Artificial Intelligence in Weaning Clinical Practice: Finding New Rules in Ventilator Support Care

When patients depend on ventilators for a long period of time, it will increase the risk of complexity and the risk of death. Thus, medical professionals try to help patients to wean off from the ventilator as soon as possible to minimize the adverse effects of the respiratory machine. This study analyzed historical clinical data to evaluate and improve the weaning protocol in operation. This study adopted a retrospective approach by collecting 1,014 weaning cases from Taiwan in 2012. We extracted the crucial rules describing the results of weaning from the ventilator using the machine learning algorithm - C4.5, which help medical professionals revise the existing weaning protocol and as supplementary indicators in a new version of the weaning protocol.