• AI-based approach for heart fa...

Treffer: AI-based approach for heart failure readmission prediction using SCG, ECG, and GSR signals.

Title:
AI-based approach for heart failure readmission prediction using SCG, ECG, and GSR signals.
Authors:
Dhar R; Quantitative Health Science, Lerner Research Institute, Cleveland Clinic, Cleveland, OH 44195, United States of America., Hossen MR; Biomedical Acoustic Research Lab, University of Central Florida, Orlando, FL 32816, United States of America., Gamage PT; Florida Tech, Melbourne, FL 32901, United States of America., Sandler RH; Biomedical Acoustic Research Lab, University of Central Florida, Orlando, FL 32816, United States of America.; Biomedical Acoustics Research Company, Orlando, FL, United States of America., Raval NY; Advent Health, Orlando, FL, United States of America., Mentz RJ; Duke University, Durham, NC 27715, United States of America., Mansy HA; Biomedical Acoustic Research Lab, University of Central Florida, Orlando, FL 32816, United States of America.; Biomedical Acoustics Research Company, Orlando, FL, United States of America.
Source:
Physiological measurement [Physiol Meas] 2025 Nov 04; Vol. 46 (11). Date of Electronic Publication: 2025 Nov 04.
Publication Type:
Journal Article
Language:
English
Journal Info:
Publisher: IOP Pub. Ltd Country of Publication: England NLM ID: 9306921 Publication Model: Electronic Cited Medium: Internet ISSN: 1361-6579 (Electronic) Linking ISSN: 09673334 NLM ISO Abbreviation: Physiol Meas Subsets: MEDLINE
Imprint Name(s):
Original Publication: Bristol, UK : IOP Pub. Ltd., c1993-
MeSH Terms:
Heart Failure*/physiopathology , Heart Failure*/diagnosis , Patient Readmission* , Electrocardiography* , Signal Processing, Computer-Assisted* , Artificial Intelligence*, Humans ; Male ; Female ; Aged ; Middle Aged ; Machine Learning ; Heart Rate
References:
Circulation. 2005 Aug 9;112(6):841-8. (PMID: 16061743)
Iran J Public Health. 2022 Jul;51(7):1481-1493. (PMID: 36248309)
PLoS Comput Biol. 2018 Oct 10;14(10):e1006438. (PMID: 30303952)
Circulation. 1999 Aug 31;100(9):999-1008. (PMID: 10468532)
Am J Cardiol. 2014 Oct 15;114(8):1249-56. (PMID: 25150135)
J Am Coll Cardiol. 2009 Jul 28;54(5):375-85. (PMID: 19628111)
J Am Soc Echocardiogr. 2015 Jan;28(1):1-39.e14. (PMID: 25559473)
Eur Heart J. 2011 Sep;32(18):2225-7. (PMID: 21551157)
Card Fail Rev. 2017 Apr;3(1):7-11. (PMID: 28785469)
Eur Heart J. 2012 Jul;33(14):1718-20. (PMID: 21900293)
Pharmacoeconomics. 2020 Nov;38(11):1219-1236. (PMID: 32812149)
Circulation. 2022 May 3;145(18):e895-e1032. (PMID: 35363499)
Circ Heart Fail. 2020 Mar;13(3):e006513. (PMID: 32093506)
Circulation. 2000 Nov 14;102(20 Suppl 4):IV14-23. (PMID: 11080127)
JAMA. 2020 Aug 04;324(5):488-504. (PMID: 32749493)
Circ Heart Fail. 2021 Apr;14(4):e008335. (PMID: 33866827)
JACC Heart Fail. 2023 Oct;11(10):1320-1332. (PMID: 37354145)
ESC Heart Fail. 2019 Apr;6(2):428-435. (PMID: 30810291)
Physiol Meas. 2023 Feb 27;44(2):. (PMID: 36638534)
Front Bioinform. 2022 Jun 27;2:927312. (PMID: 36304293)
Mol Med. 2015 Jan 26;20:527-37. (PMID: 25222914)
Am J Physiol Heart Circ Physiol. 2000 Jun;278(6):H2039-49. (PMID: 10843903)
Psychophysiology. 1997 Nov;34(6):623-48. (PMID: 9401419)
