![[PDF]](/pb-assets/Icons/adobe-pdf-icon-1498649896243.png){kind=icon}
Abstract
Developing a personalized risk prediction model of death is fundamental for improving patient care and touches on the realm of personalized medicine. The increasing availability of genomic information and large-scale meta-analytic data sets for clinicians has motivated the extension of traditional survival prediction based on the Cox proportional hazards model. The aim of our paper is to develop a personalized risk prediction formula for death according to genetic factors and dynamic tumour progression status based on meta-analytic data. To this end, we extend the existing joint frailty-copula model to a model allowing for high-dimensional genetic factors. In addition, we propose a dynamic prediction formula to predict death given tumour progression events possibly occurring after treatment or surgery. For clinical use, we implement the computation software of the prediction formula in the joint.Cox R package. We also develop a tool to validate the performance of the prediction formula by assessing the prediction error. We illustrate the method with the meta-analysis of individual patient data on ovarian cancer patients.
References
| 1. | Graf, E, Schmoor, C, Sauerbrei, W Assessment and comparison of prognostic classification schemes for survival data. Stat Med 1999; 18: 2529–2545. Google Scholar | Medline | ISI |
| 2. | Gerds, TA, Schumacher, M. Consistent estimation of the expected Brier score in general survival models with right-censored event times. Biometrical J 2006; 48: 1029–1040. Google Scholar | Medline | ISI |
| 3. | Cox, DR . Regression models and life-tables (with discussion). J R Stat Soc Ser B 1972; 34: 187–220. Google Scholar |
| 4. | Jenssen, TK, Kuo, WP, Stokke, T Association between gene expressions in breast cancer and patient survival. Hum Genet 2002; 111: 411–420. Google Scholar | Medline | ISI |
| 5. | Sabatier, R, Finetti, P, Adelaide, J Down-regulation of ECRG4, a candidate tumor suppressor gene, in human breast cancer. PLoS One 2011; 6: e27656–e27656. Google Scholar | Medline | ISI |
| 6. | Lossos, IS, Czerwinski, DK, Alizadeh, AA Prediction of survival in diffuse large-B-cell lymphoma based on the expression of six genes. N Engl J Med 2004; 350: 1828–1837. Google Scholar | Medline | ISI |
| 7. | Alizadeh, AA, Gentles, AJ, Alencar, AJ Prediction of survival in diffuse large B-cell lymphoma based on the expression of 2 genes reflecting tumor and microenvironment. Blood 2011; 118: 1350–1358. Google Scholar | Medline | ISI |
| 8. | Beer, DG, Kardia, SLR, Huang, CC Gene-expression profiles predict survival of patients with lung adenocarcinoma. Nat Med 2002; 8: 816–824. Google Scholar | Medline | ISI |
| 9. | Chen, HY, Yu, SL, Chen, CH A five-gene signature and clinical outcome in non-small-cell lung cancer. N Engl J Med 2007; 356: 11–20. Google Scholar | Medline | ISI |
| 10. | Shedden, K, Taylor, JMG, Enkemann, SA Gene expression-based survival prediction in lung adenocarcinoma: a multi-site, blinded validation study. Nat Med 2008; 14: 822–827. Google Scholar | Medline | ISI |
| 11. | Popple, A, Durrant, LG, Spendlove, I The chemokine, CXCL12, is an independent predictor of poor survival in ovarian cancer. Br J Canc 2012; 106: 1306–1313. Google Scholar | Medline | ISI |
| 12. | Yoshihara, K, Tsunoda, T, Shigemizu, D High-risk ovarian cancer based on 126-gene expression signature is uniquely characterized by downregulation of antigen presentation pathway. Clin Canc Res 2012; 18: 1374–1385. Google Scholar | Medline |
| 13. | Waldron, L, Haibe-Kains, B, Culhane, AC Comparative meta-analysis of prognostic gene signatures for late-stage ovarian cancer. J Natl Canc Inst 2014; 106: dju049–dju049. Google Scholar | Medline |
| 14. | Michiels, S, Koscielny, S, Hill, C. Prediction of cancer outcome with microarrays: a multiple random validation strategy. Lancet 2005; 365: 488–492. Google Scholar | Medline | ISI |
| 15. | Matsui, S . Predicting survival outcomes using subsets of significant genes in prognostic marker studies with microarrays. BMC Bioinformatics 2006; 7: 156–156. Google Scholar | Medline | ISI |
| 16. | Schumacher, M, Binder, H, Gerds, T. Assessment of survival prediction models based on microarray data. Bioinformatics 2007; 23: 1768–1774. Google Scholar | Medline |
