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.
The Background:
Motor vehicle crashes remain one of the most significant public health challenges in the United States. In 2022 alone, nearly 44,000 people died on American roads, and more than 2.6 million crash-related injuries required emergency care. Most people are familiar with the usual suspects: drunk driving, speeding, and distracted driving from phones. These risks are well-documented and the focus of ongoing public safety campaigns.
But a serious risk factor has been flying under the radar: untreated ADHD. Despite receiving little attention from the public, policymakers, or transportation safety agencies, it may belong in the same conversation as these better-known dangers.
ADHD is not currently recognized by the National Highway Traffic Safety Administration as a driving risk factor; yet inattention and impulsivity, two of its defining features, are consistently cited as common contributors to crashes. Beyond these core symptoms, adults with ADHD may also experience emotional dysregulation, which can further impair driving behavior.
The Research:
Prior studies on ADHD and crash risk have produced estimates ranging from a 5% to a 70% increase. This massive heterogeneity has made it difficult to draw firm conclusions. This new meta-analysis set out to offer some clarity on these numbers.
Researchers focused specifically on adults aged 18 to 65 with a formal ADHD diagnosis who were not receiving treatment, comparing them to controls without ADHD. Four studies met these criteria, collectively covering more than 2.75 million people.
The Results:
The findings were striking: untreated ADHD was associated with a 93% increase in crash risk (95% confidence interval: 88%–99%). There was no evidence of publication bias. Although there was meaningful variation across studies, most of it stemmed from the smallest study (just 36 participants) which reported an outlier estimate of a 16-fold increase.
To put the 93% figure in context: a separate meta-analysis found that alcohol use is associated with a 150% increase in crash risk. Another way to understand just how significant this risk really is, untreated ADHD raises crash risk by more than half as much as alcohol does.
The analysis also found a dose-response relationship between ADHD symptom severity and crash risk: each incremental increase in symptom severity corresponded to a 5–6% higher crash risk. At the highest severity levels, crash risk approached that associated with alcohol use. This gradient reinforces that we're not looking at a binary distinction between “has ADHD” and “doesn’t” — the worse the symptoms, the greater the danger on the road.
The Takeaway:
These findings have practical implications for patients, families, clinicians, and policymakers alike. Untreated ADHD is not a minor footnote in the driving safety literature; rather, it is a substantial, measurable, and potentially modifiable risk factor. The question of whether and how it should be factored into licensing policy, clinical practice, and public health messaging deserves serious attention.
As populations grow, more children are growing up surrounded by traffic noise and polluted air. In most cities, these two factors tend to go hand-in-hand; yet, most previous research has examined these exposures separately. Many reviews focused on a single pollutant (such as fine particulate matter, PM2.5), or on a single developmental window, such as pregnancy or early childhood. Few have asked how noise and air pollution compare as risk factors, or how prenatal and postnatal exposures differ in their effects.
A new meta-analysis set out to address those gaps. It examined evidence on both environmental noise and several major air pollutants in relation to ADHD, compared exposures before versus after birth, and pooled data across countries and regions. Eligible studies involved children and adolescents under 18, used objective measures of environmental exposure, and assessed ADHD using either clinical diagnosis or standardized rating scales.
Noise
Nine studies, combining data from over 100,000 children and adolescents (all in European countries and Canada) found that high noise exposure was associated with 3% greater odds of ADHD. Prenatal noise exposure showed no effect; childhood exposure alone drove the association, at 4% greater odds. This is a negligible effect size that could easily reflect unmeasured confounding factors rather than a true causal relationship.
Nitrogen dioxide
Thirteen studies covering nearly one million children and adolescents in Europe, Canada, China, and South Korea found that nitrogen dioxide (NO₂) exposure was associated with 11% greater odds of ADHD. As with noise, prenatal exposure showed no independent effect. When the analysis was restricted to the five studies that used clinical diagnoses alone — generally considered the most reliable measure — the estimated odds rose to between 20% and 80% higher. The wide range reflects substantial variation across studies.
Pollutants with no significant effect
Four studies (97,500 participants) examining nitric oxide (NO), three studies (over 63,000 participants) on ozone, and three studies (over 28,000 participants) on sulfur dioxide found no significant associations with ADHD.
Particulate matter
The strongest associations emerged for particulate matter. Twelve studies involving nearly 160,000 participants in China, the US, Canada, and Europe found that exposure to fine particles (PM2.5, 2.5 microns in diameter) was associated with 30% greater odds of ADHD. Ten studies covering more than a quarter of a million participants in India, China, South Korea, and Europe found that coarser particles (PM10, 10 microns) were associated with 50% greater odds. In both cases, prenatal exposure showed no association, which is consistent with the fact that fetuses do not breathe air through developed lungs. When restricted to clinically diagnosed ADHD, PM2.5 was associated with roughly 50% greater odds, and PM10 with more than double the odds.
