DEN210005 · Luminopia, Inc. · QQU · Oct 20, 2021 · Ophthalmic
Device Facts
Record ID
DEN210005
Device Name
Luminopia One
Applicant
Luminopia, Inc.
Product Code
QQU · Ophthalmic
Decision Date
Oct 20, 2021
Decision
DENG
Submission Type
Direct
Regulation
21 CFR 886.5500
Device Class
Class 2
Attributes
Software as a Medical Device, Therapeutic, Pediatric
Indications for Use
Luminopia One is a software-only digital therapeutic designed to be used with commercially available Head-Mounted Displays (HMDs) which are compatible with the software application. Luminopia One is indicated for improvement in visual acuity in amblyopia patients, aged 4-7, associated with anisometropia and/or with mild strabismus, having received treatment instructions (frequency and duration) as prescribed by a trained eye-care professional. Luminopia One is intended for both previously treated and untreated patients; however, patients with more than 12 months of prior treatment (other than refractive correction) have not been studied. Luminopia One is intended to be used as an adjunct to full-time refractive correction, such as glasses, which should also be worn under the HMD during Luminopia One therapy. Luminopia One is intended for prescription use only, in an at-home environment.
Device Story
Luminopia One is a software-only digital therapeutic for amblyopia treatment; operates on commercially available Head-Mounted Displays (HMDs). Device utilizes dichoptic presentation—delivering different images to each eye—via therapeutic algorithms to stimulate binocular vision and improve visual acuity. Used in at-home environment by pediatric patients (ages 4-7) under prescription; requires concurrent use of full-time refractive correction (glasses). Healthcare providers prescribe therapy frequency/duration; monitor patient progress. Software-based intervention aims to improve visual function; reduces reliance on traditional patching. Safety profile includes monitoring for potential adverse events like headache, dizziness, or eye strain.
Clinical Evidence
Randomized controlled study (N=117) of children aged 4-7 with amblyopia. Treatment group (n=58) used Luminopia One + refractive correction; control group (n=59) used refractive correction alone. Primary endpoint: mean improvement in amblyopic eye BCVA at 12 weeks. Treatment group showed mean improvement of 1.8 lines vs 0.85 lines in control (p=0.0011). 61.9% of treatment group achieved ≥2 lines improvement vs 32.6% of control. Safety profile showed higher rates of mild/transient AEs (headache, eye strain) in treatment group. No clinically meaningful difference in stereoacuity observed.
Technological Characteristics
Software-only digital therapeutic; utilizes dichoptic presentation via HMDs. Requires compatibility testing for display resolution, luminance, contrast, field of view, and interpupillary distance. Operates as an adjunct to refractive correction. Software verification, validation, and hazard analysis required.
Indications for Use
Indicated for improvement in visual acuity in amblyopia patients, aged 4-7, with anisometropia and/or mild strabismus. Intended as an adjunct to full-time refractive correction. Not studied in patients with >12 months prior treatment (excluding refractive correction).
Regulatory Classification
Identification
A digital therapy device for amblyopia is a device that incorporates dichoptic presentations on visual displays through therapeutic algorithms to treat amblyopia or to improve visual acuity of patients with amblyopia. Luminopia One is a software-only digital therapeutic designed to be used with commercially available Head-Mounted Displays (HMDs) which are compatible with the software application. It is indicated for improvement in visual acuity in amblyopia patients, aged 4-7, associated with anisometropia and/or with mild strabismus, as an adjunct to full-time refractive correction.
Special Controls
In combination with the general controls of the FD&C Act, the digital therapy device for amblyopia is subject to the following special controls:
- Clinical performance testing must demonstrate that the device performs as intended (1) under anticipated conditions of use with labeled compatible visual display devices, including evaluation of all adverse events and device performance to improve measures of visual function.
- (2) Software verification, validation, and hazard analysis must be performed. Documentation must include characterizations of the technical specifications of the software.
- (3) Non-clinical performance testing must demonstrate that the device performs as intended under anticipated conditions of use. All visual displays intended for use must undergo compatibility testing to ensure adequate display resolution, luminance, contrast, field of view, image quality, appropriate optical image distance, and verify their compatibility with the software and intended user (such as appropriate interpupillary distance).
- (4) Labeling must include the following:
- (i) The minimum hardware and operating system requirements that support the software of the device:
- (ii) The models of the visual displays validated to be compatible with this device;
- The length of treatment and/or retreatment supported by clinical performance (iii) testing; and
- A summary of the clinical performance testing conducted with the device. (iv)
- Labeling comprehension testing with intended users must be performed. (૨)
Submission Summary (Full Text)
{0}------------------------------------------------
### DE NOVO CLASSIFICATION REQUEST FOR LUMINOPIA ONE
#### REGULATORY INFORMATION
FDA identifies this generic type of device as:
Digital therapy device for amblyopia. A digital therapy device for amblyopia is a device that incorporates dichoptic presentations on visual displays through therapeutic algorithms to treat amblyopia or to improve visual acuity of patients with amblyopia.
