Defining thresholds of prognostic markers is essential for stratified medicine. Such thresholds are mostly estimated from purely statistical measures regardless of patient preferences potentially leading to unacceptable medical decisions. Quality-Adjusted Life-Years are a widely used preferences-based measure of health outcomes. We develop a time-dependent Quality-Adjusted Life-Years-based expected utility function for censored data that should be maximized to estimate an optimal threshold. We performed a simulation study to compare estimated thresholds when using the proposed expected utility approach and purely statistical estimators. Two applications illustrate the usefulness of the proposed methodology which was implemented in the R package ROCt (www.divat.fr). First, by reanalysing data of a randomized clinical trial comparing the efficacy of prednisone vs. placebo in patients with chronic liver cirrhosis, we demonstrate the utility of treating patients with a prothrombin level higher than 89%. Second, we reanalyze the data of an observational cohort of kidney transplant recipients: we conclude to the uselessness of the Kidney Transplant Failure Score to adapt the frequency of clinical visits. Applying such a patient-centered methodology may improve future transfer of novel prognostic scoring systems or markers in clinical practice.
BakerSGSargentDJ. Designing a randomized clinical trial to evaluate personalized medicine: a new approach based on risk prediction. J Natl Cancer Inst2010; 102: 1756–1759.
2.
SteffenJSteffenJ. Driving forces behind the past and future emergence of personalized medicine. J Pers Med2013; 3: 14–22.
3.
IoannidisJPA. Expectations, validity, and reality in omics. J Clin Epidemiol2010; 63: 945–949.
4.
Ioannidis JPA. Evolution and translation of research findings: from bench to where? PLoS Clin Trials [Internet]. 17 November 2006 [cited 3 December 2015]; 1. http://www.ncbi.nlm.nih.gov/pmc/articles/PMC1851723/.
5.
IglesiasAIMihaescuRIoannidisJPA, et al.Scientific reporting is suboptimal for aspects that characterize genetic risk prediction studies: a review of published articles based on the Genetic RIsk Prediction Studies statement. J Clin Epidemiol2014; 67: 487–499.
6.
JoynerMJPanethN. SEven questions for personalized medicine. JAMA2015; 314: 999–1000.
7.
YoudenWJ. Index for rating diagnostic tests. Cancer1950; 3: 32–35.
8.
BöhningDHollingHPatileaV. A limitation of the diagnostic-odds ratio in determining an optimal cut-off value for a continuous diagnostic test. Stat Meth Med Res2011; 20: 541–550.
9.
SubtilFRabilloudM. An enhancement of ROC curves made them clinically relevant for diagnostic-test comparison and optimal-threshold determination. J Clin Epidemiol2015; 68: 752–759.
10.
BakerSGCookNRVickersA, et al.Using relative utility curves to evaluate risk prediction. J R Stat Soc Ser A Stat Soc2009; 172: 729–748.
11.
BakerSGKramerBS. Peirce, Youden, and receiver operating characteristic curves. Am Stat2007; 61: 343–346.
12.
PaukerSGKassirerJP. The threshold approach to clinical decision making. N Engl J Med1980; 302: 1109–1117.
IrwinRJIrwinTC. A principled approach to setting optimal diagnostic thresholds: where ROC and indifference curves meet. Eur J Intern Med2011; 22: 230–234.
15.
CantorSBSunCCTortolero-LunaG, et al.A comparison of C/B ratios from studies using receiver operating characteristic curve analysis. J Clin Epidemiol1999; 52: 885–892.
16.
WeinsteinMCTorranceGMcGuireA. QALYs: the basics. Value Health J Int Soc Pharmacoeconomics Outcomes Res2009; 12: S5–S9.
17.
KindPLafataJEMatuszewskiK, et al.The use of QALYs in clinical and patient decision-making: issues and prospects. Value Health J Int Soc Pharmacoecon Outcome Res2009; 12: S27–S30.
18.
TowseA. Net clinical benefit: the art and science of jointly estimating benefits and risks of medical treatment. Value Health J Int Soc Pharmacoecon Outcome Res2010; 13: S30–S32.
19.
FergusonNDScalesDCPintoR, et al.Integrating mortality and morbidity outcomes. Am J Respir Crit Care Med2013; 187: 256–261.
20.
TorranceGW. Measurement of health state utilities for economic appraisal. J Health Econ1986; 5: 1–30.
21.
EuroQol Group. EuroQol – a new facility for the measurement of health-related quality of life. Health Policy Amst Neth1990; 16: 199–208.
22.
BrazierJRobertsJDeverillM. The estimation of a preference-based measure of health from the SF-36. J Health Econ2002; 21: 271–292.
23.
AraRWailooA. Using health state utility values in models exploring the cost-effectiveness of health technologies. Value Health2012; 15: 971–974.
24.
SchlichtingPChristensenEAndersenPK, et al.Prognostic factors in cirrhosis identified by Cox’s regression model. Hepatol Baltim Md1983; 3: 889–895.
