PMID- 35101638
OWN - NLM
STAT- MEDLINE
DCOM- 20220510
LR  - 20220711
IS  - 1532-0480 (Electronic)
IS  - 1532-0464 (Linking)
VI  - 129
DP  - 2022 May
TI  - Predicting pharmacotherapeutic outcomes for type 2 diabetes: An evaluation of 
      three approaches to leveraging electronic health record data from multiple 
      sources.
PG  - 104001
LID - S1532-0464(22)00017-X [pii]
LID - 10.1016/j.jbi.2022.104001 [doi]
AB  - Electronic health record (EHR) data are increasingly used to develop prediction 
      models to support clinical care, including the care of patients with common 
      chronic conditions. A key challenge for individual healthcare systems in 
      developing such models is that they may not be able to achieve the desired degree 
      of robustness using only their own data. A potential solution-combining data from 
      multiple sources-faces barriers such as the need for data normalization and 
      concerns about sharing patient information across institutions. To address these 
      challenges, we evaluated three alternative approaches to using EHR data from 
      multiple healthcare systems in predicting the outcome of pharmacotherapy for type 
      2 diabetes mellitus(T2DM). Two of the three approaches, named Selecting Better 
      (SB) and Weighted Average(WA), allowed the data to remain within institutional 
      boundaries by using pre-built prediction models; the third, named Combining Data 
      (CD), aggregated raw patient data into a single dataset. The prediction 
      performance and prediction coverage of the resulting models were compared to 
      single-institution models to help judge the relative value of adding external 
      data and to determine the best method to generate optimal models for clinical 
      decision support. The results showed that models using WA and CD achieved higher 
      prediction performance than single-institution models for common treatment 
      patterns. CD outperformed the other two approaches in prediction coverage, which 
      we defined as the number of treatment patterns predicted with an Area Under Curve 
      of 0.70 or more. We concluded that 1) WA is an effective option for improving 
      prediction performance for common treatment patterns when data cannot be shared 
      across institutional boundaries and 2) CD is the most effective approach when 
      such sharing is possible, especially for increasing the range of treatment 
      patterns that can be predicted to support clinical decision making.
CI  - Copyright (c) 2022 The Author(s). Published by Elsevier Inc. All rights reserved.
FAU - Tarumi, Shinji
AU  - Tarumi S
AD  - Research and Development Group, Hitachi Ltd., Kokubunji, Tokyo, Japan. Electronic 
      address: shinji.tarumi.xs@hitachi.com.
FAU - Takeuchi, Wataru
AU  - Takeuchi W
AD  - Research and Development Group, Hitachi Ltd., Kokubunji, Tokyo, Japan.
FAU - Qi, Rong
AU  - Qi R
AD  - Gainwell Technologies, Conway, AR, USA.
FAU - Ning, Xia
AU  - Ning X
AD  - Biomedical Informatics Department, The Ohio State University, Columbus, OH, USA; 
      Computer Science and Engineering Department, The Ohio State University, Columbus, 
      OH, USA; Translational Data Analytics Institute, The Ohio State University, 
      Columbus, OH, USA.
FAU - Ruppert, Laura
AU  - Ruppert L
AD  - Center for Biomedical Informatics, Regenstrief Institute, Indianapolis, IN, USA.
FAU - Ban, Hideyuki
AU  - Ban H
AD  - Research and Development Group, Hitachi Ltd., Kokubunji, Tokyo, Japan.
FAU - Robertson, Daniel H
AU  - Robertson DH
AD  - Applied Data Sciences Center, Indiana Biosciences Research Institute, 
      Indianapolis, IN, USA.
FAU - Schleyer, Titus
AU  - Schleyer T
AD  - Center for Biomedical Informatics, Regenstrief Institute, Indianapolis, IN, USA; 
      Department of Medicine, School of Medicine, Indiana University, Indianapolis, IN, 
      USA.
FAU - Kawamoto, Kensaku
AU  - Kawamoto K
AD  - Department of Biomedical Informatics, University of Utah, Salt Lake City, UT, 
      USA.
LA  - eng
GR  - UL1 TR002529/TR/NCATS NIH HHS/United States
PT  - Journal Article
PT  - Research Support, N.I.H., Extramural
PT  - Research Support, Non-U.S. Gov't
DEP - 20220129
PL  - United States
TA  - J Biomed Inform
JT  - Journal of biomedical informatics
JID - 100970413
SB  - IM
MH  - Chronic Disease
MH  - Clinical Decision-Making
MH  - *Decision Support Systems, Clinical
MH  - *Diabetes Mellitus, Type 2/drug therapy
MH  - Electronic Health Records
MH  - Humans
OTO - NOTNLM
OT  - Artificial intelligence
OT  - Chronic disease
OT  - Clinical decision support system
OT  - Disease management
OT  - Health information interoperability
EDAT- 2022/02/02 06:00
MHDA- 2022/05/11 06:00
CRDT- 2022/02/01 05:49
PHST- 2021/10/20 00:00 [received]
PHST- 2021/12/30 00:00 [revised]
PHST- 2022/01/17 00:00 [accepted]
PHST- 2022/02/02 06:00 [pubmed]
PHST- 2022/05/11 06:00 [medline]
PHST- 2022/02/01 05:49 [entrez]
AID - S1532-0464(22)00017-X [pii]
AID - 10.1016/j.jbi.2022.104001 [doi]
PST - ppublish
SO  - J Biomed Inform. 2022 May;129:104001. doi: 10.1016/j.jbi.2022.104001. Epub 2022 
      Jan 29.