PMID- 29990022
OWN - NLM
STAT- MEDLINE
DCOM- 20190225
LR  - 20190225
IS  - 2168-2208 (Electronic)
IS  - 2168-2194 (Linking)
VI  - 22
IP  - 6
DP  - 2018 Nov
TI  - Predicting High-Cost Patients at Point of Admission Using Network Science.
PG  - 1970-1977
LID - 10.1109/JBHI.2017.2783049 [doi]
AB  - Data mining models for high-cost patient encounter prediction at the 
      point-of-admission (HPEPP) in inpatient wards are scarce in the literature. This 
      is due to the lack of availability of relevant features at such an early stage of 
      treatment. In this study, we create a disease co-occurrence network (DCN) using a 
      subset of the state inpatient database of Arizona. We explore this network for 
      community formation and structural properties to create new input features for 
      HPEPP models. Tree-based data mining models are trained using input feature sets 
      including these new network features, and distinct disease communities in the DCN 
      are identified. We propose community membership and high-cost propensity scores 
      as two network-based features for HPEPP modeling. We compare the performance of 
      models with different input feature sets and find that the new features 
      significantly improve the accuracy sensitivity and specificity of prediction 
      models. This model has the potential to improve targeted care management and 
      reduce health care expenditure.
FAU - Srinivasan, Karthik
AU  - Srinivasan K
FAU - Currim, Faiz
AU  - Currim F
FAU - Ram, Sudha
AU  - Ram S
LA  - eng
PT  - Journal Article
DEP - 20171213
PL  - United States
TA  - IEEE J Biomed Health Inform
JT  - IEEE journal of biomedical and health informatics
JID - 101604520
SB  - IM
MH  - Adolescent
MH  - Adult
MH  - Child
MH  - Child, Preschool
MH  - Chronic Disease
MH  - Electronic Health Records
MH  - Female
MH  - Health Care Costs/*statistics & numerical data
MH  - Hospitalization/*economics/*statistics & numerical data
MH  - Humans
MH  - Infant
MH  - Infant, Newborn
MH  - Male
MH  - Medical Informatics/*methods
MH  - Middle Aged
MH  - *Models, Statistical
MH  - Young Adult
EDAT- 2018/07/11 06:00
MHDA- 2019/02/26 06:00
CRDT- 2018/07/11 06:00
PHST- 2018/07/11 06:00 [pubmed]
PHST- 2019/02/26 06:00 [medline]
PHST- 2018/07/11 06:00 [entrez]
AID - 10.1109/JBHI.2017.2783049 [doi]
PST - ppublish
SO  - IEEE J Biomed Health Inform. 2018 Nov;22(6):1970-1977. doi: 
      10.1109/JBHI.2017.2783049. Epub 2017 Dec 13.