Sequence Mining of Comorbid Neurodevelopmental Disorders Using the SPADE Algorithm^[*]

Summary

Objectives: Understanding the progression of comorbid neurodevelopmental disorders (NDD) during different critical time periods may contribute to our comprehension of the underlying pathophysiology of NDDs. The objective of our study was to identify frequent temporal sequences of developmental diagnoses in noisy patient data.

Methods: We used a data set of 2810 patients, documenting NDD diagnoses given to them by an NDD expert at a child developmental center during multiple visits at different ages. Extensive preprocessing steps were developed in order to allow the data set to be processed by an efficient sequence mining algorithm (SPADE).

Results: The discovered sequences were validated by cross validation for 10 iterations; all correlation coefficients for support, con -fidence and lift measures were above 0.75 and their proportions were similar. No significant differences between the distributions of sequences were found using KolmogorovSmirnov test.

Conclusions: We have demonstrated the feasibility of using the SPADE algorithm for discovery of valid temporal sequences of co-morbid disorders in children with NDDs. The identification of such sequences would be beneficial from clinical and research perspectives. Moreover, these sequences could serve as features for developing a full-fledged temporal predictive model.

Keywords

Sequence mining - SPADE - neurodevelopmental disorders - comorbidity

^* Supplementary material published on our web-site http://dx.doi.org/10.3414/ME15-01-0142

