Experiences with Modeling Composite Phenotypes in the SKELETOME Project Tudor Groza 1 , Andreas Zankl 2 , and Jane Hunter 1 1 School of ITEE, The University of Queensland, Australia tudor.groza@uq.edu.au, jane@itee.uq.edu.au 2 Bone Dysplasia Research Group UQ Centre for Clinical Research (UQCCR) The University of Queensland, Australia a.zankl@uq.edu.au Abstract. Semantic annotation of patient data in the skeletal dysplasia domain (e.g., clinical summaries) is a challenging process due to the structural and lexical differences existing between the terms used to describe radiographic findings. In this paper we propose an ontology aimed at representing the intrinsic structure of such radiographic findings in a standard manner, in order to bridge the different lexical variations of the actual terms. Furthermore, we describe and evaluate an algorithm capable of mapping concepts of this ontology to exact or broader terms in the main phenotype ontology used in the bone dysplasia domain. 1 Introduction Skeletal dysplasias represent a group of rare genetic disorders affecting the skele- tal development. Patients with such disorders suffer from complex medical issues that can be grouped into three categories: (i) clinical findings, i.e., pains in limbs; (ii) radiographic findings, i.e., bilateral arachnodactyly; (iii) genetic findings, i.e., deletion mutation in FGFR3. In a previous paper [1], we have introduced the SKELETOME project that has developed a community-driven knowledge cu- ration platform for this domain, able to capture and integrate such clinical, radiographic and genetic findings. The underlying foundation of the platform is an ontology-driven knowledge engineering cycle introduced to bridge the cur- rent knowledge about the domain and the continuously growing pool of patient cases. The cycle has two phases: (1) semantic annotation – bridging knowledge to cases – and (2) collaborative diagnosis, collaborative knowledge curation and evolution – from cases to knowledge. The semantic annotation process relies on clinical and radiographic findings grounded in Human Phenotype Ontology (HPO) [2] concepts – one of the only phenotype ontologies for rare disorders. In this paper we focus on issues associated with this semantic annotation process, and more precisely on representing, in a standard manner, radiographic findings present in X-Ray descriptions and clinical summaries. At the same time, since the phenotype knowledge in SKELETOME is modeled only via HPO con- cepts, we aim to map where possible, instances of this standard representation to P. Cudr´ e-Mauroux et al. (Eds.): ISWC 2012, Part II, LNCS 7650, pp. 82–97, 2012. c  Springer-Verlag Berlin Heidelberg 2012