When Algorithmic Predictions Use Human-Generated Data: A Bias-Aware Classification Algorithm for Breast Cancer Diagnosis

References

• Adomavicius G, Zhang J (2016) Classification, ranking, and top-K stability of recommendation algorithms. INFORMS J. Comput. 28(1):129–147.Link, Google Scholar
• Adomavicius G, Bockstedt J, Curley S, Zhang J (2014) De-biasing user preference ratings in recommender systems. Tintarev N, O’Donovan J, Brusilovsky P, Felfernig A, Semeraro G, Lops P, eds. Joint Workshop Interfaces Human Decision Making Recommender Systems, October 6, Foster City, CA, 2–9.Google Scholar
• Adomavicius G, Bockstedt JC, Curley SP, Zhang J (2013) Do recommender systems manipulate consumer preferences? A study of anchoring effects. Inform. Systems Res. 24(4):956–975.Link, Google Scholar
• Agarwal R, Dhar V (2014) Big data, data science, and analytics: The opportunity and challenge for IS research. Inform. Systems Res. 25(3):443–448.Link, Google Scholar
• Alpert HR, Hillman BJ (2004) Quality and variability in diagnostic radiology. J. Amer. College Radiology 1(2):127–132.Crossref, Google Scholar
• American Cancer Society (2014) Cancer facts and figures 2014. Technical report, American Cancer Society, Atlanta.Google Scholar
• American College of Radiology (1998) Illustrated Breast Imaging Reporting and Data System (BI-RADS TM), 3rd ed. (American College of Radiology, Reston, VA).Google Scholar
• Arnott D (2006) Cognitive biases and decision support systems development: A design science approach. Inform. Systems J. 16(1):55–78.Crossref, Google Scholar
• Ayer T, Ayvaci MUS, Liu ZX, Alagoz O, Burnside ES (2010a) Computer-aided diagnostic models in breast cancer screening. Imaging Medicine 2(3):313–323.Crossref, Google Scholar
• Ayer T, Chhatwal J, Alagoz O, Kahn CE Jr, Woods RW, Burnside ES (2010b) Comparison of logistic regression and artificial neural network models in breast cancer risk estimation. Radiographics 30(1):13–22.Crossref, Google Scholar
• Ayvaci MUS, Ahsen ME, Raghunathan S, Gharibi Z (2017) Timing the use of breast cancer risk information in biopsy decision-making. Production Oper. Management 26(7):1333–1358.Crossref, Google Scholar
• Ayvaci MUS, Alagoz O, Ahsen ME, Burnside E (2018) Preference-sensitive management of post-mammography decisions in breast cancer diagnosis. Production Oper. Management 27(12):2313–2338.Crossref, Google Scholar
• Ayvaci MUS, Alagoz O, Chhatwal J, del Rio AM, Sickles EA, Nassif H, Kerlikowske Ket al. (2014) Predicting invasive breast cancer versus DCIS in different age groups. BMC Cancer 14(1):584.Crossref, Google Scholar
• Bai X, Padman R, Ramsey J, Spirtes P (2008) Tabu search-enhanced graphical models for classification in high dimensions. INFORMS J. Comput. 20(3):423–437.Link, Google Scholar
• Ballard-Barbash R, Taplin SH, Yankaskas BC, Ernster VL, Rosenberg RD, Carney PA, Barlow WEet al. (1997) Breast cancer surveillance consortium: A national mammography screening and outcomes database. Amer. J. Roentgenology 169(4):1001–1008.Crossref, Google Scholar
• Bansal S, Gutierrez GJ, Keiser JR (2017) Using experts’ quantile judgments to quantify uncertainties for new product development. Oper. Res. 65(5):1115–1130.Link, Google Scholar
• Barlow WE, White E, Ballard-Barbash R, Vacek PM, Titus-Ernstoff L, Carney PA, Tice JAet al. (2006) Prospective breast cancer risk prediction model for women undergoing screening mammography. J. National Cancer Inst. 98(17):1204–1214.Crossref, Google Scholar
• Barocas S, Selbst AD (2016) Big data’s disparate impact. California Law Rev. 104:671–732.Google Scholar
• Berg WA, Campassi C, Langenberg P, Sexton MJ (2000) Breast imaging reporting and data system: Inter- and intraobserver variability in feature analysis and final assessment. Amer. J. Roentgenology 174(6):1769–1777.Crossref, Google Scholar
