Oct And Variants (e.g.s Below), Spectralis Fa+oct, Spectralis Icga+oct, Spectralis Oct Blue Peak, Spectralis Oct Ith Multicolor Regulation Number: 21 CFR 886.1570 Regulation Name: Ophthalmoscope Regulatory Class: Class II Product Code: OBO. MYC. Dated: March 29, 2016 Received: March 30, 2016
Dear Ms. Horwitz:
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 (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. 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.
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
{1}------------------------------------------------
(21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting of medical device-related adverse events) (21 CFR 803); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820); and if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.
If you desire specific advice for your device on our labeling regulation (21 CFR Part 801), please contact the Division of Industry and Consumer Education at its toll-free number (800) 638-2041 or (301) 796-7100 or at its Internet address
http://www.fda.gov/MedicalDevices/ResourcesforYou/Industry/default.htm. Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to
http://www.fda.gov/MedicalDevices/Safety/ReportaProblem/default.htm for the CDRH's Office of Surveillance and Biometrics/Division of Postmarket Surveillance.
You may obtain other general information on your responsibilities under the Act from the Division of Industry and Consumer Education at its toll-free number (800) 638-2041 or (301) 796-7100 or at its Internet address
http://www.fda.gov/MedicalDevices/ResourcesforYou/Industry/default.htm.
Sincerely yours,
Kesia Alexander
for Malvina B. Eydelman, M.D. Director Division of Ophthalmic and Ear, Nose and Throat Devices Office of Device Evaluation Center for Devices and Radiological Health
Enclosure
{2}------------------------------------------------
# Indications for Use
510(k) Number (if known)
### Device Name
Spectralis HRA+OCT with RNFL and ONH Normative Database
### Indications for Use (Describe)
The SPECTRALIS is a non-contact ophthalmic diagnostic imaging device. It is intended for viewing the posterior segment of the eye, including two- and three-dimensional imaging (SPECTRALIS HRA+OCT and SPECTRALIS OCT), fundus photography, fluorescence imaging (fluorescein angiography, indocyanine green angiography; SPECTRALIS HRA+OCT, SPECTRALIS HRA), autofluorescence imaging (SPECTRALIS HRA+OCT, SPECTRALIS HRA and SPECTRALIS OCT BluePeak) and to perform measurements of ocular anatomy and ocular lesions. The device is indicated as an aid in the detection and management of various ocular diseases, including agerelated macular degeneration, macular edema, diabetic retinal and choroidal vascular diseases, glaucoma, and for viewing geographic atrophy as well as changes in the eye that result from neurodegenerative diseases. The SPECTRALIS HRA+OCT and SPECTRALIS OCT include normative databases for retinal nerve fiber layer thickness and optic nerve head neuroretinal paraments, which are used to quantitatively compare the retinal nerve fiber layer and neuroretinal rim in the human retina to values found in normal subjects.
Type of Use (Select one or both, as applicable)
2 Prescription Use (Part 21 CFR 801 Subpart D)
_ Over-The-Counter Use (21 CFR 801 Subpart C)
# PLEASE DO NOT WRITE BELOW THIS LINE - CONTINUE ON A SEPARATE PAGE IF NEEDED.
### FOR FDA USE ONLY
Concurrence of Center for Devices and Radiological Health (CDRH) (Signature)
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}------------------------------------------------
# 510(k) Summarv
### Submitter I.
Heidelberg Engineering GmbH Max-Jarecki-Str. 8 69115 Heidelberg, Germany
Telephone: +49 / 6221 / 64 643 0 Fax: +49 / 6221 / 64 63 62
Contact Person: Dr. Christian Elm Date Summary Prepared: May 4, 2016
# II. Device
Trade/Device Name: SPECTRALIS HRA+OCT and Variants Common/Usual Name: Retina Angiograph / Optical Coherence Tomograph Classification Name: Tomography, Optical Coherence (21 CFR 886.1570) Regulatory Class: II Product Code: OBO, MYC
# III. Predicate Device
Heidelberg SPECTRALIS HRA+OCT, K101223, amended by K121993 Reference devices include other medical devices
- with wide field objective: Nidek Ophthalmoscope F-10, K072259 -
- with ultra-widefield objective: Optos 200 T, K111628 -
# IV. Device Description
The SPECTRALIS HRA+OCT is a real-time imaging system of anterior and posterior segments of the human eye and for aiding in the assessment and management of various diseases of the posterior segment, such as age-related macular degeneration, diabetic retinopathy, and glaucoma.
The device is a combination of optical coherence tomography (OCT) with confocal scanning laser ophthalmoscopy (cSLO). OCT imaging includes high-resolution cross-sectional imaging of ocular structures (e.g., retina, macula, optic nerve head); cSLO imaging includes high-resolution and dynamic infrared reflectance, blue reflectance, fluorescein angiography, indocyanine green angiography, and autofluorescence imaging. OCT images and cSLO images are acquired simultaneously and are viewed side-by-side on the computer screen. Images are acquired and stored using SPECTRALIS operation software, which runs on a standard personal computer. SPECTRALIS components include a laser scanning camera mount with headrest, operation panel, power supply box, operation software, and host computer. A MultiColor option is included to provide additional green reflectance imaging and a "composite color" image, which provides a different view of the features of the eye. This composite color image is not the same as fundus color photo. This submission includes Enhanced Depth Imaging (EDI) as an optional viewing mode that allows for better visualization of deep eye structures below the retina.
# V. Intended Use/Indications for Use
The SPECTRALIS is a non-contact ophthalmic diagnostic imaging device. It is intended for viewing the posterior segment of the eye, including two- and three-dimensional imaging, crosssectional imaging (SPECTRALIS HRA+OCT and SPECTRALIS OCT), fundus photography,
{4}------------------------------------------------
fluorescence imaging (fluorescein angiography, indocyanine green angiography; SPECTRALIS HRA+OCT, SPECTRALIS HRA), autofluorescence imaging (SPECTRALIS HRA+OCT, SPECTRALIS HRA and SPECTRALIS OCT with BluePeak) and to perform measurements of ocular anatomy and ocular lesions. The device is indicated as an aid in the detection and management of various ocular diseases, including age-related macular degeneration, macular edema, diabetic retinopathy, retinal and choroidal vascular diseases, glaucoma, and for viewing geographic atrophy as well as changes in the eye that result from neurodegenerative diseases. The SPECTRALIS HRA+OCT and SPECTRALIS OCT include reference databases for retinal nerve fiber layer thickness and optic nerve head neuroretinal rim parameter measurements, which are used to quantitatively compare the retinal nerve fiber layer and neuroretinal rim in the human retina to values found in normal subjects.
# VI. Comparison of Technological Characteristics with the Predicate Device
The basic technological characteristics of the SPECTRALIS predicate, with software version 5.6, and the new device, with software version 6.0, remain the same. The new device has been updated in the following ways:
- . The new device includes a new reference database that includes optic nerve head (ONH) neuroretinal rim width measurements for the parameter BMO-MRW in addition to retinal nerve fiber layer (RNFL) thickness.
- . The method for locating the fovea and the optic disc center (FoDi) were modified to result in a more accurate definition of both locations with the revised imaging software. The FoDi method is based on an IR image of the fundus, the new, more accurate definition is called Anatomic Positioning System (APS) and is based on OCT images of the fundus. It uses the fovea and the BMO center as landmarks and aligns the image axis on the fovea-BMO center axis.
- . A new scan pattern called ONH-RC, which includes RNFL thickness measurements with three fixed diameter circles of 3.5, 4.1 and 4.7 mm diameter and 48 radial scans around the BMO center. The ONH-RC scan pattern measures the parameter BMO-MRW (BMO minimum rim width) with an image orientation based on APS information
- . An additional imaging function. Enhanced Depth Imaging (EDI), is added to enhance viewing the deep structures of the eve. EDI is available for standard OCT preset scan pattern only. It allows for standard segmentation of ILM and RNFL and retinal thickness measurement. Reference data are not available for EDI scans.
- . Two optional accessory lenses have been added to allow the user conveniently to view a greater proportion of the posterior eye in one view: the Wide Field Objective and the Ultra-Widefield Objective. Both objectives are used for SLO imaging only.