The Results
Across all exposures examined, particulate matter showed the clearest and strongest associations with ADHD, followed by nitrogen dioxide. Noise reached statistical significance but at a trivially small effect size. Nitric oxide, ozone, and sulfur dioxide showed no significant associations.
The authors found no evidence of publication bias which strengthens confidence in the overall pattern. However, there was marked heterogeneity across individual studies: results varied considerably, which urges caution in treating any single estimate as definitive. These are associations, not proven causal relationships, and the possibility that unmeasured factors explain part of the signal cannot be ruled out.
The Background:
Over the past two decades, diagnostic rates for adult ADHD have roughly doubled, and stimulant prescriptions in the United States skyrocketed by more than 50% between 2012 and 2023, particularly among girls and women. While these medications help many individuals manage their symptoms, a landmark 2026 article published in European Neuropsychopharmacology tackles an important question that is rarely discussed: When should doctors and patients consider stopping them?
The Discussion:
To answer this, the American Society of Clinical Psychopharmacology (ASCP) gathered a task force of 45 international experts spanning 12 countries. Through a rigorous evaluation process, they reached an overwhelming agreement on a framework for "deprescribing", the planned, supervised reduction or cessation of a medication. Here are the core insights from these ground-breaking guidelines and what they mean for adults navigating long-term ADHD treatment.
When the Treatment Isn’t Yielding Benefits
One of the most straightforward reasons to consider stopping a stimulant is if it simply isn’t doing its job. The task force agreed that if a patient does not experience an optimal response, measured by actual symptom reduction, improved daily functioning, and a better quality of life, even after trying a high, optimized dose, it may be time to step back and look at alternative options.
Sometimes, the issue goes back to the initial evaluation. The criteria for diagnosing ADHD have expanded over the years, and brief psychiatric evaluations can occasionally lead to diagnostic inaccuracies. If a thorough reevaluation reveals that the original ADHD diagnosis was incorrect, the expert consensus is clear: stimulant deprescribing is appropriate unless another stimulant-responsive condition is evident. Furthermore, if a patient develops a persistent tolerance to the drug that cannot be resolved by safe dose adjustments, a temporary taper or drug holiday may be recommended.
When the Risks to Health Outweigh the Rewards
Our bodies and health needs naturally shift over time, meaning a medication that worked safely years ago might pose a threat to your health today. The experts concluded that deprescribing should be heavily considered if stimulants exacerbate a concurrent medical or psychiatric illness. For example, although rare, stimulants can unintentionally trigger mania or psychosis in adults with unstable or unrecognized comorbid bipolar disorder.
Physical health developments are equally critical. If an adult develops a newly arising or unstable cardiovascular condition, such as a cardiac arrhythmia, ischemia, or cardiomyopathy, the risk-benefit balance changes dramatically. Additionally, if severe side effects occur that cannot be managed by reducing the dosage, or if dangerous new drug-drug interactions emerge, stopping the medication under medical supervision protects the patient's long-term well-being.
Addressing Misuse and the Complex Role of Cannabis
Because stimulant medications target brain reward and wakefulness circuitry, they can foster a propensity for misuse. Studies indicate that more than 1 in 5 adults prescribed stimulants have misused them, and 1 in 6 have diverted their medication to others. The task force emphasizes that deprescribing is warranted if a patient persistently takes doses higher than prescribed against medical advice, uses the medication purely for unauthorized performance enhancement, or has an untreated, coexisting substance use disorder.
And what about cannabis? This topic sparked the most debate among the experts, falling just short of an official consensus with 71% agreement that regular cannabis use alone shouldn't automatically trigger a stimulant stoppage. Recognizing the complexity, such as how chronic cannabis use can overlap with ADHD executive function deficits, the task force proposed a structured monitoring approach instead of an immediate cutoff. Clinicians are encouraged to track the patient every 1 to 3 months using standardized symptom tools and random urine drug screens to verify whether cannabis use is actively neutralizing the stimulant's therapeutic benefits.
The Path Forward: Safe Tapering and Lifestyle Support
If you and your doctor decide that stopping a stimulant is the right path, it shouldn’t happen overnight. The task force strongly recommends that medications be gradually tapered off at a rate tailored to the individual to minimize potential disruptions and distinguish between transient withdrawal and a true return of ADHD symptoms.
Crucially, stopping a medication doesn't mean stopping treatment. The experts highlight that the success of any deprescribing plan is significantly enhanced when patients focus on optimizing modifiable lifestyle factors. Prioritizing sleep hygiene, staying physically active, and implementing structured behavioral strategies can support executive functioning and help sustain your cognitive gains even as the medication is reduced or eliminated.
The Takeaway:
The decision to continue or stop an ADHD medication is a deeply personal one that requires balancing real-world efficacy, safety, and individual health changes. These new consensus recommendations provide an essential roadmap to help adults navigate their long-term mental health journeys safely and effectively.
Are you or a loved one currently evaluating your long-term relationship with ADHD medication? Consider scheduling a check-in with your healthcare provider to discuss whether your current treatment plan still perfectly matches your health needs today.
_logo%201.svg)