| 17. | Bøvelstad, HM, Nygård, S, Storvold, HL Predicting survival from microarray data – a comparative study. Bioinformatics 2007; 23: 2080–2087. Google Scholar | Medline | ISI |
| 18. | Binder, H, Schumacher, M. Allowing for mandatory covariates in boosting estimation of sparse high-dimensional survival models. BMC Bioinformatics 2008; 9: 14–14. Google Scholar | Medline |
| 19. | Bøvelstad, HM, Nygård, S, Borgan, Ø. Survival prediction from clinico-genomic models – a comparative study. BMC Bioinformatics 2009; 10: 1–1. Google Scholar | Medline |
| 20. | Simon, RM, Subramanian, J, Li, MC Using cross-validation to evaluate predictive accuracy of survival risk classifiers based on high-dimensional data. Brief Bioinformatics 2011; 12: 203–214. Google Scholar | Medline | ISI |
| 21. | Goeman, J, Meijer, R, Chaturvedi, N. R penalized: L1 (lasso and fused lasso) and L2 (ridge) penalized estimation in GLMs and in the Cox model. CRAN 2016. version 0.9-47. Google Scholar |
| 22. | Van Houwelingen, H . Dynamic prediction by landmarking in event history analysis. Scand J Stat 2007; 34: 70–85. Google Scholar | ISI |
| 23. | Van Houwelingen, HC, Putter, H. Dynamic prediction in clinical survival analysis, Boca Raton: CRC Press, 2011. Google Scholar | Crossref |
| 24. | Mauguen, A, Rachet, B, Mathoulin-Pélissier, S Dynamic prediction of risk of death using history of cancer recurrences in joint frailty models. Stat Med 2013; 32: 5366–5380. Google Scholar | Medline | ISI |
| 25. | Mauguen, A, Rachet, B, Mathoulin-Pélissier, S Validation of death prediction after breast cancer relapses using joint models. BMC Med Res Methodol 2015; 15: 27–27. Google Scholar | Medline | ISI |
| 26. | Rizopoulos, D . Dynamic predictions and prospective accuracy in joint models for longitudinal and time-to-event data. Biometrics 2011; 67: 819–829. Google Scholar | Medline | ISI |
| 27. | Taylor, JM, Park, Y, Ankerst, DP Real‐time individual predictions of prostate cancer recurrence using joint models. Biometrics 2013; 69: 206–213. Google Scholar | Medline | ISI |
| 28. | Sène, M, Taylor, JM, Dignam, JJ Individualized dynamic prediction of prostate cancer recurrence with and without the initiation of a second treatment: development and validation. Stat Methods in Med Res 2016; 25: 2972–2991. Google Scholar | SAGE Journals | ISI |
| 29. | Proust-Lima, C, Séne, M, Taylor, JM Joint latent class models for longitudinal and time-to-event data: a review. Stat Methods Med Res 2014; 23: 74–90. Google Scholar | SAGE Journals | ISI |
| 30. | Rondeau, V, Mauguen, A, Laurent, A Dynamic prediction models for clustered and interval-censored outcomes: investigating the intra-couple correlation in the risk of dementia. Stat Methods Med Res 2015; 26: 2168–2183. Google Scholar | Medline |
| 31. | Król, A, Ferrer, L, Pignon, JP Joint model for left-censored longitudinal data, recurrent events and terminal event: predictive abilities of tumor burden for cancer evolution with application to the FFCD 2000-05 trial. Biometrics. 2016. DOI: 10.1111/biom.12490. Google Scholar |
| 32. | Emura, T, Nakatochi, M, Murotani, K A joint frailty-copula model between tumour progression and death for meta-analysis. Stat Methods Med Res 2015; 26: 2649–2666. Google Scholar | Medline |
| 33. | Ganzfried, BF, Riester, M, Haibe-Kains, B Curated ovarian data: clinically annotated data for the ovarian cancer transcriptome. Database 2013. Article ID bat013. DOI:10.1093/database/bat013. Google Scholar | Medline |
| 34. | Rondeau, V, Pignon, JP, Michiels, S. A joint model for dependence between clustered times to tumour progression and deaths: a meta-analysis of chemotherapy in head and neck cancer. Stat Methods Med Res 2015; 24: 711–729. Google Scholar | SAGE Journals | ISI |
| 35. | Haneuse, S, Lee, KH. Semi-competing risks data analysis, accounting for death as a competing risk when the outcome of interest is nonterminal. Circ Cardiovasc Qual Outcomes 2016; 9: 322–331. Google Scholar | Medline |
| 36. | Joly, P, Commenges, D, Letenneur, L. A penalized likelihood approach for arbitrary censored and truncated data: application to age-specific incidence of dementia. Biometrics 1998; 54: 185–194. Google Scholar | Medline | ISI |
