Cookie Preferences
By clicking, you agree to store cookies on your device to enhance navigation, analyze usage, and support marketing. More Info
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
June 17, 2026
For centuries, we’ve called the eyes the "windows to the soul," but for modern neurologists, they are quite literally a window into the brain. The retina and the central nervous system share the same embryonic origins, developing from the same neural tissue in the womb. Because of this deep biological connection, the back of your eye acts as a non-invasive map of your brain's health, displaying a complex web of nerves and blood vessels that can (theoretically!) mirror certain neurodevelopmental conditions.
Recently, a buzz rippled through the mental health community when a study published in partnership with Seoul National University Bundang Hospital claimed a massive breakthrough. Researchers developed an Artificial Intelligence (AI) model that could screen children for Attention-Deficit/Hyperactivity Disorder (ADHD) using nothing more than a simple retinal photograph. The study, which prospectively recruited children from Severance Hospital and Eunpyeong St. Mary’s Hospital, produced results that were staggering: the AI reportedly achieved an accuracy rate of 96.9%!
In the world of medical testing, scientists use a metric called AUROC (Area Under the Receiver Operating Characteristic) to measure how well a test works.
An AUROC of 96.9% is a near-perfect score, suggesting a tool is ready for immediate, real-world deployment. While headlines promised a revolution in mental health screening, a deeper look into this research and the study’s design has exposed that this 96.9% AUROC was more likely evidence of a flawed methodology rather than a biological reality.
To build their screening tool, researchers analyzed over 1,100 retinal images using a digital pipeline called AutoMorph and a machine-learning model known as XGBoost. The AI was trained to hunt for physical signals of the "Dopamine Connection." Dopamine is the primary neurotransmitter involved in ADHD, but it is also essential to the eye. It regulates synaptic formation, retinal blood flow, and vascular endothelial regulation. Because dopamine dysregulation influences how blood vessels grow and remodel, the study hypothesized that an ADHD brain would leave a unique "fingerprint" on the retinal vasculature, resulting in denser, thicker vessel structures.
On paper, the logic was sound: use AI to spot the subtle vascular remodeling caused by dopaminergic shifts. But a closer look at the investigation revealed that the AI wasn't just spotting ADHD; it was over-indexing on technical noise.
The most significant "smoking gun" flagged by critics is a massive temporal mismatch. In other words, there was a severe disparity in the timeframes and conditions under which the retinal images for the two comparison groups were collected. For an AI to learn a biological condition, it must compare groups under identical technical conditions. Instead, this study created a time-traveling dataset:
A scientific study is only as reliable as its control group. The control in any experiment acts as a baseline against which the study group is compared. In this case, the control group should be composed of children without any neurodevelopmental disorders, or of “typically developing” children.
In this study, the control group wasn't composed of healthy children from the community. Instead, they were patients visiting a tertiary ophthalmology clinic. Children visiting a specialist eye hospital are rarely "typical." They are there because they have symptomatic eye issues. This introduced a massive selection bias involving three major confounders:
When training AI, you must never allow the "test questions" to leak into the "study material." The researchers, however, committed a fundamental violation of machine learning hygiene known as Eye-to-Eye Data Leakage. The study split the data by the eye rather than by the participant.
Human eyes are highly correlated; the left eye is a near-mirror of the right. If a child's left eye was used for training and their right eye was used for testing, the AI was effectively "cheating." Instead of learning the general traits of ADHD, the model was potentially memorizing individuals. This error artificially balloons accuracy metrics.
The true test of medical AI is diagnostic specificity, or differential diagnosis. This refers to the ability to tell one condition apart from another. While the model claimed 96.9% accuracy against a flawed control group, its performance collapsed when faced with real-world complexity.
When the researchers asked the AI to differentiate between ADHD and Autism Spectrum Disorder (ASD), the accuracy plummeted to a poor 63% AUROC. In real-world clinical settings, an accuracy of 63% is dangerously close to a 50% coin flip. Since ADHD frequently co-occurs with ASD, anxiety, or intellectual disabilities, an AI that cannot handle these "clinical differentials" is functionally useless in a doctor's office. The failure at this stage proves the model was likely detecting technical quirks of the dataset rather than a unique biological marker for ADHD.
To move from the lab to the clinic, we must establish a foundation built on rigor rather than high-speed data scraping. Moving forward, we must demand these 3 Pillars of Trusted Medical AI :
The dream of a quick eye scan to diagnose ADHD is not dead, but it must be rescued from "fast science" shortcuts and buzzy headlines.
Choi H, Hong J, Kang HG, Park MH, Ha S, Lee J, Yoon S, Kim D, Park YR, Cheon KA. Retinal fundus imaging as biomarker for ADHD using machine learning for screening and visual attention stratification. NPJ Digit Med. 2025 Mar 17;8(1):164. doi: 10.1038/s41746-025-01547-9. PMID: 40097590; PMCID: PMC11914053.
