Onto-clust - A methodology for combining clustering analysis and ontological methods for identifying groups of comorbidities for developmental disorders

Children with developmental disorders usually exhibit multiple developmental problems (comorbidities). Hence, such diagnosis needs to revolve on developmental disorder groups. Our objective is to systematically identify developmental disorder groups and represent them in an ontology. We developed a methodology that combines two methods (1) a literature-based ontology that we created, which represents developmental disorders and potential developmental disorder groups, and (2) clustering for detecting comorbid developmental disorders in patient data. The ontology is used to interpret and improve clustering results and the clustering results are used to validate the ontology and suggest directions for its development. We evaluated our methodology by applying it to data of 1175 patients from a child development clinic. We demonstrated that the ontology improves clustering results, bringing them closer to an expert generated gold-standard. We have shown that our methodology successfully combines an ontology with a clustering method to support systematic identification and representation of developmental disorder groups.

[1]  Alfred Ultsch,et al.  Knowledge Extraction from Artificial Neural Networks and Applications , 1993, Transputer-Anwender-Treffen.

[2]  Orly Manor,et al.  Developmental Right-Hemisphere Syndrome , 1995, Journal of learning disabilities.

[3]  Tristram H. Smith,et al.  A Review of Subtyping in Autism and Proposed Dimensional Classification Model , 2001, Journal of autism and developmental disorders.

[4]  J. Piek,et al.  Sensory-motor deficits in children with developmental coordination disorder, attention deficit hyperactivity disorder and autistic disorder. , 2004, Human movement science.

[5]  Steffen Staab,et al.  Text clustering based on good aggregations , 2001, Proceedings 2001 IEEE International Conference on Data Mining.

[6]  Anil K. Jain,et al.  Data clustering: a review , 1999, CSUR.

[7]  Syed Sibte Raza Abidi,et al.  Analyzing Sub-Classifications of Glaucoma via SOM Based Clustering of Optic Nerve Images , 2005, MIE.

[8]  Henrik Eriksson,et al.  The evolution of Protégé: an environment for knowledge-based systems development , 2003, Int. J. Hum. Comput. Stud..

[9]  Michael A. Siani-Rose,et al.  A Knowledge-Based Clustering Algorithm Driven by Gene Ontology , 2004, Journal of biopharmaceutical statistics.

[10]  M. Ashburner,et al.  Gene Ontology: tool for the unification of biology , 2000, Nature Genetics.

[11]  C. Lindberg.  The Unified Medical Language System (UMLS) of the National Library of Medicine. , 1990, Journal.

[12]  Jiong Yang,et al.  A framework for ontology-driven subspace clustering , 2004, KDD.

[13]  Tommy W. S. Chow,et al.  Clustering of the self-organizing map using a clustering validity index based on inter-cluster and intra-cluster density , 2004, Pattern Recognit..

[14]  P. Törönen,et al.  Analysis of gene expression data using self‐organizing maps , 1999, FEBS letters.

[15]  Hagit Shatkay,et al.  Using Cluster Ensemble and Validation to Identify Subtypes of Pervasive Developmental Disorders , 2007, AMIA.

[16]  D. Steinley.  Properties of the Hubert-Arabie adjusted Rand index. , 2004, Psychological methods.

[17]  Latifur Khan,et al.  Automatic Ontology Derivation Using Clustering for Image Classification , 2002, Multimedia Information Systems.

[18]  M. V. Velzen,et al.  Self-organizing maps , 2007 .

[19]  Natalya F. Noy,et al.  The evo-lution of Prot'eg'e: An environment for knowledge-based sys-tems development , 2002 .

[20]  C. Gillberg,et al.  Deficits in attention, motor control, and perception: a brief review , 2003, Archives of disease in childhood.

[21]  P. Wilson,et al.  Practitioner review: approaches to assessment and treatment of children with DCD: an evaluative review. , 2005, Journal of child psychology and psychiatry, and allied disciplines.

[22]  K. Marx,et al.  Applications of Machine Learning and High‐Dimensional Visualization in Cancer Detection, Diagnosis, and Management , 2004, Annals of the New York Academy of Sciences.

[23]  S. Lek,et al.  Applications of artificial neural networks for patterning and predicting aquatic insect species richness in running waters , 2003 .

[24]  G. W. Milligan,et al.  A Study of the Comparability of External Criteria for Hierarchical Cluster Analysis. , 1986, Multivariate behavioral research.

[25]  Mats Wallin,et al.  Cerebral microdialysis of patients with severe traumatic brain injury exhibits highly individualistic patterns as visualized by cluster analysis with self-organizing maps* , 2004, Critical care medicine.

[26]  Pádraig Cunningham,et al.  Ontology Discovery for the Semantic Web Using Hierarchical Clustering , 2002 .

[27]  L. Rescorla,et al.  Cluster analytic identification of autistic preschoolers , 1988, Journal of autism and developmental disorders.

[28]  David G. Elliman,et al.  Automatic Derivation of On-line Document Ontologies , 2001 .

[29]  Hannu Kauppinen,et al.  EXPERIMENTS WITH SOM BASED INSPECTION OF WOOD , 2001 .

[30]  Urska Cvek,et al.  High-Dimensional Visualizations , 2002 .

[31]  Illhoi Yoo,et al.  Clustering Ontology-enriched Graph Representation for Biomedical Documents based on Scale-Free Network Theory , 2006, 2006 3rd International IEEE Conference Intelligent Systems.

[32]  D. Lindberg,et al.  The Unified Medical Language System , 1993, Methods of Information in Medicine.

[33]  D. Chen,et al.  Breast cancer diagnosis using self-organizing map for sonography. , 2000, Ultrasound in medicine & biology.

[34]  Tsvi Kuflik,et al.  Creating Consistent Diagnoses List for Developmental Disorders Using UMLS , 2006, NGITS.

[35]  Robert W Platt,et al.  Motor function at school age in children with a preschool diagnosis of developmental language impairment. , 2005, The Journal of pediatrics.