Prediction of inhibitor development in previously untreated and minimally treated children with severe and moderately severe hemophilia A using a machine-learning network.

Letícia Lemos JardimTiago A SchieberMarcio Portugal SantanaMônica Hermida CerqueiraClaudia Santos LorenzatoVivian Karla Brognoli FrancoLuciana Werneck ZuccheratoBrendon Ayala da Silva SantosDaniel Gonçalves ChavesMartín Gomez RavettiSuely Meireles Rezende

Published in: Journal of thrombosis and haemostasis : JTH (2024)

Our machine-learning algorithm demonstrated an overall accuracy of 90.5% for predicting inhibitor development in CHA, which further improved when restricting the analysis to CHA with a high-risk F8 genotype. However, our model requires validation in other cohorts. Yet, missing data for some variables hindered more precise predictions.

Keyphrases

machine learning
big data
artificial intelligence
early onset
deep learning
young adults
electronic health record
data analysis
neural network