Preprints with The Lancet is part of SSRN´s First Look, a place where journals identify content of interest prior to publication. Authors have opted in at submission to The Lancet family of journals to post their preprints on Preprints with The Lancet. The usual SSRN checks and a Lancet-specific check for appropriateness and transparency have been applied. Preprints available here are not Lancet publications or necessarily under review with a Lancet journal. These preprints are early stage research papers that have not been peer-reviewed. The findings should not be used for clinical or public health decision making and should not be presented to a lay audience without highlighting that they are preliminary and have not been peer-reviewed. For more information on this collaboration, see the comments published in The Lancet about the trial period, and our decision to make this a permanent offering, or visit The Lancet´s FAQ page, and for any feedback please contact preprints@lancet.com.
Retinal Fundus Imaging as a Biomarker for Attention-Deficit/Hyperactivity Disorder: Machine Learning for Screening and Visual Attention Stratification
Background: Attention-deficit/hyperactivity disorder (ADHD), characterized by diagnostic complexity and symptom heterogeneity, is a prevalent neurodevelopmental disorder. This study explored the machine learning analysis of retinal fundus photographs as a novel, noninvasive biomarker for ADHD screening and stratification of executive function (EF) deficits.
Methods: Children and adolescents (<19 years) with ADHD (n=323) were recruited from two tertiary South Korean hospitals between April and October 2022. Retinal photographs of age- and sex-matched individuals with typical development were retrospectively collected. Individuals with major psychiatric disorders, neurological illnesses, and eye diseases affecting the retinal fundus were excluded. Retinal features were extracted using AutoMorph. Machine learning models for ADHD screening and EF subdomain prediction were developed using the comprehensive attention test. Model performance was evaluated via five-fold cross-validation with metrics including the area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity. Feature importance was assessed using the Shapely additive explanation method.
Outcomes: We analyzed 1108 fundus photographs from 648 participants (mean age 9·5 years, 77·1% boys). ADHD screening models achieved 95·5%–96·9% AUROC values, with vessel density as the most important feature. For EF function stratification, the visual and auditory subdomains showed strong (AUROC >85%) and poor performances, respectively.
Interpretation: Machine learning analysis of retinal fundus photographs demonstrated potential as a noninvasive biomarker for ADHD screening and EF deficit stratification in the visual attention domain. Furthermore, alterations in the retinal vascular structure and optic disc characteristics indicate a neurodevelopmental process affecting both cerebral and retinal structures, potentially reflecting systemic changes in ADHD. Our findings may guide the development of innovative screening tools and personalized treatment approaches. However, further research across diverse populations and age groups is necessary to validate these findings before clinical implementation.
Funding: Ministry of Science and ICT, National Information Society Agency, National Center for Mental Health, Ministry of Health and Welfare.
Declaration of Interest: All authors declare no competing interests
Ethical Approval: This study was approved by the Institutional Review Board of Severance Hospital, Yonsei University, Republic of Korea (IRB number: 4-2022-0297). Written informed consent was obtained from all participants.
Choi, Hangnyoung and Jae Seong, Hong and Kang, Hyun Goo and Park, Min-Hyeon and Ha, Sungji and Lee, Junghan and Yoon, Sangchul and Kim, Daeseong and Park, Yu Rang and Cheon, Keun-Ah, Retinal Fundus Imaging as a Biomarker for Attention-Deficit/Hyperactivity Disorder: Machine Learning for Screening and Visual Attention Stratification. Available at SSRN: https://ssrn.com/abstract=4978423 or http://dx.doi.org/10.2139/ssrn.4978423
Subscribe to this fee journal for more curated articles on this topic
FOLLOWERS
75
PAPERS
3,382
Feedback
Feedback to SSRN
If you need immediate assistance, call 877-SSRNHelp (877 777 6435) in the United States, or +1 212 448 2500 outside of the United States, 8:30AM to 6:00PM U.S. Eastern, Monday - Friday.
Download This Paper