NEW REGULATION NUMBER: 21 CFR 886.5500
CLASSIFICATION: Class II
PRODUCT CODE: QQU
#### BACKGROUND
DEVICE NAME: Luminopia One
SUBMISSION NUMBER: DEN210005
DATE DE NOVO RECEIVED: March 1, 2021
#### SPONSOR INFORMATION:
Luminopia, Inc. 955 Massachusetts Ave #335 Cambridge, Massachusetts 02139
#### INDICATIONS FOR USE
Luminopia One is a software-only digital therapeutic designed to be used with commercially available Head-Mounted Displays (HMDs) which are compatible with the software application. Luminopia One is indicated for improvement in visual acuity in amblyopia patients, aged 4-7, associated with anisometropia and/or with mild strabismus, having received treatment instructions (frequency and duration) as prescribed by a trained eye-care professional. Luminopia One is intended for both previously treated and untreated patients; however, patients with more than 12 months of prior treatment (other than refractive correction) have not been studied. Luminopia One is intended to be used as an adjunct to full-time refractive correction, such as glasses, which should also be worn under the HMD during Luminopia One therapy. Luminopia One is intended for prescription use only, in an at-home environment.
{1}------------------------------------------------
## LIMITATIONS
Luminopia One is intended to be used as an adjunct to fulltime refractive correction such as glasses, which should also be worn under the Head-Mounted Display (HMD) headset during Luminopia One therapy.
Federal law restricts this digital therapeutic to sale by or on the order of an ophthalmologist or optometrist.
As outlined in the Indications for Use, Luminopia One is a prescription device for children ages 4 to 7 to improve visual acuity for certain medical conditions and should be used under the direct supervision of a trained eye-care professional. The device is indicated for use with compatible, commercially available head-mounted displays (HMDs). Currently, the Samsung Gear HMD is the only compatible HMD. For all other uses of such HMD, users should follow the user manual and instructional information for the specific HMD used with Luminopia One, including the age range specified by the HMD manufacturer.
Patients should only use HMDs that are compatible with Luminopia One, as described in the "Directions for Use" labeling. The Luminopia One device is currently authorized to be used with the following commercially available HMDs that have been validated as compatible with the software application:
- Samsung Gear HMD .
Patients with an interpupillary distance of less than 52 mm should not use the Luminopia One device. The Luminopia One device has not been studied on patients with interpupillary distances of less than 52 mm. Attempting to use the Luminopia One device on these patients may result in decreased effectiveness of treatment and increased risk of adverse symptoms.
Because the Luminopia One clinical study did not follow patients after 12 weeks of use, limitations include:
- Safety and effectiveness of Luminopia One therapy beyond 12 weeks is unknown ● and was not evaluated in the clinical study.
- The durability of benefit from the Luminopia One device after treatment cessation is unknown (i.e., unknown whether visual acuity improvement at 12 weeks will be maintained or regress over time).
- . The long-term effects of Head-Mounted Display (HMD) use in patients 4-7 years of age are unknown.
In the 12-week clinical study, use of Luminopia One did not demonstrate a clinically meaningful improvement in stereoacuity (depth perception).
Please refer to Luminopia One "Directions for Use" for a complete list of WARNINGS, PRECAUTIONS AND CONTRAINDICATIONS, as well as a description of CLINICAL STUDY OUTCOMES.
{2}------------------------------------------------
## DEVICE DESCRIPTION
Luminopia One is a Software as a Medical Device (SaMD) intended to improve visual acuity in pediatric patients with amblyopia (also known as lazy eye). The device is indicated for improvement in visual acuity at 12 weeks of use in amblyopia patients aged 4-7. The software is designed to be used with commercially available head-mounted displays (HMDs) (Figure 1) and is intended for at-home use. In this submission, the Samsung Gear HMD has been validated to be compatible with Luminopia One. The Patient should wear their refractive correction, such as glasses, under the HMD during treatment.
Image /page/2/Figure/2 description: The image shows two diagrams of a person wearing a virtual reality headset. The diagram on the left shows the person facing forward, with the headset covering their eyes. A dashed line runs down the center of the person's face. The diagram on the right shows the person in profile, with the headset covering their eyes and a dashed line indicating the eye level.
Figure 1. Luminopia One is used with compatible head-mounted displays.
Image /page/2/Figure/4 description: The image shows a screen display of movies and TV shows. The top row displays movie content thumbnails, including titles such as "Deepsea," "Sandman," and "Polar Explorer." Below the movies are TV shows, displayed as circular thumbnails with various cartoon characters. The bottom of the screen shows logos for Netflix and Molang.
The software allows patients to select videos to watch (Figure 2).
