Recent development on statistical methods for personalized medicine discovery

Abstract

It is well documented that patients can show significant heterogeneous responses to treatments so the best treatment strategies may require adaptation over individuals and time. Recently, a number of new statistical methods have been developed to tackle the important problem of estimating personalized treatment rules using single-stage or multiple-stage clinical data. In this paper, we provide an overview of these methods and list a number of challenges.

Keywords

dynamic treatment regimes / personalized medicine / reinforcement learning / Q-learning

References

[1] Grünwald V, Hidalgo M. Developing inhibitors of the epidermal growth factor receptor for cancer treatment. J Natl Cancer Inst2003; 95(12): 851–867

[2] Buzdar AU. Role of biologic therapy and chemotherapy in hormone receptor- and HER2-positive breast cancer. Ann Oncol2009; 20(6): 993–999

[3] Piper WE, Boroto DR, Joyce AS, McCallum M, Azim HFA. Pattern of alliance and outcome in short-term individual psychotherapy. Psychotherapy1995; 32(4): 639–647

[4] Crits-Christoph P, Siqueland L, Blaine J, Frank A, Luborsky L, Onken LS, Muenz LR, Thase ME, Weiss RD, Gastfriend DR, Woody GE, Barber JP, Butler SF, Daley D, Salloum I, Bishop S, Najavits LM, Lis J, Mercer D, Griffin ML, Moras K, Beck AT. Psychosocial treatments for cocaine dependence: National Institute on Drug Abuse Collaborative Cocaine Treatment Study. Arch Gen Psychiatry1999; 56(6): 493–502

[5] Ishigooka J, Murasaki M, Miura S, Group TOLPIS. Olanzapine optimal dose: results of an open-label multicenter study in schizophrenic patients. olanzapine late-phase ii study group. Psychiatry Clin Neurosci2000; 54(4): 467–478

[6] Fukuoka M, Wu YL, Thongprasert S, Sunpaweravong P, Leong SS, Sriuranpong V, Chao TY, Nakagawa K, Chu DT, Saijo N, Duffield EL, Rukazenkov Y, Speake G, Jiang H, Armour AA, To KF, Yang JC, Mok TS. Biomarker analyses and final overall survival results from a phase III, randomized, open-label, first-line study of gefitinib versus carboplatin/paclitaxel in clinically selected patients with advanced non-small-cell lung cancer in Asia (IPASS). J Clin Oncol2011; 29(21): 2866–2874

[7] Wagner EH, Austin BT, Davis C, Hindmarsh M, Schaefer J, Bonomi A. Improving chronic illness care: translating evidence into action. Health Aff (Millwood)2001; 20(6): 64–78

[8] Murphy SA, Oslin DW, Rush AJ, Zhu J ; MCATS. Methodological challenges in constructing effective treatment sequences for chronic psychiatric disorders. Neuropsychopharmacology2007; 32(2): 257–262

[9] Socinski MA, Stinchcombe TE. Duration of first-line chemotherapy in advanced non small-cell lung cancer: less is more in the era of effective subsequent therapies. J Clin Oncol2007; 25(33): 5155–5157

[10] Flume PA, O’Sullivan BP, Robinson KA, Goss CH, Mogayzel PJ Jr, Willey-Courand DB, Bujan J, Finder J, Lester M, Quittell L, Rosenblatt R, Vender RL, Hazle L, Sabadosa K, Marshall B; Cystic Fibrosis Foundation, Pulmonary Therapies Committee. Cystic fibrosis pulmonary guidelines: chronic medications for maintenance of lung health. Am J Respir Crit Care Med2007; 176(10): 957–969

[11] Hamburg MA, Collins FS. The path to personalized medicine. N Engl J Med2010; 363(4): 301–304

[12] Sargent DJ, Conley BA, Allegra C, Collette L. Clinical trial designs for predictive marker validation in cancer treatment trials. J Clin Oncol2005; 23(9): 2020–2027

[13] Insel TR. Translating scientific opportunity into public health impact: a strategic plan for research on mental illness. Arch Gen Psychiatry2009; 66(2): 128–133

[14] Murphy SA. An experimental design for the development of adaptive treatment strategies. Stat Med2005; 24(10): 1455–1481

[15] Pocock SJ, Assmann SE, Enos LE, Kasten LE. Subgroup analysis, covariate adjustment and baseline comparisons in clinical trial reporting: current practice and problems. Stat Med2002; 21(19): 2917–2930

