Juan de Dios Sanjuán-Antúnez
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Juan de Dios Sanjuán-Antúnez has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- David Delgado-Gómez
Department of Statistics, Universidad Carlos III, 28903 Getafe, Spain
1 shared publication - Elena Pérez-García
Independent Researcher, 28521 Rivas Vaciamadrid, Spain
1 shared publication - Enrique Baca-García
Department of Psychiatry, University Hospital Jimenez Diaz Foundation, Madrid, Spain
1 shared publication - Ernesto Curbelo
Departament of Statistics, School of Engineering, University Carlos III of Madrid, 28911 Leganés, Spain
1 shared publication - Hilario Blasco-Fontecilla
Institute for Transfer and Research (ITEI), International University of La Rioja (UNIR), 26006 Logroño, Spain
1 shared publication - Inmaculada Peñuelas-Calvo
Department of Child and Adolescent Psychiatry,Hospital Universitario 12 De Octubre,Madrid,Spain; Health Research Institute Hospital 12 de Octubre (i+12 Institute),Madrid,Spain; Department of Psychiatry,Universidad Complutense de Madrid,Madrid,Spain; CIBERSAM-ISCIII (Biomedical Research Networking Centre for Mental Health/Carlos III Health Institute),Madrid,Spain, Spain
1 shared publication
Latest Publications
- Open Access
Assessing Mental Health Without Relying on Psychiatric Data
Approximately one in seven people worldwide is affected by a mental disorder, making early identification crucial for preventing symptom progression and chronicity. However, diagnosis remains challenging, with discrepancies between referring physicians’ initial assessments and specialist psychiatric diagnoses reported in approximately half of cases. In recent years, machine learning has shown promising results in mental health assessment, with supervised techniques such as decision trees, random forests, and support vector machines among the most widely used approaches. However, these methods require large and representative datasets to capture the substantial heterogeneity of mental disorders, which can be difficult to obtain due to stigma, disease severity, and limited access to mental healthcare. This work investigates the feasibility of identifying mental disorders using data exclusively from a non-psychiatric population. The underlying hypothesis is that this population exhibits greater homogeneity and can therefore be characterized using a variational autoencoder with a Gaussian latent space. The proposed approach uses reconstruction errors from the non-psychiatric training population as a reference, with substantially higher errors in new observations indicating a potential mental disorder. Results show that the proposed VAE achieves performance comparable to that of the three aforementioned supervised techniques in the two dataset used. For the first dataset, the accuracy, sensitivity, specificity and ROC-AUC of the VAE were 0.88, 0.90, 0.85 and 0.95. These performance measures were 0.83, 0.86, 0.80, and 0.88 for decision trees; 0.88, 0.91, 0.85 and 0.94 for random forest; and 0.88, 0.91, 0.85 and 0.95 for support vector machines. Similar results were obtained for the second dataset. Moreover, the progressive increase in reconstruction errors across populations may reflect greater deviations from the patterns observed in the non-psychiatric population in groups with greater clinical complexity, supporting its potential use as a screening tool.
Open AccessAssessing Mental Health Without Relying on Psychiatric Data
Approximately one in seven people worldwide is affected by a mental disorder, making early identification crucial for preventing symptom progression and chronicity. However, diagnosis remains challenging, with discrepancies between referring physicians’ initial assessments and specialist psychiatric diagnoses reported in approximately half of cases. In recent years, machine learning has shown promising results in mental health assessment, with supervised techniques such as decision trees, random forests, and support vector machines among the most widely used approaches. However, these methods require large and representative datasets to capture the substantial heterogeneity of mental disorders, which can be difficult to obtain due to stigma, disease severity, and limited access to mental healthcare. This work investigates the feasibility of identifying mental disorders using data exclusively from a non-psychiatric population. The underlying hypothesis is that this population exhibits greater homogeneity and can therefore be characterized using a variational autoencoder with a Gaussian latent space. The proposed approach uses reconstruction errors from the non-psychiatric training population as a reference, with substantially higher errors in new observations indicating a potential mental disorder. Results show that the proposed VAE achieves performance comparable to that of the three aforementioned supervised techniques in the two dataset used. For the first dataset, the accuracy, sensitivity, specificity and ROC-AUC of the VAE were 0.88, 0.90, 0.85 and 0.95. These performance measures were 0.83, 0.86, 0.80, and 0.88 for decision trees; 0.88, 0.91, 0.85 and 0.94 for random forest; and 0.88, 0.91, 0.85 and 0.95 for support vector machines. Similar results were obtained for the second dataset. Moreover, the progressive increase in reconstruction errors across populations may reflect greater deviations from the patterns observed in the non-psychiatric population in groups with greater clinical complexity, supporting its potential use as a screening tool.