Figure 2. Selection menus for TV shows and movies
Treatment is provided through algorithms that apply modifications to the videos to encourage use of the amblyopic eve. The video presented to the fellow eye (the stronger eye) is different from the video presented to the amblyopic eve (weaker eye) (Figure 3). When a video begins in the software application, the patient will see a modified version of the original video through
{3}------------------------------------------------
each eye. This is intended to rebalance the visual input to the eyes and encourage weaker eye usage. The treatment regimen is the following: the patient watches the video 1 hour per day, 6 days per week for a total of 12 weeks.
Image /page/3/Picture/1 description: The image shows a side-by-side comparison of two video screens, labeled "WEAKER EYE" and "STRONGER EYE." Both screens display video content with a progress bar and playback controls at the bottom. The progress bar indicates that there are 23 minutes remaining in both videos. The video on the left is labeled "WEAKER EYE" and the video on the right is labeled "STRONGER EYE."
Figure 3. Left: Videos presented to the amblyopic eye (weaker eye); Right: video presented to the fellow eye (stronger eye).
Luminopia One also includes a Patient Portal. The Patient/Caregiver will also have access to an online Patient Portal where they can review the Patient's adherence and select their favorite videos to watch in the HMD. The Patient Portal enables the Caregiver to review the patient's progress and treatment plan
and curate content for the patient to watch. The Patient Portal is designed to be used by the Caregiver.
# SUMMARY OF NONCLINICAL/BENCH STUDIES
| Test | Purpose | Method | Acceptance Criteria | Results |
|------------------------------------|-----------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------|
| HMD<br>Temperature<br>measurements | To prevent thermal<br>injury and/or adverse<br>events | Human subject wore the HMD<br>with multiple temperature probes<br>placed at different locations of<br>HMD | IEC 60601-1;<br>Temperature does not<br>exceed 41°C on the<br>human contacting<br>parts of the HMD | Passed |
| Luminance<br>and its<br>uniformity | To ensure luminance is<br>sufficiently high and<br>uniform across the<br>visual display | IEC63145-20-10: Eyewear display<br>- Part 20-10: Fundamental<br>measurement methods - Optical<br>properties. Luminance<br>measurements at 9 or more<br>locations in the field of view<br>(FOV) using a uniform white<br>testing pattern to determine the<br>luminance and uniformity across<br>the FOV. | Minimum luminance<br>should not be lower<br>than 48 candela per<br>square meter (Cd/m2).<br>The percent deviation<br>from the average<br>luminance at each<br>location should not be<br>higher than 50% | Passed |
| Contrast<br>measurements | To ensure the visual<br>display has sufficient | IEC63145-20-10: Eyewear display<br>- Part 20-10: Fundamental | At least 90% at each<br>location | Passed |
# PERFORMANCE TESTING - BENCH
{4}------------------------------------------------
| | contrast to display<br>quality video and video<br>modifications<br>implemented by<br>software | measurement methods - Optical<br>properties. Contrast measurements<br>at 9 or more locations in the field<br>of view using a test pattern, such as<br>a grille pattern. Contrast can be<br>calculated using the Michelson<br>contrast equation | | |
|--------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--------|
| HMD<br>resolution | To ensure the quality of<br>the video | Calculate the horizontal and<br>vertical pixels per degree by<br>measuring horizontal and vertical<br>field of view and the number of<br>pixels in the test image. | At least 14 pixels per<br>degree | Passed |
| Crosstalk<br>testing | To ensure that light<br>from one eyepiece of<br>the HMD cannot be<br>seen by the other eye to<br>prevent interference<br>with the treatment | Measure luminance with the<br>following combinations: (1) Both<br>eyepieces have a uniform black<br>test pattern (off); (2) Eyepiece 1<br>has a uniform white test pattern<br>(on) and eyepiece 2 is off; (3)<br>Eyepiece 1 is off and eyepiece 2 is<br>on.<br>See Information Display<br>Measurements Standard 1.03<br>(IDMSv1.03) as reference. | Light entered from one<br>eyepiece to another is<br>not significantly<br>higher than<br>background levels. | Passed |
| Labeling<br>comprehension<br>testing | To ensure that the<br>Direction of Use (DFU)<br>conveys clear<br>instructions to the<br>parent/caregiver | DFU comprehension testing and<br>device use testing: (1) caregiver<br>and child pairs are tested through<br>the knowledge tasks to<br>demonstrate their understanding of<br>the DFU; (2) caregiver and child<br>pairs are tested through the<br>performance tasks to demonstrate<br>that they can use device<br>successfully. | Testing demonstrated<br>that caregivers and<br>patients understood<br>the directions of use<br>and could use the<br>device successfully.<br>There were minimal<br>use errors in the use of<br>the device. | Passed |
### SOFTWARE
Luminopia One is a Software as a Medical Device (SaMD). It was reviewed according to the FDA Guidance document, "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices," issued May 11, 2005. The software was found to have a MODERATE level of concern because a failure of the device may result in a minor injury to a patient prior to risk mitigation. FDA reviewed the software documentation provided in support of Luminopia One and found it acceptable.
