EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Developing an integrated algorithm to support autism diagnostic decisions: Model performance and statistical fairness

Aaron J Kaat iD, Ashlynn Campagna, Hannah Feiner, Jeffrey Michael Grauzer, Amanda Nicole Hobson, Maranda Jones, Jordan Paige Lee, Laura Jean Sudec, Megan York Roberts

JCPP Advances · 04.08.2026

DOI: 10.1002/jcv2.70157 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JCPP Advances, online erschienen am 04.08.2026. Verfasst von Aaron J Kaat und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical Social Sciences Northwestern University Feinberg School of Medicine Chicago Illinois USA. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Institute of Education Sciences.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Best practices in diagnosing autism spectrum disorder require an expert diagnostician to integrate multiple sources of information, including direct observations, interviews, and rating scales completed by knowledgeable informants. Machine learning methods are well‐positioned to integrate disparate information sources to improve classification. This study sought to evaluate whether a machine learning algorithm could support appropriately weighting multiple sources of diagnostically relevant information.

Methods

Telehealth diagnostic assessments were conducted for 639 toddlers (age mean = 30.4, SD = 4.3 months; 29.7% female) already receiving early intervention (EI). The Toddler Autism Symptom Interview (TASI) and the TELE‐ASD‐PEDS (TAP) were completed during separate visits. Each child's caregivers and usual EI providers asynchronously completed rating scales of autistic characteristics developed for this study. Calibration and validation data subsets were created using a 2:1 split. The optimal algorithm was developed using elastic net regularized regression in the calibration dataset, which was then evaluated in the validation dataset. Statistical fairness criteria evaluated whether the proposed algorithm functioned similarly across multiple protected group statuses.

Results

The prevalence of autism in the sample was 80.4%. The algorithm developed in the calibration dataset included both the caregiver‐ and EI provider‐completed rating scales, four items from the TASI, and six items from the TAP. Model performance was high in both the calibration and validation samples (sensitivity >0.90; specificity >0.75; kappa >0.60), but statistical fairness criteria varied. False positives were relatively rare, but were more common in advantaged groups, which may suggest systematic under‐classification by the algorithm in minoritized groups.

Conclusion

Diagnostic practices for autism require integrating multiple sources of information. Machine learning can support diagnosticians in this effort, as demonstrated here utilizing multiple rating scales, the TASI, and the TAP. However, there is a risk for bias when using machine learning and as such, no algorithm should replace expert clinical judgment.

Schlagwörter

Stichwörter der Autor:innen

TELE‐PEDS‐ASDautismelastic net regressionmachine learningtoddler autism symptom interview

Autor:innen und Institutionen

  • Department of Medical Social Sciences Northwestern University Feinberg School of Medicine Chicago Illinois USA.
  • Institute for Innovations in Developmental Sciences Northwestern University Chicago Illinois USA.
  • Communication Sciences and Disorders Northwestern University School of Communication Evanston Illinois USA.

ORCID-Profile: Aaron J Kaat

Förderung

  • Institute of Education Sciences

Zitieren

APA

Kaat, A. J., Campagna, A., Feiner, H., Grauzer, J. M., Hobson, A. N., Jones, M., Lee, J. P., Sudec, L. J., & Roberts, M. Y. (2026). Developing an integrated algorithm to support autism diagnostic decisions: Model performance and statistical fairness. JCPP Advances. https://doi.org/10.1002/jcv2.70157

Vancouver

Kaat AJ, Campagna A, Feiner H, Grauzer JM, Hobson AN, Jones M, et al. Developing an integrated algorithm to support autism diagnostic decisions: Model performance and statistical fairness. JCPP Advances. 2026. doi:10.1002/jcv2.70157

BibTeX
@article{Kaat2026,
  author = {Kaat, Aaron J and Campagna, Ashlynn and Feiner, Hannah and Grauzer, Jeffrey Michael and Hobson, Amanda Nicole and Jones, Maranda and Lee, Jordan Paige and Sudec, Laura Jean and Roberts, Megan York},
  title = {Developing an integrated algorithm to support autism diagnostic decisions: Model performance and statistical fairness},
  journal = {JCPP Advances},
  year = {2026},
  doi = {10.1002/jcv2.70157}
}
Kostenlos starten →