Accurate inference for the Youden index and its associated cutoff point based on the gamma and inverse Gaussian distributed assumption

Xiaofei Wang; Peihua Jiang; Wenzhen Liu; Xiaofei Wang; Peihua Jiang; Wenzhen Liu

doi:10.3934/math.20241299

AIMS Mathematics

2024, Volume 9, Issue 10: 26702-26720. doi: 10.3934/math.20241299

Previous Article Next Article

Research article Special Issues

Accurate inference for the Youden index and its associated cutoff point based on the gamma and inverse Gaussian distributed assumption

1.
School of Mathematics and Statistics, Huangshan University, Huangshan 245041, China
2.
School of Mathematics-Physics and Finance, Anhui Polytechnic University, Wuhu 241000, China

Received: 29 June 2024 Revised: 28 August 2024 Accepted: 02 September 2024 Published: 13 September 2024
MSC : 62F30

The Youden index is often used to measure the effectiveness of biomarkers and aids to find the optimal cutoff point. Since pooled specimens have been shown to be an effective cost-cutting technique, we proposed the exact inferential procedures for the Youden index and its associated cutoff point based on the pooled specimens under the gamma or the inverse Gaussian assumption. The generalized confidence intervals (GCIs) were proposed for the Youden index and its associated cutoff point. Monte Carlo simulations were used to assess the performance of the proposed GCIs. The simulation results show that the proposed GCIs outperformed existing methods such as the bootstrap-$ p $ CIs in terms of the coverage probability. Finally, the proposed procedures were illustrated by an example.
- Youden index,
- gamma distribution,
- inverse Gaussian distribution,
- generalized pivotal quantity,
- pooled specimens
Citation: Xiaofei Wang, Peihua Jiang, Wenzhen Liu. Accurate inference for the Youden index and its associated cutoff point based on the gamma and inverse Gaussian distributed assumption[J]. AIMS Mathematics, 2024, 9(10): 26702-26720. doi: 10.3934/math.20241299

Related Papers:

Abstract

The Youden index is often used to measure the effectiveness of biomarkers and aids to find the optimal cutoff point. Since pooled specimens have been shown to be an effective cost-cutting technique, we proposed the exact inferential procedures for the Youden index and its associated cutoff point based on the pooled specimens under the gamma or the inverse Gaussian assumption. The generalized confidence intervals (GCIs) were proposed for the Youden index and its associated cutoff point. Monte Carlo simulations were used to assess the performance of the proposed GCIs. The simulation results show that the proposed GCIs outperformed existing methods such as the bootstrap-$ p $ CIs in terms of the coverage probability. Finally, the proposed procedures were illustrated by an example.