Software controls have been implemented in Luminopia One to minimize overuse of the device. The user will be presented a pop-up warning when the daily use of the device exceeds the prescribed length of time. A software control will implement a lock-out at the end of entire prescribed treatment regimen.
### SUMMARY OF CLINICAL INFORMATION
{5}------------------------------------------------
A randomized controlled clinical study was conducted that evaluated 117 subjects age 4-7 years. treated for 12 weeks with Luminopia One (1 hour daily, 6 days a week, for 12 weeks) along with fulltime refractive correction, as compared to control treatment with refractive correction alone. with final assessment at the 12-week visit. Amblyopia is clinically defined as reduction of visual acuity (VA) that cannot be attributed to ocular or visual system abnormality or refractive error. The American Academy of Ophthalmology (AAO) considers amblyopia as an interocular difference of 2 lines or more or VA worse than or equal to 20/30 with best optical correction '. The Luminopia One clinical study inclusion criterion for VA met the AAO definition. Interim analysis was conducted per protocol after 75% of subjects completed the 12-week follow up visit. At that time there were 105 subjects (51 Luminopia One therapeutic group, 54 control group). The study was stopped early for success, per protocol, when 75% of subjects completed the 12-week visit, since primary effectiveness and safety endpoints were achieved at interim analysis. Final analysis included 117 subjects (58 Luminopia One therapeutic group, 59 control group), reported as descriptive outcome information in the device labeling.
The mean age of all study participants was 6.0±1.0 years (n = 117). Among them, 56.4% (66/117) were male and 43.6% (51/117) were female. The mean age for the Luminopia One treatment group was 6.2 ± 0.9 (n = 58) years. In the treatment group, 60.3% (35/58) of the subjects were male and 39.7% (23/58) were female. The mean age for the control group (refractive correction only) was 5.9 ± 1.1 (n = 59). In the control group, 52.5% (31/59) of the subjects were male and 47.5% (28/59) were female.
In terms of ethnicity, 22.4% (13/58) of the subjects in the treatment group were Hispanic or Latino and 77.6% (45/58) were not Hispanic or Latino. In the control group, 10.2% (6/59) of the subjects were Hispanic or Latino and 89.8% (53/59) were not Hispanic or Latino.
The percentages of subjects whose right eye is amblyopic are 45.6% (26/57) for the treatment group and 47.5% (28/59) for the control group. The percentages of subjects whose left eye is amblyopic are 54.4% (31/57) for the treatment group and 52.5% (31/59) for the control group.
1. Evidence of clinical benefit for Luminopia One as used in the clinical study with refractive correction:
o Primary Effectiveness Endpoint: Mean improvements from baseline in amblyopic eye's best corrected visual acuity (BCVA) after 12-week treatment show statistically significant difference between the treatment and control groups; superiority of the treatment was demonstrated and the endpoint was met:
· Interim analysis (N=105. n=84): Mean change -0.180 (SD=0.15) logMAR in the therapeutic group, -0.080 (SD=0.14) logMAR in the control group (see Table 1 below). Average difference between groups -0.10 logMAR, greater improvement in the treatment group compared to control group (p=0.0012). Mean BCVA improvement in amblyopic eye was 1.8 lines in the treatment group vs. 0.8 lines
<sup>1</sup> https://www.aao.org/disease-review/amblyopia-types-diagnosis-treatment-new-perspectiv
{6}------------------------------------------------
| Table 1: Amblyopic Eye BCVA1 - Intention-to-Treat (ITT) Population at Interim<br>Analysis | | | | | Results | |
|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------|------------------------------------------------------------|-------------------------------------------------|----------|---------------------------|-----------|
| | Treatment<br>Group<br>N=51 | Control Group<br>N=54 | Difference in<br>Change in<br>BCVA2<br>(90% CI) | P-value3 | Stage 1<br>Alpha<br>Level | Decision |
| Improvement from<br>Baseline at 12<br>Weeks (lines)4 | 1.8 ± 1.5 (41)<br>2.0 (-2.0, 6.0)<br>[1.3, 2.3] | 0.8 ± 1.4 (43)<br>1.0 (-2.0, 4.0)<br>[0.4, 1.3] | 1.0<br>(0.5, 1.5) | 0.0012 | 0.0176 | Reject H0 |
| Change from<br>Baseline at 12<br>Weeks (logMAR) | -0.18 ± 0.15 (41)<br>-0.20 (-0.60, 0.20)<br>[-0.23, -0.13] | -0.08 ± 0.14 (43)<br>-0.10 (-0.40, 0.20)<br>[-0.13, -0.04] | | | | |
| Baseline (logMAR) | 0.54 ± 0.21 (41)<br>0.50 (0.30, 1.00) | 0.50 ± 0.19 (43)<br>0.40 (0.30, 1.00) | | | | |
| 12 Weeks (logMAR) | 0.36 ± 0.23 (41)<br>0.30 (0.00, 1.10) | 0.42 ± 0.21 (43)<br>0.40 (0.00, 1.00) | | | | |
| 1Based on participants with available data at baseline and in-window 12-<br>week visits. Data presented as mean ± standard deviation (N) median (min, max). Change from baseline also includes [95% CI].<br>2Difference between groups (treatment - control) and 90% confidence interval are based on the coefficient associated<br>treatment group from an ANOVA model. Positive difference between groups represents larger improvement in the treatment group. | | | | | | |
in control group. Point estimate difference in improvement is 1.0 line (90% CI: 0.5-1.5 lines).