[16] Wang R, Lagakos SW, Ware JH, Hunter DJ, Drazen JM, Drazen M. Statistics in medicine—reporting of subgroup analyses in clinical trials. N Engl J Med2007; 357(21): 2189–2194

[17] Kent D, Hayward R. Subgroup analyses in clinical trials. N Engl J Med2008; 358(11): 1199

[18] Assmann SF, Pocock SJ, Enos LE, Kasten LE. Subgroup analysis and other (mis)uses of baseline data in clinical trials. Lancet2000; 355(9209): 1064–1069

[19] Lagakos SW. The challenge of subgroup analyses—reporting without distorting. N Engl J Med2006; 354(16): 1667–1669

[20] Byar DP. Assessing apparent treatment—covariate interactions in randomized clinical trials. Stat Med1985; 4(3): 255–263

[21] Sacks FM, Pfeffer MA, Moye LA, Rouleau JL, Rutherford JD, Cole TG, Brown L, Warnica JW, Arnold JM, Wun CC, Davis BR, Braunwald E. The effect of pravastatin on coronary events after myocardial infarction in patients with average cholesterol levels. Cholesterol and Recurrent Events Trial investigators. N Engl J Med1996; 335(14): 1001–1009

[22] Kehl V, Ulm K. Responder identicatifion in clinical trials with censored data. Comput Stat Data Anal2006; 50(5):1338–1355

[23] Eagle KA, Lim MJ, Dabbous OH, Pieper KS, Goldberg RJ, Van de Werf F, Goodman SG, Granger CB, Steg PG, Gore JM, Budaj A, Avezum A, Flather MD, Fox KA; GRACE Investigators. A validated prediction model for all forms of acute coronary syndrome: estimating the risk of 6-month postdischarge death in an international registry. JAMA2004; 291(22): 2727–2733

[24] Marlowe DB, Festinger DS, Dugosh KL, Lee PA, Benasutti KM. Adapting judicial supervision to the risk level of drug offenders: Discharge and 6-month outcomes from a prospective matching study. Drug Alcohol Depend2007;88 (Suppl 2):S4–13

[25] Cai T, Tian L, Uno H, Solomon SD, Wei LJ. Calibrating parametric subject-specific risk estimation. Biometrika2010; 97(2): 389–404

[26] Qian M, Murphy SA. Performance guarantees for individualized treatment rules. Ann Stat2011; 39(2): 1180–1210

[27] Robins J. Correcting for non-compliance in randomized trials using structural nested mean models. Commun Stat1994; 23(8): 2379–2412

[28] Murphy SA. Optimal dynamic treatment regimes. J R Stat Soc, B2003; 65(2): 331–355

[29] Rosenwald A, Wright G, Chan WC, Connors JM, Campo E, Fisher RI, Gascoyne RD, Muller-Hermelink HK, Smeland EB, Giltnane JM, Hurt EM, Zhao H, Averett L, Yang L, Wilson WH, Jaffe ES, Simon R, Klausner RD, Powell J, Duffey PL, Longo DL, Greiner TC, Weisenburger DD, Sanger WG, Dave BJ, Lynch JC, Vose J, Armitage JO, Montserrat E, López-Guillermo A, Grogan TM, Miller TP, LeBlanc M, Ott G, Kvaloy S, Delabie J, Holte H, Krajci P, Stokke T, Staudt LM; Lymphoma/Leukemia Molecular Profiling Project. The use of molecular profiling to predict survival after chemotherapy for diffuse large-B-cell lymphoma. N Engl J Med2002; 346(25): 1937–1947

[30] van’t Veer LJ, Bernards R. Enabling personalized cancer medicine through analysis of gene-expression patterns. Nature2008; 452(7187): 564–570

[31] Murphy SA. A generalization error for q-learning. J Mach Learn Res2005; 6: 1073–1097

[32] Zhao YQ, Zeng D, Rush AJ, Kosorok MR. Estimating individualized treatment rules using outcome weighted learning. J Am Stat Assoc2012; 107(499):1106–1118

[33] Lavori P W, Dawson R. A design for testing clinical strategies: biased adaptive withinsubject randomization. J R Stat Soc [Ser A]2000; 163: 29–38

[34] Lavori PW, Dawson R. Dynamic treatment regimes: practical design considerations. Clin Trials2004; 1(1): 9–20

