Online Evaluation of the Diagnostic Accuracy of BlinkLab's Digital Assessments for Autism

This observational study aims to evaluate how patterns of behavioral and sensorimotor responses measured using the BlinkLab Dx1 smartphone application relate to autism diagnoses in children ages 2 to 11. BlinkLab Dx1 is a non-invasive, smartphone-based application under development as a diagnostic aid for healthcare providers assessing autism.

In this study, children who have undergone a neurodevelopmental assessment within the past 12 months will complete two short, video-based sessions using the BlinkLab Dx1 app. The app presents visual and auditory stimuli and records reflexive sensorimotor responses and patterns of repetitive behavior. Additionally, primary caregivers will answer a short questionnaire in the app about symptoms and development. Information about prior neurodevelopmental assessments, including documented DSM-5-based diagnoses from routine clinical practice, will be collected retrospectively.

The study will examine how the app's neurobehavioral measurements relate to previously assigned clinical diagnoses. These paired data will be used to develop and evaluate a machine learning-based algorithm using separate training and testing datasets to assess whether patterns measured by BlinkLab Dx1 can help distinguish children with autism from children without an autism diagnosis.

This study does not involve any treatment or medical intervention.

Study Overview

• Status: Recruiting
• Conditions: Autism Spectrum Disorder; Autism; Neurodevelopmental Conditions; Autism Spectrum Disorder (ASD)
• Intervention / Treatment: Diagnostic test: BlinkLab Dx1; Behavioral: Retrospective Neurodevelopmental Diagnostic Assessment

Detailed Description

Specification of the Time Perspective section in the Study Design: this study has a hybrid time perspective, as BlinkLab Dx1 measures are collected prospectively during remote sessions, while the clinical reference standard (presence of in a DSM-5-based diagnostic report from a neurodevelopmental assessment within the prior 12 months) is collected retrospectively. The clinical reference standard is based on neurodevelopmental assessments conducted in routine clinical care and is collected without influence from study procedures.

The study will use paired BlinkLab Dx1 measurements and clinical reference standard diagnoses to develop and evaluate a machine learning-based classification algorithm. The dataset will be divided into separate training and testing subsets, with the training dataset used to develop the model and determine classification thresholds, and the independent testing dataset used to evaluate diagnostic performance. The model will generate a classification categorizing participants as "Positive for autism", "Intermediate" or "Negative for autims". Participants with intermediate results are considered to have indeterminate findings and are excluded from primary diagnostic performance analyses, which are based on participants with definitive positive or negative test results.

• Study Type: Observational
• Enrollment (Estimated): 1000

Contacts and Locations

• Study Contact: Name: Myrthe J. Ottenhoff, MD, PhD; Phone Number: 908-824-3471; Email: study@blinklab.org

Study Locations

• United States
  • New Jersey
    • Princeton, New Jersey, United States, 08540
      • Recruiting
      • Remote study conducted nationwide; all participation occurs via smartphone app at home.
      • Contact: Myrthe J. Ottenhoff, MD, PhD; Phone Number: 908-824-3471; Email: study@blinklab.org

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Child
• Accepts Healthy Volunteers: Yes

• Sampling Method: Non-Probability Sample

Study Population

Children aged 2-11 years of which the parents/caregivers and/or pediatrician (or other primary care provider) have raised concerns regarding their neurodevelopment and have undergone neurodevelopmental assessment in the last 12 months that would allow diagnosing any neurodevelopmental condition according to DSM5 criteria.

Description

Inclusion Criteria:

1. Age: Children between 2 to 11 years old
2. Parent/Caregiver/Healthcare Provider Concern: The child has received a diagnostic outcome of a neurodevelopmental assessment based on DSM-5 criteria within the past 12 months.
3. Language Proficiency: Parents and subjects must have functional English capability in the home environment.
4. Informed Consent: Parents must be able to read, understand, and voluntarily sign the Informed Consent Form (ICF).
5. Videotaping: subjects must be willing to be videotaped during the diagnostic assessment by the BlinkLab App.

