Predicting dichotomised outcomes from high-dimensional data in biomedicine

References

• C. Caspell-Garcia, T. Simuni, D. Tosun-Turgut, I. Wu, Y. Zhang, M. Nalls, A. Singleton, L.A. Shaw, J.-H. Kang, J.Q. Trojanowski, A. Siderowf, C. Coffey, S. Lasch, D. Aarsland, D. Burn, L.M. Chahine, A.J. Espay, E.D. Foster, K.A. Hawkins, I. Litvan, I. Richard, and D. Weintraub, Multiple modality biomarker prediction of cognitive impairment in prospectively followed de novo Parkinson disease, PLoS One 12 (2017), Article ID e0175674. doi: 10.1371/journal.pone.0175674
   PubMed Web of Science ®Google Scholar
• J. Cohen, The cost of dichotomization, Appl. Psychol. Meas. 7 (1983), pp. 249–253. doi: 10.1177/014662168300700301
   Web of Science ®Google Scholar
• N.V. Dawson and R. Weiss, Dichotomizing continuous variables in statistical analysis: A practice to avoid, Med. Decis. Making 32 (2012), pp. 225–226. doi: 10.1177/0272989X12437605
   PubMed Web of Science ®Google Scholar
• A.R. de Leon and B. Wu, Copula-based regression models for a bivariate mixed discrete and continuous outcome, Stat. Med. 30 (2011), pp. 175–185. doi: 10.1002/sim.4087
   PubMed Web of Science ®Google Scholar
• M. de Paula and C.A.R. Diniz, Generalized linear regression models incorporating original outcome distributions, Commun. Stat. – Theory Methods 45 (2016), pp. 5762–5786. doi: 10.1080/03610926.2014.948726
   Web of Science ®Google Scholar
• A. Dupuy and D. Nassar, Dichotomization of primary outcomes serves external validity, J. Invest. Dermatol. 134 (2014), pp. 266–267. doi: 10.1038/jid.2013.258
   PubMed Web of Science ®Google Scholar
• D.P. Farrington and R. Loeber, Some benefits of dichotomization in psychiatric and criminological research, Crim. Behav. Ment. Health 10 (2000), pp. 100–122. doi: 10.1002/cbm.349
   Google Scholar
• V. Fedorov, F. Mannino, and R. Zhang, Consequences of dichotomization, Pharm. Stat. 8 (2009), pp. 50–61. doi: 10.1002/pst.331
   PubMed Web of Science ®Google Scholar
• G.M. Fitzmaurice and N.M. Laird, Regression models for a bivariate discrete and continuous outcome with clustering, J. Am. Stat. Assoc. 90 (1995), pp. 845–852. doi: 10.2307/2291318
   Web of Science ®Google Scholar
• J. Friedman, T. Hastie, and R. Tibshirani, Regularization paths for generalized linear models via coordinate descent, J. Stat. Softw. 33 (2010), pp. 1–22. doi: 10.18637/jss.v033.i01 (glmnet).
   PubMed Web of Science ®Google Scholar
• M.E. Fullard, B. Tran, S.X. Xie, J.B. Toledo, C. Scordia, C. Linder, R. Purri, D. Weintraub, J.E. Duda, L.M. Chahine, and J.F. Morley, Olfactory impairment predicts cognitive decline in early Parkinson's disease, Parkinsonism Relat. Disord. 25 (2016), pp. 45–51. doi: 10.1016/j.parkreldis.2016.02.013
   PubMed Web of Science ®Google Scholar
• F.E. Harrell, General aspects of fitting regression models – avoiding categorization; ordinal logistic regression, in Regression Modeling Strategies, Springer, Cham, 2015, pp. 311–325. doi: 10.1007/978-3-319-19425-7
   Google Scholar
• S. Heritier and E. Ronchetti, Robust binary regression with continuous outcomes, Can. J. Stat. 32 (2004), pp. 239–249. doi: 10.2307/3315927
   Web of Science ®Google Scholar
• O. Kuss, The danger of dichotomizing continuous variables: A visualization, Teach. Stat. 35 (2013), pp. 78–79. doi: 10.1111/test.12006
   Google Scholar
• R.C. MacCallum, S. Zhang, K.J. Preacher, and D.D. Rucker, On the practice of dichotomization of quantitative variables, Psychol. Methods 7 (2002), pp. 19–40. doi: 10.1037/1082-989X.7.1.19
   PubMed Web of Science ®Google Scholar
• K. Marek, D. Jennings, S. Lasch, A. Siderowf, and C. Tanner, The Parkinson Progression Marker Initiative (PPMI), Prog. Neurobiol. 95 (2011), pp. 629–635. doi: 10.1016/j.pneurobio.2011.09.005
   PubMed Web of Science ®Google Scholar