25.
FoucherYDaguinPAklA, et al.A clinical scoring system highly predictive of long-term kidney graft survival. Kidney Int2010; 78: 1288–1294.
26.
WeinsteinMCTorranceGMcGuireA. QALYs: the basics. Value Health J Int Soc Pharmacoecon Outcome Res2009; 12: S5–S9.
27.
AndersenPKPermeMP. Pseudo-observations in survival analysis. Stat Meth Med Res2010; 19: 71–99.
28.
EfronB. Bootstrap methods: another look at the Jacknife. Ann Stat1979; 7: 1–26.
29.
R Foundation for Statistical Computing. R Development Core Team. R: A language and environment for statistical computing. Vienna, Austria, 2011. ISBN 3-900051-07-0. http://www.R-project.org/.
30.
ChristensenESchlichtingPAndersenPK, et al.Updating prognosis and therapeutic effect evaluation in cirrhosis with Cox’s multiple regression model for time-dependent variables. Scand J Gastroenterol1986; 21: 163–174.
31.
MitchisonHCPalmerJMBassendineMF, et al.A controlled trial of prednisolone treatment in primary biliary cirrhosis. Three-year results. J Hepatol1992; 15: 336–344.
32.
SwartzSLDluhyRG. Corticosteroids: clinical pharmacology and therapeutic use. Drugs1978; 16: 238–255.
33.
McLernonDJDillonJDonnanPT. Health-state utilities in liver disease: a systematic review. Med Decis Mak Int J Soc Med Decis Mak2008; 28: 582–592.
34.
DolanPGudexCKindP, et al.The time trade-off method: results from a general population study. Health Econ1996; 5: 141–154.
35.
ChevalierJde PouvourvilleG. Valuing EQ-5D using time trade-off in France. Eur J Health Econ HEPAC Health Econ Prev Care2013; 14: 57–66.
36.
HeagertyPJLumleyTPepeMS. Time-dependent ROC curves for censored survival data and a diagnostic marker. Biometrics2000; 56: 337–344.
37.
FoucherYMeuretteADaguinP, et al.A personalized follow-up of kidney transplant recipients using video conferencing based on a 1-year scoring system predictive of long term graft failure (TELEGRAFT study): protocol for a randomized controlled trial. BMC Nephrol2015; 16: 6–6.
38.
KewFMGalaalKMandervilleH. Patients’ views of follow-up after treatment for gynaecological cancer. J Obstet Gynaecol2009; 29: 135–142.
39.
LiemYSBoschJLHuninkMGM. Preference-based quality of life of patients on renal replacement therapy: a systematic review and meta-analysis. Value Health J Int Soc Pharmacoecon Outcome Res2008; 11: 733–741.
40.
GirardiVSchaedeliFMartiH-P, et al.The willingness of patients to accept an additional mortality risk in order to improve renal graft survival. Kidney Int2004; 66: 375–382.
41.
WalterSDTurnerRMacaskillP, et al.Beyond the treatment effect: Evaluating the effects of patient preferences in randomised trials. Stat Meth Med Res2014; 01–19.
42.
VickersAJElkinEB. Decision curve analysis: a novel method for evaluating prediction models. Med Decis Making2006; 26: 565–574.
43.
SteyerbergEWVickersAJ. Decision curve analysis: a discussion. Med Decis Making2008; 28: 146–149.
44.
Foucher Y, Giral M, Soulillou J-P, et al. Cut-off estimation and medical decision making based on a continuous prognostic factor: the prediction of kidney graft failure. Int J Biostat 2012; 8: 1–13.
45.
SonnenbergA. Patient–physician discordance about benefits and risks in gastroenterology decision-making. Aliment Pharmacol Ther2004; 19: 1247–1253.
46.
YuanZLevitanBBurtonP, et al.Relative importance of benefits and risks associated with antithrombotic therapies for acute coronary syndrome: patient and physician perspectives. Curr Med Res Opin2014; 30: 1733–1741.
47.
DjulbegovicBHozoISchwartzA, et al.Acceptable regret in medical decision making. Med Hypotheses1999; 53: 253–259.
48.
TsalatsanisABarnesLEHozoI, et al.Extensions to regret-based decision curve analysis: an application to hospice referral for terminal patients. BMC Med Inform Decis Making2011; 11: 77–77.
49.
WakkerPP. Lessons learned by (from?) an economist working in medical decision making. Med Decis Making2008; 28: 690–698.
50.
RoystonPParmarMK. Restricted mean survival time: an alternative to the hazard ratio for the design and analysis of randomized trials with a time-to-event outcome. BMC Med Res Methodol2013; 13: 152–152.
51.
Le BorgneFGiraudeauBQuerardAH, et al.Comparisons of the performance of different statistical tests for time-to-event analysis with confounding factors: practical illustrations in kidney transplantation. Stat Med2016; 35: 1103–1116.