Exclusion Criteria:

1. Device Compatibility: Parents without smartphone capabilities necessary for using the BlinkLab app.
2. Previous Enrollment: Subjects who have been previously enrolled in any BlinkLab clinical study.
3. Location of at home testing: Not being able to complete all remote at-home study sessions within the US.
4. History of audiogenic seizures: Participants with a known history of seizures that are triggered by auditory stimuli, including reflex or startle epilepsy provoked by sounds (audiogenic seizures), or any other form of sound-induced epilepsy.

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Model Development Group - Children evaluated for neurodevelopmental conditions.; Children aged 2-11 who have formally been evaluated for neurodevelopmental conditions in the 12 months prior to the enrollment date. This includes children with and without autism, children with other neurodevelopmental conditions and children eventually not diagnosed with any neurodevelopmental condition.	Diagnostic test: BlinkLab Dx1; BlinkLab Dx1 is a machine learning-based algorithm that generates a continuous score reflecting likelihood of autism from neurobehavioral responses (including measures such as pre-pulse inhibition and habituation, motor activity, and vocalizations) recorded during standardized video-watching sessions in a mobile application. Pre-specified thresholds, determined during model development and fixed prior to evaluation in the independent test dataset, are applied to categorize results as " Positive for autism", "Intermediate" or "Nagative for autism". Results in the intermediate category are considered indeterminate and are excluded from primary diagnostic performance analyses, which are based on participants with definitive positive or negative test results.; Behavioral: Retrospective Neurodevelopmental Diagnostic Assessment; The clinical reference standard is a retrospective neurodevelopmental diagnostic assessment conducted within 12 months prior to enrollment, based on DSM-5 criteria. Participants are classified as having or not having an autism diagnosis based on the documented diagnostic conclusions of these assessments.
Model Testing Group - Children evaluated for neurodevelopmental conditions.; Children aged 2-11 who have formally been evaluated for neurodevelopmental conditions in the 12 months prior to the enrollment date. This includes children with and without autism, children with other neurodevelopmental conditions and children eventually not diagnosed with any neurodevelopmental condition. Data collection for this group is blinded.	Diagnostic test: BlinkLab Dx1; BlinkLab Dx1 is a machine learning-based algorithm that generates a continuous score reflecting likelihood of autism from neurobehavioral responses (including measures such as pre-pulse inhibition and habituation, motor activity, and vocalizations) recorded during standardized video-watching sessions in a mobile application. Pre-specified thresholds, determined during model development and fixed prior to evaluation in the independent test dataset, are applied to categorize results as " Positive for autism", "Intermediate" or "Nagative for autism". Results in the intermediate category are considered indeterminate and are excluded from primary diagnostic performance analyses, which are based on participants with definitive positive or negative test results.; Behavioral: Retrospective Neurodevelopmental Diagnostic Assessment; The clinical reference standard is a retrospective neurodevelopmental diagnostic assessment conducted within 12 months prior to enrollment, based on DSM-5 criteria. Participants are classified as having or not having an autism diagnosis based on the documented diagnostic conclusions of these assessments.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Sensitivity of BlinkLab Dx1	Sensitivity of BlinkLab Dx1, defined as the proportion of participants with a positive clinical reference standard diagnosis of autism who are correctly identified as positive by the index test.	Baseline (including index test completed during the enrollment period and reference standard diagnosis from assessments conducted within 12 months prior to enrollment)
Specificity of BlinkLab Dx1	Specificity of the BlinkLab Dx1 algorithm, defined as the proportion of participants without a clinical reference standard diagnosis of autism who are correctly identified as negative by the index test.	Baseline (including index test completed during the enrollment period and reference standard diagnosis from assessments conducted within 12 months prior to enrollment)

