Actively Recruiting
Diagnostic Efficacy of Convolutional Neural Network Based Algorithm in Predicting Intraoperative Complications and Postoperative Outcomes in Small Incision Lenticule Extraction
Led by Second Affiliated Hospital of Nanchang University · Updated on 2026-04-24
1250
Participants Needed
1
Research Sites
N/A
Total Duration
On this page
Sponsors
S
Second Affiliated Hospital of Nanchang University
Lead Sponsor
H
Hangzhou Huaxia Eye Hospital
Collaborating Sponsor
AI-Summary
What this Trial Is About
Researchers are evaluating the ability of a deep convolutional neural network (CNN) to predict complications and outcomes related to Small Incision Lenticule Extraction (SMILE) surgery, which is used to correct refractive errors in the eye. This observational, multi-center study aims to assess the diagnostic accuracy of the AI algorithm in identifying intraoperative complications such as opaque bubble layer (OBL), negative pressure detachment, and black spots, which can affect surgery and recovery. The study is sponsored by the Second Affiliated Hospital of Nanchang University and focuses on improving prediction accuracy compared to human physicians. During the study, eyes that have undergone SMILE surgeries performed by experienced surgeons will be assessed using the AI diagnostic algorithm. The algorithm's performance will be evaluated by measuring accuracy, area under the curve (AUC), sensitivity, and specificity in predicting complications such as OBL area and progressive suction loss on the day of surgery, as well as postoperative outcomes including effective optical zone, refractive error, and central corneal thickness at day 7 and later timepoints. No treatment is administered as this is an observational study. Participants will be monitored through imaging and clinical data collected around the time of surgery and during follow-up visits up to day 90. Researchers will analyze the algorithm's ability to predict surgical complications and postoperative results to determine its real-world utility. The primary outcomes include the AUROC values for various predictions on days 0 and 7, while secondary outcomes focus on sensitivity and specificity at multiple time points. The study includes adults aged 18 to 45 years with stable myopia and excludes those with other eye conditions or systemic diseases. Total participation length varies by individual.
CONDITIONS
Brief Title
Diagnostic Efficacy of CNN in Predicting Intraoperative Complications and Postoperative Outcomes in SMILE
Who Can Participate
Eligibility Criteria
You may qualify if you...
- Age 18 years or older
- Spherical equivalent refractive error of an eye 0.50 D or less when ocular accommodation is relaxed
- Spherical equivalent (SE) of -10.0D or more
- Corrected distance visual acuity (CDVA) of 16/20 or better
- Stable myopia for at least 2 years
- No contact lens use for at least 2 weeks before participation
You will not qualify if you...
- Presence or history of eye conditions other than myopia and astigmatism, such as keratoconus or external eye injury
- History of eye surgery
- Presence or history of systemic diseases
AI-Screening
AI-Powered Screening
Complete this quick 3-step screening to check your eligibility
Your Study Journey
Duration - 2 to 4 weeks
Participants are screened for eligibility to participate in the trial.
1 visit (in-person)
Duration - Day 0
Participants undergo SMILE surgeries and the AI diagnostic algorithm assesses intraoperative complications based on surgical scan images.
1 visit (in-person)
Duration - Up to 90 days
Participants are monitored postoperatively to evaluate outcomes such as effective optical zone, refractive error, and corneal thickness.
Visits on Day 7, Day 30, and Day 90
Trial Site Locations
Total: 1 location
1
The Second Affiliated Hospital of Nanchang University
Nanchang, Jiangxi, China, 330000
Actively Recruiting
Research Team
J
Jian Xiong, docter
F
Fu Gui, docter
How is the study designed?
Study Type
OBSERVATIONAL
Masking
N/A
Allocation
N/A
Model
N/A
Primary Purpose
N/A
Number of Arms
1
Similar Trials
Frequently Asked Questions
Have more questions? Get in touch with our team for quick support
Not the Right Trial for You?
Explore thousands of other clinical trials that might be a better match.
Sign up to get personalized trial recommendations delivered to your inbox.
Already have an account? Log in here