Machine learning to predict left ventricular reverse remodeling by guideline-directed medical therapy by utilizing texture feature of extracellular volume fraction in patients with non-ischemic dilated cardiomyopathy.
Extracellular volume fraction
Heterogeneity
Histogram analysis
Magnetic resonance
Non-ischemic dilated cardiomyopathy
Journal
Heart and vessels
ISSN: 1615-2573
Titre abrégé: Heart Vessels
Pays: Japan
ID NLM: 8511258
Informations de publication
Date de publication:
Mar 2023
Mar 2023
Historique:
received:
13
05
2022
accepted:
24
08
2022
pubmed:
4
9
2022
medline:
8
2
2023
entrez:
3
9
2022
Statut:
ppublish
Résumé
Extracellular volume fraction (ECV) by cardiac magnetic resonance (CMR) allows for the non-invasive quantification of diffuse myocardial fibrosis. Texture analysis and machine learning are now gathering attention in the medical field to exploit the ability of diagnostic imaging for various diseases. This study aimed to investigate the predictive value of texture analysis of ECV and machine learning for predicting response to guideline-directed medical therapy (GDMT) for patients with non-ischemic dilated cardiomyopathy (NIDCM). A total of one-hundred and fourteen NIDCM patients [age: 63 ± 12 years, 91 (81%) males] were retrospectively analyzed. We performed texture analysis of ECV mapping of LV myocardium using dedicated software. We calculated nine histogram-based features (mean, standard deviation, maximum, minimum, etc.) and five gray-level co-occurrence matrices. Five machine learning techniques and the fivefold cross-validation method were used to develop prediction models for LVRR by GDMT based on 14 texture parameters on ECV mapping. We defined the LVRR as follows: LVEF increased ≥ 10% points and decreased LVEDV ≥ 10% on echocardiography after GDMT > 12 months. Fifty (44%) patients were classified as non-responders. The area under the receiver operating characteristics curve for predicting non-responder was 0.82 for eXtreme Gradient Boosting, 0.85 for support vector machine, 0.76 for multi-layer perception, 0.81 for Naïve Bayes, 0.77 for logistic regression, respectively. Mean ECV value was the most critical factor among texture features for differentiating NIDCM patients with LVRR and those without (0.28 ± 0.03 vs. 0.36 ± 0.06, p < 0.001). Machine learning analysis using the support vector machine may be helpful in detecting high-risk NIDCM patients resistant to GDMT. Mean ECV is the most crucial feature among texture features.
Identifiants
pubmed: 36056933
doi: 10.1007/s00380-022-02167-z
pii: 10.1007/s00380-022-02167-z
doi:
Substances chimiques
Contrast Media
0
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
361-370Informations de copyright
© 2022. Springer Japan KK, part of Springer Nature.
Références
Japp AG, Gulati A, Cook SA, Cowie MR, Prasad SK (2016) The diagnosis and evaluation of dilated cardiomyopathy. J Am Coll Cardiol 67(25):2996–3010
doi: 10.1016/j.jacc.2016.03.590
Pinto YM, Elliott PM, Arbustini E, Adler Y, Anastasakis A, Böhm M, Duboc D, Gimeno J, de Groote P, Imazio M, Heymans S, Klingel K, Komajda M, Limongelli G, Linhart A, Mogensen J, Moon J, Pieper PG, Seferovic PM, Schueler S, Zamorano JL, Caforio AL, Charron P (2016) Proposal for a revised definition of dilated cardiomyopathy, hypokinetic non-dilated cardiomyopathy, and its implications for clinical practice: a position statement of the ESC working group on myocardial and pericardial diseases. Eur Heart J 37(23):1850–1858
