Access to more data is changing healthcare for the better, not only in terms of improving the quality of patient care but also improving efficiency, reducing operating costs and increasing profits. In order to make better use of the growing influx of data, healthcare facilities are spending more on IT operations in order to develop big data strategies and apply analytics that can translate that data into better care and more cost-efficient operations.
Healthcare providers are spending more than $40 billion each year on new IT projects. IT spending in clinical healthcare alone has risen to $15.6 billion. The compound annual growth rate for IT spending in healthcare is expected to increase from 4.8 percent to 6.01 percent by 2019, and healthcare spending on big data specifically is expected to grow by 42 percent by 2019.
EHRs Provide a New Baseline for Analytics
New sources of data and a growing data archive are driving demand for better data analytics. Adoption of electronic health records (EHRs) has escalated since the passage of the Health Information Technology for Economic and Clinical Health Act (HITECH) in 2009, and as of the start of 2015, eight in 10 medical practices have an EHR system in place. (Under HITECH, those medical practices that do not have an EHR system in place will not be eligible to collect Medicare payments.) With a new baseline of patient treatment data, hospitals and clinics have more source data for analysis in order to determine where they can improve care.
EHRs provide the core information pool that can reveal a lot about a healthcare facility and its care. For example, using big data analytics, healthcare operators can assess treatment trends such as the number of patients seen daily, the most prescribed drugs, in-office efficiency, number of missed appointments and staffing requirements. And when you use big data in order to incorporate EHRs with outside data sources, the potential insights multiply exponentially.
Healthcare Data in Action
Let’s consider some of the possible applications for healthcare data and how data analysis can have a positive impact:
Evidence-based care: Cookbook medicine is a common but inefficient practice; a patient is given a common battery of tests in order to eliminate potential ailments. With access to more patient care data using EHRs, including records from other institutions, caregivers can narrow their diagnosis, testing for potential causes rather than in order to eliminate illnesses. Boston’s Beth Israel Deaconess Medical Center has developed a new smartphone app that aggregates data in order to provide 200 million data points from two million patients in order to promote evidence-based treatment. The results for the hospital are more efficient patient diagnoses that reduce spending for unnecessary tests and reduce the time required in order to administer care.
Predictive care: Organizations such as the National Institutes of Health and the Centers for Disease Control and Prevention have been using analytics for some time in order to track pandemics and predict the spread of influenza, the impact of the Zika virus and the effects of other illnesses. Such analytics are important for helping healthcare providers predict demand for specific types of care and medications. Having the ability to accurately predict the spread of a pandemic can be vital to providing needed care to the community and to ensuring that there isn’t a lack of needed vaccines or an overstock of perishable drugs.
Reduced readmissions: Patient readmissions are an ongoing problem. In fact, Medicare imposes penalties for some readmissions, and readmissions are bad for hospital efficiency as well as for the patient. Using predictive analytics, caregivers can identify those patients at greatest risk for readmission so that they can receive additional monitoring and care. In many instances, using EHRs, population data and other sources in order to model patient care has led to a dramatic drop in readmissions, which means better patient care from the outset, the availability of more beds for other patients, and better management of admissions and staffing for hospitals and clinics.
Billing and insurance reimbursements: Having access to patient care data also can optimize billings and reimbursements. For example, you can use analytics in order to identify procedures that are more or less likely to be reimbursed by insurance. Most medical practices have key performance indicators that they use in order to track operations (e.g. total charges, total number of procedures, number of patients treated, outstanding accounts receivables). Using analytics, providers can identify potential problem areas that need to be scrutinized or modified. Analytics can also make it easier to identify fraud by looking for anomalies in billing patterns and creating alerts that can flag fraudulent payments before they are reimbursed.
These are just a few of the ways that data analytics can improve healthcare operations. Having a pool of patient, billing and operational data available makes it easier to compare and contrast data points in order to isolate almost any operational trend. Areas we haven’t touched on are staffing strategies, stocking of medical supplies, equipment amortization and building management, to name only a few. If there is data available, then it can be analyzed in order to reveal trends and patterns that can be applied in order to improve operations to generate more revenue and, more important, provide better patient care.