• Blackmore CC, Mecklenburg RS, Kaplan GS (2011) Effectiveness of clinical decision support in controlling inappropriate imaging. J. Amer. College Radiology 8(1):19–25.Crossref, Google Scholar
• Blumenthal-Barby JS, Krieger H (2015) Cognitive biases and heuristics in medical decision making: A critical review using a systematic search strategy. Medical Decision Making 35(4):539–557.Crossref, Google Scholar
• Bornstein BH, Emler AC (2001) Rationality in medical decision making: A review of the literature on doctors’ decision-making biases. J. Evaluation Clinical Practice 7(2):97–107.Crossref, Google Scholar
• Boylu F, Aytug H, Koehler GJ (2007) Using a genetic algorithm to solve the strategic learning problem. Technical report, Decision and Information Sciences, University of Florida, Gainesville.Google Scholar
• Boylu F, Aytug H, Koehler GJ (2010) Induction over strategic agents. Inform. Systems Res. 21(1):170–189.Link, Google Scholar
• Brennan T, Dieterich W, Ehret B (2009) Evaluating the predictive validity of the COMPAS risk and needs assessment system. Criminal Justice Behav. 36(1):21–40.Crossref, Google Scholar
• Bright TJ, Wong A, Dhurjati R, Bristow E, Bastian L, Coeytaux RR, Samsa Get al. (2012) Effect of clinical decision-support systems: A systematic review. Ann. Internal Medicine 157(1):29–43.Crossref, Google Scholar
• Britton M (2015) Improving care through mammogram quality research. Accessed June 13, 2017, https://intermountainhealthcare.org/blogs/2015/10/breast-cancer-awareness-month-research-latest.Google Scholar
• Burnside ES, Davis J, Chhatwal J, Alagoz O, Lindstrom MJ, Geller BM, Littenberg Bet al. (2009) Probabilistic computer model developed from clinical data in national mammography database format to classify mammographic findings. Radiology 251(3):663–672.Crossref, Google Scholar
• Campbell SD, Sharpe SA (2009) Anchoring bias in consensus forecasts and its effect on market prices. J. Financial Quant. Anal. 44(2):369–390.Crossref, Google Scholar
• Cantor SB, Sun CC, Tortolero-Luna G, Richards-Kortum R, Follen M (1999) A comparison of C/B ratios from studies using receiver operating characteristic curve analysis. J. Clinical Epidemiology 52(9):885–892.Crossref, Google Scholar
• Carney PA, Cook AJ, Miglioretti DL, Feig SA, Bowles EA, Geller BM, Kerlikowske Ket al. (2012) Use of clinical history affects accuracy of interpretive performance of screening mammography. J. Clinical Epidemiology 65(2):219–230.Crossref, Google Scholar
• Cavusoglu H, Mishra B, Raghunathan S (2005) The value of intrusion detection systems in information technology security architecture. Inform. Systems Res. 16(1):28–46.Link, Google Scholar
• Chen JH, Asch SM (2017) Machine learning and prediction in medicine—Beyond the peak of inflated expectations. New England J. Medicine 376(26):2507–2509.Crossref, Google Scholar
• Chhatwal J, Alagoz O, Lindstrom MJ, Kahn CE, Shaffer KA, Burnside ES (2009) Original research. A logistic regression model based on the national mammography database format to aid breast cancer diagnosis. Amer. J. Roentgenology 192(4):1117–1127.Crossref, Google Scholar
• Clark P, Niblett T (1989) The CN2 induction algorithm. Machine Learn. 3(4):261–283.Crossref, Google Scholar
• Clemen RT, Winkler RL (1999) Combining probability distributions from experts in risk analysis. Risk Anal. 19(2):187–203.Crossref, Google Scholar
• Coiera E (2015) Technology, cognition and error. BMJ Quality Safety 24(7):417–422.Crossref, Google Scholar
• Croskerry P (2003) The importance of cognitive errors in diagnosis and strategies to minimize them. Academic Medicine 78(8):775–780.Crossref, Google Scholar
• Dalvi N, Domingos P, Sanghai S, Verma D (2004) Adversarial classification. Proc. Tenth ACM SIGKDD Internat. Conf. Knowledge Discovery Data Mining (Association for Computing Machinery, New York), 99–108.Google Scholar
