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 language | English |
|---|---|
| Pages (from-to) | 136-147 |
| Number of pages | 12 |
| Journal | Journal of Biomedical Informatics |
| Volume | 66 |
| DOIs | |
| Publication status | Published - Feb 1 2017 |
Fingerprint
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 journal › Article
}
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 -