PMID- 26898516
OWN - NLM
STAT- MEDLINE
DCOM- 20170404
LR  - 20220316
IS  - 1532-0480 (Electronic)
IS  - 1532-0464 (Linking)
VI  - 60
DP  - 2016 Apr
TI  - Modeling healthcare data using multiple-channel latent Dirichlet allocation.
PG  - 210-23
LID - S1532-0464(16)00025-3 [pii]
LID - 10.1016/j.jbi.2016.02.003 [doi]
AB  - Information and communications technologies have enabled healthcare institutions 
      to accumulate large amounts of healthcare data that include diagnoses, 
      medications, and additional contextual information such as patient demographics. 
      To gain a better understanding of big healthcare data and to develop better 
      data-driven clinical decision support systems, we propose a novel 
      multiple-channel latent Dirichlet allocation (MCLDA) approach for modeling 
      diagnoses, medications, and contextual information in healthcare data. The 
      proposed MCLDA model assumes that a latent health status group structure is 
      responsible for the observed co-occurrences among diagnoses, medications, and 
      contextual information. Using a real-world research testbed that includes one 
      million healthcare insurance claim records, we investigate the utility of MCLDA. 
      Our empirical evaluation results suggest that MCLDA is capable of capturing the 
      comorbidity structures and linking them with the distribution of medications. 
      Moreover, MCLDA is able to identify the pairing between diagnoses and medications 
      in a record based on the assigned latent groups. MCLDA can also be employed to 
      predict missing medications or diagnoses given partial records. Our evaluation 
      results also show that, in most cases, MCLDA outperforms alternative methods such 
      as logistic regressions and the k-nearest-neighbor (KNN) model for two prediction 
      tasks, i.e., medication and diagnosis prediction. Thus, MCLDA represents a 
      promising approach to modeling healthcare data for clinical decision support.
CI  - Copyright (c) 2016 Elsevier Inc. All rights reserved.
FAU - Lu, Hsin-Min
AU  - Lu HM
AD  - Department of Information Management, College of Management, National Taiwan 
      University, Taipei 106, Taiwan. Electronic address: luim@ntu.edu.tw.
FAU - Wei, Chih-Ping
AU  - Wei CP
AD  - Department of Information Management, College of Management, National Taiwan 
      University, Taipei 106, Taiwan. Electronic address: cpwei@ntu.edu.tw.
FAU - Hsiao, Fei-Yuan
AU  - Hsiao FY
AD  - Graduate Institute of Clinical Pharmacy, College of Medicine, National Taiwan 
      University, Taipei 100, Taiwan; School of Pharmacy, College of Medicine, National 
      Taiwan University, Taipei 100, Taiwan; Department of Pharmacy, National Taiwan 
      University Hospital, Taipei 100, Taiwan. Electronic address: fyshsiao@ntu.edu.tw.
LA  - eng
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
DEP - 20160216
PL  - United States
TA  - J Biomed Inform
JT  - Journal of biomedical informatics
JID - 100970413
SB  - IM
MH  - Algorithms
MH  - Comorbidity
MH  - Data Mining
MH  - Decision Making
MH  - *Decision Support Systems, Clinical
MH  - Humans
MH  - Insurance, Health/*statistics & numerical data
MH  - Medical Informatics/*methods
MH  - Models, Theoretical
MH  - Prescriptions
MH  - Software
OTO - NOTNLM
OT  - Diagnosis prediction
OT  - Diagnosis-medication associations
OT  - Health informatics
OT  - Healthcare data mining
OT  - Medication prediction
OT  - Multiple-channel latent Dirichlet allocation
EDAT- 2016/02/24 06:00
MHDA- 2017/04/05 06:00
CRDT- 2016/02/23 06:00
PHST- 2015/09/11 00:00 [received]
PHST- 2016/01/29 00:00 [revised]
PHST- 2016/02/03 00:00 [accepted]
PHST- 2016/02/23 06:00 [entrez]
PHST- 2016/02/24 06:00 [pubmed]
PHST- 2017/04/05 06:00 [medline]
AID - S1532-0464(16)00025-3 [pii]
AID - 10.1016/j.jbi.2016.02.003 [doi]
PST - ppublish
SO  - J Biomed Inform. 2016 Apr;60:210-23. doi: 10.1016/j.jbi.2016.02.003. Epub 2016 
      Feb 16.