Evidence map›Paper›PMID 39954218›Full record

Trial reportJournal of autism and developmental disorders2026

Using Artificial Intelligence to Improve Empathetic Statements in Autistic Adolescents and Adults: A Randomized Clinical Trial.

Lynn Kern Koegel, Elizabeth Ponder, Tommy Bruzzese, Mason Wang, Sina J Semnani, Nathan Chi, Brittany L Koegel, Tzu Yuan Lin, Ankush Swarnakar, Monica S Lam

Abstract readRandomized Controlled Trial
In one paragraph

Trial report in Journal of autism and developmental disorders, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 8 papers, 1 of them a synthesis that pooled it.

0numbers the graph read from it
0cells of the map it votes in
8citing papers in PubMed, 1 pooled it
–field-weighted citation impact
1 · What the graph read from it

What it found

Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.

The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.

2 · The registry

The trial behind it

Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.

Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.

3 · Its place in the literature

Who cites it

8 citing papers in PubMed, 1 synthesis or guideline pooled it.

  1. Pooled it
  2. Review
  3. Article
  4. Review
  5. Review
  6. Article
  7. Article
  8. Article
4 · The record

Corrections and comments

PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.

5 · Who and what money

Authors and funding

10 authors.

Lynn Kern KoegelDepartment of Psychiatry and Behavioral Sciences, Stanford University School of Medicine, Stanford, CA, USA. Lynnk@Stanford.edu.ORCID http://orcid.org/0000-0002-4758-6841
Elizabeth PonderDepartment of Psychiatry and Behavioral Sciences, Stanford University School of Medicine, Stanford, CA, USA.
Tommy BruzzeseDepartment of Computer Science, Stanford University, Stanford, CA, USA.
Mason WangDepartment of Computer Science, Stanford University, Stanford, CA, USA.
Sina J SemnaniDepartment of Computer Science, Stanford University, Stanford, CA, USA.
Nathan ChiDepartment of Computer Science, Stanford University, Stanford, CA, USA.
Brittany L KoegelDepartment of Psychiatry and Behavioral Sciences, Stanford University School of Medicine, Stanford, CA, USA.
Tzu Yuan LinDepartment of Psychiatry and Behavioral Sciences, Stanford University School of Medicine, Stanford, CA, USA.
Ankush SwarnakarDepartment of Computer Science, Stanford University, Stanford, CA, USA.
Monica S LamDepartment of Computer Science, Stanford University, Stanford, CA, USA.

Funding

No grant is acknowledged in the PubMed record.

6 · The paper itself

Abstract

Challenges with social communication and social interaction are a defining characteristic of autism spectrum disorder (ASD). These challenges frequently interfere with making friendships, securing and maintaining employment, and can lead to co-occurring conditions. While face-to-face clinical interventions with trained professionals can be helpful in improving social conversation, they can be costly and are unavailable to many, particularly given the high prevalence of ASD and lack of professional training. The purpose of this study was to assess whether an AI program using a Large Language Model (LLM) would improve verbal empathetic responses during social conversation. Autistic adolescents and adults, 11-35 years of age, who were able to engage in conversation but demonstrated challenges with empathetic responses participated in this study. A randomized clinical trial design was used to assess the effects of the AI program (Noora) compared to a waitlist control group. Noora asks participants to respond to leading statements and provides feedback on their answers. In this study, participants were asked to respond to 10 statements per day 5 days per week for 4 weeks for an expected total of 200 trials. Pre- and post-intervention conversation samples were collected to assess generalization during natural conversation. Additionally pre- and post-intervention questionnaires regarding each participant's comfort during social conversation and participants' satisfaction with the AI program were collected. The results of this study demonstrated that empathetic responses could be greatly improved by using an AI program for a short period of time. Participants in the experimental group showed statistically significant improvements in empathetic responses, which generalized to social conversation, compared to the waitlist control group. Some participants in the experimental group reported improved confidence in targeted areas and most reported high levels of satisfaction with the program. These findings suggest that AI using LLMs can be used to improve empathetic responses, thereby providing a time- and cost-efficient support program for improving social conversation in autistic adolescents and adults.

Indexed as

Artificial IntelligenceAutism Spectrum DisorderAutistic DisorderEmpathySocial InteractionAdolescentAdultChildCommunicationFemaleHumansInterpersonal RelationsLarge Language ModelsMaleYoung AdultArtificial intelligenceAutisticEmpathyMachine LearningSocial communication

Identifiers

PMID39954218
PMCPMC13346298

What OpenQuestion holds

Textmetadata
LicenceCC BY-NC-ND
Read underepoch 390

Registered trials

None linked

Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.