William Paiva: Transforming health care and medical education through clinical Big Data analytics

Health care is undergoing significant transformation, and digital health data is at the center of this change. According to the Centers for Disease Control, nearly 80 percent of the nation’s health care institutions have converted to an electronic medical record (EMR) system from the old paper-based system. New technologies like smartphone applications are also creating new stockpiles of digital data. Genetic data is growing as well; scientists can sequence a person’s entire DNA within 24 hours and for less than $1,000. Collectively, the amount of digital health data is expected to grow from 500,000 to 25 million terabytes over the next five years.

Why do we care that our health information is now in a digital format? How does it benefit all of us?

People who work in health care—and every industry for that matter—are smart, well trained, and do their best to stay up-to-date with the latest research, methodologies and trends. However, it is not rational to assume individuals have the depth of knowledge or data access to deal with every situation they encounter. Furthermore, the health care field is already understaffed, and this issue will only get worse as the looming mass retirement of baby boomers from the health care workforce creates an unprecedented supply-and-demand crisis.

Digitized health data has the potential to help mitigate this troubling situation. Predictive medicine uses computing power and statistical methods to analyze EMR and other health-related data to predict clinical outcomes for individual patients. Beyond health outcome forecasting, predictive medicine also can uncover surprising and often unanticipated clinical associations.

Oklahoma State University’s Center for Health Systems Innovation (CHSI), through its Institute for Predictive Medicine (IPM), is a leader in the exploding field of predictive medicine thanks to the unprecedented donation by Cerner Corporation of its HIPAA-compliant clinical health database, one of the largest available in the United States. Specifically, this dataset represents clinical information from over 63 million patients and includes admission, discharge, clinical events, pharmacy, and laboratory data spanning more than 16 years.

Over 20 full-time CHSI employees and nearly two dozen graduate students are working to execute the CHSI mission to transform rural and Native American health through data analytics. Further, CHSI has a number of ongoing partnerships with academia, health systems and corporations to extract value from digitized health data.

One example of CHSI’s numerous predictive medicine projects is an effort to help physicians determine whether the performance of particular cardiovascular drugs varies by gender or race, or both. Conversely, this study will help indicate which drugs perform poorly or even cause complications in these populations. Other CHSI studies are designed to give physicians insight into whether patients with a particular disease are likely to develop or already have an associated disease, which will aid in co-managing these conditions and lead to better health care. Another project is designed to help hospitals use data on patient demographic characteristics, comorbidities, discharge setting, and other medical information contained in comprehensive EMR systems to determine if patients are at high risk for being readmitted for disease-associated complications. If patients are considered high risk, they can get the care and support necessary to prevent frequent cycling through the health care system.

Predictive medicine can also lead to the creation and implementation of tools for managing larger patient loads, which can aid health care providers in dealing with supply-and-demand problems. For instance, CHSI has developed a clinical decision support system that can detect diabetic retinopathy with a high degree of accuracy using lab and comorbidity data available through primary care visits. This algorithm addresses the very real challenge of low patient compliance, particularly among rural and underserved populations, with annual ophthalmic eye exams, which are the gold standard for retinopathy detection and preventing vision impairment or total vision loss. CHSI is extending this work to other common diabetes-related microvascular complications with the goal of developing a comprehensive suite of tools that can help increase prevention and management of these complications among the nation’s growing diabetic population.

Видео William Paiva: Transforming health care and medical education through clinical Big Data analytics канала Stanford Medicine X