An accurate diagnosis of beta-lactam (BL) allergy improves the use of antibiotics, increases patients’ safety and reduces costs to health systems. Nevertheless, it requires skin and drug provocation tests, which are time-consuming and put the patient at risk. Furthermore, allergy testing is not available in circumstances such as the urgent need for antibiotic therapy.
To evaluate the usefulness of an artificial neural network (ANN) in the prediction of hypersensitivity to BLs, and compared it with logistic regression (LR) analysis.
In a single-center study, 656 patients evaluated for BL allergy between 1994 and 2000 were retrospectively analyzed, and the data were used to construct an ANN. The ANN predictive capabilities were compared to logistic regression and then prospectively evaluated in 615 patients that underwent BL evaluation between 2011 and 2017.
Total evaluated patients were 1,271. All patients had a definite diagnosis as allergic or non-allergic to BL. The prospective sample showed a lower percentage of allergic patients that the retrospective sample, (20.7% vs 25.8%; p=.018). In the retrospective and prospective series, the ANN reached a sensitivity of 89.5% and 81.1%; specificity, 86.1% and 97.9%; PPV, 82.1% and 91.1%; and NPV, 92.1 and 95.2%, respectively. The ANN performance was far superior that LR, whose best performance reached a sensitivity of 31.9% and a specificity of 98.8%.
This ANN demonstrated superior performance to LR in predicting BL hypersensitivity without misdiagnosing severe allergic reactions. The ANN could be a helpful tool to classify the reaction risk, particularly in the identification of low-risk patients, in which an open challenge could be done to de-label patients.

Copyright © 2020. Published by Elsevier Inc.

Author