Bipolar Disorder


Cassiopée introduces biomarkers able to differentiate between pathogenic processes (manic, mixed, depressed episode) and the euthymic phase in Bipolar Disorder (BD) with the aim to detect responses to therapeutical intervention(s) of patients using non-disruptive sensory wearables resulting in improved conditions of patients due to prediction of manic states occurrence.

Impacts on Patients’ Quality of Life

We strive to objectively differentiate the phases of bipolar disorder in order to detect therapeutical response or relapse and to identify bipolar disorder subtype(s). The “predictive” adjective is meant to indicate the possibility to monitor fine changes during treatment yielding a personalized approaches to BD. The predictive tool BD application of Cassiopée allows to treat the patient early in the episode(s) resulting in lesser functional impact on patients, and to avoid some side-effects of BD. For more detailed outline of the theory see, e.g., Publications.

Solution: Predictive Mental Health Evolution Tool

Cassiopée Applied Analytical Systems introduces tool predicting changes of mental health, in particular Bipolar Disorder and/or schizophrenia. The collection of tools provide early warning of, e.g., manic relapses. The system is based on advance wearable bio-sensors and high level mathematical models including Machine Learning based classification and/or optimized stochastic extrapolation of surrogate sensory time sequences. In shor, Cassiopée provides diagnose BD with a multi-modal sensory approach providing multi-dimensional time-series that we project on multi-fractal complexity space(s) to track subtle behavioral and physiological changes.

Prediction of Bipolar Disorder Evolution Impact

Uncovering Hidden Signals of Mania will help clinician to characterize the state and the imminent evolution of mental disorders. It is important to predict true remission and a temporary reduction in symptoms, as the latter may result in premature treatment decisions and/or discharge from the hospital, leading to relapse or exacerbation of symptoms.

For more infos and use of this diagnostic system, please, contact Cassiopée.

Complexity of Bipolar Disorder


The complexity characterization of BD states using Active-meter x-component of acceleration of a patient suffering from Bipolar Disorder. Data provided by CHUV, Department of Psychiatry, Lausanne, Switzerland.


The complexity of mental state prediction. Close to zero: mania. Close to one: depression. The data correspond to a real patiant and his/her predictied states (pink, hashed) compared to reality (blue columns).