Dry Eye Screening and Referral System

The Development of Artificial Intelligence Dry Eye Screening and Referral System

Status

UNKNOWN

Phases

Unknown

Study type

Observational

Source

ClinicalTrials.gov

Registry ID

NCT04413370

Enrollment

518

Registered

2020-06-02

Start date

2020-01-06

Completion date

2022-08-01

Last updated

2022-04-25

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Dry Eye

Brief summary

Dry eye is one of the most common ocular surface diseases. Its pathogenic factors are related to multiple etiology. Because of the complexity of the pathogenesis of dry eye, the diversity of related examinations, and the inconsistency of symptoms and signs of dry eye patients, the diagnosis of dry eye has higher requirements on the professional technology and examination equipment of ophthalmologists. The purpose of this study is to establish a case-control cohort of dry eye patients. Multimodal data will be collected from participants, including medical history information, ocular surface disease index scale (OSDI), anterior segment photography, and treatment outcome of dry eye patients. The correlation between the characteristics of anterior segment images and dry eye diagnosis will be explored by artificial intelligence algorithms. The purpose of this study was to develop an artificial intelligence dry eye screening and referral system.

Interventions

DIAGNOSTIC_TESTDry eye diagnostic test

The artificial intelligent dry eye screening platform

Study design

Observational model

CASE_CONTROL

Time perspective

PROSPECTIVE

Eligibility

Sex/Gender

ALL

Age

18 Years to No maximum

Healthy volunteers

Yes

Inclusion criteria

1. Subjects whose age are greater than or equal to 18 years old; 2. Subjects who can cooperate with the inspection; 3. Subjects who agree to participate in the study and sign the consent form.

Exclusion criteria

1. Subjects who cannot do the inspection. 2. Subjects who suffer from diseases that compromise the inspection.

Design outcomes

Primary

Measure	Time frame	Description
Area under the curve (severe)	up to 1 month	AUC values for predicting whether subject need to be referral or not.

Secondary

Measure	Time frame	Description
Area under the curve (each group)	up to 1 month	AUC values for predicting whether subject can be accurately grouped into each of the four groups.
Accuracy, true positive rate, and true negative rate	up to 1 month	The performance of this artificial platform.

Countries

China

Outcome results

None listed

Source: ClinicalTrials.gov · Data processed: Feb 4, 2026