Seedlabs

Two-Fail Flag: Embedded Validity Scoring for Adult ADHD Evaluations

Software that flags adult ADHD evaluations if the test results suggest the person wasn't trying their best.

Software that automatically computes six embedded validity indicators from tests already administered in an adult ADHD evaluation (Stroop, Trail Making, Verbal Fluency, WAIS-IV subtests) and flags the file when any two fail — a ≥90%-specificity screen for non-credible performance that adds zero extra testing time.

MedicineAttention Deficit Hyperactivity Disorder
Attention Deficit Hyperactivity DisorderBehavioral health / clinical assessment — adult ADHD diagnostic clinics and telehealth assessment platforms

Concept

A scoring layer (standalone web tool or plug-in for digital test platforms) that turns a routine adult ADHD evaluation into an automatic performance-validity check. The clinician or platform streams in scores from the Stroop Color and Word Test, Trail Making Test, Verbal Fluency Test, and WAIS-IV subtests; the tool computes the six embedded validity indicators (EVIs) validated in the new study, applies the "fail any two of six" decision rule, and returns a one-page flag report: which indicators failed, the rule's operating characteristics, and standard report language (e.g., "performance validity was not established; interpret results with caution and consider supplementary validity assessment"). For clinics that administered the full ten-indicator battery, the tool applies the equivalent "fail any three of ten" rule. The wedge is zero added testing time — every input is a test the patient already took — and it converts what has been a forensic-specialist skill into a routine, documented step any ADHD clinic or telehealth assessor can run.

Why now

  • The new study of 585 adults referred for ADHD evaluation shows why single embedded indicators have been impractical to date (AUCs .69–.78, sensitivity 19–51%) but why a packaged rule now works: six indicators drawn from Stroop, Trail Making, Verbal Fluency, and WAIS-IV reached AUC .86 — as accurate as all ten combined — and failing any two of the six kept specificity at ≥90% with ~60% sensitivity. That is a simple, validated threshold that can be coded into software rather than left in a journal article.
  • Adult ADHD evaluation volume has surged via telehealth, and digital diagnostic pathways already exist — a hybrid AI algorithm for adult ADHD diagnosis is operating in NHS clinical trials [6] — yet these workflows include no validity layer; this module is a drop-in complement to exactly that kind of digital assessment pipeline.
  • The study's caution that combining EVIs "helps only to an extent" (multivariate models explain at most 36% of variance in validity status) is designed into the product: the flag prompts further validity assessment rather than rendering a verdict, keeping the tool a screen with a false-positive rate below 10% among credible performers.

Written by GLM · 11 Oct 2026

AI assessment

Backed by 8 papers85

A high-utility, low-friction clinical tool that converts complex neuropsychological validity research into a simple 'flag' for clinicians, though it faces significant novelty challenges due to a nearly identical existing audit concept.

Evidence strength
5/5
The idea is directly derived from a robust set of corroborating studies (Papers 2, 3, 4, 5, 6, 7) that specifically validate the 'fail any two of six' rule with high specificity (≥90%) and provide the exact test components needed.
Market pull
4/5
There is a clear and urgent need for validity screening in the surging adult ADHD telehealth market to prevent misdiagnosis and fraud, with a well-defined set of institutional buyers.
Novelty & moat
2/5
The idea is essentially a clinical-side implementation of the 'Protocol Audit' idea already in the catalog, which uses the same tests and the same 'fail two' logic.
Feasibility
5/5
The product is a simple scoring calculator based on established cut-off scores; it requires no new clinical trials or complex AI, only a software wrapper for existing formulas.
Wedge clarity
5/5
The 'zero added testing time' wedge is exceptionally sharp, removing the primary barrier (patient burden/time) to implementing validity checks in routine clinics.
Simplicity / focus
5/5
The product is focused on a single, discrete function: computing a validity flag from existing test data.

Scored by Gemma 4 · 12 Oct 2026. Rated against a fixed rubric (evidence, market, novelty, feasibility, wedge, simplicity), relative to the closest ideas already in the catalog. A prior estimate to compare ideas before real-world signal arrives.

Persona discussion

AI personas trained on real people's expertise debate this idea as it evolves.

View the discussion →

Act on this idea

Ideas only matter if someone runs with them. Your message goes straight to the founder's inbox — nothing is stored on our servers.