• B.K. Moser and L.P. Coombs, Odds ratios for a continuous outcome variable without dichotomizing, Stat. Med. 23 (2004), pp. 1843–1860. doi: 10.1002/sim.1776
   PubMed Web of Science ®Google Scholar
• M.P. Naeini and G.F. Cooper, Binary classifier calibration using an ensemble of piecewise linear regression models, Knowl. Inf. Syst. 54 (2018), pp. 151–170. doi: 10.1007/s10115-017-1133-2
   PubMed Web of Science ®Google Scholar
• O. Naggara, J. Raymond, F. Guilbert, D. Roy, A. Weill, and D.G. Altman, Analysis by categorizing or dichotomizing continuous variables is inadvisable: An example from the natural history of unruptured aneurysms, AJNR Am. J. Neuroradiol. 32 (2011), pp. 437–440. doi: 10.3174/ajnr.A2425
   PubMed Web of Science ®Google Scholar
• Z.S. Nasreddine, N.A. Phillips, V. Bédirian, S. Charbonneau, V. Whitehead, I. Collin, J.L. Cummings, and H. Chertkow, The Montreal Cognitive Assessment, MoCA: A brief screening tool for mild cognitive impairment, J. Am. Geriatr. Soc. 53 (2005), pp. 695–699. doi: 10.1111/j.1532-5415.2005.53221.x
   PubMed Web of Science ®Google Scholar
• A. Rauschenberger, I. Ciocănea-Teodorescu, M.A. Jonker, R.X. Menezes, and M.A. van de Wiel, Sparse classification with paired covariates, Adv. Data Anal. Classif. 14 (2020), pp. 571–588. doi: 10.1007/s11634-019-00375-6 (palasso).
   Web of Science ®Google Scholar
• A. Rauschenberger and E. Glaab, Predicting correlated outcomes from molecular data, Bioinform. 37 (2021), pp. 3889–3895. doi: 10.1093/bioinformatics/btab576 (joinet).
   PubMed Web of Science ®Google Scholar
• A. Rauschenberger, E. Glaab, and M.A. van de Wiel, Predictive and interpretable models via the stacked elastic net, Bioinform. 37 (2021), pp. 2012–2016. doi: 10.1093/bioinformatics/btaa535 (starnet).
   PubMed Web of Science ®Google Scholar
• J. Schwarz and D. Heider, GUESS: Projecting machine learning scores to well-calibrated probability estimates for clinical decision-making, Bioinform. 35 (2019), pp. 2458–2465. doi: 10.1093/bioinformatics/bty984 (CalibratR).
   PubMed Web of Science ®Google Scholar
• Y. Shentu and M. Xie, A note on dichotomization of continuous response variable in the presence of contamination and model misspecification, Stat. Med. 29 (2010), pp. 2200–2214. doi: 10.1002/sim.3966
   PubMed Web of Science ®Google Scholar
• D.L. Streiner, Breaking up is hard to do: The heartbreak of dichotomizing continuous data, Can. J. Psychiatry 47 (2002), pp. 262–266. doi: 10.1177/070674370204700307
   PubMed Web of Science ®Google Scholar
• S. Suissa, Binary methods for continuous outcomes: A parametric alternative, J. Clin. Epidemiol. 44 (1991), pp. 241–248. doi: 10.1016/0895-4356(91)90035-8
   PubMed Web of Science ®Google Scholar
• S. Suissa and L. Blais, Binary regression with continuous outcomes, Stat. Med. 14 (1995), pp. 247–255. doi: 10.1002/sim.4780140303
   PubMed Web of Science ®Google Scholar
• R. Ulrich and M. Wirtz, On the correlation of a naturally and an artificially dichotomized variable, Br. J. Stat. Psychol. 57 (2004), pp. 235–251. doi: 10.1348/0007110042307203
   PubMed Web of Science ®Google Scholar
• M.A. van de Wiel, J. Berkhof, and W.N. van Wieringen, Testing the prediction error difference between 2 predictors, Biostat. 10 (2009), pp. 550–560. doi: 10.1093/biostatistics/kxp011
   PubMed Web of Science ®Google Scholar
• B. Zadrozny and C. Elkan, Transforming classifier scores into accurate multiclass probability estimates, in Proceedings of the Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2002, pp. 694–699. doi: 10.1145/775047.775151
   Google Scholar
• H. Zou and T. Hastie, Regularization and variable selection via the elastic net, J. R. Stat. Soc., B: Stat. Methodol. 67 (2005), pp. 301–320. doi: 10.1111/j.1467-9868.2005.00503.x
   Google Scholar