[35] Dawson R, Lavori PW. Placebo-free designs for evaluating new mental health treatments: the use of adaptive treatment strategies. Stat Med2004; 23(21): 3249–3262

[36] Thall PF, Millikan RE, Sung HG. Evaluating multiple treatment courses in clinical trials. Stat Med2000; 19(8): 1011–1028

[37] Schneider LS, Tariot PN, Lyketsos CG, Dagerman KS, Davis KL, Davis S, Hsiao JK, Jeste DV, Katz IR, Olin JT, Pollock BG, Rabins PV, Rosenheck RA, Small GW, Lebowitz B, Lieberman JA. National institute of mental health clinical antipsychotic trials of intervention effectiveness (catie): Alzheimer disease trial methodology. Am J Geriatr Psychiatry2001; 9(4): 346–360

[38] Rush AJ, Fava M, Wisniewski SR, Lavori PW, Trivedi MH, Sackeim HA, Thase ME, Nierenberg AA, Quitkin FM, Kashner TM, Kupfer DJ, Rosenbaum JF, Alpert J, Stewart JW, McGrath PJ, Biggs MM, Shores-Wilson K, Lebowitz BD, Ritz L, Niederehe G; STAR*D Investigators Group. Sequenced treatment alternatives to relieve depression (STAR*D): rationale and design. Control Clin Trials2004; 25(1): 119–142

[39] Strecher VJ, McClure JB, Alexander GL, Chakraborty B, Nair VN, Konkel JM, Greene SM, Collins LM, Carlier CC, Wiese CJ, Little RJ, Pomerleau CS, Pomerleau OF. Web-based smoking cessation components and tailoring depth: Results of a randomized trial. Am J Prev Med2008; 34: 373–381

[40] Murphy SA, van der Laan MJ, Robins JM, CPPRG. Marginal mean models for dynamic regimes. J Am Stat Assoc2001; 96(456): 1410–1423

[41] Thall PF, Sung HG, Estey EH. Selecting therapeutic strategies based on efficacy and death in multicourse clinical trials. J Am Stat Assoc2002; 97(457): 29–39

[42] Thall PF, Wooten LH, Logothetis CJ, Millikan RE, Tannir NM. Bayesian and frequentist two-stage treatment strategies based on sequential failure times subject to interval censoring. Stat Med2007; 26(26): 4687–4702

[43] Bellman R. Dynamic Programming. Princeton: Princeton University Press, 1957

[44] Sutton RS, Barto AG. Reinforcement Learning I: Introduction. Cambridge, MA: MIT Press, 1998

[45] Watkins CJCH. Learning from delayed rewards. <DissertationTip/>. Cambridge, UK: Kings College, 1989

[46] Zhao Y, Kosorok MR, Zeng D. Reinforcement learning design for cancer clinical trials. Stat Med2009; 28(26): 3294–3315

[47] Zhao Y, Zeng D, Socinski MA, Kosorok MR. Reinforcement learning strategies for clinical trials in nonsmall cell lung cancer. Biometrics2011; 67(4): 1422–1433

[48] Blatt D, Murphy SA, Zhu J. A-learning for approximate planning. 2004. http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1. 76.5799&rep=rep1&type=pdf (Accessed on December 1, 2012)

[49] Robins JM. Optimal structural nested models for optimal sequential decisions. In: Proceedings of the Second Seattle Symposium on Biostatistics. Springer, 2004:189–326

[50] Moodie EEM, Richardson TS, Stephens DA. Demystifying optimal dynamic treatment regimes. Biometrics2007; 63(2): 447–455

[51] Chakraborty B, Murphy SA, Strecher V. Inference for non-regular parameters in optimal dynamic treatment regimes. Stat Methods Med Res2010; 19(3): 317–343

[52] Schulte PJ, Tsiatis AA, Laber EB, Davidian M. Q and A-learning methods for estimating optimal dynamic treatment regimes. 2012.http://arxiv.org/abs/1202.4177 (Accessed on December 1, 2012)

[53] Goldberg Y, Kosorok MR. Q-learning with censored data. Ann Stat2012; 40(1): 529–560

[54] Laber EB, Qian M, Lizotte D, Pelham WE, Murphy S. Statistical inference in dynamic treatment regimes. Revision of Univ. of Michigan, Statistics Department Technical Report 5062011. http://arxiv.org/abs/1006.5831(Accessed on December 1, 2012)

RIGHTS & PERMISSIONS

2014 Higher Education Press and Springer-Verlag Berlin Heidelberg