References

[1]	W. J. Youden, Index for rating diagnostic tests, Cancer, 3 (1950), 32–35. https://doi.org/10.1002/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3 doi: 10.1002/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3
[2]	R. Fluss, D. Faraggi, B. Reiser, Estimation of the Youden index and its associated cutoff point, Biometr. J. Math. Meth. Biosc., 47 (2005), 458–472. https://doi.org/10.1002/bimj.200410135 doi: 10.1002/bimj.200410135
[3]	D. E. Shapiro, The interpretation of diagnostic tests, Stat. Meth. Medic. Res., 8 (1999), 113–134. https://doi.org/10.1177/096228029900800203 doi: 10.1177/096228029900800203
[4]	M. Greiner, D. Pfeiffer, R. Smith, Principles and practical application of the receiver-operating characteristic analysis for diagnostic tests, Prevent. Veter. Medic., 45 (2000), 23–41. https://doi.org/10.1016/S0167-5877(00)00115-X doi: 10.1016/S0167-5877(00)00115-X
[5]	A. Demir, N. Yarali, T. Fisgin, F. Duru, A. Kara, Most reliable indices in differentiation between thalassemia trait and iron deficiency anemia, Pediat. Int., 44 (2002), 612–616. https://doi.org/10.1046/j.1442-200X.2002.01636.x doi: 10.1046/j.1442-200X.2002.01636.x
[6]	E. F. Schisterman, D. Faraggi, B. Reiser, J. Hu, Youden index and the optimal threshold for markers with mass at zero, Stat. Medic., 27 (2008), 297–315. https://doi.org/10.1002/sim.2993 doi: 10.1002/sim.2993
[7]	M. Otto, J. Wiltfang, E. Schtz, I. Zerr, A. Otto, A. Pfahlberg, et al., Diagnosis of Creutzfeldt-Jakob disease by measurement of s100 protein in serum: prospective case-control study, BMJ, 316 (1998), 577–582. https://doi.org/10.1136/bmj.316.7131.577 doi: 10.1136/bmj.316.7131.577
[8]	G. Shan, Improved confidence intervals for the youden index, PloS One, 10 (2015), e0127272. https://doi.org/10.1371/journal.pone.0127272 doi: 10.1371/journal.pone.0127272
[9]	H. Zhou, G. Qin, New nonparametric confidence intervals for the youden index, J. Bioph. Stat., 22 (2012), 1244–1257. https://doi.org/10.1080/10543406.2011.592234 doi: 10.1080/10543406.2011.592234
[10]	L. E. Bantis, C. T. Nakas, B. Reiser, Construction of confidence intervals for the maximum of the youden index and the corresponding cutoff point of a continuous biomarker, Biomet. J., 61 (2019), 138–156. https://doi.org/10.1002/bimj.201700107 doi: 10.1002/bimj.201700107
[11]	N. J. Perkins, E. F. Schisterman, The Youden index and the optimal cut-point corrected for measurement error, Biometr. J. Math. Meth. Biosc., 47 (2005), 428–411. https://doi.org/10.1002/bimj.200410133 doi: 10.1002/bimj.200410133
[12]	E. F. Schisterman, N. J. Perkins, A. Liu, H. Bondell, Optimal cut-point and its corresponding Youden index to discriminate individuals using pooled blood samples, Epidemiology, 16 (2005), 73–81. https://doi.org/10.1097/01.ede.0000147512.81966.ba doi: 10.1097/01.ede.0000147512.81966.ba
[13]	C. T. Nakas, T. A. Alonzo, C. T. Yiannoutsos, Accuracy and cut-off point selection in three-class classification problems using a generalization of the Youden index, Stat. Medic., 29 (2010), 2946–2955. https://doi.org/10.1002/sim.4044 doi: 10.1002/sim.4044
[14]	X. Liu, Classification accuracy and cut point selection, Stat. Medic., 31 (2012), 2676–2686. https://doi.org/10.1002/sim.4509 doi: 10.1002/sim.4509
[15]	M. Rota, L. Antolini, Finding the optimal cut-point for Gaussian and Gamma distributed biomarkers, Comput. Stat. Data Anal., 69 (2014), 1–14. https://doi.org/10.1016/j.csda.2013.07.015 doi: 10.1016/j.csda.2013.07.015
[16]	C. T. Nakas, J. C. Dalrymple-Alford, T. J. Anderson, T. A. Alonzo, Generalization of Youden index for multiple-class classification problems applied to the assessment of externally validated cognition in parkinson disease screening, Stat. Medic., 32 (2013), 995–1003. https://doi.org/10.1002/sim.5592 doi: 10.1002/sim.5592
[17]	M. Yuan, P. Li, C. Wu, Semiparametric inference of the youden index and the optimal cut-off point under density ratio models, Canad. J. Stat., 49 (2021), 965–986. https://doi.org/10.1002/cjs.11600 doi: 10.1002/cjs.11600
[18]	S. Liu, Q. Tian, Y. Liu, P. Li, Joint statistical inference for the area under the roc curve and youden index under a density ratio model, Mathematics, 12 (2024), 2118. https://doi.org/10.3390/math12132118 doi: 10.3390/math12132118
