RESUMO
Non-invasive haemoglobin measurement using absolute values lacks the precision to be the sole basis for the treatment of pre-operative anaemia. However, it can possibly serve as a screening test, indexing 'anaemia' with high sensitivity when values remain under prespecified cut-off values. Based on previous data, non-invasive haemoglobin cut-off values (146 g.l-1 for women and 152 g.l-1 for men) detect true anaemia with 99% sensitivity. An index test with these prespecified cut-off values was verified by prospective measurement of non-invasive and invasive haemoglobin pre-operatively in elective surgical patients. In 809 patients, this showed an estimated sensitivity (95%CI) of 98.9% (94.1-99.9%) in women and 96.4% (91.0-99.0%) in men. This saved invasive blood tests in 9% of female and 28% of male patients. In female patients, a lower non-invasive haemoglobin cut-off value (138 g.l-1 ) would save 28% of invasive blood tests with a sensitivity of 95%. The target 99% sensitivity would be reached by non-invasive haemoglobin cut-off values of 152 g.l-1 in female and 162 g.l-1 in male patients, saving 3% and 9% of invasive blood tests, respectively. Bias and limits of agreement between non-invasive and laboratory haemoglobin levels were 2 and - 25 to 28 g.l-1 , respectively. Patient and measurement characteristics did not influence the agreement between non-invasive and laboratory haemoglobin levels. Although sensitivity was very high, the index test using prespecified cut-off values just failed to reach the target sensitivity to detect true anaemia. Nevertheless, with respect to blood-sparing effects, the use of the index test in men may be clinically useful, while an index test with a lower cut-off (132 g.l-1 ) could be more clinically appropriate in women.