Surgical mortality in patients with esophageal cancer: development and validation of a simple risk score

Abstract

Purpose: Surgery has curative potential in a proportion of patients with esophageal cancer, but is associated with considerable perioperative risks. We aimed to develop and validate a simple risk score for surgical mortality that could be applied to administrative data.

Patients and methods: We analyzed 3,592 esophagectomy patients from four cohorts. We applied logistic regression analysis to predict mortality occurring within 30 days after esophagectomy for 1,327 esophageal cancer patients older than 65 years of age, diagnosed between 1991 and 1996 in the linked Surveillance, Epidemiology and End Results (SEER)--Medicare database. A simple score chart for preoperative risk assessment of surgical mortality was developed and validated on three other cohorts, including 714 SEER-Medicare patients diagnosed between 1997 and 1999, 349 patients from a population-based registry in the Netherlands diagnosed between 1993 and 2001, and 1,202 patients from a referral hospital in the Netherlands diagnosed between 1980 and 2002.

Results: Surgical mortality in the four cohorts was 11% (147 of 1,327), 10% (74 of 714), 7% (25 of 349), and 4% (45 of 1,202), respectively. Predictive patient characteristics included age, comorbidity (cardiac, pulmonary, renal, hepatic, and diabetes), preoperative radiotherapy or combined chemoradiotherapy, and a relatively low hospital volume. At validation, the simple score showed good agreement of predicted risks with observed mortality rates (calibration), but low discrimination (area under the receiver operating characteristic curve 0.58 to 0.66).

Conclusion: A simple risk score combining clinical characteristics along with hospital volume to predict surgical mortality after esophagectomy from administrative data may form a basis for risk adjustment in quality of care assessment.