Open Access

ARTICLE

A classification tree for the prediction of benign versus malignant disease in patients with small renal masses

Ricardo A. Rendon¹, Ross J. Mason¹, Susan Kirkland², Joseph G. Lawen¹, Mohamed Abdolell³

1 Department of Urology, Dalhousie University and Queen Elizabeth II Health Sciences Centre, Halifax, Nova Scotia, Canada
2 Department of Community Health and Epidemiology, Dalhousie University, Halifax, Nova Scotia, Canada
3 Department of Diagnostic Radiology and Division of Medical Education, Dalhousie University, Halifax, Nova Scotia, Canada
Address correspondence to Dr. Ricardo A. Rendon, Department of Urology, Dalhousie University and Queen Elizabeth II Health Sciences Centre, Room 295, 1276 South Park Street, Halifax, NS B3H 2Y9 Canada

Canadian Journal of Urology 2014, 21(4), 7379-7384.

Abstract

Introduction: To develop a classification tree for the preoperative prediction of benign versus malignant disease in patients with small renal masses.
Materials and methods: This is a retrospective study including 395 consecutive patients who underwent surgical treatment for a renal mass < 5 cm in maximum diameter between July 1st 2001 and June 30th 2010. A classification tree to predict the risk of having a benign renal mass preoperatively was developed using recursive partitioning analysis for repeated measures outcomes. Age, sex, volume on preoperative imaging, tumor location (central/peripheral), degree of endophytic component (1%–100%), and tumor axis position were used as potential predictors to develop the model.
Results: Forty-five patients (11.4%) were found to have a benign mass postoperatively. A classification tree has been developed which can predict the risk of benign disease with an accuracy of 88.9% (95% CI: 85.3 to 91.8). The significant prognostic factors in the classification tree are tumor volume, degree of endophytic component and symptoms at diagnosis. As an example of its utilization, a renal mass with a volume of < 5.67 cm³ that is < 45% endophytic has a 52.6% chance of having benign pathology. Conversely, a renal mass with a volume ≥ 5.67 cm³ that is ≥ 35% endophytic has only a 5.3% possibility of being benign.
Conclusions: A classification tree to predict the risk of benign disease in small renal masses has been developed to aid the clinician when deciding on treatment strategies for small renal masses.

---

Keywords

---