Lessons from Aviation

Introduction

Despite rapid advances in information technology and medical devices, most healthcare organizations have not achieved the same high reliability and safety as other industries, such as aviation, where mistakes can have catastrophic results. Executives and physicians alike are dissatisfied with costs and outcomes, and patients are rightfully fearful of medical errors, infections and miscommunication. The Institute of Medicine estimated in 1998 that medical errors cause as many as 98,000 deaths per year, and recent reassessments indicate that roughly 15 percent of hospital patients are still being harmed.

Safer and more effi cient care will require more than just electronic medical record (EMR) updates. In the January 2013 edition of Health Affairs, the RAND Corporation stated that, "The potential of health information technology to both improve patient care and reduce spending are unlikely to be realized until healthcare providers reengineer their processes to focus on the benefits that can be achieved." Before the improvements in healthcare information technology (HIT) can significantly increase patient safety or lower costs, providers must change cultures and attitudes within their organizations.

Introduction

Experts estimate that 85% of all data exists in unstructured formats – held in e-mails, documents (contracts, memos, clinical notes, legal briefs), social media feeds, etc. Where structured data typically accounts for quantitative facts, the more interesting and potentially more valuable expert opinions and conclusions are often hidden in these unstructured formats. And with massive volumes of text being generated at unprecedented speed, there’s very little chance this information can be made useful without some process of synthesis or automation.

Automating text analysis is not easy. Too often, it requires prior knowledge of what the text is about and a great deal of upfront work to build relevant dictionaries or ontologies. The exception is InterSystems iKnow technology, which employs a unique “bottom-up” approach that analyzes text based solely on what is contained in the text itself.

This paper outlines four basic use cases for the kinds of insights that can be gained from text analysis. For each use case, we briefly describe how real InterSystems customers have leveraged iKnow technology to enhance their applications with text analysis.