The differences between the predicate device and the subject device are shown in Table 1.
| | Predicate Device<br>(SPECTRALIS HRA+OCT)<br>K101223 and amended in<br>K121993 | Subject Device |
|--------------------|-------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------|
| Optical image axis | Manually determined, FoDi<br>based, using IR images,<br>horizontally aligned | Semi-automatic aligned, APS<br>based, using OCT images<br>aligned along the fovea-BMO<br>center axis |
### TABLE 1: COMPARISON OF CHANGED PRIMARILY CHARACTERISTICS
{5}------------------------------------------------
| | Predicate Device<br>(SPECTRALIS HRA+OCT)<br>K101223 and amended in<br>K121993 | Subject Device |
|---------------------------------------------------------------|-------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------|
| Measurement of RNFLT | Using 12° fixed degree circle<br>scan pattern | Using 3.5mm, 4.1mm and 4.7<br>mm fixed diameter circle scan<br>pattern |
| Measurement of ONH<br>neuroretinal rim width | Using 24 | Using 48 BMO-centered radial<br>scans |
| Reference database for ONH<br>neuroretinal rim with and RNFLT | Caucasian population, RNFLT<br>only | Population of different races and<br>ethnicities from Canada,<br>Germany, and US, representing<br>the population mix of the U.S.A.<br>RNFLT and BMO-MRW |
| EDI imaging | No | Yes |
| Scan angle options | 30° (standard lens) | 30° (standard lens),<br>55° (WFO) and 102° (UWF) |
# TABLE 1: COMPARISON OF CHANGED PRIMARILY CHARACTERISTI
These differences were verified with clinical and bench testing and software verification and validation.
The standard hardware has not been modified compared to the predicate.
### VII. Performance Data
The following performance data were provided in support of the substantial equivalence determination.
# Electrical safety and electromagnetic compatibility (EMC)
The SPECTRALIS HRA+OCT has been tested according to IEC 60601-1 and IEC 60601-1-2 and was found to meet all requirements.
### Laser Safetv
The system is a laser product of Class 1 according to 21 CFR §1040.10 and complies with IEC 60825-1.
### Software Verification and Validation Testing
Software verification and validation testing were conducted and documentation was provided as recommended by FDA's Guidance for Industry and FDA Staff, "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices." The software for this device was considered as a "moderate" level of concern, since a malfunction of or latent design flaw in the software could lead to an erroneous diagnosis or a delay in delivery of appropriate medical care that would lead to minor injury.
A study in normal and glaucomatous human volunteers was conducted to assess precision and agreement of ONH neuroretinal rim parameter and RNFL thickness measurements. The coefficients of variation and the ANOVA analysis for the measured endpoints were within the specified range for this device.
{6}------------------------------------------------
### Clinical Studies
# RNFL Thickness Reference Database
The RNFLT reference database includes 330 eyes (167 right eyes and 163 left eyes) of 330 normal subjects (146 male and 184 female) with mean age of 49.7 years (range 20 to 90 years) and of various racial and ethnic origins (non-Hispanic White: 218; Hispanic White: 45; Black or African American: 41; Asian: 23; American Indian / Alaska Native: 3). The racial and ethnic composition of the reference database is representative for the U.S. population. Subjects were enrolled in a prospective, multi-center, observational study. Included subjects had healthy eyes without prior intraocular surgery (except cataract surgery or Lasik) and without clinically significant vitreal, retinal or choroidal diseases, diabetic retinopathy, or disease of the optic nerve, no history of glaucoma, intraocular pressure ≤21 mmHg, best corrected visual acuity ≥0.5, refraction between +6 and -6 diopters, astigmatism ≤2 diopters, normal visual field with Glaucoma Hemifield Test and Mean Deviation within normal limits, clinically normal appearance of optic disc with normal appearing neuroretinal rim with respect to color and shape.
RNFLT reference data was acquired and analyzed relative to the fovea-to-BMO-center axis, to ensure accurate and consistent positioning of the circle scans across eyes.
The first and fifth percentile reference limits for RNFLT were computed and age- and BMO areaadjusted, and used for comparison with the retinal nerve fiber layer thickness from an individual
The RNFLT reference database includes reference data for RNFL thickness along peri-papillary circle scans with 3.5 mm, 4.1 mm, and 4.7 mm diameter.
The reference database is limited by its sample size (330 subjects), the covered age range (20 to 90 years), the covered range of optic disc size (BMO area 1.0 to 3.4 mm+; 15 cases with BMO area >2.5 mm2), and the covered range of refraction (+6 to -6 diopters).
RNFL thickness in normal subjects decreases slightly with increasing age and with decreasing BMO area. To take this into account the reference database is age-adjusted and BMO areaadjusted based on multiple linear regression. As a result, the percentiles of the normal distribution used for the classification depend on the patient's age and the eye's BMO area.
Mean age and mean BMO area in the reference database are as follows:
- Mean age = 49.70 years -
- -Mean BMO area = 1.828 mm2
As an example for the effect of age and BMO area, the following Table 2 and Table 3 show the values of the 1st and the 5th percentiles of the average RNFLT (3.5 mm diameter circle) global and in the standard sectors, for a 45 years old subject with a large BMO area (2.5 mm2), and for a 65 years old subject with a small BMO area (1.5 mm2).
{7}------------------------------------------------
| | 1st percentile [µm] | 5th percentile [µm] |
|-------------------|---------------------|---------------------|
| Global | 82.5 | 88.8 |
| Temporal | 48.9 | 55.8 |
| Temporal superior | 86.1 | 100.5 |
| Temporal inferior | 115.3 | 127.5 |
| Nasal | 54.7 | 63.7 |
| Nasal superior | 71.4 | 87.8 |
| Nasal inferior | 66.5 | 82.2 |
# TABLE 2: RNFLT (3.5 MM CIRCLE DIAMETER). AGE 45 YEARS. BMO AREA 2.5 MM2
# TABLE 3: RNFLT (3.5 MM CIRCLE DIAMETER) AGE 65 YEARS, BMO AREA 1.5 MM4
| | 1st percentile [µm] | 5th percentile [µm] |
|-------------------|---------------------|---------------------|
| Global | 72.2 | 78.5 |
| Temporal | 45.0 | 51.8 |
| Temporal superior | 72.4 | 86.7 |
| Temporal inferior | 99.6 | 111.8 |
| Nasal | 47.7 | 56.6 |
| Nasal superior | 42.4 | 68.8 |
| Nasal inferior | 51.0 | 66.7 |
# BMO-MRW Reference Database
The BMO-MRW reference database includes 368 eyes (182 right eyes and 186 left eyes) of 368 normal subjects (165 male and 203 female) with mean age of 50.3 years (range 20 to 90 years) and of various racial and ethnic origins (non-Hispanic White: 246; Hispanic White: 47; Black or African American: 47; Asian: 25; American Indian / Alaska Native: 3). The racial and ethnic composition of the reference database is representative for the U.S. population. Subjects were enrolled in a prospective, multicenter, observational study. Included subjects had healthy eyes without prior intraocular surgery (except cataract surgery or Lasik) and without clinically significant vitreal, retinal or choroidal diseases, diabetic retinopathy, or disease of the optic nerve, no history of glaucoma, intraocular pressure ≤21 mmHg, best corrected visual acuity ≥0.5, refraction between +6 and -6 diopters, astigmatism ≤2 diopters, normal visual field with Glaucoma Hemifield Test and Mean Deviation within normal limits, clinically normal appearance of optic disc with normal appearing neuroretinal rim with respect to color and shape.
BMO-MRW reference data was acquired and analyzed relative to the fovea-to-BMO-center axis, to ensure accurate and consistent positioning of the BMO-MRW profiles across eyes. The first and fifth percentile reference limits for BMO-MRW were computed and age- and BMO areaadjusted, and used for comparison with the BMO minimum rim width from an individual
The reference database is limited by its sample size (368 eyes of 368 subjects), the covered age range (20 to 90 years), the covered range of optic disc size (BMO area 1.0 to 3.4 mm²; 19 cases with BMO area >2.5 mm2), and the covered range of refraction (+6 to -6 diopters).
BMO-MRW decreases with increasing age and with increasing BMO area. To take this into account, the reference database is adjusted for age and BMO area in a multiple linear regression
{8}------------------------------------------------
model. As a result, the percentiles of the normal distribution used for the classification depend on the patient's age and the eye's BMO area.
