PMID- 34143415
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20210721
IS  - 1869-6953 (Print)
IS  - 1869-6961 (Electronic)
IS  - 1869-6961 (Linking)
VI  - 12
IP  - 7
DP  - 2021 Jul
TI  - Electronic Medical Record Risk Modeling of Cardiovascular Outcomes Among Patients 
      with Type 2 Diabetes.
PG  - 2007-2017
LID - 10.1007/s13300-021-01096-w [doi]
AB  - INTRODUCTION: Increased utilization of electronic health records (EHR) has 
      enriched databases for creating risk models. We used machine learning techniques 
      to develop an EHR-based risk model locally fitted to patients with type 2 
      diabetes mellitus (T2DM) for predicting cardiovascular disease. METHODS: This 
      retrospective observational study was conducted within Ochsner Health, Louisiana, 
      USA, between 2013-2017. Data analysis included 6245 patients who had two 
      outpatient diagnoses of T2DM recorded on separate days or a diagnosis recorded 
      during an inpatient encounter. Baseline clinical data were limited to 180 days 
      before the index diagnosis. Cardiovascular outcomes were coronary heart disease 
      (CHD), heart failure and stroke. Machine learning approaches were used to select 
      predictor variables into Cox proportional hazards models for each outcome. 
      Locally fit equations were compared to "generalized" risk equations (RECODe, 
      AS-CVD, QRISK3) using model discrimination and calibration. RESULTS: Among 
      factors identified in the Ochsner (n = 11), RECODe (n = 14), AS-CVD (n = 15) and 
      QRISK3 (n = 23), only age was common to all four risk equations. The Ochsner 
      model had high internal discrimination for CHD (C-statistics 0.85) and better 
      discrimination than RECODe (C-statistics 0.45), the QRISK3 (C-statistics 0.72) 
      and AS-CVD (C-statistics 0.54). CONCLUSIONS: The Ochsner model overestimated 
      5-year CHD risk, but had relatively higher calibration than the other models in 
      CHD. Risk equations fitted for local populations improved cardiovascular risk 
      stratification for patients with T2DM. Application of machine learning simplified 
      the models compared to "generalized" risk equations.
FAU - Hong, Dongzhe
AU  - Hong D
AD  - Department of Health Policy and Management, Tulane University School of Public 
      Health and Tropical Medicine, New Orleans, LA, USA.
FAU - Fort, Daniel
AU  - Fort D
AD  - Center for Outcomes and Health Services Research, Ochsner Health, New Orleans, 
      LA, USA.
FAU - Shi, Lizheng
AU  - Shi L
AD  - Department of Health Policy and Management, Tulane University School of Public 
      Health and Tropical Medicine, New Orleans, LA, USA.
FAU - Price-Haywood, Eboni G
AU  - Price-Haywood EG
AUID- ORCID: 0000-0003-2901-3852
AD  - Center for Outcomes and Health Services Research, Ochsner Health, New Orleans, 
      LA, USA. eboni.pricehaywood@ochsner.org.
AD  - University of Queensland Ochsner Clinical School, New Orleans, LA, USA. 
      eboni.pricehaywood@ochsner.org.
LA  - eng
PT  - Journal Article
DEP - 20210618
PL  - United States
TA  - Diabetes Ther
JT  - Diabetes therapy : research, treatment and education of diabetes and related 
      disorders
JID - 101539025
PMC - PMC8266923
OTO - NOTNLM
OT  - Cardiovascular disease
OT  - Cerebrovascular stroke
OT  - Diabetes
OT  - Heart failure
OT  - Machine learning
OT  - Type 2 diabetes mellitus
EDAT- 2021/06/19 06:00
MHDA- 2021/06/19 06:01
PMCR- 2021/06/18
CRDT- 2021/06/18 12:30
PHST- 2021/04/27 00:00 [received]
PHST- 2021/06/05 00:00 [accepted]
PHST- 2021/06/19 06:00 [pubmed]
PHST- 2021/06/19 06:01 [medline]
PHST- 2021/06/18 12:30 [entrez]
PHST- 2021/06/18 00:00 [pmc-release]
AID - 10.1007/s13300-021-01096-w [pii]
AID - 1096 [pii]
AID - 10.1007/s13300-021-01096-w [doi]
PST - ppublish
SO  - Diabetes Ther. 2021 Jul;12(7):2007-2017. doi: 10.1007/s13300-021-01096-w. Epub 
      2021 Jun 18.