Smartphone App Detection for Retinoblastoma

Overseen By Carlos Rodriguez-Galindo, MD

Age: < 18

Sex: Any

Trial Phase: Academic

Sponsor: St. Jude Children's Research Hospital

Disqualifiers: Prior treatment cataracts, glaucoma, others

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Compensation: Varies

Number of Visits: 4

What You Need to Know Before You Apply

What is the purpose of this trial?

This trial explores whether a smartphone app called CRADLE (ComputeR Assisted Detector of LEukocoria) can detect leukocoria, an eye condition that may indicate serious issues like retinoblastoma, cataracts, and glaucoma, using a phone camera. Initially, the study will test the app with patients already diagnosed with leukocoria to determine the optimal usage method. Subsequently, it will evaluate the app's effectiveness in detecting leukocoria in patients referred for eye problems, comparing it to standard eye tests like the Red reflex test (Ophthalmoscope Examination). This trial suits individuals with conditions such as retinoblastoma or congenital cataracts who have not yet undergone certain treatments or those referred for eye examinations. As an unphased trial, this study offers a unique opportunity to contribute to innovative technology that could enhance early detection of serious eye conditions.

Will I have to stop taking my current medications?

The trial information does not specify whether you need to stop taking your current medications. It seems focused on using a smartphone app for detection, so it's unlikely to require changes to your medication.

What prior data suggests that this smartphone application is safe for detecting leukocoria?

Research has shown that the CRADLE app, a smartphone tool, is safe for detecting eye issues in children. Tested on over 50,000 photos, it successfully identified eye problems in 80% of children with these conditions, demonstrating its reliability and accuracy. The app is non-invasive, meaning it doesn't touch or affect the body, making it a safe choice for users.

For the red reflex test, studies indicate it is also safe and non-invasive. It helps detect serious eye problems early. While it is better at confirming eye disorders than initially spotting them, it remains useful. Both the CRADLE app and the red reflex test are designed to safely and easily check for eye problems without any known health risks. ^{1 2 3 4 5}

Why are researchers excited about this trial?

Researchers are excited about this trial because it's exploring smartphone technology to detect retinoblastoma, a type of eye cancer, using an app called CRADLE and a technique called red reflex testing. Unlike traditional methods that often rely on in-person exams with specialized equipment, this approach could make early detection more accessible and convenient for families, potentially catching the disease sooner. The CRADLE app uses a smartphone camera to identify abnormal eye reflections, which might signal a problem, offering a new, tech-savvy twist to early eye health monitoring. By harnessing widely available smartphones, this method could revolutionize how quickly and easily retinoblastoma and similar conditions are detected, providing a significant advantage in timely diagnosis and treatment.

What evidence suggests that the CRADLE app is effective for detecting leukocoria?

This trial will evaluate the effectiveness of the CRADLE app and red reflex testing in detecting eye conditions. Research has shown that the CRADLE app is promising for spotting leukocoria, a condition where the eye appears white in photos. In one study, CRADLE detected signs of leukocoria in 16 out of 18 children, suggesting it could help identify eye issues early. The app searches for "white eye" in pictures, an early sign of diseases like retinoblastoma.

Participants in this trial will undergo testing with the CRADLE app in different groups. Red reflex testing, another method under study, is well-known for identifying eye problems. It excels at confirming when an eye condition is absent but is less effective at detecting a condition when present. Both methods aim to catch eye problems early, which is crucial for treatment. ^{1 4 6 7 8}

Who Is on the Research Team?

Carlos Rodriguez-Galindo, MD

Principal Investigator

St. Jude Children's Research Hospital

Are You a Good Fit for This Trial?

This trial is for patients with retinoblastoma, congenital cataracts, or glaucoma who are visiting St. Jude Children's Research Hospital or University of Tennessee Hamilton Eye Institute. It includes new or minimally treated retinoblastoma cases and those referred for eye conditions like leukocoria.

Inclusion Criteria

I have a diagnosis of cataracts, glaucoma, or retinoblastoma and am seeing an eye specialist at St. Jude or UT.

Stratum II: Patient without prior diagnosis has been referred for ophthalmological evaluation, including leukocoria or other conditions.

