Stan Kachnowski: How do components of your research apply to digital health & healthcare around the world?

Jing Dong: We see a growing availability of data from electronic record systems and advanced devices that collect data we couldn’t even imagine a few years ago. Huge advancements in machine learning tools, and the ways in which we collect, store, and process data have changed and continue to change a lot over time.

I think a key question people don’t think about enough is how can we efficiently translate these new data and the predictive models built from these data into effective decision making tools? 

Through our research, we are trying to build systematic ways of translating vast amounts of data into better operational systems in a healthcare setting. Healthcare is an expensive environment to operate in, with huge uncertainty and fluctuation in demand. The key then to running a successful health system and providing good quality care is to improve the efficiency of such a system. 

The predictive analysis tools provide us with the opportunity of better managing proactive care. This in turn reduces the demand for hospital care, which lowers costs, waiting times, and quality of care for patients who need hospital care most. On top of that, we also aim to provide better proactive care so that the patients we discharge do not come back, but instead maintain a good quality of life after their proactive interventions.