doi: 10.1093/eurheartj/ehv727
Lehrke S, Lossnitzer D, Schöb M, Steen H, Merten C, Kemmling H, Pribe R, Ehlermann P, Zugck C, Korosoglou G, Giannitsis E, Katus HA (2011) Use of cardiovascular magnetic resonance for risk stratification in chronic heart failure: prognostic value of late gadolinium enhancement in patients with non-ischaemic dilated cardiomyopathy. Heart 97(9):727–732
doi: 10.1136/hrt.2010.205542
Iles LM, Ellims AH, Llewellyn H, Hare JL, Kaye DM, McLean CA, Taylor AJ (2015) Histological validation of cardiac magnetic resonance analysis of regional and diffuse interstitial myocardial fibrosis. Eur Heart J Cardiovasc Imaging 16(1):14–22
doi: 10.1093/ehjci/jeu182
aus dem Siepen F, Buss SJ, Messroghli D, Andre F, Lossnitzer D, Seitz S, Keller M, Schnabel PA, Giannitsis E, Korosoglou G, Katus HA, Steen H (2015) T1 mapping in dilated cardiomyopathy with cardiac magnetic resonance: quantification of diffuse myocardial fibrosis and comparison with endomyocardial biopsy. Eur Heart J Cardiovasc Imaging 16(2):210–216
doi: 10.1093/ehjci/jeu183
Messroghli DR, Nordmeyer S, Dietrich T, Dirsch O, Kaschina E, Savvatis K, Oh-I D, Klein C, Berger F, Kuehne T (2011) Assessment of diffuse myocardial fibrosis in rats using small-animal look–locker inversion recovery T1 mapping. Circ Cardiovasc Imaging 4(6):636–640
doi: 10.1161/CIRCIMAGING.111.966796
Wong TC, Piehler K, Meier CG, Testa SM, Klock AM, Aneizi AA, Shakesprere J, Kellman P, Shroff SG, Schwartzman DS, Mulukutla SR, Simon MA, Schelbert EB (2012) Association between extracellular matrix expansion quantified by cardiovascular magnetic resonance and short-term mortality. Circulation 126(10):1206–1216
doi: 10.1161/CIRCULATIONAHA.111.089409
Merlo M, Pivetta A, Pinamonti B, Stolfo D, Zecchin M, Barbati G, Di Lenarda A, Sinagra G (2014) Long-term prognostic impact of therapeutic strategies in patients with idiopathic dilated cardiomyopathy: changing mortality over the last 30 years. Eur J Heart Fail 16(3):317–324
doi: 10.1002/ejhf.16
Xu Y, Li W, Wan K, Liang Y, Jiang X, Wang J, Mui D, Li Y, Tang S, Guo J, Guo X, Liu X, Sun J, Zhang Q, Han Y, Chen Y (2021) Myocardial tissue reverse remodeling after guideline-directed medical therapy in idiopathic dilated cardiomyopathy. Circ Heart Fail 14(1):e007944
doi: 10.1161/CIRCHEARTFAILURE.120.007944
Gillies RJ, Kinahan PE, Hricak H (2016) Radiomics: images are more than pictures they are data. Radiology 278(2):563–577
doi: 10.1148/radiol.2015151169
Raisi-Estabragh Z, Izquierdo C, Campello VM, Martin-Isla C, Jaggi A, Harvey NC, Lekadir K, Petersen SE (2020) Cardiac magnetic resonance radiomics: basic principles and clinical perspectives. Eur Heart J Cardiovasc Imaging 21(4):349–356
doi: 10.1093/ehjci/jeaa028
DeGregory KW, Kuiper P, DeSilvio T, Pleuss JD, Miller R, Roginski JW, Fisher CB, Harness D, Viswanath S, Heymsfield SB, Dungan I, Thomas DM (2018) A review of machine learning in obesity. Obes Rev 19(5):668–685
doi: 10.1111/obr.12667
Lang RM, Badano LP, Mor-Avi V, Afilalo J, Armstrong A, Ernande L, Flachskampf FA, Foster E, Goldstein SA, Kuznetsova T, Lancellotti P, Muraru D, Picard MH, Rietzschel ER, Rudski L, Spencer KT, Tsang W, Voigt JU (2015) Recommendations for cardiac chamber quantification by echocardiography in adults: an update from the American Society of Echocardiography and the European Association of Cardiovascular Imaging. J Am Soc Echocardiogr 28(1):1-39.e14
doi: 10.1016/j.echo.2014.10.003
Merlo M, Caiffa T, Gobbo M, Adamo L, Sinagra G (2018) Reverse remodeling in dilated cardiomyopathy: insights and future perspectives. Int J Cardiol Heart Vasc 18:52–57
Semelka RC, Tomei E, Wagner S, Mayo J, Kondo C, Suzuki J, Caputo GR, Higgins CB (1990) Normal left ventricular dimensions and function: interstudy reproducibility of measurements with cine MR imaging. Radiology 174(3 Pt 1):763–768
doi: 10.1148/radiology.174.3.2305059
Muthalaly RG, Kwong RY, John RM, van der Geest RJ, Tao Q, Schaeffer B, Tanigawa S, Nakamura T, Kaneko K, Tedrow UB, Stevenson WG, Epstein LM, Kapur S, Zei PC, Koplan BA (2019) Left ventricular entropy is a novel predictor of arrhythmic events in patients with dilated cardiomyopathy receiving defibrillators for primary prevention. JACC Cardiovasc Imaging 12(7 Pt 1):1177–1184
doi: 10.1016/j.jcmg.2018.07.003
Shu S, Hong Z, Peng Q, Zhou X, Zhang T, Wang J, Zheng C (2021) A machine-learning-based method to predict adverse events in patients with dilated cardiomyopathy and severely reduced ejection fractions. Br J Radiol 94(1127):20210259
doi: 10.1259/bjr.20210259
Balaban G, Halliday BP, Hammersley D, Rinaldi CA, Prasad SK, Bishop MJ, Lamata P (2022) Left ventricular shape predicts arrhythmic risk in fibrotic dilated cardiomyopathy. Europace 24(7):1137–1147
doi: 10.1093/europace/euab306
Ehara S, Matsumoto K, Kitada R, Nishimura S, Shimada K, Yoshiyama M (2018) Clinical significance of discrepant mid-wall late gadolinium enhancement in patients with nonischemic dilated cardiomyopathy. Heart Vessels 33(12):1482–1489
doi: 10.1007/s00380-018-1196-3
Vera A, Cecconi A, Martínez-Vives P, Olivera MJ, Hernández S, López-Melgar B, Rojas-González A, Díez-Villanueva P, Salamanca J, Tejelo J, Caballero P, Jiménez-Borreguero LJ, Alfonso F (2022) Electrocardiogram and CMR to differentiate tachycardia-induced cardiomyopathy from dilated cardiomyopathy in patients admitted for heart failure. Heart Vessels. https://doi.org/10.1007/s00380-022-02102-2
doi: 10.1007/s00380-022-02102-2
Nakayama M, Yamamuro M, Takashio S, Uemura T, Nakayama N, Hirakawa K, Oda S, Utsunomiya D, Kaikita K, Hokimoto S, Yamashita Y, Morita Y, Kimura K, Tamura K, Tsujita K (2018) Late gadolinium enhancement on cardiac magnetic resonance imaging is associated with coronary endothelial dysfunction in patients with dilated cardiomyopathy. Heart Vessels 33(4):393–402
doi: 10.1007/s00380-017-1069-1
Kinoshita M, Kato S, Kodama S, Azuma M, Nakayama N, Fukui K, Saito N, Iwasawa T, Kimura K, Tamura K, Utsunomiya D (2022) Native T1 heterogeneity for predicting reverse remodeling in patients with non-ischemic dilated cardiomyopathy. Heart Vessels 37(9):1541–1550
doi: 10.1007/s00380-022-02057-4
Shao XN, Sun YJ, Xiao KT, Zhang Y, Zhang WB, Kou ZF, Cheng JL (2018) Texture analysis of magnetic resonance T1 mapping with dilated cardiomyopathy: a machine learning approach. Medicine 97(37):e12246
doi: 10.1097/MD.0000000000012246
El-Rewaidy H, Neisius U, Nakamori S, Ngo L, Rodriguez J, Manning WJ, Nezafat R (2020) Characterization of interstitial diffuse fibrosis patterns using texture analysis of myocardial native T1 mapping. PLoS ONE 15(6):e0233694
doi: 10.1371/journal.pone.0233694