• Dekel O, Shamir O, Xiao L (2010) Learning to classify with missing and corrupted features. Machine Learn. 81(2):149–178.Crossref, Google Scholar
• Dietvorst BJ, Simmons JP, Massey C (2015) Algorithm aversion: People erroneously avoid algorithms after seeing them err. J. Experiment. Psych.: General 144(1):114–126.Crossref, Google Scholar
• Dietvorst BJ, Simmons JP, Massey C (2016) Overcoming algorithm aversion: People will use imperfect algorithms if they can (even slightly) modify them. Management Sci. 64(3):1155–1170Link, Google Scholar
• Eberl MM, Fox CH, Edge SB, Carter CA, Mahoney MC (2006) BI-RADS classification for management of abnormal mammograms. J. Amer. Board Family Medicine 19(2):161–164.Crossref, Google Scholar
• Elliott C (2017) New artificial intelligence promises to make travel a little smarter. Does it? Washington Post (June 22), http://wapo.st/2t0wCjX?tid=ss_tw&utm_term=.acde7d2bff94.Google Scholar
• Elmore JG, Wells CK, Howard DH, Feinstein AR (1997) The impact of clinical history on mammographic interpretations. J. Amer. Medical Assoc. 277(1):49–52.Crossref, Google Scholar
• Elmore JG, Wells CK, Lee CH, Howard DH, Feinstein AR (1994) Variability in radiologists’ interpretations of mammograms. New England J. Medicine 331(22):1493–1499.Crossref, Google Scholar
• Englich B, Soder K (2009) Moody experts—How mood and expertise influence judgmental anchoring. Judgment Decision Making 4(1):41–50.Google Scholar
• Engmann NJ, Golmakani MK, Miglioretti DL, Sprague BL, Kerlikowske K (2017) Population-attributable risk proportion of clinical risk factors for breast cancer. J. Amer. Medical Assoc. Oncology 3(9):1228–1236.Google Scholar
• Eraker SA, Politser P (1982) How decisions are reached: Physician and patient. Ann. Internal Medicine 97(2):262–268.Crossref, Google Scholar
• Faraggi D, Reiser B (2002) Estimation of the area under the ROC curve. Statist. Medicine 21(20):3093–3106.Crossref, Google Scholar
• Fisher M, Raman A (1996) Reducing the cost of demand uncertainty through accurate response to early sales. Oper. Res. 44(1):87–99.Link, Google Scholar
• Freedman AN, Seminara D, Gail MH, Hartge P, Colditz GA, Ballard-Barbash R, Pfeiffer RM (2005) Cancer risk prediction models: A workshop on development, evaluation, and application. J. National Cancer Inst. 97(10):715–723.Crossref, Google Scholar
• Fryback DG, Stout NK, Rosenberg MA, Trentham-Dietz A, Kuruchittham V, Remington PL (2006) The Wisconsin breast cancer epidemiology simulation model. J. National Cancer Inst. Monographs 2006(36):37–47.Crossref, Google Scholar
• Gartner D, Kolisch R, Neill DB, Padman R (2015) Machine learning approaches for early DRG classification and resource allocation. INFORMS J. Comput. 27(4):718–734.Link, Google Scholar
• Goes PB (2013) Editor’s comments: Information systems research and behavioral economics. Management Inform. Systems Quart. 37(3):iii–viii.Google Scholar
• Gold MR (1996) Cost-Effectiveness in Health and Medicine (Oxford University Press, New York).Crossref, Google Scholar
• Gram IT, Lund E, Slenker SE (1990) Quality of life following a false positive mammogram. British J. Cancer 62(6):1018–1022.Crossref, Google Scholar
• Grand View Research (2016) Teleradiology market size & forecast report, 2013–2024. Technical report, Grand View Research, San Francisco.Google Scholar
• Greenes R (2014) Definition, scope, and challenges. Greenes RA, ed. Clinical Decision Support: The Road Ahead (Academic Press, Cambridge, MA), 3–47.Crossref, Google Scholar
• Griscom NT (2002) A suggestion: Look at the images first, before you read the history. Radiology 223(1):9–10.Crossref, Google Scholar
• Grushka-Cockayne Y, Jose VRR, Lichtendahl KC Jr (2016) Ensembles of overfit and overconfident forecasts. Management Sci. 63(4):1110–1130.Link, Google Scholar
