The cost to the U.S. healthcare system from provider performance inefficiencies and medical errors has been estimated in the range of $75-100 billion annually. The lack of good care coordination across healthcare services has been estimated to cost an additional $25-50 billion annually. These care delivery inefficiencies from individual providers are a large component of the $600-850 billion surplus in healthcare spending.

Medical errors and their impact on patient safety have been recognized as a significant issue since at least the 1960s. The Institute of Medicine (IOM. “To Err is Human: Building a Safer Health System," 1999) estimates that medical errors cause between 44,000 and 98,000 deaths annually in the US. The estimated cost of these errors is between $17 and $29 billion annually. The high error rate also leads to some patients delaying medical treatments and allowing their conditions to worsen because of concerns about becoming a victim of medical error.

[Big data and public health, part 4: Reducing administrative inefficiencies with big data tools.]

Diagnostic errors, prescription errors, and performance variance across medical sites are all part of the embedded inefficiencies that ultimately increases cost and decreases the overall quality of public health. The inability to easily share medical records across care providers and institutions also causes duplication of services and redundant costs. Big data is a critical tool for improving provider performance, reducing medical errors and improving the coordination of healthcare.

Bolstering provider performance
Hospitals are capital-intensive businesses that must make efficient use of their assets to remain viable in a cost-constrained healthcare environment. Improvements include better utilization of professional staff extenders such as nurse practitioners and physician assistants to replace routine work that before was performed by medical doctors at a higher cost.

It also includes better utilization of facilities and equipment, such as low utilization of expensive imaging equipment and the efficient scheduling of operating rooms and support teams. Most hospitals still face problems with the over-utilization of acute care (emergency room) services and intensive care units.

From a big data perspective, hospitals need to get control of their operational information. That means knowing what data they have. They need to link this data to financial drivers, and build teams of data analysts who can review the hospital data from an operations perspective to benchmark performance. Finally, this data needs to be put into a format that can be used for executive decision-making.

Reducing errors
Traditionally, medicine has relied on the mind of the individual physician as the repository of medical knowledge. With the collection of enormous data stores of individual electronic records, huge population databases, and the latest literature of clinical knowledge, it is now possible to integrate individual patient data with comprehensive medical knowledge and population health data to support an enhanced clinical decision making process – and that, in turn, promises to reduce medical errors.

According to Dr. Larry Weed, MD (Medicine in Denial, Weed & Weed 2011) two things need to happen to support the integration of patient data with medical knowledge:

1. The most relevant data need to be selected and its implications understood by the care providing team to supplement the decision process before a clinical judgment is made.
2. The data needs to be organized to manage multiple problems over time, particularly in the case of complex medical cases where there are multiple medical issues involved.

The critical big data problem is to identify the relevant data and present the implications of those data to the healthcare team. That approach couples individual patient specific information with the best medical knowledge and relevant population data to enable better diagnosis – and to do this for both simple single-problem cases and for complex cases with multiple medical issues.

Coordinating care
Patients don’t use a single healthcare provider. Yet, today, patient records remain the proprietary information of the provider and not the individual. Medical records are still not easily exchanged between institutions. When they are, it is often done via printed records hand carried or faxed. The difficulty with sharing information between providers results in duplication of tests and diagnostic effort. In critical care situations this can also result in inappropriate treatment and adverse drug reactions due to lack of medical record information.

[Part 3: Top 9 fraud and abuse areas big data tools can target.]

Better standardization of the medical record increases use of health information exchanges and patients’ ability to access, control, and manage their own medical information will improve this situation. Improved ability to share information across providers will provide better population data and enable more efficient use of healthcare resources. Both uses will enable better big data analysis results.

Go to the next page to continue reading...