With the continuous development of information technology and medical data information, more and more clinicians recognize artificial intelligence or will completely change medical practice by using advance machine learning methods. The potential of using machine learning and predictive analysis to customize specific treatments for individuals is currently under research. Machine learning can learn a large number of medical data, explore the dependencies in data concentration, thereby forming a corresponding medical model; which can quickly and accurately predict new data, which is conducive to the early diagnosis of diseases, and assisted clinical decisions. Clinical medicine faces the status quo of the relatively shortage of medical resources, the identification and rapid diagnosis and treatment of emergency critically ill patients. In the era of big data, the clinical demand is guided by clinical needs, the smart medical care of the machine is a means of solving the key to solving the above problems.