Deep-learning survival analysis for patients with calcific aortic valve disease undergoing valve replacement.
Humans
Deep Learning
Aortic Valve
/ surgery
Calcinosis
/ surgery
Female
Male
Aged
Aortic Valve Stenosis
/ surgery
Transcatheter Aortic Valve Replacement
/ mortality
Aged, 80 and over
Survival Analysis
Risk Factors
Proportional Hazards Models
Risk Assessment
/ methods
Heart Valve Prosthesis Implantation
/ mortality
Middle Aged
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
13 05 2024
13 05 2024
Historique:
received:
15
05
2023
accepted:
08
05
2024
medline:
14
5
2024
pubmed:
14
5
2024
entrez:
13
5
2024
Statut:
epublish
Résumé
Calcification of the aortic valve (CAVDS) is a major cause of aortic stenosis (AS) leading to loss of valve function which requires the substitution by surgical aortic valve replacement (SAVR) or transcatheter aortic valve intervention (TAVI). These procedures are associated with high post-intervention mortality, then the corresponding risk assessment is relevant from a clinical standpoint. This study compares the traditional Cox Proportional Hazard (CPH) against Machine Learning (ML) based methods, such as Deep Learning Survival (DeepSurv) and Random Survival Forest (RSF), to identify variables able to estimate the risk of death one year after the intervention, in patients undergoing either to SAVR or TAVI. We found that with all three approaches the combination of six variables, named albumin, age, BMI, glucose, hypertension, and clonal hemopoiesis of indeterminate potential (CHIP), allows for predicting mortality with a c-index of approximately
Identifiants
pubmed: 38740898
doi: 10.1038/s41598-024-61685-0
pii: 10.1038/s41598-024-61685-0
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
10902Informations de copyright
© 2024. The Author(s).
Références
Timmis, A. et al. European society of cardiology: Cardiovascular disease statistics 2021. Eur. Heart J. 43, 716–799. https://doi.org/10.1093/eurheartj/ehab892 (2022).
doi: 10.1093/eurheartj/ehab892
pubmed: 35016208
Garg, V. et al. Mutations in notch1 cause aortic valve disease. Nature 437, 270–274. https://doi.org/10.1038/nature03940 (2005).
doi: 10.1038/nature03940
pubmed: 16025100
Thanassoulis, G. et al. Post ws; charge extracoronary calcium working group. genetic associations with valvular calcification and aortic stenosis. N. Engl. J. Med. 368(6), 503–12. https://doi.org/10.1056/NEJMoa1109034 (2013).
Shah, S. M., Shah, J., Lakey, S. M., Garg, P. & Ripley, D. P. Pathophysiology, emerging techniques for the assessment and novel treatment of aortic stenosis. Open Heart 10. https://doi.org/10.1136/openhrt-2022-002244 (2023).
Aquila, G. et al. The notch pathway: A novel therapeutic target for cardiovascular diseases?. Expert Opin. Ther. Targets 23, 695–710. https://doi.org/10.1080/14728222.2019.1641198 (2019).
doi: 10.1080/14728222.2019.1641198
pubmed: 31304807
Libby, P. & Ebert, B. Chip (clonal hematopoiesis of indeterminate potential): Potent and newly recognized contributor to cardiovascular risk. Circulation 138(7), 666–668. https://doi.org/10.1161/CIRCULATIONAHA.118.034392 (2018).
Mathieu, P. & Boulanger, M. Autotaxin and lipoprotein metabolism in calcific aortic valve disease. Front. Cardiovasc. Med. 1, 6–18. https://doi.org/10.3389/fcvm.2019.00018 (2019).
doi: 10.3389/fcvm.2019.00018
Vieceli Dalla Sega, F. et al. Cox-2 is downregulated in human stenotic aortic valves and its inhibition promotes dystrophic calcification. Int. J. Mol. Sci. 21. https://doi.org/10.3390/ijms21238917 (2020).
Vieceli Dalla Sega, F. et al. Cardiac calcifications: Phenotypes, mechanisms, clinical and prognostic implications. Biology (Basel)11. https://doi.org/10.3390/biology11030414 (2022).