I am receiving treatment to save my eye from retinoblastoma.

Exclusion Criteria

I have had treatment for cataracts or glaucoma.

I am unable or unwilling to give consent for the study.

Timeline for a Trial Participant

Screening

Participants are screened for eligibility to participate in the trial

1-2 weeks

Initial Evaluation

Participants undergo initial evaluation using the CRADLE application and ophthalmoscope to assess leukocoria

1 day

1 visit (in-person)

Follow-up Evaluation

Participants in Stratum III undergo additional CRADLE evaluations on Days 2, 3, and 4 to compare with ophthalmoscope results

4 days

3 visits (in-person)

Follow-up

Participants are monitored for safety and effectiveness after initial evaluations

3-4 weeks

What Are the Treatments Tested in This Trial?

Interventions

• CRADLE
• Red reflex testing

Trial Overview The study tests the CRADLE smartphone app's ability to detect leukocoria compared to traditional red reflex testing using an ophthalmoscope. The trial has two parts: finding the best way to use CRADLE and measuring its accuracy (sensitivity and specificity).

How Is the Trial Designed?

Group I: Stratum III: Retinoblastoma Group Experimental Treatment 2 Interventions

A separate group of participants with known retinoblastoma and who are undergoing ocular salvage treatments will be screened with red reflex testing using direct ophthalmoscopy on Day 1. They will also undergo testing with the CRADLE software application defined as the most effect in Stratum I on Day 1 then for three additional consecutive visits which typically occur every 3 to 4 weeks.

Group II: Stratum II: Leukocoria Evaluation Group Experimental Treatment 2 Interventions

A separate group of participants who are referred for evaluation of leukocoria or any other eye condition will undergo red reflex testing testing with CRADLE on Day 1.

Group III: Stratum I: Initial Evaluation Group Experimental Treatment 1 Intervention

Initially, a small group of patients diagnosed with congenital or infantile cataracts, congenital glaucoma or retinoblastoma and who meet the eligibility criteria will undergo testing with CRADLE on Day 1.

Who Is Running the Clinical Trial?

St. Jude Children's Research Hospital

Lead Sponsor

Trials

451

Recruited

5,326,000+

Published Research Related to This Trial

The implementation of the red reflex test in newborns led to the early identification of five cases of congenital cataracts, demonstrating its effectiveness in detecting serious ocular conditions shortly after birth.

Despite its importance, less than half of the neonatology departments in Israel routinely perform the red reflex test, highlighting a gap in adherence to the American Academy of Pediatrics' recommendations for early ocular assessment.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

The red reflex examination in neonates: an efficient tool for early diagnosis of congenital ocular diseases. Eventov-Friedman, S., Leiba, H., Flidel-Rimon, O., et al.[2019]

The EyeScreen smartphone application demonstrated a high sensitivity of 87% and specificity of 73% in detecting leukocoria, indicating its potential as an effective screening tool for retinoblastoma in low-income regions.

This study, involving 1,457 participants in Ethiopia, highlights the promising use of low-cost technology and machine learning to improve early diagnosis of retinoblastoma, which is crucial for better clinical outcomes.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

EyeScreen: Development and Potential of a Novel Machine Learning Application to Detect Leukocoria. Bernard, A., Xia, SZ., Saleh, S., et al.[2022]

Retinoblastoma (RB) is a common eye cancer in children, and its diagnosis can be delayed due to factors like small tumor size and missed appointments, highlighting the need for improved screening methods.

This systematic review of 10 studies suggests that mobile devices and applications could potentially enhance the early detection of RB by both healthcare providers and parents, although more research is needed to confirm their effectiveness.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Detection and Diagnosis of Retinoblastoma: Can Mobile Devices Be the Next Step Toward Early Intervention? Jabir, AR., Zaheer, HA., Zaheer, MA., et al.[2022]

The CRADLE smartphone application effectively detects leukocoria in photographs, identifying 80% of children with serious eye disorders up to 1.3 years before clinical diagnosis, based on an analysis of 52,982 photographs.