| 37. | Emura, T, Chen, YH. Gene selection for survival data under dependent censoring, a copula-based approach. Stat Methods Med Res 2016; 25: 2840–2857. Google Scholar | SAGE Journals | ISI |
| 38. | Nelsen, RB . An introduction to copulas, 2nd ed. New York: Springer, 2006. Google Scholar |
| 39. | Tibshirani, R . The lasso method for variable selection in the Cox model. Stat Med 1997; 16: 385–395. Google Scholar | Medline | ISI |
| 40. | Van Houwelingen, HC, Bruinsma, T, Hart, AA Cross-validated Cox regression on microarray gene expression data. Stat Med 2006; 25: 3201–3216. Google Scholar | Medline |
| 41. | Tukey, JW . Tightening the clinical trial. Contr Clin Trials 1993; 14: 266–285. Google Scholar | Medline |
| 42. | Emura, T, Chen, YH, Chen, HY. Survival prediction based on compound covariate under Cox proportional hazard models. PLoS One 2012; 7: e47627–e47627. Google Scholar | Medline | ISI |
| 43. | Radmacher, MD, Mcshane, LM, Simon, RM. A paradigm for class prediction using gene expression profiles. J Comput Biol 2002; 9: 505–511. Google Scholar | Medline | ISI |
| 44. | Matsui, S, Simon, RM, Qu, P Developing and validating continuous genomic signatures in randomized clinical trials for predictive medicine. Clin Canc Res 2012; 18: 6065–6073. Google Scholar | Medline | ISI |
| 45. | Simon, RM . Design and analysis of DNA microarray investigations, New York: Springer Science & Business Media, 2003. Google Scholar |
| 46. | Emura, T . R joint.Cox: penalized likelihood estimation and dynamic prediction under the joint frailty-copula models between tumour progression and death for meta-analysis. CRAN. version 2.10 2016-10-30. Google Scholar |
| 47. | Rondeau, V, Gonzalez, JR, Mazroui, Y R frailtypack: general frailty models: shared, joint and nested frailty models with prediction. CRAN. version 2.8.3 2016-01-13. Google Scholar |
| 48. | Hastie, T, Tibshirani, R, Friedman, J. The elements of statistical learning, New York: Springer, 2009. Google Scholar |
| 49. | Schleidgen, S, Klingler, C, Bertram, T What is personalized medicine: sharpening a vague term based on a systematic literature review. BMC Med Ethic 2013; 14: 55–55. Google Scholar | Medline | ISI |
| 50. | Commenges, D, Proust-Lima, C, Samieri, C A universal approximate cross-validation criterion for regular risk functions. Int J Biostat 2015; 11: 51–67. Google Scholar | Medline |
| 51. | Burzykowski, T, Molenberghs, G, Buyse, M Validation of surrogate end points in multiple randomized clinical trials with failure time end points. Appl Stat 2001; 50: 405–422. Google Scholar | ISI |
| 52. | Burzykowski, T, Molenberghs, G, Buyse, M. The evaluation of surrogate endpoints, New York: Springer, 2005. Google Scholar |
| 53. | Michiels, S, Le Maître, A, Buyse, M Surrogate endpoints for overall survival in locally advanced head and neck cancer: meta-analyses of individual patient data. Lancet Oncol 2009; 10: 341–350. Google Scholar | Medline | ISI |
| 54. | Buyse, M, Sargent, DJ, Saad, ED. Survival is not a good outcome for randomized trials with effective subsequent therapies. J Clin Oncol 2011; 29: 4719–4720. Google Scholar | Medline | ISI |
| 55. | Oba, K, Paoletti, X, Alberts, S Disease-free survival as a surrogate for overall survival in adjuvant trials of gastric cancer: a meta-analysis. J Natl Canc Inst 2013; 105: 1600–1607. Google Scholar | Medline |
| 56. | Bellera, CA, MacGrogan, G, Debled, M Variables with time-varying effects and the Cox model: some statistical concepts illustrated with a prognostic factor study in breast cancer. BMC Med Res Methodol 2010; 10: 1–1. Google Scholar | Medline |
| 57. | Mazroui, Y, Mauguen, A, Mathoulin-Pélissier, S Time-varying coefficients in a multivariate frailty model: application to breast cancer recurrences of several types and death. Lifetime Data Anal 2016; 22: 191–215. Google Scholar | Medline |
| 58. | Baulies, S, Belin, L, Mallon, P Time-varying effect and long-term survival analysis in breast cancer patients treated with neoadjuvant chemotherapy. Br J Canc 2015; 113: 30–36. Google Scholar | Medline |
| 59. | Putter, H, Sasako, M, Hartgrink, H Long-term survival with non-proportional hazards: results from the Dutch Gastric Cancer Trial. Stat Med 2005; 24: 2807–2821. Google Scholar | Medline |
