DL Models Predicting Cycloplegic Refractive Error Based on Non-Cycloplegic Parameters in Myopic Adults

Efficacy of Deep Learning Models for Predicting Cycloplegic Refractive Error Based on Non-Cycloplegic Parameters in Adults With Myopia

This study presents a machine learning model that predicts cycloplegic refraction in adults with myopia using standard non-cycloplegic eye measurements, aiming to reduce the need for cycloplegic drops while still identifying patients who require them.

Study Overview

• Status: Recruiting
• Conditions: Refractive Errors; Accommodation; Cycloplegic Refraction
• Intervention / Treatment: Diagnostic test: Machine learning model for predicting cycloplegic refraction

Detailed Description

Myopia is a highly prevalent, irreversible refractive disorder with substantial impact on quality of life. Cycloplegic refraction is the gold standard for assessing refractive error in adults considering optical or surgical correction, but it is time-consuming, slow to recover from, and frequently associated with ocular discomfort. Non-cycloplegic refraction is therefore used routinely in clinical practice, despite known differences from cycloplegic values in a subset of adult myopes.

Critically, this discrepancy varies substantially between individuals and cannot be anticipated from non-cycloplegic measurements alone. Clinicians have no reliable way to identify, prior to dilation, which patients are likely to be overcorrected if cycloplegia is omitted, potentially leading to overcorrected prescriptions, asthenopia, and myopic progression.

Machine learning approaches that capture non-linear relationships between clinical predictors and refractive outcomes have shown promise in children, but comparable models for adults remain largely unexplored, and most rely on axial length, which is unavailable in routine optometric settings. Refractive surgery centers offer a uniquely suitable data source, as every candidate undergoes standardized paired non-cycloplegic and cycloplegic refraction with detailed anterior segment biometry during routine preoperative evaluation. This study leverages such data to develop and validate models estimating cycloplegic refractive error from non-cycloplegic parameters, providing a decision-support tool that reduces unnecessary cycloplegia while flagging patients for whom dilated refraction remains indicated.

• Study Type: Observational
• Enrollment (Estimated): 2500

Contacts and Locations

• Study Contact: Name: Jian Xiong; Phone Number: 18170906556; Email: 894040417@qq.com
• Study Contact Backup: Name: Fu Gui; Phone Number: 1387910191; Email: 564436578@qq.com

Study Locations

• China
  • Jiangxi, China
    • Recruiting
    • The Second Affiliated Hospital of Nanchang University, Nanchang, JiangXi 330000
    • Contact: Jian Xiong; Phone Number: 18170906556; Email: 894040417@qq.com
    • Contact: Fu Gui; Phone Number: 13879101919; Email: 564436578@qq.com

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

Each subject underwent a comprehensive preoperative examination, including cycloplegic and non-cycloplegic refractions, Pentacam, etc.

Description

Inclusion Criteria:

1. Age 18 to 60 years, of either sex;
2. Spherical equivalent between -0.50 diopters and -10.00 diopters, with myopia in one or both eyes, and with cylinder of 4.00 diopters or less;
3. Best-corrected visual acuity of 20/25 or better in each eye;
4. Clear cornea, no keratoconus, corneal scarring, or other pathologies; clear lens;
5. Intraocular pressure of 21 mmHg or less, with no history of glaucoma;
6. No history of ocular surgery, especially corneal refractive surgery or cataract surgery;
7. Time interval between non-cycloplegic refraction and cycloplegic refraction of 7 days or less, with complete data.

Exclusion Criteria:

1. Incomplete clinical data to support the diagnosis;
2. Ocular conditions such as subclinical keratoconus, keratoconus, or moderate-to-severe corneal haze or leukoma;
3. Allergy or contraindication to cycloplegic agents;
4. Refusal to participate in the study.

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Group with spherical equivalent change ≥0.50 diopters after cycloplegic refraction; Adult myopes with a non-cycloplegic versus cycloplegic spherical equivalent difference of ≥0.50 diopters, for whom cycloplegic refraction is clinically warranted, received routine cycloplegic refraction with tropicamide; no other intervention was given.	Diagnostic test: Machine learning model for predicting cycloplegic refraction; The machine learning model was applied to each participant's non-cycloplegic parameters to predict cycloplegic spherical equivalent.
Group with spherical equivalent change <0.50 diopters after cycloplegic refraction; Adult myopes with an absolute difference of less than 0.50 diopters between non-cycloplegic and cycloplegic spherical equivalent, for whom non-cycloplegic refraction is considered sufficient, received routine cycloplegic refraction with tropicamide; no additional intervention was applied.	Diagnostic test: Machine learning model for predicting cycloplegic refraction; The machine learning model was applied to each participant's non-cycloplegic parameters to predict cycloplegic spherical equivalent.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Accuracy of predicted cycloplegic spherical equivalent	Accuracy of the machine learning model in predicting cycloplegic spherical equivalent in the validation dataset, evaluated by mean absolute error, root mean square error, and coefficient of determination, expressed for spherical equivalent in diopters.	Day 0

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Diagnostic performance for identifying patients requiring cycloplegic refraction	Area under the receiver operating characteristic curve, sensitivity, and specificity of the model for classifying patients with an absolute difference of 0.50 diopters or more between non-cycloplegic and cycloplegic spherical equivalent in the validation dataset.	Day 0
Agreement between predicted and measured cycloplegic refraction	Agreement between predicted and measured cycloplegic spherical equivalent assessed by Bland-Altman analysis with mean bias and 95% limits of agreement, and by the intraclass correlation coefficient in the validation dataset.	Day 0

Collaborators and Investigators

• Sponsor: Second Affiliated Hospital of Nanchang University

Study record dates

Study Major Dates

• Study Start (Actual): October 3, 2023
• Primary Completion (Estimated): November 25, 2026
• Study Completion (Estimated): November 25, 2026

Study Registration Dates

• First Submitted: June 21, 2026
• First Submitted That Met QC Criteria: July 5, 2026
• First Posted (Actual): July 8, 2026

Study Record Updates

• Last Update Posted (Actual): July 9, 2026
• Last Update Submitted That Met QC Criteria: July 7, 2026
• Last Verified: July 1, 2026

More Information

Terms related to this study

• Keywords: Accommodation; Refractive errors; Cycloplegic refraction
• Additional Relevant MeSH Terms: Eye Diseases; Refractive Errors
• Other Study ID Numbers: [2026] NO.(123)

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No