Comparison of models for stroke-free survival prediction in patients with CADASIL.
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
17 Dec 2023
17 Dec 2023
Historique:
received:
17
04
2023
accepted:
09
12
2023
medline:
18
12
2023
pubmed:
18
12
2023
entrez:
17
12
2023
Statut:
epublish
Résumé
Cerebral autosomal dominant arteriopathy with subcortical infarcts and leukoencephalopathy, which is caused by mutations of the NOTCH3 gene, has a large heterogeneous progression, presenting with declines of various clinical scores and occurrences of various clinical event. To help assess disease progression, this work focused on predicting the composite endpoint of stroke-free survival time by comparing the performance of Cox proportional hazards regression to that of machine learning models using one of four feature selection approaches applied to demographic, clinical and magnetic resonance imaging observational data collected from a study cohort of 482 patients. The quality of the modeling process and the predictive performance were evaluated in a nested cross-validation procedure using the time-dependent Brier Score and AUC at 5 years from baseline, the former measuring the overall performance including calibration and the latter highlighting the discrimination ability, with both metrics taking into account the presence of right-censoring. The best model for each metric was the componentwise gradient boosting model with a mean Brier score of 0.165 and the random survival forest model with a mean AUC of 0.773, both combined with the LASSO feature selection method.
Identifiants
pubmed: 38105268
doi: 10.1038/s41598-023-49552-w
pii: 10.1038/s41598-023-49552-w
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
22443Subventions
Organisme : Agence Nationale de la Recherche
ID : ANR-16-RHUS-004
Informations de copyright
© 2023. The Author(s).
Références
Singh, R. & Mukhopadhyay, K. Survival analysis in clinical trials: Basics and must know areas. Perspect. Clin. Res. 2, 145 (2011).
pubmed: 22145125
pmcid: 3227332
doi: 10.4103/2229-3485.86872
Wang, M. M. Cadasil. Handb. Clin. Neurol. 148, 733–743 (2018).
pubmed: 29478611
doi: 10.1016/B978-0-444-64076-5.00047-8
Papakonstantinou, E. et al. NOTCH3 and CADASIL syndrome: A genetic and structural overview. EMBnet J. 24, e921 (2019).
pubmed: 31218211
pmcid: 6583802
doi: 10.14806/ej.24.0.921
Rutten, J. W. et al. Archetypal NOTCH3 mutations frequent in public exome: Implications for CADASIL. Ann. Clin. Transl. Neurol. 3, 844–853 (2016).
pubmed: 27844030
pmcid: 5099530
doi: 10.1002/acn3.344
Opherk, C. Long-term prognosis and causes of death in CADASIL: A retrospective study in 411 patients. Brain 127, 2533–2539 (2004).
pubmed: 15364702
doi: 10.1093/brain/awh282
Adib-Samii, P., Brice, G., Martin, R. J. & Markus, H. S. Clinical spectrum of CADASIL and the effect of cardiovascular risk factors on phenotype. Stroke 41, 630–634 (2010).
pubmed: 20167921
doi: 10.1161/STROKEAHA.109.568402
Chabriat, H. et al. Predictors of clinical worsening in cerebral autosomal dominant arteriopathy with subcortical infarcts and leukoencephalopathy: Prospective cohort study. Stroke 47, 4–11 (2016).
pubmed: 26578659
doi: 10.1161/STROKEAHA.115.010696
Quinn, T. J., Dawson, J., Walters, M. R. & Lees, K. R. Reliability of the modified rankin scale: A systematic review. Stroke 40, 3393–3395 (2009).
pubmed: 19679846
doi: 10.1161/STROKEAHA.109.557256
Benjamin, P. et al. Strategic lacunes and their relationship to cognitive impairment in cerebral small vessel disease. Neuroimage Clin. 4, 828–837 (2014).
pubmed: 24936433
pmcid: 4055894
doi: 10.1016/j.nicl.2014.05.009
Ling, Y. & Chabriat, H. Incident cerebral lacunes: A review. J. Cereb. Blood Flow Metab. 40, 909–921 (2020).