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Adverse Events	A qualitative description of any adverse events that occurred during the study from the time of informed consent until the completion of the diagnostic evaluation.	During individual enrollment period (up to 30 days)
Usability	The usability of the device for parents/caregivers in relation to the use-related risk analysis identified risks.	During the individual enrollment period (up to 30 days)
Autism Symptom Severity	Based on prospectively collected SRS-2 questionnaire scores and retrospectively collected standardized autism assessment results documented in the neurodevelopmental assessment report.	Baseline (including neurodevelopmental assessment data from up to 12 months prior to enrollment and a single SRS-2 assessment collected once during the enrollment period [up to 30 days after enrollment])
Positive Predictive Value (PPV) of BlinkLab Dx1	Positive predictive value, defined as the proportion of participants with a positive BlinkLab Dx1 test result who have a positive clinical reference standard diagnosis of autism.	Baseline (including index test completed during the enrollment period and reference standard diagnosis from assessments conducted within 12 months prior to enrollment)
Negative Predictive Value of BlinkLab Dx1	Negative predictive value, defined as the proportion of participants with a negative BlinkLab Dx1 test result who do not have a clinical reference standard diagnosis of autism.	Baseline (including index test completed during the enrollment period and reference standard diagnosis from assessments conducted within 12 months prior to enrollment)
False Positive Rate of BlinkLab Dx1	False positive rate, defined as the proportion of participants without a clinical reference standard diagnosis of autism who are incorrectly identified as positive by the BlinkLab Dx1 index test.	Baseline (including index test completed during the enrollment period and reference standard diagnosis from assessments conducted within 12 months prior to enrollment)
False Negative Rate of BlinkLab Dx1	False negative rate, defined as the proportion of participants with a clinical reference standard diagnosis of autism who are incorrectly identified as negative by the BlinkLab Dx1 index test.	Baseline (including index test completed during the enrollment period and reference standard diagnosis from assessments conducted within 12 months prior to enrollment)
Accuracy of BlinkLab Dx1	Accuracy, defined as the proportion of all participants who are correctly classified by the BlinkLab Dx1 index test (i.e., the sum of true positives and true negatives divided by the total number of participants), relative to the clinical reference standard diagnosis.	Baseline (including index test completed during the enrollment period and reference standard diagnosis from assessments conducted within 12 months prior to enrollment)

Other Outcome Measures

Outcome Measure	Measure Description	Time Frame
Timing Task Performance	Performance on the BlinkLab timing task and its relation with ADHD symptom severity as measured with the modified Vanderbilt ADHD Diagnostic Parent Rating Scale (VADRS)	Single time point during enrollment period (up to 30 days after enrollment)
Go/No-Go Taks Performance	Performance on the Blinklab go/no-go task and its relation with ADHD symptom severity as measured with the VADRS.	Single time point during enrollment period (up to 30 days after enrollment)
Latency Task Performance	Performance on the Blinklab latency task and its relation with ADHD symptom severity as measured with the VADRS.	Single time point during enrollment period (up to 30 days after enrollment)

Collaborators and Investigators

• Sponsor: Blinklab Limited

Study record dates

Study Major Dates

• Study Start (Actual): February 15, 2025
• Primary Completion (Estimated): September 1, 2026
• Study Completion (Estimated): December 1, 2026

Study Registration Dates

• First Submitted: May 11, 2026
• First Submitted That Met QC Criteria: May 11, 2026
• First Posted (Actual): May 15, 2026

Study Record Updates

• Last Update Posted (Actual): May 15, 2026
• Last Update Submitted That Met QC Criteria: May 11, 2026
• Last Verified: May 1, 2026

More Information

Terms related to this study

• Keywords: Autism; Observational Study; Autism Spectrum Disorder; Digital Health; Mobile Application; Eye Movements; Machine Learning; Autism Diagnosis; Digital Assessment; Neurodevelopmental Conditions; Pediatric Assessment; Smartphone-based Assessment; Remote Study; Repetitive Behavior; Reflexive Sensorimotor Behavior
• Additional Relevant MeSH Terms: Mental Disorders; Neurodevelopmental Disorders; Child Development Disorders, Pervasive; Autism Spectrum Disorder; Autistic Disorder
• Other Study ID Numbers: 08012025

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: UNDECIDED
• IPD Plan Description: BlinkLab is a publicly listed company holding patents related to the BlinkLab Dx technology. The sponsor intends to evaluate mechanisms for sharing de-identified, non-proprietary participant-level data with qualified academic investigators under data use agreements that protect participant privacy and BlinkLab's intellectual property. Any shared data will exclude raw video, audio, or algorithmic outputs that are proprietary or potentially identifiable.

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: Yes
• product manufactured in and exported from the U.S.: No