Annomalous human behavIour Detection
Brain disorders represent an enormous disease burden, in terms of human suffering and economic cost. Many brain disorders are chronic and incurable conditions that entail impairments in functioning across social, vocational and residential domains. In the AID project we will focus on two of them of higher prevalence: schizophrenia and affective disorders (depression and bipolar disease).
The avoidance of relapses increases the functional performances, but patients with brain disorders are often unaware of their disability or their symptoms. Having access to real-life and real-time monitoring of psychiatric patients will allow to identify “relapse signatures” and acute symptom triggers, and to objectively monitor the effectiveness and side effects of treatments. This monitoring method provides objective data, overcoming the limitations of self-report (including subjectivity and recall bias), and the shortcomings of external informants, such as limited reliability.
The aim of the AID project is to explore the feasibility of a method for detecting automatically the behavioral change in the beginning of a relapse of schizophrenic or affective disorder patients in ambulatory conditions by using inertial sensors. The desirable characteristics of this method are:
- to provide interpretable information,
- to be easy to personalize,
- to be able to detect on-line behavioral changes,
- to include the circadian and the calendar influence on the behavior,
- to be robust, and;
- to have a low complexity implementation.
In AID we propose to develop a Bayesian on-line changepoint detection method over the sequence of activities provided by a human activity classifier that fulfill all the above requirements. The development of the methods and the assessment of the feasibility of such a device are based on the monitoring of real patients. The whole approach represents a breakthrough in the care and monitoring of psychiatric patients.
In essence, AID project try to answer the question: are the behavioral changes detectable? Or, in other words, is the behavior predictable? If the answer is YES, the project will have great impact in the management, healthcare provision (including costs) and quality of life of patients with brain disorders. As mentioned in the introduction, if the project succeeds, the techniques can be applied to other problems like the early detection of suicide attempts. It could also have a high societal impact as it may facilitate out-of-the hospital care of patients with very prevalent brain disorders. On the other hand, It could also open the possibility of exploiting this ICT-based technology as a new professional care service.
||Annomalous human behavIour Detection
||Ministerio de Economía y Competitividad
||01-09-2015 / 31-08-2017
||Antonio Artés Rodríguez (Universidad Carlos III de Madrid)