P value is based on a one-sided F-test for the coefficient associated with treatment group from an ANOVA model
"Original visual acuity measurements captured using inprovement from baseline corresponds to a change of -0.10 lgMAR
The bar chart below (Figure 4) shows the mean BCVA improvements in the treatment group vs. the control group after 4, 8 and 12 weeks of treatment.
Image /page/6/Figure/5 description: The image is a bar graph comparing the improvement in BCVA (Lines) between a treatment group and a control group at different follow-up visits (4, 8, and 12 weeks). The y-axis represents the improvement in BCVA, ranging from 0 to 2.5 lines. At each follow-up visit, the treatment group (green bars) shows a greater improvement in BCVA compared to the control group (blue bars), with statistically significant differences indicated by asterisks.
Figure 4. Improvement in amblyopic eye BCVA from baseline - ITT population at interim analysis at 4, 8, and 12 weeks (error bars denote ± SEM, * denotes p < 0.05)
{7}------------------------------------------------
· Final analysis (N=117, n=88): Mean change was -0.181 logMAR (SD=0.15) in the therapeutic group and -0.085 logMAR (SD=0.14) in the control group (see Table 2 below). The average difference between groups was -0.096 logMAR, larger improvement in Luminopia One group (p = 0.0011), consistent with interim analysis results. BCVA improved by 1.8 lines in the treatment group vs. 0.85 lines in the control group. Point estimate of difference between groups is 0.96 line (90% CI: 0.45-1.47 lines).
| Table 2: Amblyopic Eye BCVA1 - ITT Population at Final Analysis | | | |
|-----------------------------------------------------------------|-------------------------------------------------------------------|-------------------------------------------------------------------|----------------------------------------------|
| | Treatment Group<br>N=58 | Control Group<br>N=59 | Difference in<br>Change in BCVA2<br>(90% CI) |
| Improvement from<br>Baseline<br>at 12 Weeks (lines)4 | 1.81 ± 1.52 (42)<br>2.0 (-2.0, 6.0)<br>[1.34, 2.28] | 0.85 ± 1.35 (46)<br>1.0 (-2.0, 4.0)<br>[0.45, 1.25] | 0.96<br>(0.45, 1.47) |
| Change from Baseline<br>at 12 Weeks (logMAR) | -0.181 ± 0.152 (42)<br>-0.200 (-0.600, 0.200)<br>[-0.228, -0.134] | -0.085 ± 0.135 (46)<br>-0.100 (-0.400, 0.200)<br>[-0.125, -0.045] | |
| Baseline (logMAR) | 0.536 ± 0.212 (42)<br>0.500 (0.300, 1.000) | 0.507 ± 0.190 (46)<br>0.400 (0.300, 1.000) | |
| 12 Weeks (logMAR) | 0.355 ± 0.231 (42)<br>0.300 (0.000, 1.100) | 0.422 ± 0.202 (46)<br>0.400 (0.000, 1.000) | |
1Based on participants with available data at baseline and in-window 12-week visits. Data presented as mean ± standard deviation (N) median (min, max). Change from baseline also includes [9
2Difference between groups (treatment - control) and 90% confidence interval are based on the
coefficient associated treatment group from an ANOVA model. Positive difference between groups represents larg in the treatment group.
P-value is based on a one-sided F-test for the coefficient associated with treatment group from an ANOVA mo
*Original visual acuity measurements captured using logMAR. A 1-line improvement from baseline corresponds
*Although the results from the interim analysis constitute the statistical conclusions from the study, the results analysis are based on data from all enrolled participants
o Secondary Effectiveness Endpoint: Amblyopic eye BCVA improvement 2 or more lines from baseline after 12 weeks, 62% of Luminopia subjects (95% CI: 46-76%) vs. 33% of control subjects (95% CI: 20-48%) (see the Table 3 below). This is part of the final analysis that was pre-specified as descriptive analysis only.
| Table 3: Improvement in Amblyopic Eye BCVA ≥ 2 Lines1 – ITT Population at Final Analysis | | |
|-------------------------------------------------------------------------------------------------------------------|---------------------------------|---------------------------------|
| | Treatment Group<br>N=58 | Control Group<br>N=59 |
| Improvement ≥ 2 lines<br>from Baseline to 4 weeks | 34.0% (17/50)<br>[21.2%, 48.8%] | 24.5% (12/49)<br>[13.3%, 38.9%] |
| Improvement ≥ 2 lines<br>from Baseline to 8 weeks | 50.0% (24/48)<br>[35.2%, 64.8%] | 31.8% (14/44)<br>[18.6%, 47.6%] |
| Improvement ≥ 2 lines<br>from Baseline to 12 weeks | 61.9% (26/42)<br>[45.6%, 76.4%] | 32.6% (15/46)<br>[19.5%, 48.0%] |
| 1Based on participants with available data at baseline and in-window visits. Data presented as: % (n/N) [95% CI]. | | |
P-value from post-hoc Chi-square test.