Toff, W. D. et al. Effect of transcatheter aortic valve implantation vs surgical aortic valve replacement on all-cause mortality in patients with aortic stenosis: A randomized clinical trial. JAMA 327, 1875–1887. https://doi.org/10.1001/jama.2022.5776 (2022).
doi: 10.1001/jama.2022.5776
pubmed: 35579641
pmcid: 9115619
Glaser, N., Persson, M., Franco-Cereceda, A. & Sartipy, U. Cause of death after surgical aortic valve replacement: Sweden heart observational study. J. Am. Heart Assoc. 10, e022627. https://doi.org/10.1161/JAHA.121.022627 (2021).
doi: 10.1161/JAHA.121.022627
pubmed: 34743549
pmcid: 8751948
Patel, K. P. et al. Futility in transcatheter aortic valve implantation: A search for clarity. Interv. Cardiol.17, e01. https://doi.org/10.15420/icr.2021.15 (2022).
Carnero-Alcázar, M. et al. Transcatheter versus surgical aortic valve replacement in moderate and high-risk patients: A meta-analysis. Eur. J. Cardiothorac. Surg. 51, 644–652. https://doi.org/10.1093/ejcts/ezw388 (2016).
doi: 10.1093/ejcts/ezw388
Garg, A. et al. Transcatheter aortic valve replacement versus surgical valve replacement in low-intermediate surgical risk patients: A systematic review and meta-analysis. J. Invasive Cardiol. 29, 209–216 (2017) (PMID: 28570236).
pubmed: 28570236
Vieceli Dalla Sega, F. et al. Transcriptomic profiling of calcified aortic valves in clonal hematopoiesis of indeterminate potential carriers. Sci. Rep. 12, 20400. https://doi.org/10.1038/s41598-022-24130-8 (2022).
Mas-Peiro, S. et al. Clonal haematopoiesis in patients with degenerative aortic valve stenosis undergoing transcatheter aortic valve implantation. Eur. Heart J. 41, 933–939. https://doi.org/10.1093/eurheartj/ehz591 (2020).
doi: 10.1093/eurheartj/ehz591
pubmed: 31504400
Papa, V. et al. Translating evidence from clonal hematopoiesis to cardiovascular disease: A systematic review. J. Clin. Med. 9. https://doi.org/10.3390/jcm9082480 (2020).
Libby, P. et al. Clonal hematopoiesis: Crossroads of aging, cardiovascular disease, and cancer: Jacc review topic of the week. J. Am. Coll. Cardiol. 74, 567–577. https://doi.org/10.1016/j.jacc.2019.06.007 (2019).
doi: 10.1016/j.jacc.2019.06.007
pubmed: 31345432
pmcid: 6681657
RF, W. & WR., C. Statistical methods for the analysis of biomedical data, chap. 2nd ed (New York: Wiley-Interscience, 2002).
Katzman, J. L. et al. Deepsurv: Personalized treatment recommender system using a cox proportional hazards deep neural network. BMC Med. Res. Methodol. 24, 18. https://doi.org/10.1186/s12874-018-0482-1 (2018).
doi: 10.1186/s12874-018-0482-1
Dong, W. K. et al. Deep learning-based survival prediction of oral cancer patients. Sci. Rep. 9, https://doi.org/10.1038/s41598-019-43372-7 (2019).
Chang, S., Abdul-Kareem, S., Merican, A. & Zain, R. Oral cancer prognosis based on clinicopathologic and genomic markers using a hybrid of feature selection and machine learning methods. BMC Bioinf. 14, 170. https://doi.org/10.1186/1471-2105-14-170 (2013).
Shaikhina, T. & Khovanova, N. A. Handling limited datasets with neural networks in medical applications: A small-data approach. Artif. Intell. Med. 75, 51–63. https://doi.org/10.1016/j.artmed.2016.12.003 (2017).
doi: 10.1016/j.artmed.2016.12.003
pubmed: 28363456
Grossi, E. Artificial Neural Networks and Predictive Medicine: a Revolutionary Paradigm Shift, chap. 7 (InTech, 2011).
Balaprakash, P., Salim, M., Uram, T. D., Vishwanath, V. & Wild, S. M. Deephyper: Asynchronous hyperparameter search for deep neural networks. In 2018 IEEE 25th International Conference on High Performance Computing (HiPC), 42–51. https://doi.org/10.1109/HiPC.2018.00014 (2018).
Padoin, E. L., Oliveira, D. A. d., Velho, P. & Navaux, P. O. Time-to-solution and energy-to-solution: A comparison between arm and xeon. In 2012 Third Workshop on Applications for Multi-Core Architecture, 48–53, https://doi.org/10.1109/WAMCA.2012.10 (2012).
Virtanen, P. et al. SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python. Nat. Methods 17, 261–272. https://doi.org/10.1038/s41592-019-0686-2 (2020).