pubmed: 32126874
pmcid: 7181083
doi: 10.1177/0271678X20908361
Yates, P. A. et al. Cerebral microbleeds: A review of clinical, genetic, and neuroimaging associations. Front. Neurol. 4, 205 (2014).
pubmed: 24432010
pmcid: 3881231
doi: 10.3389/fneur.2013.00205
Rudick, R. A., Fisher, E., Lee, J. C., Simon, J. & Jacobs, L. Use of the brain parenchymal fraction to measure whole brain atrophy in relapsing-remitting MS. Multiple sclerosis collaborative research group. Neurology 53, 1698–1704 (1999).
pubmed: 10563615
doi: 10.1212/WNL.53.8.1698
Vågberg, M., Granåsen, G. & Svenningsson, A. Brain parenchymal fraction in healthy adults—A Systematic review of the literature. PLoS ONE 12, e0170018 (2017).
pubmed: 28095463
pmcid: 5240949
doi: 10.1371/journal.pone.0170018
Gravesteijn, G. et al. Eighteen-year disease progression and survival in CADASIL. J. Stroke 23, 132–134 (2021).
pubmed: 33600711
pmcid: 7900403
doi: 10.5853/jos.2020.04112
Stel, V. S., Dekker, F. W., Tripepi, G., Zoccali, C. & Jager, K. J. Survival analysis II: Cox regression. Nephron Clin. Pract. 119, c255–c260 (2011).
pubmed: 21921637
doi: 10.1159/000328916
Benner, A., Zucknick, M., Hielscher, T., Ittrich, C. & Mansmann, U. High-dimensional cox models: The choice of penalty as part of the model building process. Biom. J. 52, 50–69 (2010).
pubmed: 20166132
doi: 10.1002/bimj.200900064
Suchting, R., Hébert, E. T., Ma, P., Kendzor, D. E. & Businelle, M. S. Using elastic net penalized cox proportional hazards regression to identify predictors of imminent smoking lapse. Nicotine Tob. Res. 21, 173–179 (2019).
pubmed: 29059349
doi: 10.1093/ntr/ntx201
Zhou, D. et al. A prognostic nomogram based on LASSO Cox regression in patients with alpha-fetoprotein-negative hepatocellular carcinoma following non-surgical therapy. BMC Cancer 21, 246 (2021).
pubmed: 33685417
pmcid: 7938545
doi: 10.1186/s12885-021-07916-3
Spooner, A. et al. A comparison of machine learning methods for survival analysis of high-dimensional clinical data for dementia prediction. Sci. Rep. 10, 20410 (2020).
pubmed: 33230128
pmcid: 7683682
doi: 10.1038/s41598-020-77220-w
Zhou, Y. & McArdle, J. J. Rationale and applications of survival tree and survival ensemble methods. Psychometrika 80, 811–833 (2015).
pubmed: 25228495
doi: 10.1007/s11336-014-9413-1
Ramezankhani, A., Tohidi, M., Azizi, F. & Hadaegh, F. Application of survival tree analysis for exploration of potential interactions between predictors of incident chronic kidney disease: A 15-year follow-up study. J. Transl. Med. 15, 240 (2017).
pubmed: 29183386
pmcid: 5706148
doi: 10.1186/s12967-017-1346-x
Bou-Hamad, I., Larocque, D. & Ben-Ameur, H. A review of survival trees. Stat. Surv. 5, 44–71 (2011).
doi: 10.1214/09-SS047
Ishwaran, H., Kogalur, U. B., Blackstone, E. H. & Lauer, M. S. Random survival forests. Ann. Appl. Stat. 2, 841–860 (2008).
doi: 10.1214/08-AOAS169
Chen, Y., Jia, Z., Mercola, D. & Xie, X. A gradient boosting algorithm for survival analysis via direct optimization of concordance index. Comput. Math. Methods Med. 2013, 1–8 (2013).