As an example for the effect of age and BMO area, the following Table 4 and Table 5 show the values of the 1st and the 5th percentiles of BMO-MRW for the global averages in the standard sectors, for a 45 years old subject with a small BMO area (1.5 mm²), and for a 65 years old subject with a large BMO (2.5 mm2).
| | 1st percentile [um] | 5th percentile [um] |
|-------------------|---------------------|---------------------|
| Global | 231 | 268 |
| Temporal | 146 | 177 |
| Temporal superior | 194 | 237 |
| Temporal inferior | 227 | 268 |
| Nasal | 246 | 291 |
| Nasal superior | 227 | 277 |
| Nasal inferior | 268 | 316 |
# TABLE 4: BMO-MRW, AGE 45 YEARS, BMO AREA 1.5 MM2
| | 1st percentile [µm] | 5th percentile [µm] |
|-------------------|---------------------|---------------------|
| Global | 155 | 192 |
| Temporal | 94 | 124 |
| Temporal superior | 127 | 169 |
| Temporal inferior | 170 | 212 |
| Nasal | 146 | 192 |
| Nasal superior | 146 | 197 |
| Nasal inferior | 185 | 233 |
RNFLT and BMO-MRW measurement precision for use of the ONH-RC scan pattern In a prospective, monocentric study the clinical precision of BMO-MRW and RNFLT measurements have been determined for use of the ONH-RC scan pattern.
34 subjects were enrolled into the study. Data of 32 subjects was included in analysis. 16 subjects had healthy eyes (healthy eyes without prior intraocular surgery except cataract surgery or laser in-situ keratomileusis, and without clinically significant vitreal, retinal or choroidal diseases, diabetic retinopathy, or disease of the optic nerve).
16 subjects had different stages of glaucomatous eyes (visual field mean deviation ranging from -0.5 to -25.8). All subjects' manifest spherical equivalent was between +6D and -6D, with astigmatism < 2.0D.
Three qualified individuals, each operating one of three Spectralis devices equipped with the study software, performed the study device measurements. Each patient was measured thrice at each device in baseline and thrice in follow-up mode. Outcome metrics were repeatability and reproducibility of measurements of structural parameters of the optic nerve head (in particular, the neuroretinal rim of the ONH), and the peripapillary retinal nerve fiber layer. Additionally each patient was measured once (12° circle and BMO-MRW) with manually defined landmarks
{9}------------------------------------------------
(SPECTRALIS 5.6) to evaluate differences in results according to the different landmark positioning procedures.
In summary:
- 16 left and 16 right eyes were included.
- . Average age of subjects was 57.7 years, ranging from 23 to 80 years.
- . 50% of subjects were female, 50% male.
- Average refraction was -0.2 D (range -6.0 D to +4.75 D).
All acquired images were inspected by three experienced physicians for image quality (image quality index, missing scans, truncated scans, image defocus, floaters, pathologies and layer segmentation).
Manual correction of the fovea position was necessary in 11 of 288 APS definition activities (32 subjects x 9 definitions, 3 operators x 3 repeats). One subject had no distinguishable foveal pit and needed manual placement in 7 out of 9 definitions. The remaining 4 corrections are equally distributed between the healthy and glaucoma groups.
Manual correction of the BMO position was necessary in 51 of 288 APS definitions.
An overview over all corrections is shown in Table 6.
| Group | Fovea APS – manual<br>correction | BMO APS – manual<br>correction |
|----------|----------------------------------|--------------------------------|
| Healthy | 2 of 144 (1.4%) | 22 of 144 (15.3%) |
| Glaucoma | 9 of 144 (6.3%) | 29 of 144 (20.1%) |
| All | 11 of 288 (3.8%) | 51 of 288 (17.7%) |
# TABLE 6: MANUAL CORRECTIONS OF FOVEA AND BMO POSITION DURING PRECISION DATA EVALUATION
Typical causes of manual corrections of the BMO position are small discs, myopic eves, tilted discs with external oblique border tissue, and other irregular BMO structures.
A random effect ANOVA with the effects operator (confounded with device) and eye were used for the analysis:
Yijk = Bo + B1*eye + B2*device + B3*device*eye + ejik
where Yijk stands for the repeated measurements, Bo is the intercept and Bi ~ N ( 0, o ) for i E {1, 2, 3} E {1, 2, 3}. and em iid gaussian variables for the remaining variability. The variability of each component were estimated
The following Table 7 and Table 8 contain summary data of the analysis. For each endpoint and separate for the baseline and follow-up mode, the mean and the maximum of the repeatability and reproducibility coefficient of variation (CV) are tabulated.
{10}------------------------------------------------
| Mean CV | Repeatability | | Reproducibility | |
|---------|---------------|--------|-----------------|--------|
| | BL [%] | FU [%] | BL [%] | FU [%] |
| BMO-MRW | 1.65 | 1.24 | 1.93 | 1.86 |
| 3.5 mm | 2.71 | 1.03 | 3.38 | 3.11 |
| 4.1 mm | 2.68 | 1.35 | 3.39 | 3.33 |
| 4.7 mm | 2.92 | 1.53 | 3.60 | 3.33 |
TABLE 7: MEAN CV OF THE ANOVA ANALYSIS
# TABLE 8: MAXIMUM CV OF THE ANOVA ANALYSIS
| Maximum CV | Repeatability | | Reproducibility | |
|------------|---------------|--------|-----------------|--------|
| | BL [%] | FU [%] | BL [%] | FU [%] |
| BMO-MRW | 2.98 | 2.43 | 3.45 | 3.12 |
| 3.5 mm | 3.86 | 1.65 | 5.14 | 5.04 |
| 4.1 mm | 4.11 | 2.06 | 4.95 | 5.63 |
| 4.7 mm | 4.22 | 2.84 | 5.38 | 4.90 |
The detailed results of the precision analysis for the BMO-MRW and the RNFLT circle measurements are shown in the following tables (Table 24), separated for acquisitions in baseline and follow-up mode and for the different sub-groups (Normal and Glaucoma).
{11}------------------------------------------------
# TABLE 9: REPEATABILITY AND REPRODUCIBILITY FOR BMO-MR BASELINE MODUS (NORMAL)
| | | | Repeatability | | Reproducibility | |
|----|-----------|--------|---------------|--------|-----------------|--------|
| | Mean [µm] | SD[µm] | SD [µm] | CV [%] | SD [µm] | CV [%] |
| G | 351.31 | 85.10 | 2.20 | 0.63 | 2.33 | 0.66 |
| T | 257.49 | 70.25 | 3.73 | 1.45 | 4.06 | 1.58 |
| TS | 326.74 | 78.98 | 4.60 | 1.41 | 4.85 | 1.48 |
| TI | 365.32 | 88.99 | 7.22 | 1.98 | 7.24 | 1.98 |
| N | 394.64 | 103.37 | 2.65 | 0.67 | 3.22 | 0.82 |
| NS | 381.16 | 99.30 | 5.32 | 1.40 | 5.38 | 1.41 |
| NI | 423.91 | 99.91 | 5.25 | 1.24 | 5.94 | 1.40 |
All statistics are estimated from a two-way random effect ANOVA model (REML) with the random effects operator (confounded with device) and eye.
Mean is the intercept of the ANOVA model.
SD is the standard deviation of the measurement.
Repeatability-SD is the square root of the residual variance.
Repeatability-Limit is 2.8 x Repeatability-SD.
Repeatability-CV is Repeatability-SD/Mean*100% (COV).
Reproducibility-SD is the square root of the operator variance, the interaction variance, and the residual variance.
Reproducibility-Limit is 2.8 x Reproducibility-SD.
Reproducibility-CV is Reproducibility-SD/Mean*100% (COV).
# TABLE 10: REPEATABILITY AND REPRODUCIBILITY FOR BMO-MRW -FOLLOW-UP MODUS (NORMAL)
| | Mean [um] | SD[µm] | Repeatability | | Reproducibility | |
|----|-----------|--------|---------------|--------|-----------------|--------|
| | | | SD [µm] | CV [%] | SD [µm] | CV [%] |
| G | 351.71 | 84.83 | 1.46 | 0.42 | 2.98 | 0.85 |
| T | 258.28 | 69.70 | 2.03 | 0.78 | 3.23 | 1.25 |
| TS | 327.16 | 77.54 | 3.21 | 0.98 | 5.23 | 1.60 |
| TI | 365.54 | 88.41 | 4.06 | 1.11 | 6.88 | 1.88 |
| N | 395.11 | 103.92 | 1.80 | 0.46 | 3.39 | 0.86 |
| NS | 380.80 | 99.32 | 4.14 | 1.09 | 6.85 | 1.80 |
| NI | 424.32 | 99.53 | 4.61 | 1.09 | 7.36 | 1.73 |
All statistics are estimated from a two-way random effect ANOVA model (REML) with the random effects operator (confounded with device) and eye.