Yates, F. Contingency tables involving small numbers and the [Formula: see text] test. Suppl. J. R. Stat. Soc. 1, 217–235. https://doi.org/10.2307/2983604 (1934).
doi: 10.2307/2983604
Shapiro, S. S. & Wilk, M. B. An analysis of variance test for normality (complete samples). Biometrika 52, 591–611. https://doi.org/10.1093/biomet/52.3-4.591 (1965).
doi: 10.1093/biomet/52.3-4.591
Student. The probable error of a mean. Biometrika 6, 1–25. https://doi.org/10.2307/2331554 (1908).
Kruskal, W. H. & Wallis, W. A. Use of ranks in one-criterion variance analysis. J. Am. Stat. Assoc. 47, 583–621. https://doi.org/10.1080/01621459.1952.10483441 (1952).
doi: 10.1080/01621459.1952.10483441
Goel, M., Khanna, P. & Kishore, J. Understanding survival analysis: Kaplan-meier estimate. Int. J. Ayurveda Res. 1(4), 274–278. https://doi.org/10.4103/0974-7788.76794 (2010).
doi: 10.4103/0974-7788.76794
pubmed: 21455458
pmcid: 3059453
Bland, J. M. & Altman, D. G. The logrank test. BMJ 328, 1073. https://doi.org/10.1136/bmj.328.7447.1073 (2004).
doi: 10.1136/bmj.328.7447.1073
pubmed: 15117797
pmcid: 403858
Davidson-Pilon, C. lifelines: survival analysis in python. J. Open Source Softw. 4, 1317. https://doi.org/10.21105/joss.01317 (2019).
Bray, F. et al. Global cancer statistics 2018: Globocan estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J. Clin. 68, 394–424. https://doi.org/10.3322/caac.21492 (2018).
doi: 10.3322/caac.21492
pubmed: 30207593
Ji, Q., Tang, J., Li, S. & Chen, J. Survival and analysis of prognostic factors for severe burn patients with inhalation injury: based on the respiratory SOFA score. BMC Emerg. Med. 23, 1. https://doi.org/10.1186/s12873-022-00767-6 (2023).
doi: 10.1186/s12873-022-00767-6
pubmed: 36604623
pmcid: 9813898
Wang, Y. et al. A comparison of random survival forest and Cox regression for prediction of mortality in patients with hemorrhagic stroke. BMC Med. Inform. Decis. Mak. 23, 215. https://doi.org/10.1186/s12911-023-02293-2 (2023).
doi: 10.1186/s12911-023-02293-2
pubmed: 37833724
pmcid: 10576378
Ishwaran, H., Kogalur, U., Blackstone, E. & M., L. Random survival forests. Ann. Appl. Stat. 2(3), 841–860. https://doi.org/10.1214/08-AOAS169 (2008).
Wang, H. & Li, G. A. Selective review on random survival forests for high dimensional data. Quant. Biosci.36(2), 85–96. https://doi.org/10.22283/qbs.2017.36.2.85 (2017).
Fotso, S. et al. PySurvival: Open source package for survival analysis modeling (2019).
Inglis, A., Parnell, A. & Hurley, C. Visualizing variable importance and variable interaction effects in machine learning models 2108, 04310 (2021).
Dazard, J., Ishwaran, H., Mehlotra, R., Weinberg, A. & Zimmerman, P. Ensemble survival tree models to reveal pairwise interactions of variables with time-to-events outcomes in low-dimensional setting. Stat. Appl. Genet. Mol. Biol. 17(1), 841–860. https://doi.org/10.1515/sagmb-2017-0038 (2017).
Jackson, J. A user’s guide to principal components (John Wiley and Sons, New York, 1991).
doi: 10.1002/0471725331
Westad, F., Hersleth, M., Lea, P. & Martens, H. Variable selection in pca in sensory descriptive and consumer data. Food Qual. Prefer. 14, 463–472. https://doi.org/10.1016/S0950-3293(03)00015-6 (2003). The Sixth Sense - 6th Sensometrics Meeting.
Ju, J., Banfelder, J. & Skrabanek, L. Quantitative understanding in biology; principal component analysis. https://physiology.med.cornell.edu/people/banfelder/qbio/lecture_notes/3.4_Principal_component_analysis.pdf (2019).
Jolliffe, I. T. & Cadima, J. Principal component analysis: A review and recent developments. Philos. Trans. R. Soc. A Math. Phys. Eng. Sci. 374, 20150202. https://doi.org/10.1098/rsta.2015.0202 (2016).
doi: 10.1098/rsta.2015.0202
Pedregosa, F. et al. Scikit-learn: Machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011).