This tool provides a valuable supplement to traditional screening methods, allowing parents to help monitor their children's eye health through casual photography.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Autonomous early detection of eye disease in childhood photographs. Munson, MC., Plewman, DL., Baumer, KM., et al.[2020]

The red-reflex test is significantly more effective at detecting simulated retinoblastoma lesions when using oblique viewing and pupil dilation, with detection rates improving from less than 48% to 96% for larger lesions.

Detection rates for peripheral lesions were notably low with straight-on viewing (as low as 16%), but improved to 70% or higher with oblique viewing, highlighting the importance of viewing technique in identifying potential retinoblastoma.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

The detection of simulated retinoblastoma by using red-reflex testing. Li, J., Coats, DK., Fung, D., et al.[2010]

The modified MDEyeCare app successfully detected leukocoria in early stages of retinoblastoma (RB) in 50% of cases in Group B and 83% in Group C, indicating its potential for early diagnosis by non-ophthalmologists.

In late-stage RB cases, the app achieved a 100% detection rate, suggesting that the improved smartphone methodology could lead to better treatment outcomes and vision preservation for affected children.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Smartphone-based application improves the detection of retinoblastoma. Khedekar, A., Devarajan, B., Ramasamy, K., et al.[2021]

Diabetic retinopathy (DR) is a major cause of vision impairment in adults, and early detection is crucial for improving patient outcomes; traditional detection methods can be costly and require specialized professionals.

This scoping review will evaluate the accuracy of smartphone-based ophthalmoscopy for detecting DR, potentially offering a more accessible and affordable alternative for patients, with plans to analyze data from studies published since 2000.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Use of smartphones for detecting diabetic retinopathy: a protocol for a scoping review of diagnostic test accuracy studies. Tan, CH., Quah, WH., Tan, CSH., et al.[2020]

Survival rates for retinoblastoma in South Africa are only 50% due to late diagnosis, highlighting the urgent need for effective screening methods.

Implementing mandatory red reflex tests at neonatal discharge and during routine health visits could significantly improve early detection of retinoblastoma, potentially reducing mortality rates.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Towards early detection of retinoblastoma. Freeman, N., Meyer, D.[2019]

Citations

1. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/PMC6774731/

Autonomous early detection of eye disease in childhood ... Effect of early leukocoria detection on outcomes of children with retinoblastoma. Would CRADLE have helped test children if it had been used ...

2. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/PMC9639857/

Detection and Diagnosis of Retinoblastoma: Can Mobile ... The results showed that CRADLE found evidence of leukocoria in 16 of the 18 children from the test group and on average this would have been ...

3. focus.masseyeandear.org focus.masseyeandear.org/a-fathers-mission-leads-to-app-to-detect-eye-disease-in-baby-pictures/

A Father's Mission Leads to App to Detect Eye Disease in ... The app aims to help parents detect early signs of eye disease by searching their children's photographs for traces of leukocoria, also known as white eye.

4. ophthalmologyscience.org ophthalmologyscience.org/article/S2666-9145(22)00047-1/fulltext

EyeScreen Few data have been published regarding the reliability of identifying leukocoria with smartphone cameras, and no data are available regarding ...

5. sciencedirect.com sciencedirect.com/science/article/pii/S2162098923001226

Review Article Screening for Retinoblastoma: A Systematic ... The aim of this study was to review the literature on various screening programs, devices, and applications described for the early detection of ...

6. optometrytimes.com optometrytimes.com/view/new-app-detects-pediatric-leukocoria

New app detects pediatric leukocoria Results of the CRADLE app were recently published in Science Advances . 3 The sensitivity of CRADLE at detecting pathologic leukocoria in facial ...

7. centerwatch.com centerwatch.com/clinical-trials/listings/NCT03016156/determination-of-the-sensitivity-and-specificity-of-a-smartphone-application-to-detect-retinoblastoma

Determination of the Sensitivity and Specificity ... This study seeks to determine whether a smartphone application called CRADLE (ComputeR Assisted Detection of LEukocoria) has the potential ...

8. ophthalmology360.com ophthalmology360.com/pediatrics/cradle-smartphone-app-helps-detect-eye-disease-children/

CRADLE Smartphone App Helps Detect Eye Disease in ... CRADLE was able to detect leukocoria in 80% of children with diagnosed disorders; traditional screenings detect leukocoria in only 8% of cases. Its sensitivity ...