Mean is the intercept of the ANOVA model.
SD is the standard deviation of the measurement.
Repeatability-SD is the square root of the residual variance.
Repeatability-Limit is 2.8 x Repeatability-SD.
Repeatability-CV is Repeatability-SD/Mean*100% (COV).
Reproducibility-SD is the square root of the operator variance, the interaction variance, and the residual variance.
Reproducibility-Limit is 2.8 x Reproducibility-SD.
{12}------------------------------------------------
# TABLE 11: REPEATABILITY AND REPRODUCIBILITY FOR BMO-MI BASELINE MODUS (GLAUCOMA)
| | Mean [µm] | SD[µm] | Repeatability | | Reproducibility | |
|----|-----------|--------|---------------|--------|-----------------|--------|
| | | | SD [µm] | CV [%] | SD [µm] | CV [%] |
| G | 189.43 | 53.64 | 1.84 | 0.97 | 2.58 | 1.36 |
| T | 151.28 | 49.49 | 2.36 | 1.56 | 3.01 | 1.99 |
| TS | 158.88 | 66.63 | 4.52 | 2.85 | 5.46 | 3.44 |
| TI | 190.07 | 76.28 | 3.85 | 2.02 | 6.06 | 3.19 |
| N | 207.61 | 64.28 | 2.96 | 1.43 | 3.39 | 1.63 |
| NS | 196.98 | 64.54 | 5.87 | 2.98 | 6.79 | 3.45 |
| NI | 247.66 | 71.50 | 6.16 | 2.49 | 6.49 | 2.62 |
All statistics are estimated from a two-way random effect ANOVA model (REML) with the random effects operator (confounded with device) and eye.
Mean is the intercept of the ANOVA model.
SD is the standard deviation of the measurement.
Repeatability-SD is the square root of the residual variance.
Repeatability-Limit is 2.8 x Repeatability-SD.
Repeatability-CV is Repeatability-SD/Mean*100% (COV).
Reproducibility-SD is the square root of the operator variance, the interaction variance, and the residual variance.
Reproducibility-Limit is 2.8 x Reproducibility-SD.
Reproducibility-CV is Reproducibility-SD/Mean*100% (COV).
# TABLE 12: REPEATABILITY AND REPRODUCIBILITY FOR BMO-MRW -FOLLOW-UP MODUS (GLAUCOMA)
| | Mean [µm] | SD[µm] | Repeatability | | Reproducibility | |
|----|-----------|--------|---------------|--------|-----------------|--------|
| | | | SD [µm] | CV [%] | SD [µm] | CV [%] |
| G | 189.14 | 53.43 | 1.34 | 0.71 | 2.24 | 1.19 |
| T | 151.15 | 49.90 | 2.13 | 1.41 | 2.31 | 1.53 |
| TS | 158.77 | 65.93 | 3.43 | 2.16 | 4.39 | 2.77 |
| TI | 189.45 | 75.62 | 3.26 | 1.72 | 5.43 | 2.87 |
| N | 207.71 | 64.51 | 2.59 | 1.25 | 3.93 | 1.89 |
| NS | 196.29 | 64.56 | 4.77 | 2.43 | 6.12 | 3.12 |
| NI | 246.41 | 71.06 | 4.39 | 1.78 | 6.83 | 2.77 |
All statistics are estimated from a two-way random effect ANOVA model (REML) with the random effects operator (confounded with device) and eye.
Mean is the intercept of the ANOVA model.
SD is the standard deviation of the measurement.
Repeatability-SD is the square root of the residual variance.
Repeatability-Limit is 2.8 x Repeatability-SD.
Repeatability-CV is Repeatability-SD/Mean*100% (COV).
Reproducibility-SD is the square root of the operator variance, the interaction variance, and the residual variance.
Reproducibility-Limit is 2.8 x Reproducibility-SD.
{13}------------------------------------------------
# TABLE 13: REPEATABILITY AND REPRODUCIBILITY FOR 3.5 MM CIRCLE SCAN PATTERN - BASELINE MODUS (NORMAL)
| | Mean [µm] | SD[µm] | Repeatability | | Reproducibility | |
|----|-----------|--------|---------------|--------|-----------------|--------|
| | | | SD [µm] | CV [%] | SD [µm] | CV [%] |
| G | 98.62 | 9.59 | 1.09 | 1.10 | 2.10 | 2.13 |
| T | 66.42 | 11.91 | 1.48 | 2.22 | 1.69 | 2.55 |
| TS | 135.65 | 19.55 | 3.77 | 2.78 | 4.26 | 3.14 |
| TI | 133.71 | 14.90 | 2.80 | 2.10 | 3.11 | 2.32 |
| N | 81.35 | 12.03 | 2.18 | 2.68 | 3.23 | 3.96 |
| NS | 111.20 | 15.25 | 3.00 | 2.70 | 4.14 | 3.73 |
| NI | 112.88 | 18.00 | 3.39 | 3.00 | 4.80 | 4.26 |
All statistics are estimated from a two-way random effect ANOVA model (REML) with the random effects operator (confounded with device) and eye.
Mean is the intercept of the ANOVA model.
SD is the standard deviation of the measurement.
Repeatability-SD is the square root of the residual variance.
Repeatability-Limit is 2.8 x Repeatability-SD.
Repeatability-CV is Repeatability-SD/Mean*100% (COV).
Reproducibility-SD is the square root of the operator variance, the interaction variance, and the residual variance.
Reproducibility-Limit is 2.8 x Reproducibility-SD.
Reproducibility-CV is Reproducibility-SD/Mean*100% (COV).
# TABLE 14: REPEATABILITY AND REPRODUCIBILITY FOR 3.5 MM CIRCLE SCAN PATTERN - FOLLOW-UP MODUS (NORMAL)
| | | | Repeatability | | Reproducibility | |
|-----|-----------|--------|---------------|--------|-----------------|--------|
| | Mean [um] | SD[um] | SD [um] | CV [%] | SD [um] | CV [%] |
| G | 98.85 | 9.34 | 0.43 | 0.44 | 1.81 | 1.83 |
| T | 66.55 | 11.52 | 0.74 | 1.11 | 1.51 | 2.27 |
| TS | 136.34 | 19.63 | 1.16 | 0.85 | 4.09 | 3.00 |
| TI | 134.58 | 13.81 | 1.30 | 0.97 | 2.56 | 1.91 |
| N | 81.11 | 11.68 | 0.87 | 1.07 | 2.59 | 3.20 |
| પરિ | 111.26 | 14.88 | 0.96 | 0.86 | 3.83 | 3.44 |
| NI | 113.29 | 18.78 | 0.96 | 0.85 | 4.21 | 3.71 |
All statistics are estimated from a two-way random effect ANOVA model (REML) with the random effects operator (confounded with device) and eye.
Mean is the intercept of the ANOVA model.
SD is the standard deviation of the measurement.
Repeatability-SD is the square root of the residual variance.
Repeatability-Limit is 2.8 x Repeatability-SD.
Repeatability-CV is Repeatability-SD/Mean*100% (COV).
Reproducibility-SD is the square root of the operator variance, the interaction variance, and the residual variance.
Reproducibility-Limit is 2.8 x Reproducibility-SD.
{14}------------------------------------------------
# TABLE 15: REPEATABILITY AND REPRODUCIBILITY FOR 3.5 MM CIRCLE SCAN PATTERN - BASELINE MODUS (GLAUCOMA)
| | Mean [µm] | SD[µm] | Repeatability | | Reproducibility | |
|----|-----------|--------|---------------|--------|-----------------|--------|
| | | | SD [µm] | CV [%] | SD [µm] | CV [%] |
| G | 66.22 | 19.62 | 1.09 | 1.65 | 1.41 | 2.13 |
| T | 50.50 | 15.27 | 1.39 | 2.76 | 1.81 | 3.59 |
| TS | 85.44 | 35.43 | 3.30 | 3.86 | 4.39 | 5.14 |
| TI | 91.06 | 36.84 | 2.95 | 3.24 | 2.95 | 3.24 |
| N | 51.70 | 13.71 | 1.61 | 3.11 | 1.70 | 3.28 |
| NS | 71.41 | 26.73 | 2.49 | 3.49 | 2.96 | 4.15 |
| NI | 77.44 | 26.04 | 2.48 | 3.20 | 2.82 | 3.64 |
All statistics are estimated from a two-way random effect ANOVA model (REML) with the random effects operator (confounded with device) and eye.
