Risk factors for gastrointestinal malignancy in patients with iron-deficiency anaemia

Abstract

Objectives: Iron-deficiency anaemia (IDA) is common and may be caused by blood loss from gastrointestinal tumours. The aim of this study was to define risk factors for gastrointestinal malignancy in patients with IDA.

Methods: Patients with suspected IDA referred for gastrointestinal investigations were prospectively identified from two neighbouring UK hospitals (serving a population of 550,000 patients) between 1 January 1998 and 31 December 1999. Final diagnoses were determined after 2 years, and those patients with and without gastrointestinal cancer as a cause for their IDA were compared. Data collected included sex, age, haemoglobin, serum ferritin, mean cell volume and drug history.

Results: A total of 695 patients (236 men, mean age 68.5 years; 459 women, mean age 66.2 years) with IDA were investigated. Malignancy was diagnosed in 91/695 (13.1%) and gastrointestinal malignancy in 78/91 (11.2%). The most frequently diagnosed cancers were colonic (n = 44, 6.3%), gastric (n = 25, 3.6%) and renal tract (n = 7, 1%). The adjusted odds ratio (+/-95% confidence interval) for gastrointestinal cancer as a cause of IDA was significantly higher for male sex [2.96 (1.80, 4.87)], age over 50 years [7.04 (1.69, 29.32)] and haemoglobin level at presentation (< or =9.0 g/dl) [2.25 (1.29, 3.90)]. There was no significant difference in gastrointestinal malignancy in those taking aspirin (12/111, 10.8%), non-aspirin non-steroidal anti-inflammatory drugs (5/84, 6.0%) or warfarin (4/31, 12.9%) compared with those not taking these drugs (57/470, 12.1%). No cause for IDA was found in 53.7%.

Conclusions: Cancer was diagnosed in 13.1% and gastrointestinal cancer in 11.2% of patients with IDA. Significant risk factors for gastrointestinal malignancy in IDA patients are male sex, age over 50 years and haemoglobin at presentation < or =9.0 g/dl. IDA should not be attributed to aspirin, non-steroidal anti-inflammatory drugs or warfarin use.