.png)
The Neuroeconomic Perspective
Neuroeconomics combines neuroscience, psychology, and economics to understand how people make decisions. Neuroeconomic studies suggest that brain regions responsible for evaluating risk and reward, including the prefrontal cortex and dopamine pathways, function differently in individuals with ADHD. These insights are crucial for developing more tailored interventions. For example, understanding how ADHD affects reward processing might inform strategies that help individuals resist impulsive choices or increase motivation for delayed rewards.
Understanding Decision-Making in ADHD
We know that decision-making is a sophisticated process involving various cognitive procedures. It’s not just about choosing between options but also about how to weigh risks, rewards, and potential future outcomes; Attention, motivation, and cognitive control are core to this process. For individuals with ADHD, however, this neural framework is affected by impairments in attention and impulse control, often resulting in “delay discounting”—the tendency to prefer smaller, immediate rewards over larger, delayed ones.
This propensity for impulsive decisions is more than a personal challenge; it has broader societal and economic implications. Previous studies have shown that these tendencies in ADHD can lead to issues in academics, work, finances, and personal relationships, emphasizing the need for targeted support and interventions.
Implications and Future Directions
This review highlights a need for continued research to bridge the gaps in understanding how ADHD-specific cognitive deficits influence decision-making. Viewing ADHD through a neuroeconomic lens clarifies how cognitive and neural differences affect decision-making, often leading to impulsive choices with economic and social impacts. This perspective opens doors to more effective interventions, improving decision-making for individuals with ADHD. Future policies informed by this approach could enhance support and reduce associated societal costs.
Typically, clinicians rely on both subjective and objective observations, patient interviews and questionnaires, as well as reports from family and (in the case of children) parents and teachers, in order to diagnose ADHD.
A group of researchers are aiming to find a diagnostic test that is purely objective and utilizes recent technological advancements. The method they developed involves analyzing videos of children in outpatient settings, focusing on their movements. The study included 96 children, half of whom had ADHD and half who did not.
This new method could potentially provide a more objective way to diagnose ADHD, reducing the reliance on subjective observations and reports. It can help doctors make more accurate diagnoses, ensuring that those who need help get it and that those who don't aren't misdiagnosed.
Background:
Our understanding of Attention-deficit/hyperactivity disorder (ADHD) has grown and evolved considerably since it first appeared in the DSM-II as “Hyperkinetic Reaction of Childhood.” This study aimed to find the disorder’s placement within the modern psychopathology classification systems like the Hierarchical Taxonomy Of Psychopathology (HiTOP).
The HiTOP model aims to address limitations of traditional classification systems for mental illness, such as the DSM-5 and ICD-10, by organizing psychopathology according to evidence from research on observable patterns of mental health problems.. Is ADHD best categorized under externalizing conditions, neurodevelopmental disorders, or something else entirely? A recent study by Zheyue Peng, Kasey Stanton, Beatriz Dominguez-Alvarez, and Ashley L. Watts takes a closer look at this question using a symptom-focused approach.
The Study:
Traditionally, ADHD has been associated with externalizing behaviors, such as impulsivity and hyperactivity, or with neurodevelopmental traits, like cognitive delays. However, this study challenges the idea of placing ADHD into a single category. Instead, it maps ADHD symptoms across three major psychopathology spectra: externalizing, neurodevelopmental, and internalizing.
The findings reveal that ADHD symptoms don’t fit neatly into one box. For example, symptoms like impulsivity, poor school performance, and low perseverance were strongly associated with externalizing behaviors. On the other hand, cognitive disengagement (e.g., daydreaming, blank staring) and immaturity were closely linked to neurodevelopmental challenges. Interestingly, cognitive disengagement also showed ties to internalizing symptoms, such as anxiety or depression.
This research underscores the complexity of ADHD. Rather than treating ADHD as a single, unitary construct, the study advocates for a symptom-based approach to better understand and treat individuals. By acknowledging that ADHD symptoms relate to multiple psychopathology spectra, clinicians and researchers can move toward more nuanced classification systems and targeted interventions.
Conclusion:
Ultimately, this study highlights the need for modern systems to move beyond rigid categories and adopt a more flexible, symptom-focused framework for understanding ADHD’s place in psychopathology.
.png)
The Background:
Women with polycystic ovary syndrome (PCOS) themselves show higher rates of ADHD. Because ADHD is partly heritable (meaning genes contribute to the condition), some of the increased ADHD seen in children of mothers with PCOS could come from shared genetic factors. In other words, a mother’s and her child’s increased risk might sometimes reflect common genes rather than an effect of the pregnancy itself.