Klug, M. et al. A gradient boosting machine learning model for predicting early mortality in the emergency department triage: Devising a nine-point triage score. J. Gen. Intern. Med. 35, 220–227 (2020).
pubmed: 31677104
doi: 10.1007/s11606-019-05512-7
Written on behalf of AME Big-Data Clinical Trial Collaborative Group et al. Predictive analytics with gradient boosting in clinical medicine. Ann. Transl. Med 7, 152–152 (2019).
doi: 10.21037/atm.2019.03.29
Dougherty, E., Hua, J. & Sima, C. Performance of feature selection methods. Curr. Genom. 10, 365–374 (2009).
doi: 10.2174/138920209789177629
Neums, L., Meier, R., Koestler, D. C. & Thompson, J. A. Improving survival prediction using a novel feature selection and feature reduction framework based on the integration of clinical and molecular data. Pac. Symp. Biocomput. 25, 415–426 (2020).
pubmed: 31797615
pmcid: 6941850
Briscoe, E. & Feldman, J. Conceptual complexity and the bias/variance tradeoff. Cognition 118, 2–16 (2011).
pubmed: 21112048
doi: 10.1016/j.cognition.2010.10.004
Bommert, A., Welchowski, T., Schmid, M. & Rahnenführer, J. Benchmark of filter methods for feature selection in high-dimensional gene expression survival data. Brief. Bioinform. 23, bbab354 (2022).
pubmed: 34498681
doi: 10.1093/bib/bbab354
Mustaqeem, A., Anwar, S. M., Majid, M. & Khan, A. R. Wrapper method for feature selection to classify cardiac arrhythmia. in 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) 3656–3659 (IEEE, 2017). https://doi.org/10.1109/EMBC.2017.8037650 .
Pudjihartono, N., Fadason, T., Kempa-Liehr, A. W. & O’Sullivan, J. M. A review of feature selection methods for machine learning-based disease risk prediction. Front. Bioinform. 2, 927312 (2022).
pubmed: 36304293
pmcid: 9580915
doi: 10.3389/fbinf.2022.927312
Vabalas, A., Gowen, E., Poliakoff, E. & Casson, A. J. Machine learning algorithm validation with a limited sample size. PLoS ONE 14, e0224365 (2019).
pubmed: 31697686
pmcid: 6837442
doi: 10.1371/journal.pone.0224365
Wu, C. & Li, L. Quantifying and estimating the predictive accuracy for censored time-to-event data with competing risks: predictive accuracy for censored time-to-event data. Stat. Med. 37, 3106–3124 (2018).
pubmed: 29766537
doi: 10.1002/sim.7806
Fang, C. et al. Arteriolar neuropathology in cerebral microvascular disease. Neuropathol. Appl. Neurobiol. 49, e12875 (2023).
pubmed: 36564356
pmcid: 10350910
doi: 10.1111/nan.12875
Wang, J. et al. Correction of a CADASIL point mutation using adenine base editors in hiPSCs and blood vessel organoids. J. Genet. Genom. https://doi.org/10.1016/j.jgg.2023.04.013 (2023).
doi: 10.1016/j.jgg.2023.04.013
Dupé, C. et al. Phenotypic variability in 446 CADASIL patients: Impact of NOTCH3 gene mutation location in addition to the effects of age, sex and vascular risk factors. J. Cereb. Blood Flow Metab. 43, 153–166 (2023).
pubmed: 36254369
doi: 10.1177/0271678X221126280
Jouvent, E. et al. Prediction of 3-year clinical course in CADASIL. Neurology 87, 1787–1795 (2016).
pubmed: 27694265
pmcid: 5089530
doi: 10.1212/WNL.0000000000003252
Wang, J., Li, J., Kong, F., Lv, H. & Guo, Z. Bipolar II disorder as the initial presentation of CADASIL: An underdiagnosed manifestation. Neuropsychiatr. Dis. Treat. 13, 2175–2179 (2017).
pubmed: 28860774
pmcid: 5565239
doi: 10.2147/NDT.S142321
Chabriat, H. & Lesnik Oberstein, S. Cognition, mood and behavior in CADASIL. Cereb. Circ. Cogn. Behav. 3, 100043 (2022).