[19]	X. Hu, C. Li, J. Chen, G. Qin, Confidence intervals for the youden index and its optimal cut-off point in the presence of covariates, J. Biophar. Stat., 31 (2021), 251–272. https://doi.org/10.1080/10543406.2020.1832107 doi: 10.1080/10543406.2020.1832107
[20]	L. E. Bantis, J. V. Tsimikas, G. R. Chambers, M. Capello, S. Hanash, Z. Feng, The length of the receiver operating characteristic curve and the two cutoff youden index within a robust framework for discovery, evaluation, and cutoff estimation in biomarker studies involving improper receiver operating characteristic curves, Stat. Medic., 40 (2021), 1767–1789. https://doi.org/10.1002/sim.8869 doi: 10.1002/sim.8869
[21]	J. Wang, J. Yin, L. Tian, Evaluating joint confidence region of hypervolume under roc manifold and generalized youden index, Stat. Medic., 43 (2024), 869–889. https://doi.org/10.1002/sim.9998 doi: 10.1002/sim.9998
[22]	C. Farrington, Estimating prevalence by group testing using generalized linear models, Stat. Medic., 11 (1992), 1591–1597. https://doi.org/10.1002/sim.4780111206 doi: 10.1002/sim.4780111206
[23]	L. F. Barcellos, W. Klitz, L. L. Field, R. Tobias, A. M. Bowcock, R. Wilson, et al., Association mapping of disease loci, by use of a pooled dna genomic screen, American J. Human Genet., 61 (1997), 734–747. https://doi.org/10.1086/515512 doi: 10.1086/515512
[24]	C. Kendziorski, Y. Zhang, H. Lan, A. Attie, The efficiency of pooling mrna in microarray experiments, Biostatistics, 4 (2003), 465–477. https://doi.org/10.1093/biostatistics/4.3.465 doi: 10.1093/biostatistics/4.3.465
[25]	S. Gunasekera, L. Weerasena, A. Saram, O. Ajumobi, Exact inference for the Youden index to discriminate individuals using two-parameter exponentially distributed pooled samples, Biostat. Epidem., 3 (2019), 38–61. https://doi.org/10.1080/24709360.2019.1587264 doi: 10.1080/24709360.2019.1587264
[26]	A. Liu, E. F. Schisterman, Comparison of diagnostic accuracy of biomarkers with pooled assessments, Biometr. J. Math. Meth. Biosc., 45 (2003), 631–644. https://doi.org/10.1002/bimj.200390038 doi: 10.1002/bimj.200390038
[27]	D. Faraggi, B. Reiser, E. F. Schisterman, Roc curve analysis for biomarkers based on pooled assessments, Stat. Medic., 22 (2003), 2515–2527. https://doi.org/10.1002/sim.1418 doi: 10.1002/sim.1418
[28]	X. M. Tu, E. Litvak, M. Pagano, On the informativeness and accuracy of pooled testing in estimating prevalence of a rare disease: Application to hiv screening, Biometrika, 82 (1995), 287–297. https://doi.org/10.1093/biomet/82.2.287 doi: 10.1093/biomet/82.2.287
[29]	S. Weerahandi, Generalized inference in repeated measures: Exact methods in MANOVA and mixed models, New York: John Wiley & Sons, 2004.
[30]	C. Li, J. Chen, G. Qin, Partial Youden index and its inferences, J. Bioph. Stat., 29 (2019), 385–399. https://doi.org/10.1080/10543406.2018.1535502 doi: 10.1080/10543406.2018.1535502
[31]	C. M. McCrimmon, Distance metrics for gamma distributions, arXiv Prep., 1 (2018), 1802.01041. https://doi.org/10.48550/arXiv.1802.01041 doi: 10.48550/arXiv.1802.01041
[32]	B. X. Wang, F. Wu, Inference on the gamma distribution, Technometrics, 60 (2018), 235–244. https://doi.org/10.1080/00401706.2017.1328377 doi: 10.1080/00401706.2017.1328377
[33]	G. Iliopoulos, Exact confidence intervals for the shape parameter of the gamma distribution, J. Stat. Compu. Simul., 86 (2016), 1635–1642. https://doi.org/10.1080/00949655.2015.1080705 doi: 10.1080/00949655.2015.1080705
[34]	J. Folks, R. Chhikara, The inverse Gaussian distribution and its statistical application a review, J. Royal Stat. Society Series B: Stat. Meth., 40 (1978), 263–275. https://doi.org/10.1111/j.2517-6161.1978.tb01039.x doi: 10.1111/j.2517-6161.1978.tb01039.x
[35]	J. H. Shi, J. L. Lv, A new generalized p-value for testing equality of inverse Gaussian means under heterogeneity, Stat. Prob. Lett., 82 (2012), 96–102. https://doi.org/10.1016/j.spl.2011.08.022 doi: 10.1016/j.spl.2011.08.022

Reader Comments

Your name:*

Email:*
© 2024 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)