Beyond genetics, growing evidence points to maternal metabolic problems during pregnancy as another important risk factor for neurodevelopmental outcomes. PCOS is one of these conditions and is considered both potentially modifiable (treatable or manageable) and biologically plausible as a contributor to risk. PCOS affects an estimated 5–10% of women of reproductive age worldwide and is characterized by signs such as hyperandrogenism (higher-than-normal levels of “male” hormones), insulin resistance (poorer ability to use the hormone insulin, which can affect blood sugar and metabolism), and chronic low-grade inflammation.
However, studies to date have not all reached the same conclusions. Some research suggests the association between maternal PCOS and offspring ADHD is stronger for girls, while other studies did not analyze results by child sex. Methodological differences make it harder to draw clear conclusions.
The Study:
It’s important to note that the studies included in this meta-analysis were observational (cohort studies and case-control studies). Observational studies can identify associations (that two things occur together) but cannot prove that one causes the other. A cohort study follows people over time, and a case-control study compares people with a condition to similar people without it.
The pooled results came from six studies that together included almost 1.4 million mother–child pairs and that adjusted for confounders (other factors that might influence the result, such as maternal age or socioeconomic status). After statistical adjustment, children of mothers with PCOS had about 40% greater odds of ADHD than children of mothers without PCOS. The analysis reported no evidence of publication bias (no clear sign that only positive studies were published) and zero heterogeneity (the results were consistent across the studies).
There was no meaningful difference in results between cohort and case-control studies, and the meta-analysis did not find a significant difference in the association when comparing male and female offspring.
The Take-Away:
The research team concluded that this large-scale synthesis found an association between maternal PCOS and higher odds of ADHD and other neuropsychiatric conditions in children. They suggested that children born to mothers with PCOS may benefit from developmental monitoring to identify and address problems early, while emphasizing that causal relationships have not been established. They called for further studies to confirm these findings and to investigate the biological and environmental mechanisms that might explain the association. Indeed, because women with PCOS show higher rates of ADHD than other women, we need genetically informed research designs to see if the reported association is confounded.
The Background:
Food insecurity is a widespread public‑health problem. Food insecurity refers to limited or uncertain access to enough safe, nutritious food. This term is used to describe households that sometimes or often can’t afford enough food or can only buy cheaper, less‑healthy options.
In the United States, almost eleven million children and teens (14%) lived in food‑insecure households in 2019. By 2023, the share of households with food‑insecure children and adolescents was estimated to have risen to about 18%.
Food insecurity is linked to worse physical health in children, including conditions like anemia (low red‑blood‑cell count), asthma, and delays in physical or mental development. It is also associated with problems in thinking and conduct (for example, aggressive behavior, anxiety, depression, and trouble concentrating or sitting still).
Those thinking and behavior problems can look a lot like ADHD (persistent patterns of inattention, hyperactivity, and impulsivity. This can make it hard for clinicians to tell whether symptoms come from ADHD itself, from the stress of poverty and food insecurity, or a mix of both. That overlap can complicate diagnosis and sometimes lead to misdiagnosis.
Smaller recent studies have looked at mental‑health links and found higher odds of ADHD and other mental‑health conditions among food‑insecure children aged 5–11 years. In one set of findings, moderate food insecurity was associated with 50% greater odds of an ADHD diagnosis and severe food insecurity with about 67% greater odds relative to food‑secure children.
The Study:
Because many past studies looked at single risk factors or only measured symptom severity, fewer investigations have focused specifically on household food insecurity as it relates to actual ADHD diagnoses and how that might matter for care. To address that gap, researchers used multiple years (2016–2022) of data from the U.S. National Survey of Children’s Health (NSCH). This survey is designed to be nationally representative and asks parents about their child’s health, including whether a doctor or other clinician has diagnosed ADHD.
The study included 232,571 children and adolescents (ages 3–17) and used statistical methods to adjust for other factors that could affect ADHD risk. Those factors included the child’s sex and race/ethnicity; the mother’s age; family income expressed as a percentage of the federal poverty level (a government measure used to classify income groups); the highest level of parent education; adverse childhood experiences (such as exposure to abuse, household substance use, or parental separation); birthweight (for example, low birthweight); and not getting enough sleep. Adjusting for these variables helps isolate the association between food insecurity and ADHD, though it cannot prove cause and effect.
The Results:
In this large, nationally representative sample, the researchers found a clear dose–response relationship: as the level of household food insecurity increased, so did the odds of a child having a clinician‑diagnosed ADHD (as reported by parents). In other words, greater food insecurity was linked to a higher likelihood of ADHD.
