Integration of an <scp>EEG</scp> biomarker with a clinician's <scp>ADHD</scp> evaluation
Bibliographic record
Abstract
BACKGROUND: This study is the first to evaluate an assessment aid for attention-deficit/hyperactivity disorder (ADHD) according to both Class-I evidence standards of American Academy of Neurology and De Novo requirements of US Food and Drug Administration. The assessment aid involves a method to integrate an electroencephalographic (EEG) biomarker, theta/beta ratio (TBR), with a clinician's ADHD evaluation. The integration method is intended as a step to help improve certainty with criterion E (i.e., whether symptoms are better explained by another condition). METHODS: To evaluate the assessment aid, investigators conducted a prospective, triple-blinded, 13-site, clinical cohort study. Comprehensive clinical evaluation data were obtained from 275 children and adolescents presenting with attentional and behavioral concerns. A qualified clinician at each site performed differential diagnosis. EEG was collected by separate teams. The reference standard was consensus diagnosis by an independent, multidisciplinary team (psychiatrist, psychologist, and neurodevelopmental pediatrician), which is well-suited to evaluate criterion E in a complex clinical population. RESULTS: Of 209 patients meeting ADHD criteria per a site clinician's judgment, 93 were separately found by the multidisciplinary team to be less likely to meet criterion E, implying possible overdiagnosis by clinicians in 34% of the total clinical sample (93/275). Of those 93, 91% were also identified by EEG, showing a relatively lower TBR (85/93). Further, the integration method was in 97% agreement with the multidisciplinary team in the resolution of a clinician's uncertain cases (35/36). TBR showed statistical power specific to supporting certainty of criterion E per the multidisciplinary team (Cohen's d, 1.53). Patients with relatively lower TBR were more likely to have other conditions that could affect criterion E certainty (10 significant results; P ≤ 0.05). Integration of this information with a clinician's ADHD evaluation could help improve diagnostic accuracy from 61% to 88%. CONCLUSIONS: The EEG-based assessment aid may help improve accuracy of ADHD diagnosis by supporting greater criterion E certainty.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.007 | 0.014 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".