New machine learning tool that predicts the evolution of OCD patients

The HUB Psychiatry Service and the IDIBELL Psychiatry and Mental Health group have carried out the first study that relates clinical information with long-term prognosis through machine learning.

Two-thirds of patients are resistant to standardized treatments and machine learning could contribute to their personalization.

Estudi Dr Segalas_240202_06

The OCD Unit of the Psychiatry Service of the Bellvitge University Hospital (HUB) and the Psychiatry and Mental Health group of IDIBELL have promoted the first study that builds a long-term prognosis model, based on machine learning, of patients with Obsessive Compulsive Disorder (OCD). It has done so thanks to the monitoring of patients at the center for more than a decade, which represents a step forward in the specialty: “It is a machine learning model that allows predicting the evolution of patients with OCD, through clinical variables and neuropsychological performance collected from the beginning of the follow-up,” highlights Dr. Cinto Segalàs, specialist at the HUB and IDIBELL, and principal investigator of the study.


The research, published in the Journal of Affective Disorders, also shows that two-thirds of patients are resistant to standardized treatments, such as medication, cognitive behavioral therapy or psychosurgery. Furthermore, according to the researchers, the results reinforce the idea that OCD is a chronic disease. In this context, machine learning could help facilitate more personalized therapy. Recently, there is growing interest in machine learning, a subfield of artificial intelligence, to examine data sets and create models to make predictions or make decisions by learning from the data. In the field of psychiatry, it has been used for the diagnosis of diseases, treatment predictions or detection of potential biomarkers. Some studies using machine learning have already been conducted in OCD to predict symptom remission and suicide attempts.


The study sample consisted of 134 people, 60 patients from the OCD Unit of the Bellvitge Hospital and 74 volunteers. Although the researchers call for expanding the sample and having even more reliable algorithms, they maintain that machine learning could predict the long-term outcomes of OCD patients using only basic clinical and cognitive information.


OCD, the “disease of doubt”


People who suffer from Obsessive Compulsive Disorder (OCD) experience unwanted thoughts, images or impulses (obsessions) that cause repetitive behaviors or mental actions (compulsions). These obsessions and compulsions, as well as avoidant behaviors, impact daily life activities, causing great emotional suffering. Approximately 2% of the general population develops OCD, and a specific cause is not known, although genetic and environmental factors are involved. The OCD Unit of the HUB Psychiatry Service is a reference in research on this disorder internationally and continues research to improve the quality of life of people who suffer from it.




The Bellvitge Biomedical Research Institute (IDIBELL) is a biomedical research center created in 2004. It is participated by the Bellvitge University Hospital and the Viladecans Hospital of the Catalan Institute of Health, the Catalan Institute of Oncology, the University of Barcelona and the City Council of L’Hospitalet de Llobregat.

IDIBELL is a member of the Campus of International Excellence of the University of Barcelona HUBc and is part of the CERCA institution of the Generalitat de Catalunya. In 2009 it became one of the first five Spanish research centers accredited as a health research institute by the Carlos III Health Institute. In addition, it is part of the “HR Excellence in Research” program of the European Union and is a member of EATRIS and REGIC. Since 2018, IDIBELL has been an Accredited Center of the AECC Scientific Foundation (FCAECC).


Original paper:

Cognitive and clinical predictors of a long-term course in obsessive compulsive disorder: A machine learning approach in a prospective cohort study. Segalàs C, Cernadas E, Puialto M, Fernández-Delgado M, Arrojo M, Bertolin S, Real E, Menchón JM, Carracedo A, Tubío-Fungueiriño M, Alonso P, Fernández-Prieto M. J Affect Disord. 2024 Jan 19;350:648-655. doi: 10.1016/j.jad.2024.01.157. Online ahead of print.

Share on:

Scroll to Top