Journal article
Artificial intelligence-quantified schisis volume as a structural endpoint for gene therapy clinical trials in X-linked retinoschisis
Acta ophthalmologica (Oxford, England), Vol.103(6), pp.715-724
09/2025
DOI: 10.1111/aos.17485
PMCID: PMC12340173
PMID: 40156473
Abstract
To use artificial intelligence (AI) for quantifying schisis volume (ASV) in X-linked retinoschisis (XLRS) for use as a structural endpoint in gene therapy clinical trials.
We used data from Singapore, the United Kingdom, the Netherlands, and the United States. The AI model was developed on 250 optical coherence tomography (OCT) slices, with human annotation of schisis cavities (Dataset 1). ASV was quantified on Dataset 2 - 16 OCT scans from 8 eyes with XLRS at two time points, and Dataset 4 - 62 OCT scans from 31 eyes at two time points before and after carbonic anhydrase inhibitor (CAI) treatment. A clinical trial was simulated comparing CAI treatment against control. Changes in ASV, central subfield thickness (CST) and central foveal thickness (CFT) were compared. Effect size (Cohen's d) of the three structural endpoints was determined and used in sample size calculations for a future XLRS gene therapy clinical trial, at a 0.05 significance level and 80% power.
In the simulated clinical trial, all structural metrics showed greater reductions with intervention than with control, but only change in ASV reached statistical significance (p = 0.004). Cohen's d for ASV, CST and CFT were 0.972, 0.685 and 0.521, respectively. For the future gene therapy clinical trial, sample sizes required in each arm for ASV, CST and CFT were 18, 35 and 59 participants, respectively.
ASV measurements can track changes in schisis volume in response to treatment. As an endpoint, ASV has a greater statistical effect size than CST/CFT, which reduces sample size requirements for future XLRS gene therapy clinical trials.
Details
- Title: Subtitle
- Artificial intelligence-quantified schisis volume as a structural endpoint for gene therapy clinical trials in X-linked retinoschisis
- Creators
- Tien-En Tan - University of OxfordPeilun Dai - Institute of High Performance ComputingJonathan Hensman - Department of Ophthalmology, Amsterdam University Medical Center, Amsterdam, The NetherlandsPeter Kiraly - University of OxfordBeau J Fenner - University of IowaYong Liu - Institute of High Performance ComputingRick S M Goh - Institute of High Performance ComputingIan C Han - University of IowaDaniel S W Ting - Duke-NUS Medical SchoolCamiel J F Boon - Leiden University Medical CenterM Dominik Fischer - Centre for Ophthalmology, University Hospital Tuebingen, Tuebingen, Germany
- Resource Type
- Journal article
- Publication Details
- Acta ophthalmologica (Oxford, England), Vol.103(6), pp.715-724
- DOI
- 10.1111/aos.17485
- PMID
- 40156473
- PMCID
- PMC12340173
- NLM abbreviation
- Acta Ophthalmol
- ISSN
- 1755-3768
- eISSN
- 1755-3768
- Publisher
- WILEY
- Grant note
- 05/FY2020/EX/15-A58 / Duke-NUS Medical School A20H4g2141 / Agency for Science, Technology and Research H20C6a0032 / Agency for Science, Technology and Research 05/FY2022/EX/66-A128 / Duke-NUS Medical School MOH001014-00 / National Medical Research Council Duke-NUS/RSF/2021/0018 / Duke-NUS Medical School MOH-000655-00 / National Medical Research Council
- Language
- English
- Electronic publication date
- 03/29/2025
- Date published
- 09/2025
- Academic Unit
- Ophthalmology and Visual Sciences
- Record Identifier
- 9984804805802771
Metrics
7 Record Views