Predicting elevated natriuretic peptide in chest radiography: emerging utilization gap for artificial intelligence

Abstract

Abstract Aims This study assessed an artificial intelligence (AI) model’s performance in predicting elevated brain natriuretic peptide (BNP) levels from chest radiograms and its effect on diagnostic performance among healthcare professionals. Methods and results Patients who underwent chest radiography and BNP testing on the same day were included. Data were sourced from two hospitals: one for model development, and the other for external testing. Two final ensemble models were developed to predict elevated BNP levels of ≥ 200 pg/mL and ≥ 100 pg/mL, respectively. Humans were evaluated to predict elevated BNP levels, followed by the same test, referring to the AI model’s predictions. A total of 8390 images were collected for model creation, and 1713 images, for tests. The AI model achieved an accuracy of 0.855, precision of 0.873, sensitivity of 0.827, specificity of 0.882, f1 score of 0.850, and receiver-operating-characteristics area-under-curve of 0.929. The accuracy of the testing by 35 participants significantly improved from 0.708 ± 0.049 to 0.829 ± 0.069 (P < 0.001) with the AI assistance (an accuracy of 0.920). Without the AI assistance, the accuracy of the veterans in the medical career was higher than that of early-career professionals (0.728 ± 0.051 vs. 0.692 ± 0.042, P = 0.030); however, with the AI assistance, the accuracy of the early-career professionals was rather higher than that of the veterans (0.851 ± 0.074 vs. 0.803 ± 0.054, P = 0.033). Conclusion The AI model can predict elevated BNP levels from chest radiograms and has the potential to improve human performance. The gap in utilizing new tools represents one of the emerging issues.

Ähnliche Arbeiten