A timely detection of the pathological mood fluctuations in bipolar disorder (BD) is crucial in establishing effective treatments, preventing adverse outcomes, and improving the overall prognosis of this severe and recurrent illness. However, the diagnosis, treatment, and assessment of BD episodes are still solely based on subjective information collected through clinical interviews, questionnaires, and scales. Thus, the criteria for prescribing medications in BD are still primarily dictated by a trial-and-error approach resulting in roughly 40% of individuals having the expected response. During these uncertain and lengthy periods, adverse outcomes are frequent (i.e., side-effects, relapses, suicide attempts).
Wearable devices are now capable of incorporating a wide array of sensors to collect digital biomarkers to gain insight into an individual's behavioral, stress and sleep patterns alongside other neurophysiological parameters.
Our mission with INTREPIBD is to identify specific illness physiological patterns based on digital biomarkers (i.e., Actigraphy, EDA, Heart rate variability) collected with a novel wearable device and to follow-up symptoms with a smartphone app. Based on this data, we also aim to determine objective digital signatures of treatment response and predicted outcomes through exploratory analyses and innovative modelling of multi-modal data powered by machine learning.
The identification of these parameters could mark a breakthrough advancement in real-world clinical practice as it will provide both clinicians and patients with the necessary objective parameters to timely detect acute episodes and determine treatment response.


  • 134

    Participants recurited

  • 219

    Sessions recorded

  • 7

    Research outputs


Selected publication and research output. All software developed are available on github.com/INTREPIBD.

  • Wearable data from subjects playing Super Mario, sitting university exams, or performing physical exercise help detect acute mood episodes via self-supervised learning
    Filippo Corponi, Bryan M. Li, Gerard Anmella, Clàudia Valenzuela-Pascual, Ariadna Mas, Isabella Pacchiarotti, Marc Valentí, Iria Grande, Antonio Benabarre, Marina Garriga, Eduard Vieta, Allan H Young, Stephen M. Lawrie, Heather C. Whalley, Diego Hidalgo-Mazzei, Antonio Vergari
    Preprint. 2023.
    [ Paper ]
  • Electrodermal activity in bipolar disorder: Differences between mood episodes and clinical remission using a wearable device in a real-world clinical setting
    Gerard Anmella, Ariadna Mas, Miriam Sanabra, Clàudia Valenzuela-Pascual, Marc Valentí, Isabella Pacchiarotti, Antoni Benabarre, Iria Grande, Michele De Prisco, Vincenzo Oliva, Giovanna Fico, Anna Giménez-Palomo, Anna Bastidas, Isabel Agasi, Allan H. Young, Marina Garriga, Filippo Corponi, Bryan M. Li, Peter de Looff, Eduard Vieta, Diego Hidalgo-Mazzei
    Journal of Affective Disorders. 2023.
    [ Paper ]
  • Exploring electrodermal activity differences during acute episodes of bipolar disorder (BD) with wearable devices
    Ariadna Mas, Miriam Sanabra, Gerard Anmella, Filippo Corponi, Bryan M. Li, Marc Valentí, Antoni Benabarre, Iria Grande, Anna Giménez-Palomo, Isabella Pacchiarotti, Anna Bastidas, Isabel Agasi, Marina Garriga, Peter de Looff, Eduard Vieta, Diego Hidalgo-Mazzei.
    36th ECNP Congress. 2023.
    [ Poster ]
  • Automated mood disorder symptoms monitoring from multivariate time-series sensory data: Getting the full picture beyond a single number
    Filippo Corponi*, Bryan M. Li*, Gerard Anmella, Ariadna Mas, Miriam Sanabra, Eduard Vieta, INTREPIBD Group, Stephen M. Lawrie, Heather C. Whalley, Diego Hidalgo-Mazzei, Antonio Vergari.
    Preprint. 2023.
    [ Paper ]
  • Exploring digital biomarkers of illness activity in mood episodes: hypotheses generating and model development study
    Gerard Anmella*, Filippo Corponi*, Bryan M. Li*, Ariadna Mas, Miriam Sanabra, Isabella Pacchiarotti, Marc Valentí, Iria Grande, Antoni Benabarre, Anna Giménez-Palomo, Marina Garriga, Isabel Agasi, Anna Bastidas, Myriam Cavero, Tabatha Fernández-Plaza, Néstor Arbelo, Miquel Bioque, Clemente García-Rizo, Norma Verdolini, Santiago Madero, Andrea Murru, Silvia Amoretti, Anabel Martínez-Aran, Victoria Ruiz, Giovanna Fico, Michele De Prisco, Vincenzo Oliva, Aleix Solanes, Joaquim Radua, Ludovic Samalin, Allan H. Young, Eduard Vieta, Antonio Vergari, Diego Hidalgo-Mazzei.
    JMIR mHealth and uHealth. 2023.
    [ Paper ] [ Code ]
  • Inferring mood disorder symptoms from multivariate time-series sensory data
    Bryan M. Li*, Filippo Corponi*, Gerard Anmella, Ariadna Mas, Miriam Sanabra, Diego Hidalgo-Mazzei, Antonio Vergari.
    NeurIPS Workshop on Learning from Time Series for Health. 2022.
    [ Paper ] [ Code ] [ Poster ]

The Team

We are a group of psychiatrists, clinicans and computer scientists interested in tackling the challenges in machine learning for mental healthcare.

  • Gerard Anmella

    Postdoctoral researcher
    Hospital Clínic de Barcelona

  • Filippo CorponiTwitter

    Data scientist
    University of Edinburgh

  • Bryan M. LiTwitter

    Data scientist
    University of Edinburgh

  • Eduard Vieta

    Project supervisor
    Hospital Clínic de Barcelona

  • Antonio VergariTwitter

    Principal investigator
    University of Edinburgh

  • Diego Hidalgo-MazzeiTwitter

    Principal investigator
    Hospital Clínic de Barcelona


This project is funded by:

This project is supported by: