Septic shock is a common deadly disease often associated with cardiovascular dysfunction. Left ventricular longitudinal strain (LV LS) has been proposed as a sensitive marker to measure cardiovascular function; however, it is not available universally in standard clinical echocardiograms. We sought to derive a predictive model for LV LS, using machine learning techniques with the hope that we may uncover surrogates for LV LS. We found that left ventricular ejection fraction, tricuspid annular plane systolic excursion, sepsis source, height, mitral valve Tei index, LV systolic dimension, aortic valve ejection time, and peak acceleration rate were all predictive of LV LS in this initial exploratory model. Future modeling work may uncover combinations of these variables which may be powerful surrogates for LV LS and cardiovascular function.
AngusDCLinde-ZwirbleWTLidickerJClermontGCarcilloJPinskyMR. Epidemiology of severe sepsis in the United States: analysis of incidence, outcome, and associated costs of care. Crit Care Med. 2001;29(7):1303-1310.
2.
Shankar-HariMPhillipsGSLevyML, et al.Developing a New definition and assessing New clinical criteria for septic shock: for the third international consensus definitions for sepsis and septic shock (sepsis-3). Jama.2016;315(8):775-787.
3.
KaukonenKMBaileyMSuzukiSPilcherDBellomoR. Mortality related to severe sepsis and septic shock among critically ill patients in Australia and New Zealand, 2000–2012. JAMA.2014;311(13):1308-1316.
4.
BeesleySJWeberGSargeT, et al.Septic cardiomyopathy. Crit Care Med.2018;46(4):625-634.
5.
Vieillard-BaronACailleVCharronCBelliardGPageBJardinF. Actual incidence of global left ventricular hypokinesia in adult septic shock. Crit Care Med. 2008;36(6):1701-1706.
6.
Müller-WerdanUWerdanK. Septic cardiomyopathy. Current Opinion in Critical Care. 1999;5(5):415-421.
7.
Muller-WerdanUBuerkeMEbeltH, et al.Septic cardiomyopathy–A not yet discovered cardiomyopathy?Experimental & Clinical Cardiology. 2006;11(3):226.
8.
WerdanKOelkeAHettwerS, et al.Septic cardiomyopathy: hemodynamic quantification, occurrence, and prognostic implications. Clinical Research in Cardiology. 2011;100(8):661-668.
9.
WerdanKMüller-WerdanU. Elucidating molecular mechanisms of septic cardiomyopathy — the cardiomyocyte modelBiochemical Regulation of Myocardium. Vol 19. Springer; 1996:291–303.
10.
SchorrCADellingerRP. The surviving sepsis campaign: past, present and future. Trends Mol Med. 2014;20(4):192-194.
11.
WilkmanEKaukonenKMPettilaVKuitunenAVarpulaM. Association between inotrope treatment and 90-day mortality in patients with septic shock. Acta Anaesthesiol Scand. 2013;57(4):431-442.
12.
Sevilla BerriosRAO‘HoroJCVelagapudiVPulidoJN. Correlation of left ventricular systolic dysfunction determined by low ejection fraction and 30–day mortality in patients with severe sepsis and septic shock: a systematic review and meta-analysis. J Crit Care.2014;29(4):495-499.
13.
StantonTLeanoRMarwickTH. Prediction of all-cause mortality from global longitudinal speckle strain: comparison with ejection fraction and wall motion scoring. Circ Cardiovasc Imaging. 2009;2(5):356-364.
14.
LiangHYCauduroSPellikkaP, et al.Usefulness of two-dimensional speckle strain for evaluation of left ventricular diastolic deformation in patients with coronary artery disease. Am J Cardiol.2006;98(12):1581-1586.
15.
BellaviaDPellikkaPAAl-ZahraniGB, et al.Independent predictors of survival in primary systemic (Al) amyloidosis, including cardiac biomarkers and left ventricular strain imaging: an observational cohort study. J Am Soc Echocardiogr. 2010;23(6):643-652.
16.
BellaviaDAbrahamTPPellikkaPA, et al.Detection of left ventricular systolic dysfunction in cardiac amyloidosis with strain rate echocardiography. J Am Soc Echocardiogr. 2007;20(10):1194-1202.
17.
PrakasaKRWangJTandriH, et al.Utility of tissue Doppler and strain echocardiography in arrhythmogenic right ventricular dysplasia/cardiomyopathy. Am J Cardiol.2007;100(3):507-512.
18.
SawayaHSebagIAPlanaJC, et al.Early detection and prediction of cardiotoxicity in chemotherapy-treated patients. Am J Cardiol.2011;107(9):1375-1380.
19.
LennemanCGSawyerDB. Cardio-Oncology: an update on cardiotoxicity of cancer-related treatment. Circ Res.2016;118(6):1008-1020.