*Although the results from the interim analysis conclusions from the study, the results from the fina analysis are based on data from all enrolled participants
{8}------------------------------------------------
o Supplemental analysis: Lines of improvement in BCVA: Luminopia One group demonstrates better visual acuity improvement outcome than control group at 4, 8 and 12 weeks (see the Table 4 below).
| Table 4: Amblyopic Eye Change in BCVA by Visit¹ - ITT Population at Final Analysis | | | | | | |
|----------------------------------------------------------------------------------------------------------------------------|------------------|------------------|------------------|------------------|------------------|---------------|
| | 4 Weeks | | 8 Weeks | | 12 Weeks | |
| Number of<br>Lines Change<br>(follow-up -<br>baseline)² | Tx | Control | Tx | Control | Tx | Control |
| 6-line<br>improvement | 0.0%<br>(0/50) | 0.0%<br>(0/49) | 0.0%<br>(0/48) | 0.0%<br>(0/44) | 2.4%<br>(1/42) | 0.0% (0/46) |
| 4-line<br>improvement | 4.0%<br>(2/50) | 0.0%<br>(0/49) | 6.3%<br>(3/48) | 6.8%<br>(3/44) | 2.4%<br>(1/42) | 2.2% (1/46) |
| 3-line<br>improvement | 10.0%<br>(5/50) | 8.2%<br>(4/49) | 12.5%<br>(6/48) | 13.6%<br>(6/44) | 31.0%<br>(13/42) | 10.9% (5/46) |
| 2-line<br>improvement | 20.0%<br>(10/50) | 16.3%<br>(8/49) | 31.3%<br>(15/48) | 11.4%<br>(5/44) | 26.2%<br>(11/42) | 19.6% (9/46) |
| 1-line<br>improvement | 32.0%<br>(16/50) | 22.4%<br>(11/49) | 29.2%<br>(14/48) | 31.8%<br>(14/44) | 23.8%<br>(10/42) | 19.6% (9/46) |
| No change | 24.0%<br>(12/50) | 32.7%<br>(16/49) | 14.6%<br>(7/48) | 15.9%<br>(7/44) | 7.1%<br>(3/42) | 34.8% (16/46) |
| 1-line decrease | 8.0%<br>(4/50) | 10.2%<br>(5/49) | 6.3%<br>(3/48) | 13.6%<br>(6/44) | 2.4%<br>(1/42) | 10.9% (5/46) |
| 2-line decrease | 2.0%<br>(1/50) | 6.1%<br>(3/49) | 0.0%<br>(0/48) | 6.8%<br>(3/44) | 4.8%<br>(2/42) | 2.2% (1/46) |
| 3-line decrease | 0.0%<br>(0/50) | 2.0%<br>(1/49) | 0.0%<br>(0/48) | 0.0%<br>(0/44) | 0.0%<br>(0/42) | 0.0% (0/46) |
| 7-line decrease | 0.0%<br>(0/50) | 2.0%<br>(1/49) | 0.0%<br>(0/48) | 0.0%<br>(0/44) | 0.0%<br>(0/42) | 0.0% (0/46) |
| ¹Based on participants with available data and in-window visits. Categorical variables presented as n/N (%) where N is the | | | | | | |
'Based on participants with available data and in-window visits. Categorical variables presented as n/N (%) where N is the
number of participants with available data.
²Original visual acuity measurements captured using logMAR. A 1-line improvement from baseline corresponds to a change
of -0.10 logMAR.
*Although the results from the interim analysis constitute the statistical conclusions from the study, the results from the final
analysis are based on data from all enrolled participants.
#### o Exploratory Analyses:
• Stereoacuity (depth perception) did not show meaningful difference between groups.
· Mean Treatment Adherence with Luminopia One device was 75.7% from baseline to 12 weeks (note: 99% adherence with refractive correction was similar between groups).
2. Evidence of clinical safety for Luminopia One as used in clinical study with refractive correction:
## Co-Primary Safety Endpoints:
{9}------------------------------------------------
o Adverse Events (AEs) demonstrate moderate probability of device-related adverse events. AE categories below demonstrate clinically meaningful higher rate in the Luminopia One group than in the control group (see Table 5 below):
· Overall AE rate: 25% of Luminopia One group (14 subjects, 25 events) vs.
