Mining comorbidity patterns using retrospective analysis of big collection of outpatient records

• DOI: 10.1007/s13755-017-0024-y
• Publication Date: 2017-09-28T21:16:24Z
• Authors: Svetla Boytcheva; Galia Angelova; Zhivko Angelov; Dimitar Tcharaktc...
• Keywords: Identification; Reimbursement

Abstract Background Studying comorbidities of disorders is important for detection and prevention. For discovering frequent patterns diseases we can use retrospective analysis population data, by filtering events with common properties similar significance. Most pattern mining methods do not consider contextual information about extracted patterns. Further data developments might enable more efficient applications in specific tasks like identification. Methods We propose a cascade approach enriched context information, including new algorithm MIxCO maximal mining. Text tools extract entities from free text deliver additional attributes beyond the structured patients. Results The proposed was tested using pseudonymised reimbursement requests (outpatient records) submitted to Bulgarian National Health Insurance Fund 2010–2016 than 5 million citizens yearly. Experiments were run on 3 collections. Some known Schizophrenia, Hyperprolactinemia Diabetes Mellitus Type 2 are confirmed; novel hypotheses stable generated. evaluation shows that big dense datasets. Conclusion Explicating itemsets enables build concerning relationships between exogeneous endogeneous factors triggering formation these sets. MixCO will help identify risk groups patients predisposition develop socially-significant diabetes. This turn static archives Register Bulgaria powerful alerting predictive framework.