20.
LanspaMJShahulSHershA, et al.Associations among left ventricular systolic function, tachycardia, and cardiac preload in septic patients. Ann Intensive Care. 2017;7(1):17.
21.
LanspaMJPittmanJEHirshbergEL, et al.Association of left ventricular longitudinal strain with central venous oxygen saturation and serum lactate in patients with early severe sepsis and septic shock. Crit Care. 2015;19(1):1–9.
22.
ChangWTLeeWHLeeWT, et al.Left ventricular global longitudinal strain is independently associated with mortality in septic shock patients. Intensive Care Med.2015;41(10):1791–1799. doi:10.1007/s00134-015-3970-3
23.
PalmieriVInnocentiFGuzzoAGuerriniEVignaroliDPiniR. Left ventricular systolic longitudinal function as predictor of outcome in patients With sepsis. Circ Cardiovasc Imaging. 2015;8(11):e003865. discussion e003865.
24.
LanspaMJGutscheARWilsonEL, et al.Application of a simplified definition of diastolic function in severe sepsis and septic shock. Crit Care. 2016;20(1):243.
25.
LevyMMFinkMPMarshallJC, et al.2001 SCCM/ESICM/ACCP/ATS/SIS international sepsis definitions conference. Crit Care Med.2003;31(4):1250-1256.
26.
WulffJNEjlskovL. Multiple imputation by chained equations in praxis: guidelines and review. Electronic Journal of Business Research Methods. 2017;15(1):41–56.
27.
RubinDB. Multiple imputation after 18 + years. Journal of the American Statistical Association. 1996;91(434):473-489.
28.
van BuurenSGroothuis-OudshoornK. Mice: multivariate imputation by chained equations in R. Journal of Statistical Software. 2011;45(3):1-67.
29.
BreimanL. Random forests. Machine Learning. 2001;45(1):5-32.
30.
PetersenMLLeDellESchwabJ, et al.Super learner analysis of electronic adherence data improves viral prediction and May provide strategies for selective HIV RNA monitoring. J Acquir Immune Defic Syndr. 2015;69(1):109-118.
31.
Van der LaanMJPolleyECHubbardAE. Super learner. Statistical Applications in Genetics and Molecular Biology. 2007;6(1):Article 25. doi:10.2202/1544-6115.1309
32.
Van Der LaanMJDudoitS. Unified cross-validation methodology for selection among estimators and a general cross-validated adaptive epsilon-net estimator: Finite sample oracle inequalities and examples. 2003.
33.
PolleyECVan der LaanMJ. Super learner in prediction. 2010.
34.
AkaikeH. Information theory and an extension of the maximum likelihood principle. Paper presented at: 2nd International Symposium on Information Theory; 1973; Tsahkadsor, Armenia, USSR.
35.
FriedmanJH. Greedy function approximation: a gradient boosting machine. Annals of Statistics. 2001:1189-1232.
36.
KohaviR. A study of cross-validation and bootstrap for accuracy estimation and model selection. Ijcai. 1995;14(2):1137–1143.
37.
SteyerbergEWHarrellFEJrBorsboomGJEijkemansMJVergouweYHabbemaJD. Internal validation of predictive models: efficiency of some procedures for logistic regression analysis. J Clin Epidemiol. 2001;54(8):774-781.
38.
PirracchioRPetersenMLCaroneMRigonMRChevretSvan der LaanMJ. Mortality prediction in intensive care units with the super ICU learner algorithm (SICULA): a population-based study. Lancet Respir Med. 2015;3(1):42-52.
39.
RoseS. Mortality risk score prediction in an elderly population using machine learning. American Journal of Epidemiology. 2013;177(5):443-452.
40.
PfaffenbergerSBartkoPGrafA, et al.Size matters! impact of age, sex, height, and weight on the normal heart size. Circ Cardiovasc Imaging. 2013;6(6):1073-1079.
41.
DalenHThorstensenAAaseSA, et al.Segmental and global longitudinal strain and strain rate based on echocardiography of 1266 healthy individuals: the HUNT study in Norway. Eur J Echocardiogr. 2010;11(2):176-183.
42.
YingchoncharoenTAgarwalSPopovicZBMarwickTH. Normal ranges of left ventricular strain: a meta-analysis. J Am Soc Echocardiogr. 2013;26(2):185-191.
43.
ThavendiranathanPPoulinFLimKDPlanaJCWooAMarwickTH. Use of myocardial strain imaging by echocardiography for the early detection of cardiotoxicity in patients during and after cancer chemotherapy: a systematic review. J Am Coll Cardiol.2014;63(25 Pt A):2751-2768.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
