Early Detection of Generalized Anxiety Disorder Using a Virtual Assistant: Predictive Analysis of Symptomatology Based on Machine Learning
DOI:
https://doi.org/10.70577/asce.v5i2.866Keywords:
Artificial intelligence, Mental health, Psychotherapy, Educational technology, Computer programming, Diagnosis.Abstract
This research was born from the purpose of developing and testing "Maya," a virtual assistant designed to support the early detection of Generalized Anxiety Disorder (GAD). In this context, we understood early detection not merely as a technical diagnosis, but as a vital opportunity to identify red flags and thought patterns before anxiety became overwhelming for the patient, thus creating a bridge toward professional help.
To bring this tool to life, we merged psychology and technology in a profound way. We integrated the foundations of Cognitive Behavioral Therapy (CBT) through dialogues that guided users in questioning their own thoughts, serving as a safe space for digital self-reflection. Furthermore, the ability of GPT-3.5 models to identify symptoms was no mere coincidence; it was based on a semantic analysis logic capable of recognizing the "language of anxiety." The model successfully interpreted specific linguistic markers, such as constant rumination and the tendency to imagine catastrophic scenarios, translating these natural expressions into clear clinical indicators.
The evaluation process was a shared experience between technology, a clinical psychology expert, and 50 individuals who interacted with the assistant. The results were deeply human: the System Usability Scale (SUS) reached 84%, reflecting an excellent reception. Most importantly, 96% of users felt their symptoms were understood with accuracy, while 98% found comfort and guidance in the suggested coping strategies. ultimately, "Maya" proved to be a warm and accessible support resource, focused on emotional education and preventive triage, always aiming to complement the specialist's work, never to replace it.
Downloads
References
Barcos Andradez, A. O. (2023). Desarrollo de un prototipo de asistente virtual como herramienta de apoyo en el proceso de Aprendizaje. https://repositorio.ug.edu.ec/search?query=barco%20andradez
Brooke, J. (1996). SUS: A quick and dirty usability scale. En P. W. Jordan, B. Thomas, B. A. Weerdmeester, & I. L. McClelland (Eds.), Usability evaluation in industry (pp. 189–194). Taylor & Francis. https://www.researchgate.net/publication/228593520_SUS_A_quick_and_dirty_usability_scale
Camargo, L., Herrera-Pino, J., Shelach, S., Soto-Añari, M., Porto, M. F., & Alonso, M. (2023). Escala de ansiedad generalizada GAD-7 en profesionales médicos colombianos durante pandemia de COVID-19: Validez de constructo y confiabilidad. Revista Colombiana de Psiquiatría, 52(3), 245–250. https://www.elsevier.es/en-revista-revista-colombiana-psiquiatria-english-edition--479-pdf-S2530312023000504
Chieng Cueva, A. I., & Medina Aguirre, G. E. (2022). Evaluación de trastornos mentales de ansiedad y depresión vía chatbot. https://repositorio.ulima.edu.pe/handle/20.500.12724/16335
Franco Chóez, X. E., et al. (2021). Claves para el tratamiento de la ansiedad en tiempos de COVID-19. Revista Universidad y Sociedad, 13(3), 456–465. http://scielo.sld.cu/scielo.php?script=sci_arttext&pid=S2218-36202021000300271
Hollis, C., Morriss, R., Martin, J., Amani, S., Cotton, R., Denis, M., & Lewis, S. (2015). Technological innovations in mental healthcare: Harnessing the digital revolution. The British Journal of Psychiatry, 206(4), 263–265. https://doi.org/10.1192/bjp.bp.113.142612
Liu, H., Peng, H., Song, X., Xu, C., & Zhang, M. (2022). Using AI chatbots to provide self-help depression interventions for university students: A randomized trial of effectiveness. Internet Interventions, 27, 100495. https://doi.org/10.1016/j.invent.2022.100495
Muñoz, R. F., Cuijpers, P., Smit, F., Barr Taylor, C., & Simon, G. E. (2010). Prevention of major depression. Annual Review of Clinical Psychology, 6, 181–212. https://doi.org/10.1146/annurev-clinpsy-033109-132040
Pelissolo, A. (2019). Trastornos de ansiedad y fóbicos. EMC - Tratado de Medicina, 23(1), 1–7. https://www.sciencedirect.com/science/article/abs/pii/S1636541019419983
Taylor, C. B., Ruzek, J. I., Fitzsimmons-Craft, E. E., Sadeh-Sharvit, S., & Newman, M. G. (2020). Using digital technology to reduce the prevalence of mental health disorders in populations: Time for a new approach. Journal of Medical Internet Research, 22(7), e17493. https://doi.org/10.2196/17493
World Health Organization. (2022). COVID-19 pandemic triggers 25% increase in prevalence of anxiety and depression worldwide. https://www.who.int/news/item/02-03-2022-covid-19-pandemic-triggers-25-increase-in-prevalence-of-anxiety-and-depression-worldwide
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Ingrid Angélica García Torres , Oswaldo Orlando Aráuz Arroyo , Maria Katherine Mora Barzola , Maria Fernanda Peñafiel Cox
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Eres libre de:
- Compartir : copiar y redistribuir el material en cualquier medio o formato
- Adaptar : remezclar, transformar y desarrollar el material
- El licenciante no puede revocar estas libertades siempre y cuando usted cumpla con los términos de la licencia.
En los siguientes términos:
- Atribución : Debe otorgar el crédito correspondiente , proporcionar un enlace a la licencia e indicar si se realizaron cambios . Puede hacerlo de cualquier manera razonable, pero no de ninguna manera que sugiera que el licenciante lo respalda a usted o a su uso.
- No comercial : no puede utilizar el material con fines comerciales .
- CompartirIgual — Si remezcla, transforma o construye sobre el material, debe distribuir sus contribuciones bajo la misma licencia que el original.
- Sin restricciones adicionales : no puede aplicar términos legales ni medidas tecnológicas que restrinjan legalmente a otros hacer algo que la licencia permite.
