Evaluating ADHD screening tools: A comparative analysis of accuracy, cost, and complexity
Bibliographic record
Abstract
BACKGROUND: Debate over the rising prevalence of ADHD diagnoses underscores the need for accurate screening. This study provides clinicians a comparative inventory of tools, evaluating balanced accuracy, item count, cost, reporter type, and predictive values at realistic base rates. METHODS: Tools were identified via systematic searches of MEDLINE, PsycINFO, and EMBASE (Jan 2021-July 2025), extending prior reviews. Instruments for children, adolescents, and adults were characterized by reporter type. Balanced accuracy was modeled using mixed-effects beta regression with a random intercept for tool and fixed effects for reporter type, cost, and item count; minimum age was included in sensitivity analyses. Positive/negative predictive values (PPV/NPV) were also examined. RESULTS: Seventy-four assessments covering 40 reporter-based screening tools were analyzed (mean balanced accuracy 76 %, SD = 0.09). Self-report tools outperformed teacher reports; differences were not significant after adjusting for age. Cost showed no association with balanced accuracy; item count showed a small, non-significant positive trend (p = 0.06). At 10 % prevalence, PPV was modest (0.10-0.30) and NPV was high (0.95-0.99). CONCLUSIONS: ADHD screening tools showed fair to good accuracy. Brief tools can perform well, with no observed advantage for longer or paid tools. Reporter-type effects were partially explained by age. Given low PPV but high NPV at base rates, positive screens warrant full assessment, while negative screens could reliably rule out most ADHD cases. Our findings suggest that the selection of ADHD screening tools should be guided by population, content, and context rather than by length or cost.
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 | 0.068 | 0.309 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.005 | 0.006 |
| Bibliometrics | 0.014 | 0.008 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.005 | 0.005 |
| Open science | 0.002 | 0.004 |
| Research integrity | 0.003 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".