PMID- 36610062
OWN - NLM
STAT- MEDLINE
DCOM- 20230403
LR  - 20230508
IS  - 1532-2092 (Electronic)
IS  - 1099-5129 (Print)
IS  - 1099-5129 (Linking)
VI  - 25
IP  - 3
DP  - 2023 Mar 30
TI  - Improved prediction of sudden cardiac death in patients with heart failure 
      through digital processing of electrocardiography.
PG  - 922-930
LID - 10.1093/europace/euac261 [doi]
AB  - AIMS: Available predictive models for sudden cardiac death (SCD) in heart failure 
      (HF) patients remain suboptimal. We assessed whether the electrocardiography 
      (ECG)-based artificial intelligence (AI) could better predict SCD, and also 
      whether the combination of the ECG-AI index and conventional predictors of SCD 
      would improve the SCD stratification among HF patients. METHODS AND RESULTS: In a 
      prospective observational study, 4 tertiary care hospitals in Tokyo enrolled 2559 
      patients hospitalized for HF who were successfully discharged after acute 
      decompensation. The ECG data during the index hospitalization were extracted from 
      the hospitals' electronic medical record systems. The association of the ECG-AI 
      index and SCD was evaluated with adjustment for left ventricular ejection 
      fraction (LVEF), New York Heart Association (NYHA) class, and competing risk of 
      non-SCD. The ECG-AI index plus classical predictive guidelines (i.e. LVEF </=35%, 
      NYHA Class II and III) significantly improved the discriminative value of SCD 
      [receiver operating characteristic area under the curve (ROC-AUC), 0.66 vs. 0.59; 
      P = 0.017; Delong's test] with good calibration (P = 0.11; Hosmer-Lemeshow test) 
      and improved net reclassification [36%; 95% confidence interval (CI), 9-64%; P = 
      0.009]. The Fine-Gray model considering the competing risk of non-SCD 
      demonstrated that the ECG-AI index was independently associated with SCD 
      (adjusted sub-distributional hazard ratio, 1.25; 95% CI, 1.04-1.49; P = 0.015). 
      An increased proportional risk of SCD vs. non-SCD with an increasing ECG-AI index 
      was also observed (low, 16.7%; intermediate, 18.5%; high, 28.7%; P for trend = 
      0.023). Similar findings were observed in patients aged </=75 years with a 
      non-ischaemic aetiology and an LVEF of >35%. CONCLUSION: To improve risk 
      stratification of SCD, ECG-based AI may provide additional values in the 
      management of patients with HF.
CI  - (c) The Author(s) 2023. Published by Oxford University Press on behalf of the 
      European Society of Cardiology.
FAU - Shiraishi, Yasuyuki
AU  - Shiraishi Y
AUID- ORCID: 0000-0001-8788-1186
AD  - Department of Cardiology, Keio University School of Medicine, 35 Shinanomachi 
      Shinjuku-ku, Tokyo 160-8582, Japan.
FAU - Goto, Shinichi
AU  - Goto S
AUID- ORCID: 0000-0002-0450-0331
AD  - One Brave Idea and Division of Cardiovascular Medicine, Department of Medicine, 
      Brigham and Women's Hospital, Boston, MA, USA.
FAU - Niimi, Nozomi
AU  - Niimi N
AUID- ORCID: 0000-0002-6909-0740
AD  - Department of Cardiology, Keio University School of Medicine, 35 Shinanomachi 
      Shinjuku-ku, Tokyo 160-8582, Japan.
FAU - Katsumata, Yoshinori
AU  - Katsumata Y
AUID- ORCID: 0000-0001-5576-5789
AD  - Institute for Integrated Sports Medicine, Keio University School of Medicine, 
      Tokyo, Japan.
FAU - Goda, Ayumi
AU  - Goda A
AUID- ORCID: 0000-0002-4388-7639
AD  - Department of Cardiovascular Medicine, Kyorin University Faculty of Medicine, 
      Tokyo, Japan.
FAU - Takei, Makoto
AU  - Takei M
AUID- ORCID: 0000-0002-9851-4522
AD  - Department of Cardiology, Saiseikai Central Hospital, Tokyo, Japan.
