Clinical diagnoses are reported in Electronic Medical Records (EMRs) as a code which summarizes the clinical process and health workflow of patients during their staying in health structures. Moreover, biological laboratories manage biochemical analytes (such as glycemia, bilirubin, cholesterol) as information useful for patients' clinical treatments. Often biological analyses follow standard protocols such as repetition frequency, outcomes and are considered as input for diagnosis or medical treatment definition. In this paper we process diagnosis codes and biochemical analytes of a set of 20 thousands biological analyses on a set of hospitalized patients during one observation year. We cross reference data by using a semantic-based clustering procedure, extract information from EMRs and then cluster them looking for similar patterns of diseases. Finally, biological data are related to diagnosis codes and analyzed towards areas of interest in order to map calculated outliers patients.

Relating Clinical Diagnosis and Biological Analytes via EMRs Clustering

Pietro Hiram Guzzi;Veltri Pierangelo;Cannataro M
2014-01-01

Abstract

Clinical diagnoses are reported in Electronic Medical Records (EMRs) as a code which summarizes the clinical process and health workflow of patients during their staying in health structures. Moreover, biological laboratories manage biochemical analytes (such as glycemia, bilirubin, cholesterol) as information useful for patients' clinical treatments. Often biological analyses follow standard protocols such as repetition frequency, outcomes and are considered as input for diagnosis or medical treatment definition. In this paper we process diagnosis codes and biochemical analytes of a set of 20 thousands biological analyses on a set of hospitalized patients during one observation year. We cross reference data by using a semantic-based clustering procedure, extract information from EMRs and then cluster them looking for similar patterns of diseases. Finally, biological data are related to diagnosis codes and analyzed towards areas of interest in order to map calculated outliers patients.
2014
Diseases
Unified modeling language
Medical diagnostic imaging
Data mining
Pathology
Semantics
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.11770/362557
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 0
social impact