• Gunderman RB (2009) Biases in radiologic reasoning. Amer. J. Roentgenology 192(3):561–564.Crossref, Google Scholar
• Hajian S, Bonchi F, Castillo C (2016) Algorithmic bias: From discrimination discovery to fairness-aware data mining. Krishnapuram B, ed. Proc. 22nd ACM SIGKDD Internat. Conf. Knowledge Discovery Data Mining (Association for Computing Machinery, New York), 2125–2126.Google Scholar
• Hawley JR, Taylor CR, Cubbison AM, Erdal BS, Yildiz VO, Carkaci S (2016) Influences of radiology trainees on screening mammography interpretation. J. Amer. College Radiology 13(5):554–561.Crossref, Google Scholar
• Haybittle JL (1998) Life expectancy as a measurement of the benefit shown by clinical trials of treatment for early breast cancer. Clinical Oncology 10(2):92–94.Crossref, Google Scholar
• Holmes-Rovner M, Nelson WL, Pignone M, Elwyn G, Rovner DR, O’Connor AM, Coulter Aet al. (2007) Are patient decision aids the best way to improve clinical decision making? Report of the IPDAS symposium. Medical Decision Making 27(5):599–608.Crossref, Google Scholar
• Hong T, Tsang S (1997) A generalized version space learning algorithm for noisy and uncertain data. IEEE Trans. Knowledge Data Engrg. 9(2):336–340.Crossref, Google Scholar
• Ichikawa LE, Barlow WE, Anderson ML, Taplin SH, Geller BM, Brenner RJ (2010) Time trends in radiologists’ interpretive performance at screening mammography from the community-based breast cancer surveillance consortium, 1996–2004. Radiology 256(1):74–82.Crossref, Google Scholar
• Ip IK, Schneider L, Seltzer S, Smith A, Dudley J, Menard A, Khorasani R (2013) Impact of provider-led, technology-enabled radiology management program on imaging. Amer. J. Medicine 126(8):687–692.Crossref, Google Scholar
• Jiang Z, Mookerjee VS, Sarkar S (2005) Lying on the web: Implications for expert systems redesign. Inform. Systems Res. 16(2):131–148.Link, Google Scholar
• Kao H, Tang K (2013) Cost-sensitive decision tree induction with label-dependent late constraints. INFORMS J. Comput. 26(2):238–252.Link, Google Scholar
• Kardaras C, Žitković G (2011) Stability of the utility maximization problem with random endowment in incomplete markets. Math. Finance 21(2):313–333.Google Scholar
• Kohli R, Piontek F (2008) DSS in healthcare: Advances and opportunities. Burstein F, Holsapple CW, eds. Handbook on Decision Support Systems, Vol. 2 (Springer, Berlin), 483–497.Crossref, Google Scholar
• Lee CS, Nagy PG, Weaver SJ, Newman-Toker DE (2013) Cognitive and system factors contributing to diagnostic errors in radiology. Amer. J. Roentgenology 201(3):611–617.Crossref, Google Scholar
• Li KC, Marcovici P, Phelps A, Potter C, Tillack A, Tomich J, Tridandapani S (2013) Digitization of medicine: How radiology can take advantage of the digital revolution. Academic Radiology 20(12):1479–1494.Crossref, Google Scholar
• Li M, Petruzzi NC, Zhang J (2017) Overconfident competing newsvendors. Management Sci. 63(8):2637–2646.Link, Google Scholar
• Lin A, Harris M, Zalis M (2010) Initial observations of electronic medical record usage during CT and MRI interpretation: Frequency of use and impact on workflow. Amer. J. Roentgenology 195(1):188–193.Crossref, Google Scholar
• Lo JY, Baker JA, Kornguth PJ, Floyd CE (1999) Effect of patient history data on the prediction of breast cancer from mammographic findings with artificial neural networks. Academic Radiology 6(1):10–15.Crossref, Google Scholar
• Loy CT, Irwig L (2004) Accuracy of diagnostic tests read with and without clinical information: A systematic review. J. Amer. Medical Assoc. 292(13):1602–1609.Crossref, Google Scholar
• MacCormack A, Verganti R (2003) Managing the sources of uncertainty: Matching process and context in software development. J. Product Innovation Management 20(3):217–232.Crossref, Google Scholar