• References

• 1 Diagnostic and Statistical Manual of Mental Disorders (5th ed). 2013
• 2 Lipkin P, Schertz M. Chapter 26. Early Intervention and Its Efficacy Capute and Accardos Neurodevelopmental Disabilities in Infancy and Childhood. edn Brookes Publishing; 2008
• 3 Filipek PA, Accardo PJ, Ashwal S, Baranek GT, Cook EH, Dawson G. et al. Practice parameter: screening and diagnosis of autism. Report of the Quality Standards Subcommittee of the American Academy of Neurology and the Child Neurology Society. Neurology 2000; 55: 468-479.
• 4 American Academy of Pediatrics (AAP).. The pediatrician’s role in the diagnosis and management of autism spectrum disorder in children. Pediatrics 2001; 1221-1226.
• 5 Leyfer OT, Folstein SE, Bacalman S, Davis NO, Dinh E, Morgan J. et al. Comorbid psychiatric disorders in children with autism: interview development and rates of disorders. J Autism Dev Disord 2006; 36 (Suppl. 07) 849-861.
• 6 Taurines R, Schmitt J, Renner T, Conner AC, Warnke A, Romanos M. Developmental comorbidity in attention-deficit/hyperactivity disorder. Atten Defic Hyperact Disord 2010; 2 (Suppl. 04) 267-289.
• 7 Karmiloff-Smith A. Development itself is the key to understanding developmental disorders. Trends Cogn Sci 1998; 2 (Suppl. 10) 389-398.
• 8 Kaplan BJ, Dewey DM, Crawford SG, Wilson BN. The term comorbidity is of questionable value in reference to developmental disorders: data and theory. J Learn Disabil 2001; 34 (Suppl. 06) 555-565.
• 9 Peleg M, Asbeh N, Kuflik T, Schertz M. Onto-clust – a methodology for combining clustering analysis and ontological methods for identifying groups of comorbidities for developmental disorders. J Biomed Inform 2007; 42 (Suppl. 01) 165-175.
• 10 Schertz M, Zuk L, Green D. Long-term neurodevelopmental follow-up of children with congenital muscular torticollis. J Child Neurol 2013; 28 (Suppl. 10) 1215-1221.
• 11 O’Neill A, Schneiderman R, Rajendran K, Marks D, Halperin J, Predict A. Reliable Ratings or Reading Tea Leaves: Can Parent, Teacher, and Clinician Behavioral Ratings of Preschoolers Predict ADHD at Age Six?. Journal of Abnormal Child Psychology 2013; 42 (Suppl. 04) 623-634.
• 12 Pless M, Carlsson M, Sundelin C, Persson K. Pre-school children with developmental coordination disorder: a short-term follow-up of motor status at seven to eight years of age. Acta Paediatr 2002; 91 (Suppl. 05) 521-528.
• 13 Yang P, Lung F-W, Jong Y-J, Hsu H-Y, Chen C-C. Stability and change of cognitive attributes in children with uneven/delayed cognitive development from preschool through childhood. Res Dev Disabil 2010; 31 (Suppl. 04) 895-902.
• 14 Moskovitch R, Shahar Y. Fast time intervals mining using the transitivity of temporal relations. Knowl Inf Syst 2015; 42: 21-48.
• 15 Mörchen F. Algorithms for Time Series Knowledge Mining. Proc KDD. 2006
• 16 Sacchi L, Larizza C, Combi C, Bellazi R. Data mining with temporal abstractions: learning rules from time series. Data Min Knowledge Discovery 2007; 15: 217-247.
• 17 Patnaik D, Butler P, Ramakrishnan N, Parida L, Keller BJ, Hanauer DA. Experiences with mining temporal event sequences from electronic medical records: initial successes and some challenges. 17th ACM SIGKDD international conference on Knowledge discovery and data mining; 2011
• 18 Hrovat G, Stiglic G, Kokol P, Ojsteršek M. Contrasting temporal trend discovery for large health-care databases. Comput Methods Programs Biomed 2014; 113 (Suppl. 01) 251-257.
• 19 Zaki M. SPADE: An Efficient Algorithm for Mining Frequent Sequences. Mach Learn J 2001; 42: 31-60.
• 20 Agrawal R, Srikant R. Fast Algorithms for Mining Association Rules. Proc 20th International Conference Very Large Data Bases 1994 pp 487-499.
• 21 Buchta C, Hahsler M. arulesSequences: Mining frequent sequences. 2014 Available at: http://CRAN.R-project.org/package=arulesSequences
• 22 Asbeh N, Peleg M, Schertz M, Kuflik T, Using U. Systems Kibbutz.. Creating Consistent Diagnoses List for Developmental Disorders. In: Next Generation Information Technologies and Israel. LNCS 4032 2006: 333-336. http://mis.hevra.haifa.ac.il~morpeleg/pubs/Nuaman_NGITS_final.pdf.
• 23 Squires J, Bricker D. Ages & Stages Questionnaires. Third Edition (ASQ-3). Baltimore: Brooks Publishing; 2009. Available from: www.agesandstages.com
