This page was translated automatically from Turkish. Read the original

This page is an AI-assisted Turkish summary of the study presented at the 26th World Congress of Psychiatry. The study belongs to the presenting authors; please refer to the original source when citing it.

EV0183

E-PosterDigital Psychiatry and Artificial IntelligenceRetrospective study

Comorbidity-based clustering of adults with autism spectrum disorder using self-organizing maps applied to routine mental health diagnoses

COMORBIDITY BASED CLUSTERING OF ADULTS WITH AUTISM SPECTRUM DISORDER USING SELF ORGANIZING MAPS APPLIED TO ROUTINE MENTAL HEALTH DIAGNOSES

Presenter: Jordi Rodeiro-Boliart

Country: Spain

Institution: Institut de Recerca Sant Joan de Déu

Four clinically interpretable comorbidity clusters were identified in autistic adults using self-organizing maps based on routine clinical diagnoses.

The study aimed to classify adults with autism spectrum disorder (ASD) into clinically meaningful subgroups using routinely collected mental health diagnoses. This retrospective study examined the period from May 9, 2017, to July 10, 2025, at Parc Sanitari Sant Joan de Deu; the sample consisted of adults over 18 years of age with a clinician-assigned diagnosis of ASD (ICD-10 F84.x) (N = 927). The data source comprised diagnoses from the ICD-10 F, Q, and Z chapters extracted from routine clinical records; diagnoses were coded as present or absent, multiple episodes of the same diagnosis were counted once, and ASD codes were excluded to prevent trivial clustering. Self-organizing maps (SOM) were used to group patients according to similarities in their comorbidity profiles, yielding a four-cluster solution. Patients with no recorded comorbidities were excluded from clustering and described separately. The identified clusters were a mood, anxiety, and personality disorder cluster (25.6%), an intellectual disability and childhood-onset disorders cluster (23.1%), a predominantly psychotic cluster (15.7%), and a predominantly anxiety cluster (15.6%). Approximately 20% of individuals had no recorded mental health diagnosis. The authors suggest that these profiles, ranging from neurodevelopmental profiles to psychotic and internalizing presentations, may inform individualized assessment, the prioritization of follow-up needs, and treatment planning.

View the original poster

How to cite this study

APA 7: Rodeiro-Boliart, J., Olaya, B., Golobardes, E., & Huerta-Ramos, E. (2026, September 23-26). Comorbidity based clustering of adults with autism spectrum disorder using self organizing maps applied to routine mental health diagnoses [E-poster]. 26th WPA World Congress of Psychiatry (WCP 2026), Stockholm, Sweden. https://cslide.ctimeetingtech.com/wcp26/attendee/eposter/file/57

Vancouver: Rodeiro-Boliart J, Olaya B, Golobardes E, Huerta-Ramos E. Comorbidity based clustering of adults with autism spectrum disorder using self organizing maps applied to routine mental health diagnoses [e-poster]. 26th WPA World Congress of Psychiatry (WCP 2026); 2026 Sep 23-26; Stockholm, Sweden. Available from: https://cslide.ctimeetingtech.com/wcp26/attendee/eposter/file/57

Author names and title formatting were generated automatically from the congress system; please check them against the original poster before use.

All WCP 2026 summaries

Sitenin son güncellemesi: 8 Kasım 2026 · Site editörü: Doç. Dr. Alişan Burak Yaşar, info@alisanburak.com