• Mamede S, van Gog T, van den Berge K, Rikers RMJP, van Saase JLCM, van Guldener C, Schmidt HG (2010) Effect of availability bias and reflective reasoning on diagnostic accuracy among internal medicine residents. J. Amer. Medical Assoc. 304(11):1198–1203.Crossref, Google Scholar
• Mandelblatt JS, Wheat ME, Monane M, Moshief RD, Hollenberg JP, Tang J (1992) Breast cancer screening for elderly women with and without comorbid conditions. Ann. Internal Medicine 116(9):722–730.Crossref, Google Scholar
• Metz CE (1978) Basic principles of ROC analysis. Seminars Nuclear Medicine 8(4):283–298.Crossref, Google Scholar
• Meyer G, Adomavicius G, Johnson PE, Elidrisi M, Rush WA, Sperl-Hillen JM, O’Connor PJ (2014) A machine learning approach to improving dynamic decision making. Inform. Systems Res. 25(2):239–263.Link, Google Scholar
• Mookerjee VS (2001) Debiasing training data for inductive expert system construction. IEEE Trans. Knowledge Data Engrg. 13(3):497–512.Crossref, Google Scholar
• Nance JW Jr, Meenan C, Nagy PG (2013) The future of the radiology information system. Amer. J. Roentgenology 200(5):1064–1070.Crossref, Google Scholar
• National Cancer Institute (2014a) Breast cancer risk assessment tool. Accessed January 15, 2015, http://www.cancer.gov/bcrisktool/.Google Scholar
• National Cancer Institute (2014b) Breast Cancer PDQ®; screening. Accessed January 15, 2015, http://www.cancer.gov/cancertopics/pdq/screening/breast/healthprofessional/page7.Google Scholar
• Obermeyer Z, Lee TH (2017) Lost in thought–the limits of the human mind and the future of medicine. New England J. Medicine 377(13):1209–1211.Crossref, Google Scholar
• Ogdie AR, Reilly JB, Pang WG, Keddem S, Barg FK, Von Feldt JM, Myers JS (2012) Seen through their eyes: Residents’ reflections on the cognitive and contextual components of diagnostic errors in medicine. Academic Medicine 87(10):1361–1367.Crossref, Google Scholar
• O’Malley AS (2011) Tapping the unmet potential of health information technology. New England J. Medicine 364(12):1090–1091.Crossref, Google Scholar
• Pace LE, Keating NL (2014) A systematic assessment of benefits and risks to guide breast cancer screening decisions. J. Amer. Medical Assoc. 311(13):1327–1335.Crossref, Google Scholar
• Parssian A (2006) Managerial decision support with knowledge of accuracy and completeness of the relational aggregate functions. Decision Support Systems 42(3):1494–1502.Crossref, Google Scholar
• Pasquale F (2015) Digital star chamber. Aeon (August 18), https://aeon.co/essays/judge-jury-and-executioner-the-unaccountable-algorithm.Google Scholar
• Patel VL, Kannampallil TG, Shortliffe EH (2015) Role of cognition in generating and mitigating clinical errors. BMJ Quality Safety 24(7):468–474.Crossref, Google Scholar
• Pisano ED, Gatsonis C, Hendrick E, Yaffe M, Baum JK, Acharyya S, Conant EFet al. (2005) Diagnostic performance of digital versus film mammography for breast-cancer screening. New England J. Medicine 353(17):1773–1783.Crossref, Google Scholar
• Provost F (2005) Toward economic machine learning and utility-based data mining. Weiss G, Saar-Tsechansky M, Zadrozny B, eds. Proc. 1st Internat. Workshop Utility-Based Data Mining (Association for Computing Machinery, New York), 1.Google Scholar
• Quinlan JR (1986) The effect of noise on concept learning. Michalski RS, Carbonell JG, Mitchell TM, eds. Machine Learning: An Artificial Intelligence Approach, Vol. 2, 149–166.Google Scholar
• Raja AS, Ip IK, Prevedello LM, Sodickson AD, Farkas C, Zane RD, Hanson Ret al. (2012) Effect of computerized clinical decision support on the use and yield of CT pulmonary angiography in the emergency department. Radiology 262(2):468–474.Crossref, Google Scholar