FAU - Saji, Mike
AU  - Saji M
AUID- ORCID: 0000-0003-2057-109X
AD  - Department of Cardiology, Sakakibara Heart Institute, Tokyo, Japan.
FAU - Sano, Motoaki
AU  - Sano M
AD  - Department of Cardiology, Keio University School of Medicine, 35 Shinanomachi 
      Shinjuku-ku, Tokyo 160-8582, Japan.
FAU - Fukuda, Keiichi
AU  - Fukuda K
AUID- ORCID: 0000-0003-1413-0482
AD  - Department of Cardiology, Keio University School of Medicine, 35 Shinanomachi 
      Shinjuku-ku, Tokyo 160-8582, Japan.
FAU - Kohno, Takashi
AU  - Kohno T
AUID- ORCID: 0000-0003-2604-1284
AD  - Department of Cardiovascular Medicine, Kyorin University Faculty of Medicine, 
      Tokyo, Japan.
FAU - Yoshikawa, Tsutomu
AU  - Yoshikawa T
AD  - Department of Cardiology, Sakakibara Heart Institute, Tokyo, Japan.
FAU - Kohsaka, Shun
AU  - Kohsaka S
AUID- ORCID: 0000-0003-3779-2972
AD  - Department of Cardiology, Keio University School of Medicine, 35 Shinanomachi 
      Shinjuku-ku, Tokyo 160-8582, Japan.
LA  - eng
GR  - Japanese Circulation Society/
GR  - SECOM Science and Technology Foundation/
GR  - Uehara Memorial Foundation/
GR  - 18K15860/Grant-in-Aid for Young Scientists/
GR  - 23591062/Grant-in-Aid for Scientific Research/
GR  - 201439013C/Japan Agency for Medical Research and Development/
GR  - Sakakibara Clinical Research Grants for the Promotion of Science/
PT  - Journal Article
PT  - Observational Study
PL  - England
TA  - Europace
JT  - Europace : European pacing, arrhythmias, and cardiac electrophysiology : journal 
      of the working groups on cardiac pacing, arrhythmias, and cardiac cellular 
      electrophysiology of the European Society of Cardiology
JID - 100883649
SB  - IM
MH  - Humans
MH  - Stroke Volume
MH  - *Artificial Intelligence
MH  - Ventricular Function, Left
MH  - Death, Sudden, Cardiac/epidemiology/etiology/prevention & control
MH  - *Heart Failure/complications/diagnosis
MH  - Electrocardiography
MH  - Risk Factors
MH  - Risk Assessment
PMC - PMC10062335
OTO - NOTNLM
OT  - Artificial intelligence
OT  - Electrocardiogram
OT  - Heart failure
OT  - Left ventricular ejection fraction
OT  - Sudden cardiac death
COIS- Conflict of interest: Y.S. received honoraria from Otsuka Pharmaceuticals Co., 
      Ltd and Ono Pharmaceuticals Co., Ltd. S.K. received an unrestricted research 
      grant from the Department of Cardiology, Keio University School of Medicine, 
      Bayer Pharmaceuticals Co., Ltd, Daiichi Sankyo Co., Ltd, and Novartis Pharma Co., 
      Ltd. The authors declare no conflicts of interest. The authors declare no 
      patents, products in development, or marketed products.
EDAT- 2023/01/08 06:00
MHDA- 2023/04/03 06:41
PMCR- 2023/01/04
CRDT- 2023/01/07 17:12
PHST- 2022/09/02 00:00 [received]
PHST- 2022/12/10 00:00 [accepted]
PHST- 2023/04/03 06:41 [medline]
PHST- 2023/01/08 06:00 [pubmed]
PHST- 2023/01/07 17:12 [entrez]
PHST- 2023/01/04 00:00 [pmc-release]
AID - 6968506 [pii]
AID - euac261 [pii]
AID - 10.1093/europace/euac261 [doi]
PST - ppublish
SO  - Europace. 2023 Mar 30;25(3):922-930. doi: 10.1093/europace/euac261.