Mean is the intercept of the ANOVA model.
SD is the standard deviation of the measurement.
Repeatability-SD is the square root of the residual variance.
Repeatability-Limit is 2.8 x Repeatability-SD.
Repeatability-CV is Repeatability-SD/Mean*100% (COV).
Reproducibility-SD is the square root of the operator variance, the interaction variance, and the residual variance.
Reproducibility-Limit is 2.8 x Reproducibility-SD.
Reproducibility-CV is Reproducibility-SD/Mean*100% (COV).
# TABLE 16: REPEATABILITY AND REPRODUCIBILITY FOR 3.5 MM CIRCLE SCAN PATTERN - FOLLOW-UP MODUS (GLAUCOMA)
| | Mean [µm] | SD[µm] | Repeatability | | Reproducibility | |
|----|-----------|--------|---------------|--------|-----------------|--------|
| | | | SD [µm] | CV [%] | SD [µm] | CV [%] |
| G | 66.66 | 19.58 | 0.47 | 0.70 | 1.35 | 2.03 |
| T | 50.80 | 14.90 | 0.67 | 1.33 | 1.75 | 3.45 |
| TS | 85.96 | 35.05 | 1.24 | 1.44 | 4.33 | 5.04 |
| TI | 91.28 | 36.30 | 0.86 | 0.95 | 2.65 | 2.90 |
| N | 52.40 | 14.21 | 0.86 | 1.65 | 1.95 | 3.73 |
| NS | 71.55 | 26.84 | 0.76 | 1.06 | 2.23 | 3.11 |
| NI | 78.06 | 26.06 | 0.95 | 1.21 | 3.08 | 3.95 |
All statistics are estimated from a two-way random effect ANOVA model (REML) with the random effects operator (confounded with device) and eye.
Mean is the intercept of the ANOVA model.
SD is the standard deviation of the measurement.
Repeatability-SD is the square root of the residual variance.
Repeatability-Limit is 2.8 x Repeatability-SD.
Repeatability-CV is Repeatability-SD/Mean*100% (COV).
Reproducibility-SD is the square root of the operator variance, the interaction variance, and the residual variance.
Reproducibility-Limit is 2.8 x Reproducibility-SD.
{15}------------------------------------------------
## TABLE 17: REPEATABILITY AND REPRODUCIBILITY FOR 4.1 MM CIRCLE SCAN PATTERN - BASELINE MODUS (NORMAL)
| | Mean [µm] | SD[µm] | Repeatability | | Reproducibility | |
|----|-----------|--------|---------------|--------|-----------------|--------|
| | | | SD [µm] | CV [%] | SD [µm] | CV [%] |
| G | 84.54 | 7.68 | 0.90 | 1.06 | 1.62 | 1.91 |
| T | 59.37 | 10.05 | 1.25 | 2.11 | 1.61 | 2.72 |
| TS | 121.94 | 16.54 | 2.73 | 2.24 | 3.42 | 2.80 |
| TI | 120.50 | 11.88 | 2.63 | 2.18 | 3.01 | 2.50 |
| N | 66.52 | 9.17 | 1.63 | 2.45 | 2.30 | 3.45 |
| NS | 92.16 | 10.90 | 2.53 | 2.75 | 3.43 | 3.72 |
| NI | 89.91 | 14.23 | 2.44 | 2.71 | 3.35 | 3.73 |
All statistics are estimated from a two-way random effect ANOVA model (REML) with the random effects operator (confounded with device) and eye.
Mean is the intercept of the ANOVA model.
SD is the standard deviation of the measurement.
Repeatability-SD is the square root of the residual variance.
Repeatability-Limit is 2.8 x Repeatability-SD.
Repeatability-CV is Repeatability-SD/Mean*100% (COV).
Reproducibility-SD is the square root of the operator variance, the interaction variance, and the residual variance.
Reproducibility-Limit is 2.8 x Reproducibility-SD.
Reproducibility-CV is Reproducibility-SD/Mean*100% (COV).
# TABLE 18: REPEATABILITY AND REPRODUCIBILITY FOR 4.1 MM CIRCLE SCAN PATTERN - FOLLOW-UP MODUS (NORMAL)
| | Mean [um] | SD[um] | Repeatability | | Reproducibility | |
|----|-----------|--------|---------------|--------|-----------------|--------|
| | | | SD [um] | CV [%] | SD [um] | CV [%] |
| G | 84.77 | 7.52 | 0.54 | 0.64 | 1.48 | 1.74 |
| T | 59.50 | 9.77 | 0.89 | 1.49 | 1.78 | 2.99 |
| TS | 122.28 | 16.21 | 1.05 | 0.86 | 2.99 | 2.45 |
| TI | 121.37 | 11.06 | 1.26 | 1.04 | 2.66 | 2.19 |
| N | 66.60 | 9.18 | 0.96 | 1.45 | 2.01 | 3.02 |
| NS | 92.00 | 10.64 | 1.19 | 1.29 | 3.64 | 3.96 |
| NI | 90.33 | 14.34 | 0.96 | 1.06 | 3.39 | 3.75 |
All statistics are estimated from a two-way random effect ANOVA model (REML) with the random effects operator (confounded with device) and eye.
Mean is the intercept of the ANOVA model.
SD is the standard deviation of the measurement.
Repeatability-SD is the square root of the residual variance.
Repeatability-Limit is 2.8 x Repeatability-SD.
Repeatability-CV is Repeatability-SD/Mean*100% (COV).
Reproducibility-SD is the square root of the operator variance, the interaction variance, and the residual variance.
Reproducibility-Limit is 2.8 x Reproducibility-SD.
{16}------------------------------------------------
# TABLE 19: REPEATABILITY AND REPRODUCIBILITY FOR 4.1 MM CIRCLE SCAN PATTERN - BASELINE MODUS (GLAUCOMA)
| | Mean [µm] | SD[µm] | Repeatability | | Reproducibility | |
|----|-----------|--------|---------------|--------|-----------------|--------|
| | | | SD [µm] | CV [%] | SD [µm] | CV [%] |
| G | 58.73 | 16.13 | 0.97 | 1.66 | 1.16 | 1.98 |
| T | 46.73 | 12.59 | 1.92 | 4.11 | 2.31 | 4.95 |
| TS | 79.33 | 30.55 | 2.91 | 3.66 | 3.90 | 4.92 |
| TI | 83.30 | 34.62 | 2.16 | 2.60 | 2.38 | 2.85 |
| N | 45.02 | 10.41 | 1.42 | 3.16 | 1.55 | 3.45 |
| NS | 59.91 | 21.16 | 2.07 | 3.46 | 2.65 | 4.42 |
| NI | 63.80 | 20.33 | 2.13 | 3.35 | 2.55 | 4.00 |
All statistics are estimated from a two-way random effect ANOVA with the random effects operator (confounded with device) and eye.
Mean is the intercept of the ANOVA model.
SD is the standard deviation of the measurement.
Repeatability-SD is the square root of the residual variance.
Repeatability-Limit is 2.8 x Repeatability-SD.
Repeatability-CV is Repeatability-SD/Mean*100% (COV).
Reproducibility-SD is the square root of the operator variance, the interaction variance, and the residual variance.
Reproducibility-Limit is 2.8 x Reproducibility-SD.
Reproducibility-CV is Reproducibility-SD/Mean*100% (COV).
# TABLE 20: REPEATABILITY AND REPRODUCIBILITY FOR 4.1 MM CIRCLE SCAN PATTERN - FOLLOW-UP MODUS (GLAUCOMA)
| | Mean [µm] | SD[µm] | Repeatability | | Reproducibility | |
|----|-----------|--------|---------------|--------|-----------------|--------|
| | | | SD [µm] | CV [%] | SD [µm] | CV [%] |
| G | 59.30 | 16.19 | 0.60 | 1.01 | 1.11 | 1.87 |
| T | 47.08 | 12.22 | 0.84 | 1.78 | 2.65 | 5.63 |
| TS | 80.28 | 30.84 | 1.06 | 1.32 | 3.70 | 4.61 |
| TI | 83.94 | 34.56 | 1.16 | 1.39 | 2.07 | 2.46 |
| N | 45.63 | 10.52 | 0.78 | 1.72 | 1.59 | 3.48 |
| NS | 60.47 | 21.54 | 1.08 | 1.78 | 2.57 | 4.25 |
| NI | 64.26 | 20.96 | 1.32 | 2.06 | 2.67 | 4.16 |
All statistics are estimated from a two-way random effect ANOVA model (REML) with the random effects operator (confounded with device) and eve.