Compared with children in households that “could always afford to eat good, nutritious meals” (the reference group), the study found the following increases in odds of ADHD: children in households that “could always afford enough to eat but not always the kinds of food we should eat” had about 30% greater odds; children in households that sometimes “could not afford enough to eat” had about 55% greater odds; and children in households that often “could not afford enough to eat” had about 80% greater odds. (Saying “30% greater odds,” etc., means the odds were 1.30, 1.55, and 1.80 times those of the reference group, respectively — this describes a relative increase, not the absolute percentage of children with ADHD.)
The Take-Away:
The authors conclude that household food insecurity was associated with higher odds of parent‑reported clinician‑diagnosed ADHD in a dose‑response pattern. They suggest that reducing food insecurity (for example, ,by improving access to nutritious food and combining nutritional supports with mental‑health care) may help lower ADHD risk or reduce symptoms in some children. Reducing food insecurity should be a priority for society, but it is premature to conclude it will reduce the risk for ADHD. We know that parents with ADHD are more likely to lose their jobs and have lower incomes compared to parents with ADHD. That might create food insecurity for their children who we know are at high risk for ADHD from genetic studies.
The Background:
Many studies have tried to determine whether exercise improves executive function in children and adolescents with ADHD, but their conclusions have not always agreed. To bring the evidence together more clearly, the research team re-analyzed the available randomized controlled trials using a statistical approach designed to handle the kinds of data common in this field.
Executive functions are skills that help us control attention and behavior. The three core components are inhibitory control (the ability to stop or override impulses), working memory (holding and manipulating information in mind), and cognitive flexibility (switching between tasks or perspectives). Because a single study often reports multiple tests that tap these different skills, one study can contribute several related results (called effect sizes). Traditional meta-analysis typically treats each effect size as independent; when they are actually correlated, that can bias the combined estimate or force reviewers to discard useful data.
To avoid those problems, the team used a three-level meta-analysis. In this model, variance in the data is separated into three sources:
(1) sampling variance: the random error in each measured effect
(2) within-study variance: differences between multiple effect sizes reported in the same study
(3) between-study variance: differences in effects from one study to another
Accounting for all three levels makes it possible to include every eligible effect size from each study, which preserves information and statistical power and reduces the risk that correlations among effect sizes will overstate results.
The Study:
The review focused on long-term exercise interventions and also tested whether certain factors might change (or moderate) the effects. These potential moderators included participant age, which executive-function subcomponent was measured, the type of exercise, how long each session lasted, the total length of the intervention, and how often sessions occurred.
To be included, studies had to be randomized controlled trials (RCTs) of children or adolescents aged 6–18 diagnosed with ADHD. RCTs randomly assign participants to an intervention or a comparison group and are considered a strong design for testing cause-and-effect. The exercise programs had to be structured and last at least six weeks. Comparison groups varied by study and could include usual care, medication, sedentary activities, health education, waiting lists, or everyday life without the specific exercise program. Fifteen studies including 658 participants met these criteria.
The Results:
The three-level meta-analysis showed that long-term exercise interventions were associated with moderate-to-strong improvements in overall executive function. When statistical outliers were removed, the result remained positive: 13 RCTs with 598 participants showed moderate improvements. In plain terms, this suggests improvements that are noticeable and meaningful on average, not just tiny changes that are unlikely to matter in daily life.
Those moderate gains appeared across all three executive-function domains (inhibitory control, working memory, and cognitive flexibility, meaning the benefits were not limited to a single cognitive skill. The authors also examined exercise type:
“Open-skill” activities, which require reacting to changing situations (for example, many team sports, martial arts sparring, or racket sports), produced moderate-to-large improvements.
“Closed-skill” activities, which are more predictable and repetitive (for example, running or stationary cycling), showed only small, non-significant improvements in this analysis.
The review also found dose-related patterns. Interventions lasting at least twelve weeks were about three times more effective than interventions of six to twelve weeks, and sessions longer than an hour were about twice as effective as shorter sessions. Benefits were largest among adolescents aged 13 and older.
These patterns suggest that longer, more intensive programs, and those that involve open-skill activities, may produce larger gains. However, the authors caution that the overall certainty of the evidence was low. “Low certainty” means that limitations in the available studies (for example, small sample sizes, variability in methods, or possible bias) make it difficult to be confident that the observed effects will hold up exactly the same way in future research. Some subgroup findings (age, intervention duration, and others) were based on only a small number of effect sizes, so those moderator results should be treated as exploratory rather than definitive.
The Take-Away:
In short, this three-level meta-analysis suggests that regular, structured exercise (particularly longer programs and open-skill activities) may help improve executive functions in children and adolescents with ADHD. The evidence is promising but not yet strong enough to be considered conclusive, and the authors recommend more, larger randomized trials to confirm specifically which types and doses of exercise are most effective. Moreover, neither this meta-analysis or others show that exercise can replace standard treatments for reducing the core symptoms of ADHD (inattention, hyperactivity, impulsivity).
_logo%201.svg)