13.6% of control group (all mild except one AE "worsening night terrors" severe) · Headaches: 14.3% Luminopia One group (8 subjects, 9 events) vs. 1.7% control group (1 subject, 1 event) - All intermittent and mild, no Rx treatments, no OTC medication, all resolved without sequelae.
· Eye strain: 3.6% (2 subjects, 3 events) Luminopia One group vs. 0% control group
· "Other" includes "increased frequency of night terrors*, facial redness, eyelidtwitch, dizziness, parent-reported intermittent eve turning when tired": 7.1% (4 subjects, 5 events) Luminopia One group vs. 0% control group.
[*1 subject had prior history of night terrors, parent reported increase frequency of night terrors after beginning treatment, investigator graded as severe, parent withdrew child from the study.]
| Table 5: Non-Serious Adverse Events¹ - As-Treated (AT) Population² at Final Analysis | | |
|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------|---------------------------------|
| | Treatment Group² (N=56) | Control Group² (N=59) |
| Diplopia | 0 (0.0%) [0] [0.0%, 6.4%] | 1 (1.7%) [1] [0.0%, 9.1%] |
| New heterotropia | 4 (7.1%) [4] [2.0%, 17.3%] | 4 (6.8%) [4] [1.9%, 16.5%] |
| Worsening heterotropia | 0 (0.0%) [0] [0.0%, 6.4%] | 1 (1.7%) [1] [0.0%, 9.1%] |
| Worsening BCVA | 3 (5.4%) [4] [1.1%, 14.9%] | 4 (6.8%) [4] [1.9%, 16.5%] |
| Headache | 8 (14.3%) [9] [6.4%, 26.2%] | 1 (1.7%) [1] [0.0%, 9.1%] |
| Nausea | 0 (0.0%) [0] [0.0%, 6.4%] | 0 (0.0%) [0] [0.0%, 6.1%] |
| Eye strain | 2 (3.6%) [3] [0.4%, 12.3%] | 0 (0.0%) [0] [0.0%, 6.1%] |
| Other³ | 4 (7.1%) [5] [2.0%, 17.3%] | 0 (0.0%) [0] [0.0%, 6.1%] |
| Overall | 14 (25.0%) [25]<br>[14.4%, 38.4%] | 8 (13.6%) [11]<br>[6.0%, 25.0%] |
| ¹Includes events classified with Possible, Probable, or Definite relation to study treatment. Data presented as: n (%) [m]<br>[95% CI], where n is number of participants with event and m is the<br>number of events. Participants may experience more than one AE. | | |
| ²AT is defined as subjects with > 0% adherence of device use are in the treatment arm,<br>otherwise control; there are no control subjects treated with the device. | | |
| ³Other AEs in treatment group include: Eye Twitch, Facial Redness, Increase in Frequency of Night Terrors, Dizziness,<br>Parent reported intermitted eye turning when tired | | |
o Mean change non-amblyopic (fellow) eye BCVA from baseline, Luminopia One treatment group demonstrated non-inferiority to control group:
· Interim analysis (N=105, n=84): Mean change in fellow eye BCVA was -0.03 logMAR (SD=0.08) in therapeutic group and -0.02 logMAR (SD=0.06) in control group, indicating both groups had improvement in fellow eye vision. Difference
{10}------------------------------------------------
between groups was -0.02 logMAR with upper 95% confidence limit of 0.010 and p-value <0.0001 for non-inferiority test, outcome suggests no additional risk for fellow eye vision and reverse amblyopia associated with Luminopia One.
· Final analysis (N=117, n=88): mean change in fellow eye BCVA from baseline to 12 weeks was -0.036 logMAR in therapeutic group and -0.017 in control group. The difference between groups was -0.018 logMAR with upper 95% confidence limit of 0.006 and p-value <0.0001 for non-inferiority
# LABELING
Directions for Use (DFU) labeling provides product description, Indications for Use, software (the operating system) and hardware requirements for device operation, the compatible HMD. and instructions for how to operate the device. The DFU also provides a brief description of the clinical study design including the treatment duration and a summary of the study outcomes including the adverse events. The DFU includes warnings and precautions describing limitations and risks of the device. The DFU labeling is sufficient and satisfies the requirements of 21 CFR § 801.109 for prescription devices.