Mean is the intercept of the ANOVA model.
SD is the standard deviation of the measurement.
Repeatability-SD is the square root of the residual variance.
Repeatability-Limit is 2.8 x Repeatability-SD.
Repeatability-CV is Repeatability-SD/Mean*100% (COV).
Reproducibility-SD is the square root of the operator variance, the interaction variance, and the residual variance.
Reproducibility-Limit is 2.8 x Reproducibility-SD.
{17}------------------------------------------------
# TABLE 21: REPEATABILITY AND REPRODUCIBILITY FOR 4.7 MM CIRCLE SCAN PATTERN - BASELINE MODUS (NORMAL
| | Mean [µm] | SD[µm] | Repeatability | | Reproducibility | |
|----|-----------|--------|---------------|--------|-----------------|--------|
| | | | SD [µm] | CV [%] | SD [µm] | CV [%] |
| G | 74.16 | 6.85 | 0.95 | 1.28 | 1.37 | 1.85 |
| T | 54.69 | 8.99 | 1.59 | 2.92 | 1.68 | 3.07 |
| TS | 109.08 | 15.88 | 2.31 | 2.12 | 2.81 | 2.58 |
| TI | 110.83 | 10.09 | 2.11 | 1.90 | 2.64 | 2.38 |
| N | 56.71 | 7.47 | 1.29 | 2.27 | 1.85 | 3.27 |
| NS | 76.50 | 8.07 | 2.26 | 2.95 | 2.52 | 3.30 |
| NI | 74.09 | 12.46 | 2.49 | 3.36 | 2.96 | 4.00 |
All statistics are estimated from a two-way random effect ANOVA model (REML) with the random effects operator (confounded with device) and eye.
Mean is the intercept of the ANOVA model.
SD is the standard deviation of the measurement.
Repeatability-SD is the square root of the residual variance.
Repeatability-Limit is 2.8 x Repeatability-SD.
Repeatability-CV is Repeatability-SD/Mean*100% (COV).
Reproducibility-SD is the square root of the operator variance, the interaction variance, and the residual variance.
Reproducibility-Limit is 2.8 x Reproducibility-SD.
Reproducibility-CV is Reproducibility-SD/Mean*100% (COV).
# TABLE 22: REPEATABILITY AND REPRODUCIBILITY FOR 4.7 MM CIRCLE SCAN PATTERN - FOLLOW-UP MODUS (NORMAL)
| | Mean [µm] | SD[µm] | Repeatability | | Reproducibility | |
|----|-----------|--------|---------------|--------|-----------------|--------|
| | | | SD [µm] | CV [%] | SD [µm] | CV [%] |
| G | 74.22 | 6.48 | 0.49 | 0.66 | 1.24 | 1.67 |
| T | 54.66 | 8.67 | 0.90 | 1.64 | 1.53 | 2.81 |
| TS | 108.81 | 15.85 | 0.89 | 0.82 | 2.50 | 2.30 |
| TI | 111.80 | 8.71 | 0.99 | 0.89 | 2.98 | 2.66 |
| N | 56.49 | 7.39 | 0.82 | 1.45 | 2.04 | 3.61 |
| NS | 76.51 | 7.80 | 1.07 | 1.40 | 2.18 | 2.84 |
| NI | 74.34 | 12.57 | 0.94 | 1.26 | 2.26 | 3.04 |
All statistics are estimated from a two-way random effect ANOVA model (REML) with the random effects operator (confounded with device) and eye.
Mean is the intercept of the ANOVA model.
SD is the standard deviation of the measurement.
Repeatability-SD is the square root of the residual variance.
Repeatability-Limit is 2.8 x Repeatability-SD.
Repeatability-CV is Repeatability-SD/Mean*100% (COV).
Reproducibility-SD is the square root of the operator variance, the interaction variance, and the residual variance.
Reproducibility-Limit is 2.8 x Reproducibility-SD.
{18}------------------------------------------------
# TABLE 23: REPEATABILITY AND REPRODUCIBILITY FOR 4.7 MM CIRCLE SCAN PATTERN - BASELINE MODUS (GLAUCOMA)
| | | | Repeatability | | Reproducibility | |
|----|-----------|--------|---------------|--------|-----------------|--------|
| | Mean [µm] | SD[µm] | SD [µm] | CV [%] | SD [µm] | CV [%] |
| G | 52.75 | 13.81 | 0.91 | 1.72 | 1.20 | 2.27 |
| T | 43.49 | 11.16 | 1.77 | 4.07 | 2.15 | 4.94 |
| TS | 73.64 | 28.49 | 2.77 | 3.76 | 3.92 | 5.32 |
| TI | 75.96 | 30.90 | 2.36 | 3.11 | 2.59 | 3.41 |
| N | 40.23 | 8.18 | 1.42 | 3.52 | 1.63 | 4.06 |
| NS | 51.60 | 16.79 | 2.18 | 4.22 | 2.78 | 5.38 |
| NI | 53.35 | 15.21 | 1.96 | 3.68 | 2.42 | 4.53 |
All statistics are estimated from a two-way random effect ANOVA model (REML) with the random effects operator (confounded with device) and eye.
Mean is the intercept of the ANOVA model.
SD is the standard deviation of the measurement.
Repeatability-SD is the square root of the residual variance.
Repeatability-Limit is 2.8 x Repeatability-SD.
Repeatability-CV is Repeatability-SD/Mean*100% (COV).
Reproducibility-SD is the square root of the operator variance, the interaction variance, and the residual variance.
Reproducibility-Limit is 2.8 x Reproducibility-SD.
Reproducibility-CV is Reproducibility-SD/Mean*100% (COV).
# TABLE 24: REPEATABILITY AND REPRODUCIBILITY FOR 4.7 MM CIRCLE SCAN PATTERN - FOLLOW-UP MODUS (GLAUCOMA)
| | | Repeatability | | Reproducibility | | |
|----|-----------|---------------|---------|-----------------|---------|--------|
| | Mean [um] | SD[µm] | SD [µm] | CV [%] | SD [µm] | CV [%] |
| G | 53.17 | 13.74 | 0.52 | 0.97 | 1.13 | 2.13 |
| T | 43.53 | 11.05 | 0.87 | 2.00 | 2.13 | 4.90 |
| TS | 74.24 | 28.26 | 1.54 | 2.08 | 3.31 | 4.46 |
| TI | 76.63 | 30.69 | 1.45 | 1.89 | 3.02 | 3.95 |
| N | 40.74 | 8.17 | 0.72 | 1.76 | 1.42 | 3.50 |
| NS | 51.90 | 16.77 | 0.87 | 1.69 | 2.13 | 4.11 |
| NI | 54.04 | 15.58 | 1.53 | 2.83 | 2.51 | 4.64 |
All statistics are estimated from a two-way random effect ANOVA model (REML) with the random effects operator (confounded with device) and eye.
Mean is the intercept of the ANOVA model.
SD is the standard deviation of the measurement.
Repeatability-SD is the square root of the residual variance.
Repeatability-Limit is 2.8 x Repeatability-SD.
Repeatability-CV is Repeatability-SD/Mean*100% (COV).
Reproducibility-SD is the square root of the operator variance, the interaction variance, and the residual variance.
Reproducibility-Limit is 2.8 x Reproducibility-SD.
{19}------------------------------------------------
# Limit of Agreement BMO center position
To evaluate potential differences according to the different landmark positioning procedures the results of the 12° circle scan pattern with the manually defined landmarks (SPECTRALIS 5.6) and the 3.5 mm circle scan pattern with the APS semi-automated defined landmarks (SPECTRALIS 6.0) are compared. The following Table 26 summarize the results, the results derived from both measurements agree.