pubmed: 36324403
pmcid: 9616390
Jolly, A. A., Nannoni, S., Edwards, H., Morris, R. G. & Markus, H. S. Prevalence and predictors of vascular cognitive impairment in patients with CADASIL. Neurology https://doi.org/10.1212/WNL.0000000000200607 (2022).
doi: 10.1212/WNL.0000000000200607
pubmed: 35641310
pmcid: 9421602
Cava, W. L., Bauer, C., Moore, J. H. & Pendergrass, S. A. Interpretation of machine learning predictions for patient outcomes in electronic health records. AMIA Annu. Symp. Proc. 2019, 572–581 (2019).
pubmed: 32308851
Ginestet, P. G., Gabriel, E. E. & Sachs, M. C. Survival stacking with multiple data types using pseudo-observation-based-AUC loss. J. Biopharm. Stat. https://doi.org/10.1080/10543406.2022.2041655 (2022).
doi: 10.1080/10543406.2022.2041655
pubmed: 35574690
Long, J. D. & Mills, J. A. Joint modeling of multivariate longitudinal data and survival data in several observational studies of Huntington’s disease. BMC Med. Res. Methodol. 18, 138 (2018).
pubmed: 30445915
pmcid: 6240282
doi: 10.1186/s12874-018-0592-9
Amorim, L. D. & Cai, J. Modelling recurrent events: A tutorial for analysis in epidemiology. Int. J. Epidemiol. 44, 324–333 (2015).
pubmed: 25501468
doi: 10.1093/ije/dyu222
Zhao, J. et al. Learning from longitudinal data in electronic health record and genetic data to improve cardiovascular event prediction. Sci. Rep. 9, 717 (2019).
pubmed: 30679510
pmcid: 6345960
doi: 10.1038/s41598-018-36745-x
Collin, C., Wade, D. T., Davies, S. & Horne, V. The Barthel ADL Index: A reliability study. Int. Disabil. Stud. 10, 61–63 (1988).
pubmed: 3403500
doi: 10.3109/09638288809164103
Cockrell, J. R. & Folstein, M. F. Mini-mental state examination (MMSE). Psychopharmacol. Bull. 24, 689–692 (1988).
pubmed: 3249771
Paraskevas, G. P. et al. The diagnostic value of mattis dementia rating scale-initiation perseveration subscale in vascular cognitive disorders. Neuro Res. 1, 1–6 (2019).
doi: 10.35702/nrj.10002
Ferris, S. H. General measures of cognition. Int. Psychogeriatr. 15, 215–217 (2003).
pubmed: 16191243
doi: 10.1017/S1041610203009220
Bowie, C. R. & Harvey, P. D. Administration and interpretation of the Trail Making Test. Nat. Protoc. 1, 2277–2281 (2006).
pubmed: 17406468
doi: 10.1038/nprot.2006.390
Cerciello, M., Isella, V., Proserpi, A. & Papagno, C. Assessment of free and cued recall in Alzheimer’s disease and vascular and frontotemporal dementia with 24-item Grober and Buschke test. Neurol. Sci. 38, 115–122 (2017).
pubmed: 27672033
doi: 10.1007/s10072-016-2722-7
He, K. et al. Component-wise gradient boosting and false discovery control in survival analysis with high-dimensional covariates. Bioinformatics https://doi.org/10.1093/bioinformatics/btv517 (2015).
doi: 10.1093/bioinformatics/btv517
pubmed: 26677964
pmcid: 4907396
Tibshirani, R. The lasso method for variable selection in the Cox model. Stat. Med. 16, 385–395 (1997).
pubmed: 9044528
doi: 10.1002/(SICI)1097-0258(19970228)16:4<385::AID-SIM380>3.0.CO;2-3
Gholami, B., Norton, I., Tannenbaum, A. R. & Agar, N. Y. R. Recursive feature elimination for brain tumor classification using desorption electrospray ionization mass spectrometry imaging. In 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society 5258–5261 (IEEE, 2012). https://doi.org/10.1109/EMBC.2012.6347180 .