A New Method and a Non-Invasive Device to Estimate Anemia Based on Digital Images of the Conjunctiva

To determine the value of conjunctival pallor in ruling in or ruling out the presence of severe anemia (hemoglobin < or = 90 g/L) and to determine the interobserver agreement in assessing this sign. Patients were prospectively assessed for pallor by at least one of three observers. All observations were made without information of the patient's hemoglobin value or of another observer's assessment. Tertiary-care, university-affiliated teaching hospital. Three hundred and two medical and surgical inpatients. Likelihood ratios (LRs) calculated for conjunctival pallor present, borderline, and absent were as follows: pallor present, LR 4.49 (95% confidence interval [CI] 1.80, 10.99); pallor borderline, LR 1.80 (95% CI 1.18, 2.62); pallor absent, LR 0.61 (95% CI 0.44, 0.80). Kappa scores of interobserver agreement between paired observers were 0.75 and 0.54. The presence of conjunctival pallor, without other information suggesting anemia, is reason enough to perform a hemoglobin determination. The absence of conjunctival pallor is not likely to be of use in ruling out severe anemia. With well-defined criteria, interobserver agreement is good to very good.

The objective of this study was to determine whether digital photography could be used to calculate hemoglobin. This prospective blinded study was conducted in a tertiary care Emergency Department (ED). A convenience sample of 65 patients provided consent; 44 patients were enrolled for formula derivation and 19 for prospective analysis. Hemoglobin concentration in blood was determined by a cell counter. Software was developed to predict the hemoglobin value based on a formula derived using the images and known hemoglobin values from a derivation set of patients. Pearson's rank order correlation between the calculated and measured hemoglobin was r(77) = 0.634, p < 0.01 for the derivation group and r(36) = 0.522, p < 0.01 for the evaluation group. It is possible to derive an objective method that correlates conjunctiva color with measured hemoglobin and, when applied prospectively, is able to predict hemoglobin concentration in ED patients. This technology has broad applications in regions with limited resources.