Medical data application method and device based on machine learning and storage medium

The invention discloses a medical data application method and device based on machine learning and a storage medium, and the method comprises the steps: obtaining an initial medical data set which comprises OAK clinical research data and blood test parameters; according to the blood test parameters, constructing and training to generate an initial risk assessment model; training the initial risk assessment model according to the OAK clinical research data to obtain a first intermediate risk assessment model; optimizing the parameter variables of the first intermediate risk assessment model by using a preset verification model to obtain a target risk assessment model; acquiring to-be-analyzed blood test parameters, and inputting the to-be-analyzed blood test parameters into the target risk assessment model to obtain a risk assessment result. The initial risk assessment model is constructed, trained and generated by using the initial medical data set, and the target risk assessment model is obtained by performi