MACHINE LEARNING FOR PREDICTION OF ADVERSE DRUG REACTION: APPLICATION TO NEONATES IN INTENSIVE CARE
Adverse Drug Reaction, Big Data, Neonatal ICU, Neonate, machine learning
The intensive care of newborns is associated with a large volume of data in their medical records. This volume of data is called Big Data and is potentially usable for therapeutic purposes. The processing of these data can be done through Machine Learning: a tool capable of assisting in the detection and decision-making of a wide range of medical conditions, including adverse drug reactions (ADR). ADRs have a significant potential for harm to neonates, and are a constant concern in intensive care. The aim of the study is to investigate patterns of adverse drug reactions in neonates admitted to an ICU using a data-driven approach. Observational study developed in the Neonatal Intensive Care Unit of a teaching hospital in Brazil. Clinical data was collected daily and analyzed using a data-driven approach. Preliminary results show the potential of this new method through recall values (0.823). The most prescribed class of drugs for these patients are antimicrobials, especially aminoglycosides.