OCT-PRO Model vs. Clinicians: Cataract Surgery Outcome Prediction

A Randomized Controlled Trial Comparing the Accuracy of the Postoperative Vision Prediction Model for Cataract Surgery (OCT-PRO) With Clinicians' Predictions of Surgical Outcomes

Cataract is the leading cause of blindness worldwide, yet 5-20% of patients fail to achieve satisfactory visual recovery after surgery. Current methods for predicting postoperative visual acuity lack accuracy, particularly in patients with co-morbid fundus diseases. The OCT-PRO model, developed by our team, uses artificial intelligence (AI) to integrate optical coherence tomography (OCT) images and clinical data to forecast surgical outcomes. This multi-center, randomized, single-blind trial aims to compare the predictive accuracy of OCT-PRO-assisted predictions versus standard clinician predictions. A total of 534 participants will be randomized 1:1 to either the experimental group (OCT-PRO-assisted prediction) or the control group (routine care). The primary outcome is the mean absolute error (MAE) between predicted and actual postoperative best-corrected visual acuity (BCVA). Secondary outcomes include patient satisfaction, informed decision-making scores, and clinician acceptance of the AI tool. This study will provide high-level evidence on the clinical utility of AI in optimizing cataract surgical decision-making and patient communication.

Study Overview

• Status: Not yet recruiting
• Conditions: Cataract
• Intervention / Treatment: Device: OCT-PRO prediction model; Behavioral: Routine Preoperative Counseling

Detailed Description

Cataract is the leading cause of blindness worldwide, yet 5-20% of patients fail to achieve satisfactory visual recovery after surgery. Accurate preoperative prediction remains challenging, particularly for eyes with co-morbid retinal pathologies, as current methods relying on clinician experience and traditional tests (e.g., laser interferometry) often lack reproducibility. Although AI models like OCT-PRO show promise, prospective RCT evidence comparing their accuracy against clinicians is lacking.

This multi-center, randomized, assessor-blinded trial will enroll 534 adults scheduled for cataract surgery. Participants are allocated 1:1 to either the Experimental Group or the Control Group via centralized randomization. In the Experimental Group, clinicians use the OCT-PRO model-integrating OCT images and clinical data-to obtain a predicted postoperative BCVA. Physicians may confirm or adjust this prediction, and the final value is communicated to patients during preoperative counseling. The Control Group receives standard care, where predictions are based solely on conventional clinical assessments without AI assistance. Outcome assessors will be blinded to group allocation.

The primary endpoint is the Mean Absolute Error (MAE) between predicted and actual postoperative BCVA. Secondary endpoints include patient-reported outcomes (expectations, informed choice, satisfaction), clinician acceptance of the model, and correlation analyses. Analysis will follow the Intention-to-Treat principle. This study aims to provide high-level evidence on integrating AI into clinical workflows to enhance prognostic accuracy and optimize shared decision-making in cataract surgery.

• Study Type: Interventional
• Enrollment (Estimated): 534
• Phase: Not Applicable

Participation Criteria

Eligibility Criteria

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

Description

Inclusion Criteria:

• Age ≥18 years scheduled to undergo phacoemulsification with intraocular lens (Phaco+IOL) implantation.
• Outpatient diagnosis of senile, complicated, or metabolic cataract.
• For bilateral cataracts, the eye with more advanced disease will be included.

Exclusion Criteria:

• History of amblyopia or neuro-ophthalmic disease in the operative eye.
• Poor-quality OCT images precluding clear visualization of fundus structures.
• Previous intraocular surgery in the operative eye.
• Hearing or intellectual impairment preventing adequate cooperation.

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Other
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: Single

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: OCT-PRO Assisted Prediction; Clinicians input preoperative OCT images and clinical data into the OCT-PRO model to generate a predicted postoperative BCVA. Physicians may confirm or adjust this AI prediction to determine a final value. This final prediction value is then communicated to the patient as supplementary information during routine preoperative counseling.	Device: OCT-PRO prediction model; The OCT-PRO model integrates optical coherence tomography (OCT) images and clinical data to predict postoperative best-corrected visual acuity (BCVA). In the experimental group, clinicians input preoperative data into the model, confirm or adjust the prediction, and communicate the final value to patients during preoperative counseling.
Active Comparator: Routine Clinical Prediction; Clinicians perform standard preoperative assessments based on clinical experience and examination results. Predictions of postoperative visual acuity are made solely by physician judgment without AI assistance. Patients receive routine preoperative counseling regarding surgical risks and expected outcomes.	Behavioral: Routine Preoperative Counseling; Standard preoperative communication based on clinical experience and conventional examinations without AI assistance.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Time Frame
The Mean Absolute Error (MAE) between the predicted postoperative BCVA and the actual measured BCVA at 1 month post-surgery.	Baseline, 1 month post-surgery

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Patient-reported consistency between surgical outcomes and expectations	Patient-perceived alignment between actual surgical outcomes and preoperative expectations, measured via a validated questionnaire using a 5-point Likert scale (strongly disagree to strongly agree).	Baseline, 1 month post-surgery
Patient-reported psychological impact of preoperative prognostic disclosure	Psychological response to receiving preoperative prognostic information (e.g., anxiety, reassurance), measured via a validated questionnaire using a 5-point Likert scale (strongly disagree to strongly agree).	Baseline, 1 month post-surgery
Patient-reported willingness to recommend prognostic information to others	Willingness to recommend cataract surgery prognostic information to others (e.g., family or friends), measured via a validated questionnaire using a 5-point Likert scale (strongly disagree to strongly agree).	Baseline, 1 month post-surgery
Patient-reported satisfaction with healthcare services	Patient satisfaction with overall healthcare services received during cataract surgery (e.g., communication, care quality, information clarity), measured via a validated questionnaire using a 5-point Likert scale (strongly disagree to strongly agree).	Baseline, 1 month post-surgery
Clinician-reported outcomes assessing the satisfaction of using OCT-PRO in cataract treatment decision-making	Clinician-reported satisfaction with incorporating OCT-PRO into preoperative decision-making (e.g., ease of use, confidence in prediction, communication aid), measured via a validated questionnaire using a 5-point Likert scale (strongly disagree to strongly agree).	Baseline, 1 month post-surgery
Correlation coefficients (Pearson/Spearman) between predicted and actual BCVA in both groups		From before surgery to 1 month (±1 week) post-surgery

Collaborators and Investigators

• Sponsor: Zhongshan Ophthalmic Center, Sun Yat-sen University

Study record dates

Study Major Dates

• Study Start (Estimated): July 20, 2026
• Primary Completion (Estimated): October 31, 2026
• Study Completion (Estimated): December 31, 2026

Study Registration Dates

• First Submitted: July 14, 2026
• First Submitted That Met QC Criteria: July 17, 2026
• First Posted (Actual): July 20, 2026

Study Record Updates

• Last Update Posted (Actual): July 20, 2026
• Last Update Submitted That Met QC Criteria: July 17, 2026
• Last Verified: July 1, 2026

More Information

Terms related to this study

• Keywords: Cataract; Artificial intelligence; Clinical decision support; Multimodal data fusion; Post-operative prognosis
• Additional Relevant MeSH Terms: Eye Diseases; Lens Diseases; Cataract
• Other Study ID Numbers: 2026KYPJ063

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