Canvas Dx

by Cognoa  · Based in United States → — We make life-changing early diagnosis and interventions possible with breakthrough innovations that save time, optimize resources, and positively impact the lives of children and families.
Family Medicine Pediatrics Psychiatry

Regulatory Status Disclosed

Overview

Cognoa is a pediatric behavioral health company that develops digital diagnostic and therapeutic products for children with behavioral health disorders.5 to 6 years. The tool leverages responsible artificial intelligence to provide an informed, rapid, and universally accessible path to care, aiming to overcome diagnostic delays and inequities. Canvas Dx utilizes a combination of caregiver questionnaires, home video recordings of the child’s behavior, and clinician input, processed by a machine-learning algorithm, to aid in diagnosis.

Reviewed by Pouyan Golshani, MD — Interventional Radiologist

Key Features

  • AI-powered diagnostic aid for autism
  • Diagnoses or rules out autism in children ages 1.5 to 6 years
  • Remote, digital evaluation via smartphone app for caregivers
  • Caregiver questionnaires and home video recordings
  • Clinician questionnaire and portal
  • Machine-learning algorithm processes independent inputs
  • Provides positive, negative, or indeterminate diagnosis for ASD
  • Auto-generates detailed developmental reports
  • Supports rapid diagnosis (days, not months or years)
  • Objective, data-driven approach to alleviate biases

Use Cases

  • Early diagnosis of Autism Spectrum Disorder (ASD) in young children
  • Reducing diagnostic delays for autism
  • Equipping primary care clinicians to diagnose autism
  • Overcoming geographical barriers to specialized care
  • Providing objective, data-driven insights to aid clinical judgment
  • Streamlining the path to care and intervention

What Physicians Need to Know

Evidence Base
Canvas Dx is an FDA-authorized diagnostic aid for autism spectrum disorder (ASD) in children aged 18 to 72 months. Its underlying machine learning algorithm was trained on data from thousands of children with diverse demographic backgrounds and behavioral health presentations. Foundational research began at Harvard Medical School's Center for Biomedical Informatics, applying machine learning to electronic patient record data. The device integrates data from a caregiver questionnaire, a video analyst questionnaire, and a clinician questionnaire. It is intended to be used in conjunction with patient history, clinical observations, and other clinical evidence, and is not a stand-alone diagnostic device. The tool automatically maps concerns to DSM-5 compatible criteria for autism diagnosis. Clinicians should follow established guidelines, such as those from the American Academy of Pediatrics, when making medical decisions.
Clinical Validation Studies
Canvas Dx has undergone rigorous testing and clinical validation, with results published in peer-reviewed journals. A pivotal study led to its FDA authorization on June 2, 2021. This study demonstrated high accuracy, with a Positive Predictive Value (PPV) of 87.5% (95% CI, 82.5%-96.7%) and a Negative Predictive Value (NPV) of 96.1% (95% CI, 93.4%-98.6%) for determinate results. The device provided a determinate (positive or negative) output in 66.5% of cases, with 96% of indeterminate cases having one or more neurodevelopmental conditions according to blinded specialist assessment. A real-world data study involving 124 children across 15 states confirmed these high performance metrics, showing an NPV of 95.2% and a PPV of 94.4% for determinate results, with 60.5% receiving a determinate result. This real-world analysis also indicated that children using Canvas Dx received a positive autism output over a year earlier than the current median age of diagnosis in the United States.
Alert Fatigue Management
Canvas Dx is designed to provide a clear "Positive for autism," "Negative for autism," or "Indeterminate" result. The "Indeterminate" result is a safety feature, indicating insufficient information for a highly predictive determination, thereby reducing the risk of false predictions. This approach aims to provide actionable insights without overwhelming clinicians with ambiguous data.
Override Rate Data
The device is intended as an aid to diagnosis and not a stand-alone diagnostic tool. Clinicians are expected to use the Canvas Dx result in conjunction with their clinical judgment, patient history, observations, and other evidence. The system provides a detailed report to inform clinical decision-making, and clinicians can view questionnaire responses and uploaded videos to support their judgment.
Differential Diagnosis Support
Canvas Dx provides a detailed report that includes a visual summary of the child's challenges across developmental domains, identified strengths, and challenges mapped to DSM-5 compatible domains relevant to autism diagnosis. This report helps clinicians understand the child's neurodevelopmental profile, aiding in differential diagnosis and guiding next steps, even for children with indeterminate results or those without autism.
Clinical Workflow Integration
Canvas Dx is designed for integration into both primary care and specialist settings. The workflow involves caregivers completing a questionnaire and uploading videos via a smartphone app, while clinicians complete a separate questionnaire in a web portal. The AI algorithm combines these inputs to generate a result and a detailed report. The system aims to streamline the diagnostic journey, reduce wait times, and provide auto-generated documentation for insurance and access to services. Training materials and case studies are available to help clinicians integrate Canvas Dx into their practice.
Decision Audit Trail
The Canvas Dx portal allows clinicians to view the status of each patient's journey, including dates of task completion and outstanding tasks. Clinicians can also access and review recorded responses from both caregiver and their own questionnaires.
Physician Tip

Canvas Dx is a prescription-only diagnostic aid for autism in children aged 18-72 months. It is not a standalone diagnostic tool and should be used in conjunction with your clinical expertise and other evidence. Utilize the detailed reports provided by Canvas Dx, which map concerns to DSM-5 criteria, to inform your diagnostic decisions and guide next steps for every child, regardless of the Canvas Dx outcome. For indeterminate results, further specialist evaluation is typically warranted. The tool aims to expedite diagnosis, potentially allowing for earlier interventions, which are critical for improving long-term outcomes.

