RETRACTED: Clustering of comorbidities based on conditional probabilities of diseases in hypertensive patients

Bukhanov, N.; Balakhontceva, Marina A.; Krikunov, Alexey V.; Sabirov, A.; Semakova, A.; Звартау, Надежда; Конради, А. О.

doi:10.1016/j.procs.2017.05.073

Cited by 2 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These documents have a narrative format, which allows the health professional to write in a flexible manner. The notes contain local dialectal phrases, negations, acronyms, abbreviations, misspellings and typing errors, which combined, make it difficult to automatically extract patients' information from them [1,2].…”

Section: Introductionmentioning

confidence: 99%

“…Even automatic extraction is extremely difficult because the information sought is hidden within significant amounts of data residing in clinical notes [2]. The process of getting structured medical information requires extracting named entities or concepts and then mapping them to codes according to controlled vocabulary or medical standards [1]. Two standards used to map biomedical concepts are the Unified Medical Language System (UMLS) [3] and the Systematized Nomenclature of Medicine -Clinical Terms (SNOMED-CT) [4].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Cluster Analysis of Obesity Disease Based on Comorbidities Extracted from Clinical Notes

et al. 2019

View full text Add to dashboard Cite

Clinical notes provide a comprehensive and overall impression of the patient's health. However, the automatic extraction of information within these notes is challenging due to their narrative style. In this context, our goal was to identify clusters of patients based on fourteen comorbidities related to obesity, automatically extracted with the cTAKES tool from the i2b2 Obesity Challenge data. Furthermore, results were compared with clusters obtained from experts' annotated data. The sparse K-means algorithms were used in both experiment at two levels: at the first level, three clusters were found, and at the second, new clusters were found by applying the same algorithm to each of the clusters from the former level. The results show that three types of clusters could be identified based on the number of comorbidities and the percentage of patients suffering from them. Diabetes, hypercholesterolemia, atherosclerotic cardiovascular diseases, congestive heart failure, obstructive sleep apnea, and depression were the diseases with the highest weights contributing to the cluster distribution. Keywords Obesity . Clinical notes . cTAKES . Cluster analysisThis article is part of the Topical Collection on Transactional Processing Systems

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%