An Ontology-Based Approach for Cerebral Palsy Diagnosis and Physical Therapy in Gaza Strip

Abstract

World Health Organization (WHO) published a factsheet in 2015 shows that over one billion people have disabilities around the world. This means 15% of world population has some forms of disability. Most of these disabilities are physical disabilities. Cerebral Palsy (CP) is one of the most complicated disabilities which is a permanent motor disorder that appears in early age and cause mental and physical disabilities. In Gaza Strip, 2.6% of population has some forms of disability. The children under 18 years with CP disability represent 3.1% of disability population in Gaza Strip. Based on domain experts, there is very little studies targeted disability doamin in Gaza Strip especially Cerebral Palsy. In addition, different reports published by governmental and non-goverenmental organizations such as Cerebral Palsy Center of Palestinian Avenir for Childhood Foundation ask for more focus on cerebral palsy disability in Gaza Strip inorder to improve diagnosis and treatment basing on the available resources in Gaza Strip. Globally, there are different studies conducted to improve and assist CP diagnosis and physical therapy treatment, most of those studies do not provide diagnosis techniques for the children in their early ages. This means that the impact and the effectiveness of physical therapy treatment may be lost because of the delay in diagnosis. So, the real need is to find an approach that diagnoses CP in early ages. In this research, we proposed an ontology based approach to diagnose children with CP in early ages, generate physical therapy planning, and assist in knowledge sharing. We used ontology to build and represent CP disability domain. Then, a set of rules has been manually built in collaboration with a domain expert. The rules have been optimized through a set of symptoms that have been weighted through a knowledge-based survey in order to be used in CP diagnosis. The proposed approach improves CP diagnosis and by cosequance positively reflects physical therapy treatment. The proposed approach was evaluated by a real dataset consisted of 70 pre-diagnosed cases, where our approach correctly diagnosed 84% of those cases.