PMID- 38448993
OWN - NLM
STAT- MEDLINE
DCOM- 20240308
LR  - 20240313
IS  - 1475-2840 (Electronic)
IS  - 1475-2840 (Linking)
VI  - 23
IP  - 1
DP  - 2024 Mar 6
TI  - Use of the energy waveform electrocardiogram to detect subclinical left 
      ventricular dysfunction in patients with type 2 diabetes mellitus.
PG  - 91
LID - 10.1186/s12933-024-02141-1 [doi]
LID - 91
AB  - BACKGROUND: Recent guidelines propose N-terminal pro-B-type natriuretic peptide 
      (NT-proBNP) for recognition of asymptomatic left ventricular (LV) dysfunction 
      (Stage B Heart Failure, SBHF) in type 2 diabetes mellitus (T2DM). Wavelet 
      Transform based signal-processing transforms electrocardiogram (ECG) waveforms 
      into an energy distribution waveform (ew)ECG, providing frequency and energy 
      features that machine learning can use as additional inputs to improve the 
      identification of SBHF. Accordingly, we sought whether machine learning model 
      based on ewECG features was superior to NT-proBNP, as well as a conventional 
      screening tool-the Atherosclerosis Risk in Communities (ARIC) HF risk score, in 
      SBHF screening among patients with T2DM. METHODS: Participants in two clinical 
      trials of SBHF (defined as diastolic dysfunction [DD], reduced global 
      longitudinal strain [GLS </= 18%] or LV hypertrophy [LVH]) in T2DM underwent 
      12-lead ECG with additional ewECG feature and echocardiography. Supervised 
      machine learning was adopted to identify the optimal combination of ewECG 
      extracted features for SBHF screening in 178 participants in one trial and tested 
      in 97 participants in the other trial. The accuracy of the ewECG model in SBHF 
      screening was compared with NT-proBNP and ARIC HF. RESULTS: SBHF was identified 
      in 128 (72%) participants in the training dataset (median 72 years, 41% female) 
      and 64 (66%) in the validation dataset (median 70 years, 43% female). Fifteen 
      ewECG features showed an area under the curve (AUC) of 0.81 (95% CI 0.787-0.794) 
      in identifying SBHF, significantly better than both NT-proBNP (AUC 0.56, 95% CI 
      0.44-0.68, p < 0.001) and ARIC HF (AUC 0.67, 95%CI 0.56-0.79, p = 0.002). ewECG 
      features were also led to robust models screening for DD (AUC 0.74, 95% CI 
      0.73-0.74), reduced GLS (AUC 0.76, 95% CI 0.73-0.74) and LVH (AUC 0.90, 95% CI 
      0.88-0.89). CONCLUSIONS: Machine learning based modelling using additional ewECG 
      extracted features are superior to NT-proBNP and ARIC HF in SBHF screening among 
      patients with T2DM, providing an alternative HF screening strategy for 
      asymptomatic patients and potentially act as a guidance tool to determine those 
      who required echocardiogram to confirm diagnosis. Trial registration LEAVE-DM, 
      ACTRN 12619001393145 and Vic-ELF, ACTRN 12617000116325.
CI  - (c) 2024. The Author(s).
FAU - Soh, Cheng Hwee
AU  - Soh CH
AD  - Imaging Research Laboratory, Baker Heart and Diabetes Institute, PO Box 6492, 
      Melbourne, VIC, 3004, Australia.
AD  - Baker Department of Cardiometabolic Health, University of Melbourne, Melbourne, 
      Australia.
FAU - de Sa, Alex G C
AU  - de Sa AGC
AD  - Baker Department of Cardiometabolic Health, University of Melbourne, Melbourne, 
      Australia.
AD  - Computational Biology and Clinical Informatics, Baker Heart and Diabetes 
      Institute, Melbourne, Australia.
AD  - School of Chemistry and Molecular Biosciences, University of Queensland, 
      Brisbane, Australia.
AD  - Systems and Computational Biology, Bio21 Institute, Parkville, Australia.
FAU - Potter, Elizabeth
AU  - Potter E
AD  - Imaging Research Laboratory, Baker Heart and Diabetes Institute, PO Box 6492, 
      Melbourne, VIC, 3004, Australia.
FAU - Halabi, Amera
AU  - Halabi A
AD  - Imaging Research Laboratory, Baker Heart and Diabetes Institute, PO Box 6492, 
      Melbourne, VIC, 3004, Australia.
FAU - Ascher, David B
AU  - Ascher DB
AD  - Baker Department of Cardiometabolic Health, University of Melbourne, Melbourne, 
      Australia.
AD  - Computational Biology and Clinical Informatics, Baker Heart and Diabetes 
      Institute, Melbourne, Australia.
AD  - School of Chemistry and Molecular Biosciences, University of Queensland, 
      Brisbane, Australia.
AD  - Systems and Computational Biology, Bio21 Institute, Parkville, Australia.
FAU - Marwick, Thomas H
AU  - Marwick TH
AD  - Imaging Research Laboratory, Baker Heart and Diabetes Institute, PO Box 6492, 
      Melbourne, VIC, 3004, Australia. tom.marwick@baker.edu.au.
AD  - Baker Department of Cardiometabolic Health, University of Melbourne, Melbourne, 
      Australia. tom.marwick@baker.edu.au.
AD  - Menzies Institute for Medical Research, Hobart, Australia. 
      tom.marwick@baker.edu.au.
LA  - eng
GR  - Partnership grant (1059538)/National Health and Medical Research Council/
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
DEP - 20240306
PL  - England
TA  - Cardiovasc Diabetol
JT  - Cardiovascular diabetology
JID - 101147637
SB  - IM
MH  - Humans
MH  - Female
MH  - Male
MH  - *Diabetes Mellitus, Type 2/complications/diagnosis
MH  - Electrocardiography
MH  - Echocardiography
MH  - Risk Factors
MH  - *Atherosclerosis
MH  - Hypertrophy, Left Ventricular
PMC - PMC10918872
OTO - NOTNLM
OT  - Diabetes mellitus
OT  - Echocardiography
OT  - Electrocardiogram
OT  - Heart failure
COIS- The authors declare that they have no competing interests.
EDAT- 2024/03/07 00:42
MHDA- 2024/03/08 06:42
PMCR- 2024/03/06
CRDT- 2024/03/06 23:47
PHST- 2023/11/26 00:00 [received]
PHST- 2024/01/22 00:00 [accepted]
PHST- 2024/03/08 06:42 [medline]
PHST- 2024/03/07 00:42 [pubmed]
PHST- 2024/03/06 23:47 [entrez]
PHST- 2024/03/06 00:00 [pmc-release]
AID - 10.1186/s12933-024-02141-1 [pii]
AID - 2141 [pii]
AID - 10.1186/s12933-024-02141-1 [doi]
PST - epublish
SO  - Cardiovasc Diabetol. 2024 Mar 6;23(1):91. doi: 10.1186/s12933-024-02141-1.