# RISKS TO HEALTH
The table below identifies the risks to health that may be associated with use of a digital therapy device for amblyopia and the measures necessary to mitigate these risks.
| Identified Risks to Health | Mitigation Measures |
|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------|
| Adverse events due to device treatment (e.g.,<br>headache, new or worsening heterotropia,<br>worsened vision in either eye, eye strain, eye<br>twitching, facial redness, increased night<br>terrors, thermal injury, dizziness, seizure,<br>nausea, or double vision) | Clinical performance testing<br>Labeling |
| Ineffective treatment leading to worsening of<br>condition | Clinical performance testing<br>Software verification, validation, and hazard<br>analysis<br>Labeling |
| Therapeutic effect not sustained leading to<br>delay of treatment | Clinical performance testing<br>Labeling |
| Software malfunction leading to delay of<br>treatment | Software verification, validation, and hazard<br>analysis<br>Labeling |
| Improper use of the device including HMD or<br>other visual display leading to ineffective<br>treatment or adverse events | Labeling<br>Labeling comprehension testing |
{11}------------------------------------------------
| Performance variations among different<br>brands/models of visual displays leading to<br>ineffective treatment and/or adverse events | Clinical performance testing |
|--------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------|
| | Non-clinical performance testing |
| | Labeling |
| | Software verification, validation, and hazard<br>analysis |
## SPECIAL CONTROLS
In combination with the general controls of the FD&C Act, the digital therapy device for amblyopia is subject to the following special controls:
- Clinical performance testing must demonstrate that the device performs as intended (1) under anticipated conditions of use with labeled compatible visual display devices, including evaluation of all adverse events and device performance to improve measures of visual function.
- (2) Software verification, validation, and hazard analysis must be performed. Documentation must include characterizations of the technical specifications of the software.
- (3) Non-clinical performance testing must demonstrate that the device performs as intended under anticipated conditions of use. All visual displays intended for use must undergo compatibility testing to ensure adequate display resolution, luminance, contrast, field of view, image quality, appropriate optical image distance, and verify their compatibility with the software and intended user (such as appropriate interpupillary distance).
- (4) Labeling must include the following:
- (i) The minimum hardware and operating system requirements that support the software of the device:
- (ii) The models of the visual displays validated to be compatible with this device;
- The length of treatment and/or retreatment supported by clinical performance (iii) testing; and
- A summary of the clinical performance testing conducted with the device. (iv)
- Labeling comprehension testing with intended users must be performed. (૨)
### BENEFIT-RISK DETERMINATION
The risks of the device are based on the clinical performance testing data collected in a clinical study described above.
{12}------------------------------------------------
The clinical study has shown that the treatment with Luminopia One was associated with several adverse events with moderate probability. These adverse events include diplopia (double vision), new or worsening heterotropia (strabismus, "eye turn" or "crossed eyes"), worsened vision in in in the amblyopic eye and/or in the fellow eye, headaches, nausea, eye strain (asthenopia), and other events. These events were reversable and considered non-serious. DFU labeling notes that patients should stop using Luminopia One and contact doctor for evaluation and permission to continue treatment if they experience any of these during or after using the device.
The probable benefits of the device are also based on data collected in the clinical study as described above.
The clinical study clearly demonstrated that treatment with Luminopia One improved the visual acuity of the amblyopic eve more than the control (refractive correction alone). Significantly more subjects experienced improvement of the amblyopic eye by BCVA 2 lines or more in the treatment group than in the control group. No reduction in BCVA in the fellow eye was observed between the treatment and control group suggesting no additional risk for fellow eye vision and reverse amblyopia associated with Luminopia One. In addition, Luminopia One provides an alternative for patients who have exhausted currently available treatments.
Although it is unknown whether the benefits of treatment with Luminopia One can be retained beyond 12 weeks, the overall probable benefits of visual acuity improvement in the amblyopic eye outweigh the probable risks of non-serious adverse events associated with the use of Luminopia One.
# PATIENT PERSPECTIVES
Patient perspectives considered for Luminopia One included: Questionnaires during the clinical study provided to patients and caregivers during visits and through phone calls. The adverse events reported during the clinical study in Table 5 a demonstrated a clinically meaningful higher rate in the Luminopia One treatment group than in the control group.
# BENEFIT/RISK CONCLUSION
In conclusion, given the available information above, for the following indication statement:
Luminopia One is a software-only digital therapeutic designed to be used with commercially available Head-Mounted Displays (HMDs) which are compatible with the software application. Luminopia One is indicated for improvement in visual acuity in amblyopia patients, aged 4-7, associated with anisometropia and/or with mild strabismus, having received treatment instructions (frequency and duration) as prescribed by a trained eye-care professional. Luminopia One is intended for both previously treated and untreated patients: however, patients with more than 12 months of prior treatment (other than refractive correction) have not been studied. Luminopia One is intended to be used as an adiunct to full-time refractive correction. such as glasses, which should also be worn under
{13}------------------------------------------------
the HMD during Luminopia One therapy. Luminopia One is intended for prescription use only, in an at-home environment.
The probable benefits outweigh the probable risks for the Luminopia One. The device provides benefits, and the risks can be mitigated by the use of general controls and the identified special controls.
## CONCLUSION
The De Novo request for the Luminopia One is granted and the device is classified as follows:
Product Code: QQU Device Type: Digital therapy device for amblyopia Regulation Number: 21 CFR 886.5500 Class: II
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.