Details

Category Clinical Decision Support & Reference, Mental & Behavioral Health AI
Pricing Unknown
DeploymentRemote, digital evaluation
Compliance
BAA AvailableUnknown
HIPAA CompliantUnknown
FDA Status Cleared AI-estimated
Integrations
EHR Not specified
Specialties Family Medicine, Pediatrics, Psychiatry

FDA clearance history

This product’s FDA authorization. From FDA’s list of AI-enabled medical devices; each number links to FDA’s record.

Decision dateNumberName as listed by FDA
2025-04-11K243558 510(k)Canvas Dx

Ratings & Reviews

No reviews yet. Be the first to review this tool!

Rate Canvas Dx

Clinical Value
Ease of Use
Integration
Support & Docs
Value for Money
No press coverage or publications on file yet. Know of some? Suggest an edit →

Videos

Product demos, reviews, and walkthroughs for Canvas Dx.

View all on YouTube

Frequently Asked Questions

Canvas Dx is a prescription-only digital diagnostic aid for healthcare professionals to assist in diagnosing or ruling out Autism Spectrum Disorder (ASD) in children aged 18 months to 6 years who are at risk for developmental delay. It gathers information from caregivers via a smartphone app (questionnaires and two short videos of the child), and from the clinician through a web portal questionnaire. An AI algorithm then processes this data to provide an output of positive, negative, or indeterminate for autism, along with a detailed report mapping to DSM-5 criteria. This report helps clinicians make informed decisions and streamline documentation for activating care.
Canvas Dx is the first and only FDA-authorized diagnostic aid for autism. It is a prescription-only device, intended to be used as an adjunct to the diagnostic process, not as a stand-alone diagnostic tool. Healthcare professionals are expected to use Canvas Dx in conjunction with patient history, clinical observations, and other clinical evidence. While it is FDA-authorized, some policies may still consider it experimental or investigational.
While Canvas Dx is a unique FDA-authorized digital diagnostic for autism, other AI-powered clinical decision support tools exist for various medical fields. These can include AI for general diagnosis support, treatment planning, and documentation. However, these alternatives typically serve broader purposes or different specialties and are not direct substitutes for an FDA-authorized diagnostic specifically for ASD.
The cost of Canvas Dx can be around $1,860.20 to $1,947 for a miscellaneous package without insurance. Highmark has announced coverage for Canvas Dx for its commercial members, including the full price of the tool and the provider's administration time, without requiring prior authorization. It is recommended to contact individual insurance carriers for specific formulary coverage and copay details, as coverage can vary.
Canvas Dx is not a stand-alone diagnostic instrument and should be used as an aid in conjunction with other clinical evidence. It is intended for children aged 18 months to 72 months who are at risk for developmental delay. The device may produce an 'indeterminate' result if there is insufficient information, which means it cannot render a reliable outcome. Additionally, it requires caregivers to have functional English capability and access to a compatible smartphone with an internet connection.

Related Tools

Stanford University
Stanford University
Clinical Decision Support & Reference
Stanford Online's "AI in Healthcare" program provides a comprehensive overview of artificial intelligence's applications and implications within the medical field.
RADIN Health
RADIN Health
Clinical Decision Support & Reference
RADINA is an AI-powered platform by RADIN Health designed to optimize radiology workflows, enhance diagnostic accuracy, and streamline reporting.
Med-PaLM 2
Google
Clinical Decision Support & Reference
Med-PaLM 2 is a large language model from Google, fine-tuned for healthcare to provide high-quality answers to medical questions and support clinical decision-making.
Pacmed Critical Discharge
Pacmed
Clinical Decision Support & Reference
Pacmed Critical Discharge is an AI tool that predicts the probability of death or readmission within seven days of ICU discharge, providing explainable insights for physicians.
AiZtech Labs
AiZtech Labs
Clinical Decision Support & Reference
AiZtech Labs provides enterprise-grade AI solutions for healthcare, focusing on operational efficiency, diagnostic accuracy, and patient care workflows for providers and health systems.
Stethophone Pro
Sparrow Acoustics
Cardiology AI
Stethophone Pro transforms smartphones into advanced cardiac screening tools, enabling clinicians to capture, interpret, and visualize heart sounds for early detection of cardiovascular diseases.

See all Clinical Decision Support & Reference tools →

Suggest an Edit → | Report an issue | Last Verified: 2026-11-05 | First Added: 2026-04-18
AI Tool Finder
AI-powered search. Results may not be comprehensive.