### TABLE 25: LIMIT OF AGREEMENT SUMMARY OF RNFLT 3.5MM CIRCLE SCAN PATTER USING APS WITH MANUAL POSITIONED 12° CIRCLE SCAN PATTERN-NORMAL SUBJECTS
| | Mean Diff [µm] | Mean Diff [%] | Min Diff [µm] | Max Diff [µm] | SD [µm] | LOA low [µm] | LOA up [µm] |
|----|----------------|---------------|---------------|---------------|---------|--------------|-------------|
| G | -0.6 | -0.5 | -10.4 | 7.2 | 5.4 | -11.1 | 10.0 |
| T | 0.5 | 0.8 | -6.0 | 6.1 | 3.4 | -6.3 | 7.2 |
| TS | 1.9 | 1.5 | -15.7 | 21.6 | 7.8 | -13.5 | 17.3 |
| TI | -0.4 | -0.3 | -12.4 | 10.3 | 6.2 | -12.6 | 11.7 |
| N | -2.6 | -2.4 | -22.2 | 10.6 | 8.2 | -18.6 | 13.5 |
| NS | -1.0 | -0.2 | -18.3 | 13.8 | 10.3 | -21.2 | 19.3 |
| NI | 0.5 | 0.7 | -20.4 | 18.2 | 10.3 | -19.6 | 20.7 |
Mean of the differences (measurement - predicate)
Mean of the percentile differences, with respect to the predicate
Minimum of the differences
Maximum of the differences
Standard deviation of the differences Lower LOA = Mean - 1.96 standard deviation
Lower LOA = Mean - 1.96 standard deviation
Upper LOA = Mean + 1.96 standard deviation
Upper LOA = Mean + 1.96 standard deviation
{20}------------------------------------------------
# TABLE 26: LIMIT OF AGREEMENT SUMMARY OF RNFLT 3.5MM CIRCLE SCAN PATTERN USING APS WITH MANUAL POSITIONED 12° CIRCLE SCAN PATTERN -GLAUCOMA SUBJECTS
| | Mean Diff<br>[µm] | Mean Diff<br>[%] | Min Diff<br>[µm] | Max Diff<br>[µm] | SD [µm] | LOA low<br>[µm] | LOA up<br>[µm] |
|----|-------------------|------------------|------------------|------------------|---------|-----------------|----------------|
| G | 1.1 | 1.2 | -4.2 | 10.7 | 3.8 | -6.4 | 8.6 |
| T | 0.7 | 0.8 | -3.0 | 9.0 | 2.9 | -4.9 | 6.3 |
| TS | 1.9 | 3.8 | -7.1 | 15.7 | 5.5 | -8.8 | 12.6 |
| TI | 1.3 | 0.6 | -6.0 | 8.2 | 4.7 | -7.9 | 10.5 |
| N | 0.6 | 0.8 | -6.7 | 9.7 | 4.0 | -7.1 | 8.4 |
| NS | 3.1 | 5.4 | -8.2 | 22.1 | 8.7 | -14.0 | 20.2 |
| NI | 0.7 | -0.1 | -10.8 | 15.2 | 7.0 | -12.9 | 14.4 |
Mean of the percentile differences, with respect to the predicate
Minimum of the differences
Maximum of the differences
Standard deviation of the differences
Lower LOA = Mean - 1.96 standard deviation
Upper LOA = Mean + 1.96 standard deviation
# RNFLT and BMO-MRW measurement agreement with the predicate device
In a prospective, monocentric study the measurement agreement between BMO-MRW and RNFLT measurements with an OCT based landmark definition process and RNFLT measurements with an infrared image based landmark definition process has been determined. 48 subjects were enrolled into the study. Data of 40 subjects were included in analysis.
20 subjects had healthy eyes (healthy eves without prior intraocular surgery except cataract surgery or laser in-situ keratomileusis, and without clinically significant vitreal, retinal or choroidal diseases, diabetic retinopathy, or disease of the optic nerve).
20 subjects had different stages of glaucomatous eyes (visual field mean deviation ranging from -0.02 to -31.95). All subjects' manifest spherical equivalent was in between +6D and -6D, with astigmatism ≤ 2.0D.
The study aimed to evaluate the agreement of structural parameters of the optic nerve head (ONH), in particular, the neuroretinal rim of the ONH, and the peripapillary retinal nerve fiber layer based on infrared (IR) image-based (Fovea-to-Disc-Alignment technology - FoDi) and optical coherence tomography (OCT) (Anatomic positioning System - APS) based scan alignment. All subjects were examined once with each device version and underwent further supporting diagnostics.
In summary:
- . 20 left and 20 right eyes were included.
- . Average age of subjects was 56.3 years, ranging from 23 to 81 years.
- . 50% of subjects were female. 50% male.
- . Average refraction was -0.79 D (range -5.25 D to +3.50 D).
{21}------------------------------------------------
All acquired images were inspected by the investigator for image quality (image quality index. missing scans, truncated scans, image defocus, floaters, pathologies, scan center position alignment, and layer segmentation).
To test agreement of parameters of the optic nerve head and the peripapillary retinal nerve fiber layer measurements acquired with the different alignment methods and circle characteristics, the following statistic are calculated
- . The mean of the differences (measurement - predicate),
- . the minimum and maximum difference.
- . the standard deviation of the differences.
- . the 95% limits of agreement (LOA)
All differences between the different RNFLT scans are overall small and within expected ranges and below predefined thresholds. Therefore results derived from the predicate software version 5.6 and the subject device software version 6.0 are considered to agree.
The following Table 27 and Table 28 show the detailed agreement data for the comparison between RNFL thickness measurements from the 3.5 mm circle scan and RNFL thickness measurements from the 12° circle scan of the predicate device (software version 5.6). The global and sector values are tabulated separate for the sub-groups (Normal and Glaucoma).
# TABLE 27: LIMIT OF AGREEMENT SUMMARY OF RNFLT 3.5 MM CIRCLE SCAN PATTERN WITH THE 12° CIRCLE SCAN PATTERN- NORMAL SUBJECTS
| | Mean Diff<br>[µm] | Mean Diff<br>[%] | Min Diff<br>[µm] | Max Diff<br>[µm] | SD [µm] | LOA low<br>[µm] | LOA up<br>[µm] |
|----|-------------------|------------------|------------------|------------------|---------|-----------------|----------------|
| G | 4.5 | 4.7 | -1.6 | 13.4 | 4.5 | -4.2 | 13.2 |
| T | -1.0 | -0.8 | -12.0 | 12.8 | 5.1 | -11.0 | 9.1 |
| TS | 4.7 | 3.6 | -12.1 | 26.9 | 8.1 | -11.3 | 20.6 |
| TI | 4.2 | 3.0 | -6.1 | 18.6 | 7.1 | -9.8 | 18.1 |
| N | 6.6 | 10.5 | -7.4 | 22.8 | 7.2 | -7.4 | 20.7 |
| NS | 6.4 | 5.9 | -6.1 | 22.7 | 9.0 | -11.4 | 24.1 |
| NI | 9.3 | 9.7 | -25.9 | 33.9 | 11.9 | -13.9 | 32.6 |
Mean of the differences (measurement - predicate)
Mean of the percentile differences, with respect to the predicate
Minimum of the differences
Maximum of the differences
Standard deviation of the differences
Lower LOA = Mean - 1.96 standard deviation Upper LOA = Mean + 1.96 standard deviation
{22}------------------------------------------------
# TABLE 28: LIMIT OF AGREEMENT SUMMARY OF RNFLT 3.5 MM CIRCLE SCAN PATTER WITH THE 12° CIRCLE SCAN PATTER - GLAUCOMA SUBJECTS
| | Mean Diff<br>[µm] | Mean Diff<br>[%] | Min Diff<br>[µm] | Max Diff<br>[µm] | SD [µm] | LOA low<br>[µm] | LOA up<br>[µm] |
|----|-------------------|------------------|------------------|------------------|---------|-----------------|----------------|
| G | 3.7 | 6.7 | -5.5 | 13.5 | 5.4 | -6.8 | 14.3 |
| T | -0.2 | 0.8 | -25.5 | 7.4 | 6.7 | -13.2 | 12.9 |
| TS | 7.0 | 12.2 | -3.2 | 42.9 | 11.8 | -16.2 | 30.2 |
| TI | 1.3 | 1.9 | -14.9 | 23.3 | 8.2 | -14.8 | 17.4 |
| N | 3.3 | 12.0 | -20.6 | 28.8 | 11.4 | -18.9 | 25.6 |
| NS | 10.0 | 30.1 | -5.5 | 50.3 | 13.9 | -17.2 | 37.2 |
| NI | 5.2 | 9.9 | -5.7 | 16.8 | 5.7 | -5.9 | 16.4 |
Mean of the differences (measurement - predicate)
Mean of the percentile differences, with respect to the predicate
Minimum of the differences
Maximum of the differences
Standard deviation of the differences
Lower LOA = Mean - 1.96 standard deviation
Upper LOA = Mean + 1.96 standard deviation
### VIII. Conclusions
The SPECTRALIS HRA+OCT has the same Intended Use as the predicate device. The basic technological characteristics remain the same, and the device has been updated to include a new reference database that includes optic nerve head (ONH) neuroretinal rim width measurements in addition to retinal nerve fiber layer (RNFL) thickness. The method for locating the fovea and the optic disc center were modified to result in a more accurate definition of both locations with the revised imaging software. An additional imaging function, Enhanced Depth Imaging (EDI), is added to enhance viewing the deep structures of the eye. These differences do not affect safety or effectiveness, as verified with clinical and bench testing and software verification and validation. Therefore, it is concluded that the SPECTRALIS HRA+OCT is substantially equivalent to the predicate device.
