The current healthcare system mainly focusses on disease treatments. However, at current time, many diseases either lacks reversible approaches and need life-time medicines, such as diabetes, or need high medical costs, such as cancers. The recent rapid developments in Big Data, Machine Learning(ML), and Artificial Intelligence(AI), it is possible to develop disease predictive models for early or pre-diseases, and then followed with effective interventions. The data used in this process can include multidimensional data, such as medical exam data, biochemical data, multiomics data, environmental data and geographic data as well as imaging data. The interventive approaches can vary too, such as life-style changes, nutrition modification, immune modulation and herb supplements. If these overall processes are well monitored and controlled, similar to current drug discovery/development process, it can form a new type of medical science-predictive interventive medicine. A major difference between the traditional preventive medicine and the predictive interventive medicine is that the predicted disease risk is associated with individual, not the population, in the latter case. The effective implementation of the predictive interventive medicine can bring multiple benefits to improve the current healthcare system. First, it can prevent and/or slow down disease progression of individuals; Second, the reduction of diseases of individuals can improve personal life quality and reduce burdens for the family; Third, most of interventive approaches are less expensive than therapeutics, therefore, can reduce financial pressure of medical cares for both individuals and governments. We therefore propose that the predictive interventive medicine can be an effective strategy for better healthcare in the future.
扫码关注我们
求助内容:
应助结果提醒方式:
