X. Zheng et al. (Eds.): ICSH 2014, LNCS 8549, pp. 171–180, 2014. © Springer International Publishing Switzerland 2014 A Preliminary Variable Selection Based Regression Analysis for Predicting Patient Satisfaction on Physician-Patient Cancer Prognosis Communication Shuai Fang 1 , Wenting Shi 1 , Nan Kong 2 , and Cleveland G. Shields 3 1 Department of Statistics, Purdue University, West Lafayette, IN, USA {fang53,shi68}@purdue.edu 2 Weldon School of Biomedical Engineering, Purdue University, West Lafayette, IN, USA nkong@purdue.edu 3 Department of Human Development and Family Studies, Purdue University, West Lafayette, IN, USA cgshields@purdue.edu Abstract. We explore the use of variable selection methods to deal with high correlations among predicative variables (e.g., physician’s voice tone and language certainty) for examining physician communication associated with prognosis discussion with cancer patients. Our main method is principal com- ponent analysis. The comparative results show its benefit in predicting patient satisfaction on the prognosis communication. This preliminary regression anal- ysis is expected to offer insights into patient-centered communication strategy design, especially for cancer prognosis communication with end-stage patients. Keywords: Patient centeredness, Variable selection, Principal component anal- ysis, Patient Satisfaction, Cancer prognosis. 1 Introduction Patient centeredness is identified as a core component of quality care [1]. It is defined as “health care that establishes a partnership among practitioners, patients, and their families (when appropriate) to ensure that decisions respect patients’ wants, needs, and preferences and the patients have the education and support they need to make decisions and participate in their own care.”[2]. Patient-centered care is supported by good physician-patient communication so that patients are treated as unique individu- als rather than the illness is the strict focus [2,3,4,5]. The patient-centered approach in health care has been shown to help build a therapeutic alliance based on the patients’ and the provider’s perspectives and consequently improve patients’ health and health care [3,4], [6,7,8] and reduce unnecessary medical spending [6], [9,10]. Unfortunate- ly, many barriers exist to good communication. First and foremost, physicians often differ in communication proficiency, including varied listening skills and different views of symptoms and treatment effectiveness from their patients’ [11]. Additional factors influencing patient centeredness and physician-patient communication Fang†, S., Shi†, W., Kong, N., & Shields, C. G. (2014). A Preliminary Variable Selection Based Regression Analysis for Predicting Patient Satisfaction on Physician-Patient Cancer Prognosis Communication. In X. Zheng, D. Zeng, H. Chen, Y. Zhang, C. Xing, & D. B. Neill (Eds.), Smart Health (pp. 171–180). Springer International Publishing. Retrieved from http://link.springer.com/ chapter/10.1007/978-3-319-08416-9_18