Two optional accessory lenses have been added to allow the user to view a greater proportion of the posterior eye in one view: the Wide Field Objective and the Ultra-Widefield Objective. These lenses are similar to two reference devices. Nidek Ophthalmoscope F-10 (K072259) and Optos 200T (K111628) and do not raise new issues of safety and effectiveness.
Predicate graph will load when search results are available.
Embedding visualization will load when search results are available.
PDF viewer will load when search results are available.
Loading panels...
Select an item from Submissions
Click any panel, subpart, regulation, product code, or device to see details here.
Section Matches
Results will appear here.
Product Code Matches
Results will appear here.
Special Control Matches
Results will appear here.
Loading collections...
Loading
My Alerts
You will receive email notifications based on the filters and frequency you set for each alert.
Sort by:
Create Alert
Search Filters
Agent Token
Create a read-only bearer token for Claude, ChatGPT, or other agents that can call HTTP APIs.
Copy this now. It will not be shown again.
Connected apps
Apps you authorized through browser sign-in. Disconnecting revokes their access immediately.
Learn the FDA Browser
Two short videos show you everything — or skip straight to the written tutorial if you'd rather read. You can reopen this any time from the Tutorial button in the top bar.
Part 1 — Search, results, and everyday workflows 16 min
Part 2 — Embeddings: the galaxy map 3 min
1. Search: exact and fuzzy
Type a phrase like "coronary artery calcification" into the search box. You get two kinds of results. Exact results match the literal phrase — prefix searches work ("coronary artery calcificati") but suffix searches do not. Fuzzy results match on the meaning and intent of your phrase rather than the exact words, and are sorted by relevance score. Hover over the Exact or Fuzzy badge on any row to see exactly why it matched.
Use the checkboxes above the results to narrow: SaMD keeps only software-only devices, AI / ML keeps only devices with AI.
Exact vs. fuzzy search: what's the difference?
Exact matches on the literal phrase (prefix search works, suffix does not). Fuzzy matches on the meaning and intent of the phrase rather than the exact words. Hover over the badge on any row to see why it matched.
You search "coronary artery calcification" and want only software devices with AI. What two filters do you apply?
Narrow by SaMD (software-only devices), then narrow by AI/ML (devices with AI).
2. The results table
Scroll right in the results table. The intended use is extracted for you — no need to open the PDF. The device story gives a high-level snapshot of what the device does and how it's used. The AI Performance sub-table shows each output name, acceptance criteria, observed values, and development/test dataset descriptions — the same format Innolitics uses for regulatory strategy outputs, and the fastest high-level fingerprint of an AI device. It is AI-generated but has been very reliable in practice.
Where do you find a device's intended use without opening the PDF?
Scroll right in the search results table. The intended use column is extracted for you; no need to dig into the 510(k) summary PDF.
What does the AI Performance sub-table show, and why is it useful?
Output name, acceptance criteria, observed values, development dataset description, and test dataset description. It's the same format we use for regulatory strategy output and Fast 510(k) input, and the fastest high-level fingerprint of an AI device. AI-generated but reliable in practice.
3. Judging fuzzy relevance
Fuzzy results trail off in relevance as you scroll. Use three signals to decide how far down to go: the fuzzy badge explanations, the intended use column, and whether your target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, you're past the relevant zone. A top hit with a low score (~0.4) and a stretched explanation is a hint the closest predicates are far away — the project may be headed for De Novo. Note the fuzzy search is a pattern match: it doesn't handle negation ("not") well, and hardware devices can appear — filter by SaMD/AI ML to cut them.
How do you judge how far down fuzzy search results to go?
Use the relevancy signals: the fuzzy badge explanations, the intended use column, and whether the target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, results are trailing off in relevancy.
4. Device detail page: chat and citations
Click a device name to open its detail page: device facts on the left, a chat window on the right. Ask something like "Describe the training data". The answer carries little citation bubbles — click one to jump to the highlighted passage in the source PDF, so you can verify every AI answer against the document. There's also a Download PDF button for sharing.
How do you verify an AI chat answer on the device detail page?
Click the citation bubbles to jump to the relevant highlight in the source document.
Reading rule for every project: how many summaries do you read in full?
At least the three most relevant 510(k) or De Novo summaries, in full. After that, use targeted chat questions to confirm your memory quickly. The tool supports this professional habit — it doesn't replace it.
5. Side-by-side comparison
Select multiple rows in the results table (aim for under ~10), then open the PDF Viewer tab. Ask one question — it goes to all selected devices in parallel, each with citations. This is the fastest way to compare and contrast devices: training data, PCCP scope, how they handled adding new scanners, and so on.
What does the side-by-side PDF viewer mode do?
Select multiple devices, open the PDF viewer tab, and ask one question (e.g., "Describe the training data"). It queries all selected devices simultaneously with citations, so you can compare and contrast quickly.
6. Collections
With rows selected, go to the Collections tab and create a labeled collection (e.g., "Cobb Angle Project"). Reload that selection any time — before a client call, pull up the collection and ask questions across all of its devices at once.
How do you save a set of selected devices for later use?
Select the rows, go to the Collections tab, and create a labeled collection (e.g., "Cobb Angle Project"). You can reload the selection anytime and carry it into the PDF viewer and other tabs that support selections.
7. Product codes and the regulations tree
Click a product code in the results to jump to it in the regulations tree — identification text, sibling product codes, and devices you can open in a PDF viewer on the right. Click a regulation number to see its identification, special controls, and related product codes. You can also search by product code or regulation number at the top of the tree. Always read the special controls if any exist for your device — it broadens your search and sharpens pre-kickoff research.
What can you do from the regulations tree view?
Browse product codes and regulation numbers, read the identification text and special controls, browse sibling product codes, open device PDFs on the right, and search by product code or regulation number at the top of the tree.
8. Chart view
Click Show Chart and segment by regulation number (or product code) to see which regulations dominate your result set. Clicking a regulation takes you into the regulations tree. Great for spotting that most matches are, say, hardware laparoscopic devices — a cue to go back and filter.
How do you see which regulations dominate a search result set?
Click "Show Chart" and segment by Regulation Number. Clicking a regulation takes you to the regulations tree.
9. The predicate graph
Open the Predicates tab for a family-tree view of predicate relationships. Click a node to trace its parents and children; selections from search carry over pre-selected. Commonly predicated devices are worth reading — a lot of people predicated them for a reason. The visual lineage is also handy on client calls, e.g. to show how a predicate family evolved and justify why your predicate still holds.
In the predicate graph, why are commonly predicated devices worth reading?
A lot of people predicated them for a reason. Clicking a node traces parents and children, and selections from search carry over pre-selected.
10. Embeddings: the galaxy map
The Embeddings tab plots every matching document in a 2-D "galaxy map" where semantically similar devices cluster together. Hover or click clusters to explore, and let AI label the clusters for you. Embeddings beat product codes for grouping: two devices can carry different product codes (LLZ vs. QIH) yet do the same thing — the embedding captures the meaning of the intended use and device story. This is also exactly how retrieval-augmented generation (RAG) works under the hood, and it makes a great visual on client calls.
Try it yourself
Head to the search page and work through a few of these AI/ML fuzzy searches to build intuition: perivascular fat on CT · aortic valve calcification opportunistic screening on noncontrast CT · breast cancer prediction on digital pathology slides · autism detection · gestational age prediction · a hearing aid that can also detect a pulse · foundation model based analysis of ECG · large language models · penetration test. Watch how the relevance scores, intended use, and AI Performance tables tell you when results stop being meaningful.