PMID- 31671144
OWN - NLM
STAT- MEDLINE
DCOM- 20200313
LR  - 20200313
IS  - 1932-6203 (Electronic)
IS  - 1932-6203 (Linking)
VI  - 14
IP  - 10
DP  - 2019
TI  - Deep-learning-based risk stratification for mortality of patients with acute 
      myocardial infarction.
PG  - e0224502
LID - 10.1371/journal.pone.0224502 [doi]
LID - e0224502
AB  - OBJECTIVE: Conventional risk stratification models for mortality of acute 
      myocardial infarction (AMI) have potential limitations. This study aimed to 
      develop and validate deep-learning-based risk stratification for the mortality of 
      patients with AMI (DAMI). METHODS: The data of 22,875 AMI patients from the 
      Korean working group of the myocardial infarction (KorMI) registry were 
      exclusively divided into 12,152 derivation data of 36 hospitals and 10,723 
      validation data of 23 hospitals. The predictor variables were the initial 
      demographic and laboratory data. The endpoints were in-hospital mortality and 
      12-months mortality. We compared the DAMI performance with the global registry of 
      acute coronary event (GRACE) score, acute coronary treatment and intervention 
      outcomes network (ACTION) score, and the thrombolysis in myocardial infarction 
      (TIMI) score using the validation data. RESULTS: In-hospital mortality for the 
      study subjects was 4.4% and 6-month mortality after survival upon discharge was 
      2.2%. The areas under the receiver operating characteristic curves (AUCs) of the 
      DAMI were 0.905 [95% confidence interval 0.902-0.909] and 0.870 [0.865-0.876] for 
      the ST elevation myocardial infarction (STEMI) and non ST elevation myocardial 
      infarction (NSTEMI) patients, respectively; these results significantly 
      outperformed those of the GRACE (0.851 [0.846-0.856], 0.810 [0.803-0.819]), 
      ACTION (0.852 [0.847-0.857], 0.806 [0.799-0.814] and TIMI score (0.781 
      [0.775-0.787], 0.593[0.585-0.603]). DAMI predicted 30.9% of patients more 
      accurately than the GRACE score. As secondary outcome, during the 6-month 
      follow-up, the high risk group, defined by the DAMI, has a significantly higher 
      mortality rate than the low risk group (17.1% vs. 0.5%, p < 0.001). CONCLUSIONS: 
      The DAMI predicted in-hospital mortality and 12-month mortality of AMI patients 
      more accurately than the existing risk scores and other machine-learning methods.
FAU - Kwon, Joon-Myoung
AU  - Kwon JM
AD  - Department of Emergency Medicine, Mediplex Sejong Hospital, Incheon, Korea.
AD  - Artificial intelligence and big data center, Sejong medical research institute, 
      Gyeonggi, Korea.
FAU - Jeon, Ki-Hyun
AU  - Jeon KH
AUID- ORCID: 0000-0002-6277-7697
AD  - Artificial intelligence and big data center, Sejong medical research institute, 
      Gyeonggi, Korea.
AD  - Division of Cardiology, Cardiovascular Center, Mediplex Sejong Hospital, Incheon, 
      Korea.
FAU - Kim, Hyue Mee
AU  - Kim HM
AD  - Division of Cardiology, Cardiovascular Center, Mediplex Sejong Hospital, Incheon, 
      Korea.
FAU - Kim, Min Jeong
AU  - Kim MJ
AD  - Division of Cardiology, Cardiovascular Center, Mediplex Sejong Hospital, Incheon, 
      Korea.
FAU - Lim, Sungmin
AU  - Lim S
AD  - Division of Cardiology, Cardiovascular Center, Mediplex Sejong Hospital, Incheon, 
      Korea.
FAU - Kim, Kyung-Hee
AU  - Kim KH
AD  - Artificial intelligence and big data center, Sejong medical research institute, 
      Gyeonggi, Korea.
AD  - Division of Cardiology, Cardiovascular Center, Mediplex Sejong Hospital, Incheon, 
      Korea.
FAU - Song, Pil Sang
AU  - Song PS
AD  - Division of Cardiology, Cardiovascular Center, Mediplex Sejong Hospital, Incheon, 
      Korea.
FAU - Park, Jinsik
AU  - Park J
AD  - Division of Cardiology, Cardiovascular Center, Mediplex Sejong Hospital, Incheon, 
      Korea.
FAU - Choi, Rak Kyeong
AU  - Choi RK
AD  - Division of Cardiology, Cardiovascular Center, Mediplex Sejong Hospital, Incheon, 
      Korea.
FAU - Oh, Byung-Hee
AU  - Oh BH
AD  - Division of Cardiology, Cardiovascular Center, Mediplex Sejong Hospital, Incheon, 
      Korea.
LA  - eng
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
DEP - 20191031
PL  - United States
TA  - PLoS One
JT  - PloS one
JID - 101285081
SB  - IM
MH  - Acute Disease/mortality
MH  - Aged
MH  - Area Under Curve
MH  - Deep Learning
MH  - Female
MH  - Hospital Mortality
MH  - Humans
MH  - Machine Learning
MH  - Male
MH  - Middle Aged
MH  - Myocardial Infarction/*mortality
MH  - Non-ST Elevated Myocardial Infarction/mortality
MH  - ROC Curve
MH  - Registries
MH  - Republic of Korea/epidemiology
MH  - Risk Assessment/*methods
MH  - Risk Factors
MH  - ST Elevation Myocardial Infarction/mortality
MH  - Time Factors
PMC - PMC6822714
COIS- The authors have declared that no competing interests exist.
EDAT- 2019/11/02 06:00
MHDA- 2020/03/14 06:00
PMCR- 2019/10/31
CRDT- 2019/11/01 06:00
PHST- 2019/05/17 00:00 [received]
PHST- 2019/10/15 00:00 [accepted]
PHST- 2019/11/01 06:00 [entrez]
PHST- 2019/11/02 06:00 [pubmed]
PHST- 2020/03/14 06:00 [medline]
PHST- 2019/10/31 00:00 [pmc-release]
AID - PONE-D-19-14012 [pii]
AID - 10.1371/journal.pone.0224502 [doi]
PST - epublish
SO  - PLoS One. 2019 Oct 31;14(10):e0224502. doi: 10.1371/journal.pone.0224502. 
      eCollection 2019.