Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-0293
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-07-20T08:46:26.468790Z
status: published
lens: g_space
sector: health
headline: An analysis of the real world performance of an artificial intelligence based autism diagnostic
dek: Rapidly rising demand for pediatric autism evaluations has outpaced specialist capacity and created a crisis of delayed diagnoses and treatment. Streamlining the diagnostic process could reduce wait times and optimize use of limited specialist resources. Following strong clinical trial results, Canvas Dx, an AI-based diagnostic, was FDA authorized to support accurate diagnosis or rule-out of autism in children 18-72 months with caregiver or healthcare provider concern for developmental delay. To gain insight int…
gain_title: In real-world use among 254 young children with developmental concern, the AI-based Canvas Dx provided accurate autism predictions with high negative and positive predictive values and enabled diagnosis at a median age of 37.2 months.
problem_title: (none)
trace_subject: (none)
gain_reading: In real-world use among 254 young children with developmental concern, the AI-based Canvas Dx provided accurate autism predictions with high negative and positive predictive values and enabled diagnosis at a median age of 37.2 months.
gain_evidence: Canvas Dx had a NPV of 97.6% (CI- 92.8% -100.0%) and a PPV of 92.4% (CI-87.7%-97.2%) | median age of children who received a positive for autism output was 37.2 months, which is more than 2 years earlier than the current median age of autism diagnosis
problem_reading: (none)
problem_evidence: (none)
quick_read: Published August 12, 2025, this peer-reviewed analysis examined real-world performance of Canvas Dx, an FDA-authorized AI-based tool to support diagnosis or rule-out of autism in children 18-72 months. In 254 children evaluated after market authorization, the tool produced determinate positive or negative outputs in 63% of cases and showed high predictive values when compared to clinical reference diagnoses.

The findings matter because demand for pediatric autism evaluations has outpaced specialist capacity, creating delayed diagnoses. Earlier accurate identification at around 37 months could help children access therapies during a critical neurodevelopmental window, though the data reflect only an initial 254-case sample, 37% of cases remained indeterminate, and broader impacts on waitlists and access depend on coverage and adoption that were not yet measured by the study date.
limitation: Device output was determinate in only 63% of cases, and evaluation was limited to children 18-72 months with caregiver or healthcare provider concern for developmental delay in a small initial sample of 254 prescriptions.
tag: Model-prefilled gain
key_points: Analysis covered the initial 254 Canvas Dx prescriptions fulfilled after FDA authorization in children 18-72 months with concern for developmental delay. | Sample characteristics were 54.7% autism prevalence, 29.1% female, average age 39.99 months. | Sensitivity and specificity of determinate results were 99.1% and 81.6% respectively, with no performance differences noted based on patients' sex. | Real-world performance was equivalent to clinical trial results for all key metrics except determinate rate and PPV, which were significantly improved.
rundown: Researchers conducted a de-identified aggregate analysis of the first 254 fulfilled Canvas Dx prescriptions post-market authorization to compare real-world accuracy to clinical reference standard and prior trial data and to describe prescriber and patient characteristics.

Among children with 54.7% autism prevalence, the device showed NPV 97.6% and PPV 92.4%, with determinate sensitivity 99.1% and specificity 81.6%, and a median age of 37.2 months for positive outputs.
sources:
- peer_reviewed | Scientific Reports | https://doi.org/10.1038/s41598-025-15575-8 | 2025-08-12
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

df1c312d6c533d218f9aefc48383aa29c301e1f89408ca06307344897c146958

previous

0000000000000000000000000000000000000000000000000000000000000000