Temporal electronic phenotyping by mining careflows of breast cancer patients

Arianna Dagliati, L. Sacchi, A. Zambelli, V. Tibollo, L. Pavesi, John H. Holmes, R. Bellazzi

Research output: Contribution to journalArticle

Abstract

In this work we present a careflow mining approach designed to analyze heterogeneous longitudinal data and to identify phenotypes in a patient cohort. The main idea underlying our approach is to combine methods derived from sequential pattern mining and temporal data mining to derive frequent healthcare histories (careflows) in a population of patients. This approach was applied to an integrated data repository containing clinical and administrative data of more than 4000 breast cancer patients. We used the mined histories to identify sub-cohorts of patients grouped according to healthcare activities pathways, then we characterized these sub-cohorts with clinical data. In this way, we were able to perform temporal electronic phenotyping of electronic health records (EHR) data.

Original languageEnglish
Pages (from-to)136-147
Number of pages12
JournalJournal of Biomedical Informatics
Volume66
DOIs
Publication statusPublished - Feb 1 2017

Fingerprint

Data mining
Health
Breast Neoplasms
Delivery of Health Care
Data Mining
Electronic Health Records
Phenotype
Population

Keywords

  • Careflow mining
  • Electronic phenotyping
  • Heterogeneous data sets
  • Temporal data mining

ASJC Scopus subject areas

  • Computer Science Applications
  • Health Informatics

Cite this

Temporal electronic phenotyping by mining careflows of breast cancer patients. / Dagliati, Arianna; Sacchi, L.; Zambelli, A.; Tibollo, V.; Pavesi, L.; Holmes, John H.; Bellazzi, R.

In: Journal of Biomedical Informatics, Vol. 66, 01.02.2017, p. 136-147.

Research output: Contribution to journalArticle

Dagliati, Arianna ; Sacchi, L. ; Zambelli, A. ; Tibollo, V. ; Pavesi, L. ; Holmes, John H. ; Bellazzi, R. / Temporal electronic phenotyping by mining careflows of breast cancer patients. In: Journal of Biomedical Informatics. 2017 ; Vol. 66. pp. 136-147.
@article{91d5a80303664da9b35be4c5af82c230,
title = "Temporal electronic phenotyping by mining careflows of breast cancer patients",
abstract = "In this work we present a careflow mining approach designed to analyze heterogeneous longitudinal data and to identify phenotypes in a patient cohort. The main idea underlying our approach is to combine methods derived from sequential pattern mining and temporal data mining to derive frequent healthcare histories (careflows) in a population of patients. This approach was applied to an integrated data repository containing clinical and administrative data of more than 4000 breast cancer patients. We used the mined histories to identify sub-cohorts of patients grouped according to healthcare activities pathways, then we characterized these sub-cohorts with clinical data. In this way, we were able to perform temporal electronic phenotyping of electronic health records (EHR) data.",
keywords = "Careflow mining, Electronic phenotyping, Heterogeneous data sets, Temporal data mining",
author = "Arianna Dagliati and L. Sacchi and A. Zambelli and V. Tibollo and L. Pavesi and Holmes, {John H.} and R. Bellazzi",
year = "2017",
month = "2",
day = "1",
doi = "10.1016/j.jbi.2016.12.012",
language = "English",
volume = "66",
pages = "136--147",
journal = "Journal of Biomedical Informatics",
issn = "1532-0464",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Temporal electronic phenotyping by mining careflows of breast cancer patients

AU - Dagliati, Arianna

AU - Sacchi, L.

AU - Zambelli, A.

AU - Tibollo, V.

AU - Pavesi, L.

AU - Holmes, John H.

AU - Bellazzi, R.

PY - 2017/2/1

Y1 - 2017/2/1

N2 - In this work we present a careflow mining approach designed to analyze heterogeneous longitudinal data and to identify phenotypes in a patient cohort. The main idea underlying our approach is to combine methods derived from sequential pattern mining and temporal data mining to derive frequent healthcare histories (careflows) in a population of patients. This approach was applied to an integrated data repository containing clinical and administrative data of more than 4000 breast cancer patients. We used the mined histories to identify sub-cohorts of patients grouped according to healthcare activities pathways, then we characterized these sub-cohorts with clinical data. In this way, we were able to perform temporal electronic phenotyping of electronic health records (EHR) data.

AB - In this work we present a careflow mining approach designed to analyze heterogeneous longitudinal data and to identify phenotypes in a patient cohort. The main idea underlying our approach is to combine methods derived from sequential pattern mining and temporal data mining to derive frequent healthcare histories (careflows) in a population of patients. This approach was applied to an integrated data repository containing clinical and administrative data of more than 4000 breast cancer patients. We used the mined histories to identify sub-cohorts of patients grouped according to healthcare activities pathways, then we characterized these sub-cohorts with clinical data. In this way, we were able to perform temporal electronic phenotyping of electronic health records (EHR) data.

KW - Careflow mining

KW - Electronic phenotyping

KW - Heterogeneous data sets

KW - Temporal data mining

UR - http://www.scopus.com/inward/record.url?scp=85009371764&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85009371764&partnerID=8YFLogxK

U2 - 10.1016/j.jbi.2016.12.012

DO - 10.1016/j.jbi.2016.12.012

M3 - Article

AN - SCOPUS:85009371764

VL - 66

SP - 136

EP - 147

JO - Journal of Biomedical Informatics

JF - Journal of Biomedical Informatics

SN - 1532-0464

ER -