Schmid, M., Wright, M. N. & Ziegler, A. On the use of harrell’s c for clinical risk prediction via random survival forests. Expert Syst. Appl. 63, 450–459. https://doi.org/10.1016/j.eswa.2016.07.018 (2016).
doi: 10.1016/j.eswa.2016.07.018
Akiba, T., Sano, S., Yanase, T., Ohta, T. & Koyama, M. Optuna: A next-generation hyperparameter optimization framework. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2623–2631. https://doi.org/10.1145/3292500.3330701 (2019).
Huang, Y., Li, J., Li, M. & Aparasu, R. R. Application of machine learning in predicting survival outcomes involving real-world data: A scoping review. BMC Med. Res. Methodol. 23, 268. https://doi.org/10.1186/s12874-023-02078-1 (2023).
doi: 10.1186/s12874-023-02078-1
pubmed: 37957593
pmcid: 10641971
Ishwaran, H. & Kogalur, U. B. Consistency of random survival forests. Stat. Probab. Lett. 80, 1056–1064. https://doi.org/10.1016/j.spl.2010.02.020 (2010).
doi: 10.1016/j.spl.2010.02.020
pubmed: 20582150
pmcid: 2889677
Strobl, C., Boulesteix, A.-L., Zeileis, A. & Hothorn, T. Bias in random forest variable importance measures: Illustrations, sources and a solution. BMC Bioinformatics 8, 25. https://doi.org/10.1186/1471-2105-8-25 (2007).
doi: 10.1186/1471-2105-8-25
pubmed: 17254353
pmcid: 1796903
Mbogning, C. & Broët, P. Bagging survival tree procedure for variable selection and prediction in the presence of nonsusceptible patients. BMC Bioinformatics 17, 230. https://doi.org/10.1186/s12859-016-1090-x (2016).
doi: 10.1186/s12859-016-1090-x
pubmed: 27266372
pmcid: 4895817
Fernández-Delgado, M., Cernadas, E., Barro, S. & Amorim, D. Do we need hundreds of classifiers to solve real world classification problems?. J. Mach. Learn. Res. 15, 3133–3181. https://doi.org/10.5555/2627435.2697065 (2014).
doi: 10.5555/2627435.2697065
Akirov, A., Masri-Iraqi, H., Atamna, A. & Shimon, I. Low albumin levels are associated with mortality risk in hospitalized patients. Am. J. Med. 130(1465), e11-1465.e19. https://doi.org/10.1016/j.amjmed.2017.07.020 (2017).
doi: 10.1016/j.amjmed.2017.07.020
Goldwasser, P. & Feldman, J. Association of serum albumin and mortality risk. J. Clin. Epidemiol. 50, 693–703. https://doi.org/10.1016/s0895-4356(97)00015-2 (1997).
doi: 10.1016/s0895-4356(97)00015-2
pubmed: 9250267
Koifman, E. et al. Impact of pre-procedural serum albumin levels on outcome of patients undergoing transcatheter aortic valve replacement. Am. J. Cardiol. 115, 1260–4. https://doi.org/10.1016/j.amjcard.2015.02.009 (2015).
doi: 10.1016/j.amjcard.2015.02.009
pubmed: 25759105
Liu, G. et al. Meta-analysis of the impact of pre-procedural serum albumin on mortality in patients undergoing transcatheter aortic valve replacement. Int. Heart J. 61, 67–76. https://doi.org/10.1536/ihj.19-395 (2020).
doi: 10.1536/ihj.19-395
pubmed: 31956151
Hebeler, K. R. et al. Albumin is predictive of 1-year mortality after transcatheter aortic valve replacement. Ann. Thorac. Surg. 106, 1302–1307. https://doi.org/10.1016/j.athoracsur.2018.06.024 (2018).
doi: 10.1016/j.athoracsur.2018.06.024
pubmed: 30048632
Aasbrenn, M., Christiansen, C. F., Esen, B., Suetta, C. & Nielsen, F. E. Mortality of older acutely admitted medical patients after early discharge from emergency departments: A nationwide cohort study. BMC Geriatr. 21, 410. https://doi.org/10.1186/s12877-021-02355-y (2021).
doi: 10.1186/s12877-021-02355-y
pubmed: 34215192
pmcid: 8252197
Atramont, A. et al. Association of age with short-term and long-term mortality among patients discharged from intensive care units in France. JAMA Netw. Open 2, e193215. https://doi.org/10.1001/jamanetworkopen.2019.3215 (2019).
doi: 10.1001/jamanetworkopen.2019.3215
pubmed: 31074809
pmcid: 6512465
Maggioni, A. P. et al. Age-related increase in mortality among patients with first myocardial infarctions treated with thrombolysis. the investigators of the gruppo italiano per lo studio della sopravvivenza nell’infarto miocardico (gissi-2). N. Engl. J. Med. 329, 1442–1448. https://doi.org/10.1056/NEJM199311113292002 (1993).
