Linking glycemic dysregulation in diabetes to symptoms, comorbidities, and genetics through EHR data mining

• Published in: eLife 2019-12, Vol.8
• Main Authors: Kirk, Isa Kristina, Simon, Christian, Banasik, Karina, Holm, Peter Christoffer, Haue, Amalie Dahl, Jensen, Peter Bjødstrup, Juhl Jensen, Lars, Rodríguez, Cristina Leal, Pedersen, Mette Krogh, Eriksson, Robert, Andersen, Henrik Ullits, Almdal, Thomas, Bork-Jensen, Jette, Grarup, Niels, Borch-Johnsen, Knut, Pedersen, Oluf, Pociot, Flemming, Hansen, Torben, Bergholdt, Regine, Rossing, Peter, Brunak, Søren
• Format: Article
• Language: English
• Subjects: Adolescent; Adult; Aged; Aged, 80 and over; Algorithms; Child; Codes; Cohort Studies; comorbidities; Comorbidity; Computational and Systems Biology; Data Mining; Denmark - epidemiology; Diabetes; Diabetes Complications - diagnosis; Diabetes Complications - epidemiology; Diabetes Complications - genetics; Diabetes Complications - therapy; Diabetes mellitus; Diabetes Mellitus - diagnosis; Diabetes Mellitus - epidemiology; Diabetes Mellitus - genetics; Diabetes Mellitus - therapy; diabetes subtypes; EHR; Electronic Health Records; Electronic medical records; Epidemiology and Global Health; Female; genotyping; Humans; Insulin; Male; Medical records; Middle Aged; Patients; Phenotypic variations; Physiology; Risk Factors; Single-nucleotide polymorphism; Terminology as Topic; text mining; Treatment Outcome; Vocabulary; Young Adult
• ISSN: 2050-084X; 2050-084X
• DOI: 10.7554/eLife.44941

Diabetes is a diverse and complex disease, with considerable variation in phenotypic manifestation and severity. This variation hampers the study of etiological differences and reduces the statistical power of analyses of associations to genetics, treatment outcomes, and complications. We address these issues through deep, fine-grained phenotypic stratification of a diabetes cohort. Text mining the electronic health records of 14,017 patients, we matched two controlled vocabularies (ICD-10 and a custom vocabulary developed at the clinical center Steno Diabetes Center Copenhagen) to clinical narratives spanning a 19 year period. The two matched vocabularies comprise over 20,000 medical terms describing symptoms, other diagnoses, and lifestyle factors. The cohort is genetically homogeneous (Caucasian diabetes patients from Denmark) so the resulting stratification is not driven by ethnic differences, but rather by inherently dissimilar progression patterns and lifestyle related risk factors. Using unsupervised Markov clustering, we defined 71 clusters of at least 50 individuals within the diabetes spectrum. The clusters display both distinct and shared longitudinal glycemic dysregulation patterns, temporal co-occurrences of comorbidities, and associations to single nucleotide polymorphisms in or near genes relevant for diabetes comorbidities.