Circulation. 2012 Jul 24;126(4):501-6. (PMID: 22825412)
IEEE J Biomed Health Inform. 2021 Nov;25(11):4175-4184. (PMID: 34077377)
Arch Intern Med. 2011 Jul 25;171(14):1238-43. (PMID: 21788541)
Auton Neurosci. 2013 Nov;178(1-2):50-9. (PMID: 23664242)
Circulation. 2020 Mar 3;141(9):e139-e596. (PMID: 31992061)
Biomedicines. 2022 Jan 24;10(2):. (PMID: 35203454)
Circ Heart Fail. 2018 Jan;11(1):e004313. (PMID: 29330154)
IEEE Trans Biomed Eng. 1985 Mar;32(3):230-6. (PMID: 3997178)
ESC Heart Fail. 2020 Oct;7(5):2894-2903. (PMID: 32729678)
Eur J Heart Fail. 2009 Sep;11(9):855-62. (PMID: 19654140)
Eur J Heart Fail. 2019 Nov;21(11):1306-1325. (PMID: 31523902)
BMC Cardiovasc Disord. 2018 May 2;18(1):74. (PMID: 29716540)
Front Physiol. 2018 May 18;9:546. (PMID: 29867582)
Sensors (Basel). 2018 Oct 19;18(10):. (PMID: 30347695)
J Am Coll Cardiol. 1991 Aug;18(2):464-72. (PMID: 1856414)
Pac Symp Biocomput. 2016;22:276-287. (PMID: 27896982)
Proc Natl Acad Sci U S A. 1978 Dec;75(12):5831-5. (PMID: 282605)
Heart Fail Rev. 2018 Jan;23(1):131-145. (PMID: 29124528)
Vibration. 2019 Mar;2(1):64-86. (PMID: 34113791)
Bioengineering (Basel). 2017 Apr 07;4(2):. (PMID: 28952511)
JACC Heart Fail. 2017 Mar;5(3):216-225. (PMID: 28254128)
Grant Information:
R44 HL099053 United States HL NHLBI NIH HHS
Contributed Indexing:
Keywords: heart failure readmission; machine learning; seismocardiogram; signal processing
Entry Date(s):
Date Created: 20251024 Date Completed: 20251104 Latest Revision: 20251107
Update Code:
20251107
PubMed Central ID:
PMC12583931
DOI:
10.1088/1361-6579/ae178c
PMID:
41135577
Database:
MEDLINE

Weitere Informationen

Objective. Heart failure (HF) is considered a global pandemic because of increasing prevalence, high mortality rate, frequent hospitalization, and associated economic burden. This study explores a noninvasive method that may help in managing HF patients by predicting HF readmission. Methods. Seismocardiogram (SCG) signal is the low-frequency chest vibration produced by the mechanical activity of the heart. SCG signal was acquired from 101 patients with HF, including those readmitted to the hospital during the study period. SCG signals were segmented into heartbeats and clustered based on respiration phases. Features were extracted from each cluster. Several conventional machine learning (ML) models were developed using selected SCG and heart rate variability features. Furthermore, SCG signals were transformed into images using a time-frequency distribution method. Images were used to train a deep learning model. The models were able to predict the readmission status of HF patients. Results. ML algorithms achieved higher accuracy than the deep learning model in classifying the readmitted and non-readmitted HF patients. K-nearest neighbor achieved the highest classification accuracy (89.4% accuracy, 87.8% sensitivity, 90.1% specificity, 78.2% precision, and 82.7% F 1-score). A detailed discussion of the extracted features was provided, correlating them with HF conditions. Conclusions . The study results suggest that SCG signals may be useful for readmission prediction of HF patients.
(Creative Commons Attribution license.)