Hussain, A. I. et al. Age-dependent morbidity and mortality outcomes after surgical aortic valve replacement. Interact. Cardiovasc. Thorac. Surg. 27, 650–656. https://doi.org/10.1093/icvts/ivy154 (2018).
doi: 10.1093/icvts/ivy154
pubmed: 29746650
Abawi, M. et al. Effect of body mass index on clinical outcome and all-cause mortality in patients undergoing transcatheter aortic valve implantation. Neth Heart J 25, 498–509. https://doi.org/10.1007/s12471-017-1003-2 (2017).
doi: 10.1007/s12471-017-1003-2
pubmed: 28536936
pmcid: 5571592
Forgie, K. et al. The effects of body mass index on outcomes for patients undergoing surgical aortic valve replacement. BMC Cardiovasc. Disord. 20, 255. https://doi.org/10.1186/s12872-020-01528-8 (2020).
doi: 10.1186/s12872-020-01528-8
pubmed: 32471345
pmcid: 7256925
Voigtländer, L. et al. Prognostic impact of underweight (body mass index <20 kg/m. Am. J. Cardiol. 129, 79–86. https://doi.org/10.1016/j.amjcard.2020.05.002 (2020).
doi: 10.1016/j.amjcard.2020.05.002
pubmed: 32540167
Lv, W. et al. Diabetes mellitus is an independent prognostic factor for mid-term and long-term survival following transcatheter aortic valve implantation: a systematic review and meta-analysis. Interact. Cardiovasc. Thorac. Surg. 27, 159–168. https://doi.org/10.1093/icvts/ivy040 (2018).
doi: 10.1093/icvts/ivy040
pubmed: 29528407
Halkos, M. E. et al. The effect of diabetes mellitus on in-hospital and long-term outcomes after heart valve operations. Ann. Thorac. Surg. 90, 124–30. https://doi.org/10.1016/j.athoracsur.2010.03.111 (2010).
doi: 10.1016/j.athoracsur.2010.03.111
pubmed: 20609762
Tjang, Y. S., van Hees, Y., Körfer, R., Grobbee, D. E. & van der Heijden, G. J. Predictors of mortality after aortic valve replacement. Eur. J. Cardiothorac. Surg. 32, 469–74. https://doi.org/10.1016/j.ejcts.2007.06.012 (2007).
doi: 10.1016/j.ejcts.2007.06.012
pubmed: 17658266
Baranowska, O. et al. Factors affecting long-term survival after aortic valve replacement. Kardiol. Pol. 70, 1120–1129 (2012).
Penso, M. et al. Predicting long-term mortality in tavi patients using machine learning techniques. J. Cardiovasc. Dev. Dis. 8. https://doi.org/10.3390/jcdd8040044 (2021).
Sanada, F. et al. Source of chronic inflammation in aging. Front. Cardiovasc. Med. 5, 12. https://doi.org/10.3389/fcvm.2018.00012 (2018).
doi: 10.3389/fcvm.2018.00012
pubmed: 29564335
pmcid: 5850851
Ronit, A. et al. Plasma albumin and incident cardiovascular disease: Results from the cgps and an updated meta-analysis. Arterioscler. Thromb. Vasc. Biol. 40, 473–482. https://doi.org/10.1161/ATVBAHA.119.313681 (2020).
doi: 10.1161/ATVBAHA.119.313681
pubmed: 31852221
Tsalamandris, S. et al. The role of inflammation in diabetes: Current concepts and future perspectives. Eur. Cardiol. 14, 50–59. https://doi.org/10.15420/ecr.2018.33.1 (2019).
Fuster, J. J. et al. Clonal hematopoiesis associated with tet2 deficiency accelerates atherosclerosis development in mice. Science 355, 842–847. https://doi.org/10.1126/science.aag1381 (2017).
doi: 10.1126/science.aag1381
pubmed: 28104796
pmcid: 5542057