System and method thereof for establishing extubation prediction using machine learning model

A method for establishing an extubation prediction using an machine learning model, capable of predicting a possibility of extubation in real time, and comprising following steps:

• step a:
• inputting feature data used for training, wherein the feature data are obtained from patients who use a ventilatory assistance device during hospitalization, and the feature data comprise consciousness data, input/output liquid data, ventilatory function data and physiological parameter data;
• step b:
• training a machine learning model by using at least a part of the feature data used for training to generate an extubation prediction model and a key feature, wherein the key feature comprises age, a number of days of using a ventilator, and GCS score, urine volume, injection volume, nutrition amount, RASS score, PIP, MAP, ventilatory rate and heart rate of 1 day and 2 days before a day of performing the extubation prediction;
• step c:
• inputting key feature data of a patient subject to the extubation prediction, wherein the patient subject to the extubation prediction is in a state of using a ventilatory assistance device;
• and
• step d:
• analyzing the key feature data by using the extubation prediction model, and obtaining a probability of extubation of the patient subject to the extubation prediction within 24 hours after a day of performing the extubation prediction.