• 24 Coppock D. Why Lift? Information Management. 2002 Available from: http://www.information-management.com/news/columns/-5329–1.html
• 25 Allen JF. Maintaining knowledge about temporal intervals. Comm ACM 1983; 26 (Suppl. 11) 832-843.
• 26 Shahar Y. A Knowledge-based Method for Temporal Abstraction of Clinical Data [Internet]. Stanford University; 1994 p 78. Available from: http://i.stanford.edu/pub/cstr/reports/cs/tr/94/1529/CS-TR-94–1529.pdf
• 27 Lorentzos N. The Interval-extended Relational Model and Its Application to Valid Time Databases. In: Tansel AU, Clifford J, Gadia S, Segev A, Snodgrass R. (editors). Temporal Databases. Theory, Design, and Implementation. Redwood City, CA: Benjamin/Cummings; 1993. pp 67-91.
• 28 Sarda N. Extensions to SQL for Historical Databases. IEEE Trans Knowl Data Eng 1990; 2 (Suppl. 02) 220-230.
• 29 Navathe S, Ahmed R. Temporal Extensions to the Relational Model and SQL. In: Tansel A. Temporal Databases: Theory, Design, and Implementation. Benjamin/Cummings Pub; 1993. pp 92-109.
• 30 Taylor R. Interpretation of the correlation coefficient: a basic review. J Diagn Med Sonogr 1990; 6 (Suppl. 01) 35-39.
• 31 Yang P, Lung FW, Jong YJ, Hsu HY, Chen CC. Stability and change of cognitive attributes in children with uneven/delayed cognitive development from preschool through childhood. Res Dev Disabil 2010; 31 (Suppl. 04) 895-902.
• 32 Sonuga-Barke EJ, Auerbach JS, Campbell SB, Daley D, Thompson M. Varieties of preschool hyperactivity: multiple pathways from risk to disorder. Dev Sci 2005; 8 (Suppl. 02) 141-150.
• 33 Gabis L V, Tsubar NM, Leon O, Ashkenasi A, Shefer S. Assessment of Abilities and Comorbidities in Children with Cerebral Palsy. J Child Neurol 2015; 30 (Suppl. 12) 1640-1645.
• 34 Tervo RC. Identifying patterns of developmental delays can help diagnose neurodevelopmental disorders. Clin Pediatr 2006; 45 (Suppl. 06) 509-517.
• 35 Law EC, Sideridis GD, Prock LA, Sheridan MA. Attention-deficit/hyperactivity disorder in young children: predictors of diagnostic stability. Pediatrics 2014; 133 (Suppl. 04) 659-667.
• 36 Concaro S, Sacchi L, Cerra C, Fratino P, Bellazzi R. Mining health care administrative data with temporal association rules on hybrid events. Methods Inf Med 2011; 50 (Suppl. 02) 166-179.
• 37 Batal I, Fradkin D, Harrison J, Moerchen F, Hauskrecht M. Mining Recent Temporal Patterns for Event Detection in Multivariate Time Series Data. Proc Knowl Discov Data Min KDD Beijing China. 2012
• 38 Moskovitch R, Shahar Y. Classification of Multivariate Time Series via Temporal Abstraction and Time Intervals Mining. Knowl Inf Syst 2015; 45 (Suppl. 01) 35-74.
• 39 Barbaresi WJ, Colligan RC, Weaver AL, Voigt RG, Killian JM, Katusic SK. Mortality, ADHD, and psychosocial adversity in adults with childhood ADHD: a prospective study. Pediatrics 2013; 131 (Suppl. 04) 637-644.
• 40 Biederman J, Petty CR, Evans M, Small J, Faraone SV. How persistent is ADHD? A controlled 10-year follow-up study of boys with ADHD. Psychiatry Res 2010; 177 (Suppl. 03) 299-304.
• 41 Martin A. The hard work of growing up with ADHD. Am J Psychiatry 2005; 162 (Suppl. 09) 1575-1577.
• 42 Kessler RC, Adler L, Barkley R, Biederman J, Conners CK, Demler O. et al. The prevalence and correlates of adult ADHD in the United States: results from the National Comorbidity Survey Replication. Am J Psychiatry 2006; 163 (Suppl. 04) 716-723.
• 43 Webster R, Erdos C, Evans K, Majnemer A, Kehayia E. The Clinical Spectrum of Developmental Language Impairment in School-Aged Children: Language, Cognitive, and Motor Findings. Pediatrics 2006; 118 (Suppl. 05) e1541-1549.
• 44 Carlsson LH, Norrelgen F, Kjellmer L, Westerlund J, Gillberg C, Fernell E. Coexisting disorders and problems in preschool children with autism spectrum disorders. ScientificWorldJournal 2013; 213979.
• 45 Soke GN, Philofsky A, Diguiseppi C, Lezotte D, Rogers S, Hepburn S. Longitudinal changes in Scores on the Autism Diagnostic Interview – Revised (ADI-R) in pre-school children with autism: Implications for diagnostic classification and symptom stability. Autism 2011; 15 (Suppl. 05) 545-562.
• 46 Matson JL, Williams LW. The making of a field: the development of comorbid psychopathology research for persons with intellectual disabilities and autism. Res Dev Disabil 2014; 35 (Suppl. 01) 234-238.