Health care is in need of innovation. Embracing new technologies and changing mind-set will establish new demand for prevention, diagnosis, monitoring and treatment. Given the ever increasing economic pressures to transform health-care system(s) resides possibly with improved Digital-Health platforms in its many different incantations to meet requirements pertaining to, e.g., active and assisted living or dealing with objective diagnoses of neuro-pathologies. Our technology based on interdisciplinary effort constitutes a fundamental step beyond the state-of-art that resides with the demonstration that a number of behavioural data, i.e. those time-series that can be obtained by non-invasive sensing over long periods of time, provide a framework that allow for analyses of behavioural patterns similar to measurements over time of temperature or blood pressure. The complexity-based approach in combination with application of Artificial Intelligence based approach differs from anything available so far despite the fast-growing market of wearable sensors.
The combination of advanced microelectronics and high-level mathematics-based indexing is adding objective measures to subjective evaluations based on point observations or questionnaires provided by practitioners. Objective behavioural measures provide robust and invariant evaluations of individual behavioural states and their changes over time. This approach is aimed at elderly to provide early diagnoses as well as at emotional workplaces to diagnose, e.g., stress levels.
Behavioural Monitoring System based on years of research Cassiopée Applied Analytical Solutions, Ltd., provides IoT/AI based computational eco-system yielding data-driven solutions to health care-givers to let them embrace a more patient-centric health care focus on prevention, diagnostics through wearables and sensors that improve acuity, improve efficiency and allow patient health to be monitored more effectively in a real time.
Our fundamental technology is based on the fact that number of behavioural surrogates, i.e., those time-series that can be obtained by non-invasive sensing over long periods of time,
posses self-similarity and scaling properties that allow for clinical applications of behavioural complexity indexing similar to measurements over time of temperature or blood pressure.
The complexity-based approach differs from anything available so far on the fast growing market of wearable sensors.