AI Science Tracker
EN

Intra-topic latency as an automated behavioral marker of treatment response in autism spectrum disorder.

Department of Psychiatry, Weill Cornell Medicine, New York, NY, USA · 28 Feb 2022 · multidisciplinary

Discovery

Intra-topic latency as an automated behavioral marker of treatment response in autism spectrum disorder.

Source check: Source checked. Not independent scientific confirmation.

Finding: Across 210 child-social-partner dyads at four sites, the treatment group showed greater pre/post reduction in child latency than the matched treatment-as-usual group (change-score difference p<0.001, d=0.43); latency also correlated with ADOS-2 calibrated severity score. Full-text Methods and Results use repeated-measures mixed models with clinical covariates and examine site effects. This was not randomized; intervention and control representation differed by site, and 46.4% of dyads had different partners across visits. Authors call for validation in controlled trials and broader populations.

Technology: A two-layer feed-forward DNN classifies speech/non-speech from MFCCs, while ASR and lexical-coherence segmentation identify conversation topics; the resulting intra-topic response latency is the studied behavioral measure.

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
A two-layer feed-forward DNN classifies speech/non-speech from MFCCs, while ASR and lexical-coherence segmentation identify conversation topics; the resulting intra-topic response latency is the studied behavioral measure.
Test and result
Across 210 child-social-partner dyads at four sites, the treatment group showed greater pre/post reduction in child latency than the matched treatment-as-usual group (change-score difference p<0.001, d=0.43); latency also correlated with ADOS-2 calibrated severity score.
Limitation / still unknown
Full-text Methods and Results use repeated-measures mixed models with clinical covariates and examine site effects. This was not randomized; intervention and control representation differed by site, and 46.4% of dyads had different partners across visits. Authors call for validation in controlled trials and broader populations.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://www.nature.com/articles/s41598-022-07299-w

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 22 Nov 2026. Review scope: The primary full text documents an automated signal-processing/ML measure of intra-topic conversational latency and a specific four-site clinical finding in 210 children with ASD. In the treatment group, child latency declined from 2.94 to 2.69 seconds while the treatment-as-usual group increased from 2.63 to 3.05 seconds; the adjusted treatment contrast remained significant. The version of record was published 2022-02-28. Exact DOI/title checks found no active or archived match. The observational, nonrandomized design and site imbalance limit causal interpretation; the result is a candidate response measure, not proof of treatment efficacy..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open in the full catalog for filters, charts and related discoveries. Browse multidisciplinary discoveries.