Analyze-Me
Software tools for processing physiological signals from patients with a non-verbal form of autism
Phase 2
Type of project: Prototype
Disability concerned: Autism and Pervasive Developmental Disorders, Mental disability, Polydisability
Topics: , Autonomy, Services and communication, Health, Interpersonal relationships
Status: In progress
The project aims to develop software for the detection and visualisation of physiological signals in patients with a non-verbal form of autism.
Patients with a non-verbal form of autism are unable to communicate with others and are at risk of developing difficult behaviours (self-aggression, hetero-aggression, shouting, destruction, motor instability). Certain behaviours, particularly self-mutilation, can be dangerous not only for the patient but also for their carers. When crises do occur, it is essential to anticipate them so as to act preventively and appropriately on the environmental conditions and thus mitigate their consequences. Knowing that verbal communication is very limited, or even impossible in some cases, it is difficult to understand the reasons for such a crisis.
It is difficult to determine whether they are an alternative way of expressing a person’s needs or whether they reflect a state of consciousness or a somatic experience, stress or pain.
The presence of stress/pain factors or harmful emotions activates a response via the sympathetic nervous system (SNS), resulting in measurable physical effects such as increased heart rate and sweating. The parasympathetic nervous system (PNS) works in concert with the SNS to activate the ‘rest and digest’ response and return the body to homeostasis after activation.
Our project aims to develop software for the detection and visualisation of SNS activation known to correlate with acute pain and stress by analysing physiological signals collected with the Empatica E4 wristband, providing measures such as electrodermal activity (EDA), blood volume pulse (BVP), temperature and 3D acceleration (ACC). This tool will extract features from the signals and provide them as input to the Deep Learning (DL) algorithm refined to classify pain/stress and predict challenging behaviours in non-verbal autistic patients.