Business analysis

The PESTEL analysis reveals a strong product-market fit driven by the surge in telehealth ADHD assessments and a critical need for efficiency in validity screening. While technological and economic drivers are highly positive, the primary risks are legal and social, specifically regarding the potential for false positives to impact patient care and the regulatory scrutiny of automated diagnostic aids.

Political2

Economic3

Social3

Technological3

Environmental2

Legal3

The viability of a clinical diagnostic tool depends heavily on healthcare regulations, medical ethics, and the legal standards for ADHD diagnosis. · Generated 2026-10-12 by Gemma 4AI-generatedFull PESTEL Analysis →

Who benefits

  • ADHD Onlinecompany

    This telehealth company performs ADHD assessments at scale; an automated embedded-validity flag adds an objective credibility check to every evaluation, strengthening its standing with regulators and payers concerned about overdiagnosis and stimulant diversion.

  • Pearson Clinical Assessmentcompany

    Its Q-interactive digital assessment platform already digitizes administration and scoring of Stroop, Trail Making, Verbal Fluency, and WAIS-IV; a validated multivariate validity module is a natural premium add-on that differentiates its ADHD batteries.

  • South London and Maudsley NHS Foundation Trustorganization

    Its adult ADHD service faces long waitlists and high assessment demand; a validity check computed from tests already administered adds rigor to each diagnosis without adding any appointment time.

  • Massachusetts General Hospital Adult ADHD Programorganization

    A high-volume adult ADHD evaluation program whose clinicians must document the credibility of findings to support medication and accommodation decisions; the tool standardizes and documents that step across all assessors.

  • Psychological Assessment Resources (PAR)company

    PAR publishes and scores several of the source measures (including the Stroop Color and Word Test); adding a validated combined-rule validity output creates a differentiated upsell for its existing scoring-software customers.

Research it builds on

  1. Wechsler Adult Intelligence Scale-Fourth Edition (WAIS-IV) processing speed scores as measures of noncredible responding: The third generation of embedded performance validity indicators.
    László A. Erdődi, Christopher A. Abeare, Jonathan D. Lichtenstein et al. · 2016 · 126 citations
    All ideas from this paper →
  2. Not so fast! Limitations of processing speed and working memory indices as embedded performance validity tests in a mixed neuropsychiatric sample
    Gabriel P. Ovsiew, Zachary J. Resch, Kritika Nayar et al. · 2020 · 46 citations
    All ideas from this paper →
  3. Diagnosing attention-deficit hyperactivity disorder (ADHD) using artificial intelligence: a clinical study in the UK
    Tianhua Chen, Ilias Tachmazidis, Sotiris Batsakis et al. · 2023 · 45 citations
    All ideas from this paper →
  4. Multivariate examination of embedded indicators of performance validity for ADHD evaluations: A targeted approach
    John‐Christopher A. Finley, Julia M. Brooks, Amanda N. Nili et al. · 2023 · 43 citations
    All ideas from this paper →
  5. Stronger Together: The Wechsler Adult Intelligence Scale—Fourth Edition as a Multivariate Performance Validity Test in Patients with Traumatic Brain Injury
    László A. Erdődi, Christopher A. Abeare · 2019 · 38 citations
    All ideas from this paper →
  6. Comparing embedded performance validity indicators within the WAIS-IV Letter-Number sequencing subtest to Reliable Digit Span among adults referred for evaluation of attention-deficit/hyperactivity disorder
    John‐Christopher A. Finley, Violeta J. Rodriguez, Brian M. Cerny et al. · 2024 · 16 citations
    All ideas from this paper →
  7. A Direct Comparison of 10 WAIS-IV Digit Span Embedded Validity Indicators among a Mixed Neuropsychiatric Sample with Varying Degrees of Cognitive Impairment
    Zachary J. Resch, Brian M. Cerny, Gabriel P. Ovsiew et al. · 2022 · 12 citations
    All ideas from this paper →
  8. Identifying Factors that Increase False-Positive Rates on Embedded Performance Validity Testing in ADHD Evaluations
    John‐Christopher A. Finley, Logan M. Tufty, Steven A. Abalos et al. · 2024 · 4 citations
    All ideas from this paper →
Leave feedback
feasibility