• Ranjan R, Gneiting T (2010) Combining probability forecasts. J. Roy. Statist. Soc.: Ser. B (Statist. Methodology) 72(1):71–91.Crossref, Google Scholar
• Ransbotham S, Fichman RG, Gopal R, Gupta A (2016) Special section introduction—Ubiquitous IT and digital vulnerabilities. Inform. Systems Res. 27(4):834–847.Link, Google Scholar
• Rosenberg RD, Yankaskas BC, Abraham LA, Sickles EA, Lehman CD, Geller BM, Carney PAet al. (2006) Performance benchmarks for screening mammography. Radiology 241(1):55–66.Crossref, Google Scholar
• Saar-Tsechansky M, Provost F (2007) Handling missing values when applying classification models. J. Machine Learn. Res. 8(7):1624–1657.Google Scholar
• Saposnik G, Redelmeier D, Ruff CC, Tobler PN (2016) Cognitive biases associated with medical decisions: A systematic review. BMC Medical Informatics Decision Making 16(1):138.Crossref, Google Scholar
• Sheng VS, Provost F, Ipeirotis PG (2008) Get another label? Improving data quality and data mining using multiple, noisy labelers. Liu B, Sarawagi S, Li Y, eds. Proc. 14th ACM SIGKDD Internat. Conf. Knowledge Discovery Data Mining (Association for Computing Machinery, New York), 614–622.Google Scholar
• Sibbald M, Cavalcanti RB (2011) The biasing effect of clinical history on physical examination diagnostic accuracy. Medical Ed. 45(8):827–834.Crossref, Google Scholar
• Siegel R, Ma J, Zou Z, Jemal A (2014) Cancer statistics, 2014. CA: Cancer J. Clinicians 64(1):9–29.Crossref, Google Scholar
• Sim I, Gorman P, Greenes RA, Haynes RB, Kaplan B, Lehmann H, Tang PC (2001) Clinical decision support systems for the practice of evidence-based medicine. J. Amer. Medical Informatics Assoc. 8(6):527–534.Crossref, Google Scholar
• Smith RA, Brooks D, Cokkinides V, Saslow D, Brawley OW (2013) Cancer screening in the United States, 2013. CA: Cancer J. Clinicians 63(2):87–105.Crossref, Google Scholar
• Stone M (1961) The opinion pool. Ann. Math. Statist. 32(4):1339–1342.Crossref, Google Scholar
• Tice JA, Cummings SR, Smith-Bindman R, Ichikawa L, Barlow WE, Kerlikowske K (2008) Using clinical factors and mammographic breast density to estimate breast cancer risk: Development and validation of a new predictive model. Ann. Internal Medicine 148(5):337–347.Crossref, Google Scholar
• Tversky A, Kahneman D (1974) Judgment under uncertainty: Heuristics and biases. Science 185(4157):1124–1131.Crossref, Google Scholar
• Tyrer J, Duffy SW, Cuzick J (2004) A breast cancer prediction model incorporating familial and personal risk factors. Statist. Medicine 23(7):1111–1130.Crossref, Google Scholar
• Ulvila JW, Gaffney JE Jr (2004) A decision analysis method for evaluating computer intrusion detection systems. Decision Anal. 1(1):35–50.Link, Google Scholar
• U.S. Food and Drug Administration (2015) MQSA national statistics. Accessed January 15, 2015, http://www.fda.gov/Radiation-EmittingProducts/MammographyQualityStandardsActandProgram/FacilityScorecard/ucm113858.htm.Google Scholar
• Wallsten TS (1981) Physician and medical student bias in evaluating diagnostic information. Medical Decision Making 1(2):145–164.Crossref, Google Scholar
• Winkler RL (1981) Combining probability distributions from dependent information sources. Management Sci. 27(4):479–488.Link, Google Scholar
• Wu W, Zhang W, Li H (2003) Knowledge acquisition in incomplete fuzzy information systems via the rough set approach. Expert Systems 20(5):280–286.Crossref, Google Scholar
• Wu Y, Vanness DJ, Ayvaci MUS, Alagoz O, Burnside ES (2011) Expected utility model used to compare the value of screening versus diagnostic mammography. 33rd Annual Meeting Soc. Medical Decision Making (Society for Medical Decision Making, Hillsborough, NJ), 245–248.Google Scholar
• Zhang J, Aytug H, Koehler GJ (2014) Discriminant analysis with strategically manipulated data. Inform. Systems Res. 25(3):654–662.Link, Google Scholar